ISO/TS 9491-1:2023
(Main)Biotechnology — Predictive computational models in personalized medicine research — Part 1: Constructing, verifying and validating models
Biotechnology — Predictive computational models in personalized medicine research — Part 1: Constructing, verifying and validating models
This document specifies requirements and recommendations for the design, development and establishment of predictive computational models for research purposes in the field of personalized medicine. It addresses the set-up, formatting, validation, simulation, storing and sharing of computational models used for personalized medicine. Requirements and recommendations for data used to construct or required for validating such models are also addressed. This includes rules for formatting, descriptions, annotations, interoperability, integration, access and provenance of such data. This document does not apply to computational models used for clinical, diagnostic or therapeutic purposes.
Biotechnologie — Modèles informatiques prédictifs dans la recherche sur la médecine personnalisée — Partie 1: Construction, vérification et validation des modèles
General Information
Buy Standard
Standards Content (Sample)
TECHNICAL ISO/TS
SPECIFICATION 9491-1
First edition
2023-06
Biotechnology — Predictive
computational models in personalized
medicine research —
Part 1:
Constructing, verifying and validating
models
Biotechnologie — Modèles informatiques prédictifs dans la recherche
sur la médecine personnalisée —
Partie 1: Construction, vérification et validation des modèles
Reference number
ISO/TS 9491-1:2023(E)
© ISO 2023
---------------------- Page: 1 ----------------------
ISO/TS 9491-1:2023(E)
COPYRIGHT PROTECTED DOCUMENT
© ISO 2023
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of this publication may
be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting on
the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address below
or ISO’s member body in the country of the requester.
ISO copyright office
CP 401 • Ch. de Blandonnet 8
CH-1214 Vernier, Geneva
Phone: +41 22 749 01 11
Email: copyright@iso.org
Website: www.iso.org
Published in Switzerland
ii
© ISO 2023 – All rights reserved
---------------------- Page: 2 ----------------------
ISO/TS 9491-1:2023(E)
Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Principles . 4
4.1 General . 4
4.2 Computational models in personalized medicine . 4
4.2.1 General . 4
4.2.2 Cellular systems biology models . 5
4.2.3 Risk prediction for common diseases. 6
4.2.4 Disease course and therapy response prediction . 6
4.2.5 Pharmacokinetic/-dynamic modelling and in silico trial simulations . 7
4.2.6 Artificial intelligence models . 7
4.3 Standardization needs for computational models. 8
4.3.1 General . 8
4.3.2 Challenges . 8
4.3.3 Common standards relevant for personalized medicine . 9
4.4 Data preparation for integration into computer models . 9
4.4.1 General . 9
4.4.2 Sampling data . . 9
4.4.3 Data formatting . 10
4.4.4 Data description . 11
4.4.5 Data annotation (semantics) . 11
4.4.6 Data interoperability requirements across subdomains .12
4.4.7 Data integration .13
4.4.8 Data provenance information . 13
4.4.9 Data access . 14
4.5 Model formatting . . 14
4.6 Model validation . 15
4.6.1 General .15
4.6.2 Specific recommendations for model validation .15
4.7 Model simulation . 17
4.7.1 General . 17
4.7.2 Requirements for capturing and sharing simulation set-ups. 18
4.7.3 Requirements for capturing and sharing simulation results . 19
4.8 Requirements for model storing and sharing . 19
4.9 Application of models in clinical trials and research . 19
4.9.1 General . 19
4.9.2 Specific recommendations . 20
4.10 Ethical requirements for modelling in personalized medicine . 20
Annex A (informative) Common standards relevant for personalized medicine and in silico
approaches .21
Annex B (informative) Information on modelling approaches relevant for personalized
medicine . .24
Bibliography .26
iii
© ISO 2023 – All rights reserved
---------------------- Page: 3 ----------------------
ISO/TS 9491-1:2023(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www.iso.org/patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and
expressions related to conformity assessment, as well as information about ISO’s adherence to
the World Trade Organization (WTO) principles in the Technical Barriers to Trade (TBT), see
www.iso.org/iso/foreword.html.
This document was prepared by Technical Committee ISO/TC 276, Biotechnology.
A list of all parts in the ISO 9491 series can be found on the ISO website.
Any feedback or questions on this document should be directed to the user’s national standards body. A
complete listing of these bodies can be found at www.iso.org/members.html.
iv
© ISO 2023 – All rights reserved
---------------------- Page: 4 ----------------------
ISO/TS 9491-1:2023(E)
Introduction
The capacity to generate data in life sciences and health research has greatly increased in the last decade.
In combination with patient/personal-derived data, such as electronic health records, patient registries
and databases, as well as lifestyle information, this big data holds an immense potential for clinical
applications, especially for computer-based models with predictive capacities in personalized medicine.
However, and despite the ever-progressing technological advances in producing data, the exploitation of
big data to generate new knowledge for medical benefits, while guaranteeing data privacy and security,
is lacking behind its full potential. A reason for this obstacle is the inherent heterogeneity of big data
and the lack of broadly accepted standards allowing interoperable integration of heterogeneous health
data to perform analysis and interpretation for predictive modelling approaches in health research,
such as personalized medicine.
Common standards lead to a mutual understanding and improve information exchange within and
across research communities and are indispensable for collaborative work. In order to setup computer
models in personalized medicine, data integration from heterogeneous and different sources at different
times plays a key role. Consistent documentation of data, models and simulation results based on basic
guiding principles for data management practices, such as FAIR (findable, accessible, interoperable,
[7]
reusable) or ALCOA (attributable, legible, contemporaneous, original, accurate), and standards can
ensure that the data and the corresponding metadata (data describing the data and its context), as well
as the models, methods and visualizations, are of reliable high quality.
Hence, standards for biomedical and clinical data, simulation models and data exchange are a
prerequisite for reliable integration of health-related data. Such standards, together with harmonized
ways to describe their metadata, ensure the interoperability of tools used for data integration and
modelling, as well as the reproducibility of the simulation results. In this sense, modelling standards are
agreed ways of consistently structuring, describing, and associating models and data, their respective
parts and their graphical visualization, as well as the information about applied methods and the
outcome of model simulations. Such standards also assist in describing how constituent parts interact,
or are linked together, and how they are embedded in their physiological context.
Major challenges in the field of personalized medicine are to:
a) harmonize the standardization efforts that refer to different data types, approaches and
technologies;
b) make the standards interoperable, so that the data can be compared and integrated into models.
An overall goal is to FAIRify data and processes in order to improve data integration and reuse. An
additional challenge is to ensure a legal and ethical framework enabling interoperability.
This document presents modelling requirements and recommendations for research in the field of
personalized medicine, especially with focus on collaborative research, such that health-related data
can be optimally used for translational research and personalized medicine worldwide.
v
© ISO 2023 – All rights reserved
---------------------- Page: 5 ----------------------
TECHNICAL SPECIFICATION ISO/TS 9491-1:2023(E)
Biotechnology — Predictive computational models in
personalized medicine research —
Part 1:
Constructing, verifying and validating models
1 Scope
This document specifies requirements and recommendations for the design, development and
establishment of predictive computational models for research purposes in the field of personalized
medicine. It addresses the set-up, formatting, validation, simulation, storing and sharing of
computational models used for personalized medicine. Requirements and recommendations for data
used to construct or required for validating such models are also addressed. This includes rules for
formatting, descriptions, annotations, interoperability, integration, access and provenance of such data.
This document does not apply to computational models used for clinical, diagnostic or therapeutic
purposes.
2 Normative references
The following documents are referred to in the text in such a way that some or all of their content
constitutes requirements of this document. For dated references, only the edition cited applies. For
undated references, the latest edition of the referenced document (including any amendments) applies.
ISO 20691:2022, Biotechnology — Requirements for data formatting and description in the life sciences
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
ISO and IEC maintain terminology databases for use in standardization at the following addresses:
— ISO Online browsing platform: available at https:// www .iso .org/ obp
— IEC Electropedia: available at https:// www .electropedia .org/
3.1
artificial intelligence
AI
capability to acquire, process, create and apply knowledge, held in the form of a model, to
conduct one or more given tasks
[SOURCE: ISO/IEC TR 24030:2021, 3.1]
3.2
molecular biomarker
biomarker
molecular marker
detectable and/or quantifiable molecule or group of molecules used to indicate a biological condition,
state, identity or characteristic or an organism
EXAMPLE Nucleic acid sequences, proteins, small molecules such as metabolites, other molecules such as
lipids and polysaccharides.
1
© ISO 2023 – All rights reserved
---------------------- Page: 6 ----------------------
ISO/TS 9491-1:2023(E)
[SOURCE: ISO 16577:2022, 3.4.28]
3.3
big data in health
high volume, high diversity biological, clinical, environmental, and lifestyle information collected from
single individuals to large cohorts, in relation to their health and wellness status, at one or several time
points
[SOURCE: Reference [8]]
3.4
community standard
standard that reflects the results of a grass-roots standardization effort from a specific user group, and
that is created by individual organizations or communities
3.5
computational model
in silico model
description of a system in a mathematical expression and/or graphical form highlighting objects and
their interfaces
Note 1 to entry: An object distributed processing (ODP) concept.
Note 2 to entry: The computational model is similar to OMT ad UML notion of a class diagram when using the
graphical form.
[SOURCE: ISO/IEC 16500-8:1999, 3.6, modified — Admitted term added. “mathematical expression
and/or” added, and “as such it is similar to the OMT and UML notion of a class Diagram” deleted from
the definition. “An object distributed processing (ODP) concept” moved to Note 1 to entry. Note 2 to
entry added.]
3.6
data-driven model
model developed through the use of data derived from tests or from the output of investigated process
[SOURCE: ISO 15746-1:2015, 2.4]
3.7
data harmonization
technical process of bringing together different data types to make them processable in the same
computational framework
3.8
data integration
systematic combining of data from different independent and potentially heterogeneous sources, to
create a more compatible, unified view of these data for research purpose
[SOURCE: ISO 5127:2017, 3.1.11.24]
3.9
genome-wide association studies
GWAS
testing of genetic variants across the genomes of many individuals to identify genotype–phenotype
associations
3.10
in silico clinical trial
use of individualized computer simulation in the development or regulatory evaluation of a medicinal
product, medical device or medical intervention
[SOURCE: Reference [9]]
2
© ISO 2023 – All rights reserved
---------------------- Page: 7 ----------------------
ISO/TS 9491-1:2023(E)
3.11
in silico approach
computer-executable analyses of mathematical model(s) (3.13) to study and simulate a biological system
3.12
machine learning
ML
computer technology with the ability to automatically learn and improve from experience without
being explicitly programmed
EXAMPLE Speech recognition, predictive text, spam detection, artificial intelligence.
[SOURCE: ISO 20252:2019, 3.52, modified — Abbreviated term “ML” added.]
3.13
mathematical model
sets of equations that describes the behaviour of a physical system
[SOURCE: ISO 16730-1:2015, 3.11]
3.14
mechanism-based
approach in computational modelling that aims for a structural representation
3.15
model validation
comparison between the output of the calibrated model and the measured data, independent of the
data set used for calibration
[SOURCE: ISO 14837-1:2005, 3.7]
3.16
model verification
confirmation that the mathematical elements of the model behave as intended
[SOURCE: ISO 14837-1:2005, 3.8]
3.17
personalized medicine
medical model using characterization of individuals’ phenotypes and genotypes for tailoring the right
therapeutic strategy for the right person at the right time, and/or to determine the predisposition to
disease and/or to deliver timely and targeted prevention
Note 1 to entry: Examples for individuals’ phenotypes and genotypes are molecular profiling, medical imaging
and lifestyle data.
Note 2 to entry: Medical decisions, prevention strategies and therapies in personalized medicine are based on
this individuality.
[10]
[SOURCE: EU 2015/C 421/03 ]
3.18
raw data
data in its originally acquired, direct form from its source before subsequent processing
[SOURCE: ISO 5127:2017, 3.1.10.04]
3
© ISO 2023 – All rights reserved
---------------------- Page: 8 ----------------------
ISO/TS 9491-1:2023(E)
4 Principles
4.1 General
Research in the field of personalized medicine is highly dependent on the exchange of data from
different sources, as well as harmonized integrative analysis of large-scale personalized medicine data
(big data in health). Computational modelling approaches play a key role for understanding, simulating
and predicting the molecular processes and pathways that characterize human biology. Modelling
approaches in biomedical research also lead to a more profound understanding of the mechanisms and
factors that drive disease, and consequently allow for adapting personalized treatment strategies that
are guided by central clinical questions. Patients can greatly benefit from this development in research
that equips personalized medicine with predictive capabilities to simulate in silico clinically relevant
questions, such as the effect of therapies, the response to drug treatments or the progression of disease.
4.2 Computational models in personalized medicine
4.2.1 General
Computational models have the potential to translate in vitro, non-clinical and clinical results (and
their related uncertainty) into descriptive or predictive expressions. The added value of such models
[11][12]
in medicine and pharmacology has increasingly been recognized by the scientific community,
[13][14]
as well as by regulatory bodies such as the European Medicines Agency (e.g. EMA guideline on
[15] [16][17]
PBPK reporting ), or the US Food and Drug Administration (FDA). Computational models are
integrated in different fields in medicine and drug development expanding from disease modelling,
molecular biomarker research to assessment of drug efficacy and safety. In silico approaches are also
[18][19] [20][21]
expanding in neighbouring fields, such as pharmacoeconomics, analytical chemistry and
[22][23]
biology that are out of scope of this document.
Model creation starts with a clinical question and the collection of data (see Figure 1). The data employed
need harmonized approaches for data integration to start the model construction. The initial model
usually undergoes several refinement and improvement iterations to enhance predictive capabilities.
Common standards (see 4.3.3) should be used for the model building and curation process. Accuracy
measurements and validation processes are key, and should be transparent, while model output and
function should ideally be interpretable or explainable.
A number of computational modelling approaches in pre-clinical and clinical research already address
these questions in detail (see 4.2.2 to 4.2.6) and, therefore, play a leading role for the future development
of personalized medicine.
4
© ISO 2023 – All rights reserved
---------------------- Page: 9 ----------------------
ISO/TS 9491-1:2023(E)
Figure 1 — Modelling approach for personalized medicine
4.2.2 Cellular systems biology models
4.2.2.1 General
For the simulation of complex dynamic biological processes and networks, models can be either data-
driven (“bottom-up”) or mechanism-based (“top-down”).
Mechanism-based concepts aim for a structural representation of the governing physiological
processes based on model equations with limited amount of data, which are required for the base model
[24] [25][26] [11][27]
establishment or, alternatively, on static interacting networks. Data-driven approaches
require sufficiently rich and quantitative time-course data to train and to validate the model. Due to the
often black-box nature of data driven approaches, the model validation process relies on performance
tests against known results.
4.2.2.2 Challenges
The challenges are as follows:
— Creation of models that balance the level of abstraction with comprehensiveness to make modelling
efforts reproducible and reusable (abstraction versus size).
— Development of prediction models that can be adopted easily to individual patient profiles.
— Efficient parameter estimation tools to cope with population and disease heterogeneity.
— Overfitting of the model to the experimental/patient data and optimization methods for model
predictions in a realistic parametric uncertainty.
— Flexibility in models to cope with missing data (e.g. diverse patient profiles).
— Scaling from cellular to organ and to organism levels (e.g. high clinical relevance, high hurdles for
regulatory acceptancy).
5
© ISO 2023 – All rights reserved
---------------------- Page: 10 ----------------------
ISO/TS 9491-1:2023(E)
4.2.3 Risk prediction for common diseases
4.2.3.1 General
Predictive models stratify patients into distinct subgroups at different levels of risk for clinical
outcomes (risk prediction for disease). By training the algorithm on clinical data, phenotypic or
genotypic, subgroups can be identified which have identifiably different patterns of clinical markers. By
then identifying which patterns a patient fits best, the model can place a particular patient within the
most similar trajectory, thereby also stratifying the patient to a particular level of risk. Clinical markers
used in such models can be any health feature, tokenized as to be analysable by the model, from data
such as disease history symptoms, treatment and other exposure data, family history, laboratory data,
etc., to genetic data.
4.2.3.2 Challenges
The challenges are as follows:
— Understanding the possible implication to patients at an individual level. What can be inferred?
How to test the inference made?
— Limited replication of genetic associations and poor application of diverse populations (e.g. too
poorly represented to be of interest for specific analyses), specifically of mixed or non-European
ancestry.
— Varying transparency of methodological choices and reproducibility.
— Limited cellular/tissue context and harmonized functional data availability across populations/
studies.
— Missing environmental information coupled to genetic data.
4.2.4 Disease course and therapy response prediction
4.2.4.1 General
Prediction of the disease behaviour (mild versus severe, stable versus progressive) early in the disease
course based on specific molecular biomarkers can allow an improved timing of therapy introduction,
[28]
as well as the choice of therapy scheme (targeted therapy). Ideally, these models can provide a
prediction of multi-factorial diseases at unprecedented resolution, in a way that clinicians can use the
information in their daily decision-making.
4.2.4.2 Challenges
The challenges are as follows:
— Harmonization and standardization of clinical information for measuring the disease of interest.
— Developing transparent and quality-controlled workflows for molecular data generation and
interpretation in clinical settings.
— Harmonization and application of existing and upcoming pre-examination workflow standards
(including specimen collection, storage and nucleic acid isolation), as well as developing feasible
ring trial formats and external quality assurance (EQA) schemes for given molecular analysis types.
— Transparent reduction of contents and definition of appropriate marker sets and dynamic models to
foster clinical translation.
— Developing intuitive visualization results and insights into molecular analyses, as well as critical
appraisal of limitations of models by physicians.
6
© ISO 2023 – All rights reserved
---------------------- Page: 11 ----------------------
ISO/TS 9491-1:2023(E)
4.2.5 Pharmacokinetic/-dynamic modelling and in silico trial simulations
4.2.5.1 General
[29][30]
Pharmacokinetic/pharmacodynamic (PK/PD) models can usefully translate in vitro, non-clinical
and clinical PK/PD data into meaningful information to support decision-making. At the individual
level, substance PKs can either be described by non-compartmental analysis and compartmental PK
modelling or by physiologically-based PK (PBPK) modelling. At the population level, population PK
have become the most commonly used top-down models that derive a pharmaco-statistical model from
observed systemic concentrations. PK/PD modelling involves on the one hand a quantification of drug
absorption and disposition (PK) and on the other hand a description of the drug-induced effect (PD).
PK/PD models and quantitative systems pharmacology (QSP) both aim for mechanistic and quantitative
[31]
analyses of the interactions between a substance such as a drug and a specific biological system.
PK and PBPK modelling are curr
...
FINAL
TECHNICAL ISO/DTS
DRAFT
SPECIFICATION 9491-1
ISO/TC 276
Biotechnology — Predictive
Secretariat: DIN
computational models in personalized
Voting begins on:
2023-03-06 medicine research —
Voting terminates on:
Part 1:
2023-05-01
Constructing, verifying and validating
models
RECIPIENTS OF THIS DRAFT ARE INVITED TO
SUBMIT, WITH THEIR COMMENTS, NOTIFICATION
OF ANY RELEVANT PATENT RIGHTS OF WHICH
THEY ARE AWARE AND TO PROVIDE SUPPOR TING
DOCUMENTATION.
IN ADDITION TO THEIR EVALUATION AS
Reference number
BEING ACCEPTABLE FOR INDUSTRIAL, TECHNO-
ISO/DTS 9491-1:2023(E)
LOGICAL, COMMERCIAL AND USER PURPOSES,
DRAFT INTERNATIONAL STANDARDS MAY ON
OCCASION HAVE TO BE CONSIDERED IN THE
LIGHT OF THEIR POTENTIAL TO BECOME STAN-
DARDS TO WHICH REFERENCE MAY BE MADE IN
NATIONAL REGULATIONS. © ISO 2023
---------------------- Page: 1 ----------------------
ISO/DTS 9491-1:2023(E)
FINAL
TECHNICAL ISO/DTS
DRAFT
SPECIFICATION 9491-1
ISO/TC 276
Biotechnology — Predictive
Secretariat: DIN
computational models in personalized
Voting begins on:
medicine research —
Voting terminates on:
Part 1:
Constructing, verifying and validating
models
COPYRIGHT PROTECTED DOCUMENT
© ISO 2023
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of this publication may
be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting on
the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address below
or ISO’s member body in the country of the requester.
RECIPIENTS OF THIS DRAFT ARE INVITED TO
ISO copyright office
SUBMIT, WITH THEIR COMMENTS, NOTIFICATION
OF ANY RELEVANT PATENT RIGHTS OF WHICH
CP 401 • Ch. de Blandonnet 8
THEY ARE AWARE AND TO PROVIDE SUPPOR TING
CH-1214 Vernier, Geneva
DOCUMENTATION.
Phone: +41 22 749 01 11
IN ADDITION TO THEIR EVALUATION AS
Reference number
Email: copyright@iso.org
BEING ACCEPTABLE FOR INDUSTRIAL, TECHNO-
ISO/DTS 9491-1:2023(E)
Website: www.iso.org
LOGICAL, COMMERCIAL AND USER PURPOSES,
DRAFT INTERNATIONAL STANDARDS MAY ON
Published in Switzerland
OCCASION HAVE TO BE CONSIDERED IN THE
LIGHT OF THEIR POTENTIAL TO BECOME STAN-
DARDS TO WHICH REFERENCE MAY BE MADE IN
ii
© ISO 2023 – All rights reserved
NATIONAL REGULATIONS. © ISO 2023
---------------------- Page: 2 ----------------------
ISO/DTS 9491-1:2023(E)
Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Principles . 4
4.1 General . 4
4.2 Computational models in personalized medicine . 4
4.2.1 General . 4
4.2.2 Cellular systems biology models . 5
4.2.3 Risk prediction for common diseases. 6
4.2.4 Disease course and therapy response prediction . 6
4.2.5 Pharmacokinetic/-dynamic modelling and in silico trial simulations . 7
4.2.6 Artificial intelligence models . 7
4.3 Standardization needs for computational models. 8
4.3.1 General . 8
4.3.2 Challenges . 8
4.3.3 Common standards relevant for personalized medicine . 9
4.4 Data preparation for integration into computer models . 9
4.4.1 General . 9
4.4.2 Sampling data . . 9
4.4.3 Data formatting . 10
4.4.4 Data description . 11
4.4.5 Data annotation (semantics) . 11
4.4.6 Data interoperability requirements across subdomains .12
4.4.7 Data integration .13
4.4.8 Data provenance information . 13
4.4.9 Data access . 14
4.5 Model formatting . . 14
4.6 Model validation . 15
4.6.1 General .15
4.6.2 Specific recommendations for model validation .15
4.7 Model simulation . 17
4.7.1 General . 17
4.7.2 Requirements for capturing and sharing simulation set-ups. 17
4.7.3 Requirements for capturing and sharing simulation results . 18
4.8 Requirements for model storing and sharing . 18
4.9 Application of models in clinical trials and research . 19
4.9.1 General . 19
4.9.2 Specific recommendations . 19
4.10 Ethical requirements for modelling in personalized medicine . 20
Annex A (informative) Common standards relevant for personalized medicine and in silico
approaches .21
Annex B (informative) Information on modelling approaches relevant for personalized
medicine . .24
Bibliography .26
iii
© ISO 2023 – All rights reserved
---------------------- Page: 3 ----------------------
ISO/DTS 9491-1:2023(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www.iso.org/patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and
expressions related to conformity assessment, as well as information about ISO’s adherence to
the World Trade Organization (WTO) principles in the Technical Barriers to Trade (TBT), see
www.iso.org/iso/foreword.html.
This document was prepared by Technical Committee ISO/TC 276, Biotechnology.
A list of all parts in the ISO 9491 series can be found on the ISO website.
Any feedback or questions on this document should be directed to the user’s national standards body. A
complete listing of these bodies can be found at www.iso.org/members.html.
iv
© ISO 2023 – All rights reserved
---------------------- Page: 4 ----------------------
ISO/DTS 9491-1:2023(E)
Introduction
The capacity to generate data in life sciences and health research has greatly increased in the last decade.
In combination with patient/personal-derived data, such as electronic health records, patient registries
and databases, as well as lifestyle information, this big data holds an immense potential for clinical
applications, especially for computer-based models with predictive capacities in personalized medicine.
However, and despite the ever-progressing technological advances in producing data, the exploitation of
big data to generate new knowledge for medical benefits, while guaranteeing data privacy and security,
is lacking behind its full potential. A reason for this obstacle is the inherent heterogeneity of big data
and the lack of broadly accepted standards allowing interoperable integration of heterogeneous health
data to perform analysis and interpretation for predictive modelling approaches in health research,
such as personalized medicine.
Common standards lead to a mutual understanding and improve information exchange within and
across research communities and are indispensable for collaborative work. In order to setup computer
models in personalized medicine, data integration from heterogeneous and different sources at different
times plays a key role. Consistent documentation of data, models and simulation results based on basic
guiding principles for data management practices, such as FAIR (findable, accessible, interoperable,
[7]
reusable) or ALCOA (attributable, legible, contemporaneous, original, accurate), and standards can
ensure that the data and the corresponding metadata (data describing the data and its context), as well
as the models, methods and visualizations, are of reliable high quality.
Hence, standards for biomedical and clinical data, simulation models and data exchange are a
prerequisite for reliable integration of health-related data. Such standards, together with harmonized
ways to describe their metadata, ensure the interoperability of tools used for data integration and
modelling, as well as the reproducibility of the simulation results. In this sense, modelling standards are
agreed ways of consistently structuring, describing, and associating models and data, their respective
parts and their graphical visualization, as well as the information about applied methods and the
outcome of model simulations. Such standards also assist in describing how constituent parts interact,
or are linked together, and how they are embedded in their physiological context.
Major challenges in the field of personalized medicine are to:
a) harmonize the standardization efforts that refer to different data types, approaches and
technologies;
b) make the standards interoperable, so that the data can be compared and integrated into models.
An overall goal is to FAIRify data and processes in order to improve data integration and reuse. An
additional challenge is to ensure a legal and ethical framework enabling interoperability.
This document presents modelling requirements and recommendations for research in the field of
personalized medicine, especially with focus on collaborative research, such that health-related data
can be optimally used for translational research and personalized medicine worldwide.
v
© ISO 2023 – All rights reserved
---------------------- Page: 5 ----------------------
TECHNICAL SPECIFICATION ISO/DTS 9491-1:2023(E)
Biotechnology — Predictive computational models in
personalized medicine research —
Part 1:
Constructing, verifying and validating models
1 Scope
This document specifies requirements and recommendations for the design, development and
establishment of predictive computational models for research purposes in the field of personalized
medicine. It addresses the set-up, formatting, validation, simulation, storing and sharing of
computational models used for personalized medicine. Requirements and recommendations for data
used to construct or required for validating such models are also addressed. This includes rules for
formatting, descriptions, annotations, interoperability, integration, access and provenance of such data.
This document does not apply to computational models used in clinical, diagnostic or therapeutic
purposes.
2 Normative references
The following documents are referred to in the text in such a way that some or all of their content
constitutes requirements of this document. For dated references, only the edition cited applies. For
undated references, the latest edition of the referenced document (including any amendments) applies.
ISO 20691:2022, Biotechnology — Requirements for data formatting and description in the life sciences
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
ISO and IEC maintain terminology databases for use in standardization at the following addresses:
— ISO Online browsing platform: available at https:// www .iso .org/ obp
— IEC Electropedia: available at https:// www .electropedia .org/
3.1
artificial intelligence
AI
capability to acquire, process, create and apply knowledge, held in the form of a model, to
conduct one or more given tasks
[SOURCE: ISO/IEC TR 24030:2021, 3.1]
3.2
molecular biomarker
biomarker
molecular marker
detectable and/or quantifiable molecule or group of molecules used to indicate a biological condition,
state, identity or characteristic or an organism
EXAMPLE Nucleic acid sequences, proteins, small molecules such as metabolites, other molecules such as
lipids and polysaccharides.
1
© ISO 2023 – All rights reserved
---------------------- Page: 6 ----------------------
ISO/DTS 9491-1:2023(E)
[SOURCE: ISO 16577:2022, 3.4.28]
3.3
big data in health
high volume, high diversity biological, clinical, environmental, and lifestyle information collected from
single individuals to large cohorts, in relation to their health and wellness status, at one or several time
points
[SOURCE: Reference [8]]
3.4
community standard
standard that reflects the results of a grass-roots standardization effort from a specific user group, and
that is created by individual organizations or communities
3.5
computational model
in silico model
description of a system in a mathematical expression and/or graphical form highlighting objects and
their interfaces
Note 1 to entry: An object distributed processing (ODP) concept.
Note 2 to entry: The computational model is similar to OMT ad UML notion of a class diagram when using the
graphical form.
[SOURCE: ISO/IEC 16500-8:1999, 3.6, modified — Admitted term added. “mathematical expression
and/or” added, and “as such it is similar to the OMT and UML notion of a class Diagram” deleted from
the definition. “An object distributed processing (ODP) concept” moved to Note 1 to entry. Note 2 to
entry added.]
3.6
data-driven model
model developed through the use of data derived from tests or from the output of investigated process
[SOURCE: ISO 15746-1:2015, 2.4]
3.7
data harmonization
technical process of bringing together different data types to make them processable in the same
computational framework
3.8
data integration
systematic combining of data from different independent and potentially heterogeneous sources, to
create a more compatible, unified view of these data for research purpose
[SOURCE: ISO 5127:2017, 3.1.11.24]
3.9
genome-wide association studies
GWAS
testing of genetic variants across the genomes of many individuals to identify genotype–phenotype
associations
3.10
in silico clinical trial
use of individualized computer simulation in the development or regulatory evaluation of a medicinal
product, medical device or medical intervention
[SOURCE: Reference [9]]
2
© ISO 2023 – All rights reserved
---------------------- Page: 7 ----------------------
ISO/DTS 9491-1:2023(E)
3.11
in silico approach
computer-executable analyses of mathematical model(s) (3.13) to study and simulate a biological system
3.12
machine learning
ML
computer technology with the ability to automatically learn and improve from experience without
being explicitly programmed
EXAMPLE Speech recognition, predictive text, spam detection, artificial intelligence.
[SOURCE: ISO 20252:2019, 3.52, modified — Abbreviated term “ML” added.]
3.13
mathematical model
sets of equations that describes the behaviour of a physical system
[SOURCE: ISO 16730-1:2015, 3.11]
3.14
mechanism-based
approach in computational modelling that aims for a structural representation
3.15
model validation
comparison between the output of the calibrated model and the measured data, independent of the
data set used for calibration
[SOURCE: ISO 14837-1:2005, 3.7]
3.16
model verification
confirmation that the mathematical elements of the model behave as intended
[SOURCE: ISO 14837-1:2005, 3.8]
3.17
personalized medicine
medical model using characterization of individuals’ phenotypes and genotypes for tailoring the right
therapeutic strategy for the right person at the right time, and/or to determine the predisposition to
disease and/or to deliver timely and targeted prevention
Note 1 to entry: Examples for individuals’ phenotypes and genotypes are molecular profiling, medical imaging
and lifestyle data.
Note 2 to entry: Medical decisions, prevention strategies and therapies in personalized medicine are based on
this individuality.
[10]
[SOURCE: EU 2015/C 421/03 ]
3.18
raw data
data in its originally acquired, direct form from its source before subsequent processing
[SOURCE: ISO 5127:2017, 3.1.10.04]
3
© ISO 2023 – All rights reserved
---------------------- Page: 8 ----------------------
ISO/DTS 9491-1:2023(E)
4 Principles
4.1 General
Research in the field of personalized medicine is highly dependent on the exchange of data from
different sources, as well as harmonized integrative analysis of large-scale personalized medicine data
(big data in health). Computational modelling approaches play a key role for understanding, simulating
and predicting the molecular processes and pathways that characterize human biology. Modelling
approaches in biomedical research also lead to a more profound understanding of the mechanisms and
factors that drive disease, and consequently allow for adapting personalized treatment strategies that
are guided by central clinical questions. Patients can greatly benefit from this development in research
that equips personalized medicine with predictive capabilities to simulate in silico clinically relevant
questions, such as the effect of therapies, the response to drug treatments or the progression of disease.
4.2 Computational models in personalized medicine
4.2.1 General
Computational models have the potential to translate in vitro, non-clinical and clinical results (and
their related uncertainty) into descriptive or predictive expressions. The added value of such models
[11][12]
in medicine and pharmacology has increasingly been recognized by the scientific community,
[13][14]
as well as by regulatory bodies such as the European Medicines Agency (e.g. EMA guideline on
[15] [16][17]
PBPK reporting ), or the US Food and Drug Administration (FDA). Computational models are
integrated in different fields in medicine and drug development expanding from disease modelling,
molecular biomarker research to assessment of drug efficacy and safety. In silico approaches are also
[18][19] [20][21]
expanding in neighbouring fields, such as pharmacoeconomics, analytical chemistry and
[22][23]
biology that are out of scope of this document.
Model creation starts with a clinical question and the collection of data (see Figure 1). The data employed
need harmonized approaches for data integration to start the model construction. The initial model
usually undergoes several refinement and improvement iterations to enhance predictive capabilities.
Common standards (see 4.3.3) should be used for the model building and curation process. Accuracy
measurements and validation processes are key, and should be transparent, while model output and
function should ideally be interpretable or explainable.
A number of computational modelling approaches in pre-clinical and clinical research already address
these questions in detail (see 4.2.2 to 4.2.6) and, therefore, play a leading role for the future development
of personalized medicine.
4
© ISO 2023 – All rights reserved
---------------------- Page: 9 ----------------------
ISO/DTS 9491-1:2023(E)
Figure 1 — Modelling approach for personalized medicine
4.2.2 Cellular systems biology models
4.2.2.1 General
For the simulation of complex dynamic biological processes and networks, models can be either data-
driven (“bottom-up”) or mechanism-based (“top-down”).
Mechanism-based concepts aim for a structural representation of the governing physiological
processes based on model equations with limited amount of data, which are required for the base model
[24] [25][26] [11][27]
establishment or, alternatively, on static interacting networks. Data-driven approaches
require sufficiently rich and quantitative time-course data to train and to validate the model. Due to its
often black-box nature, the model validation process in data-driven approaches relies on performance
tests against known results.
4.2.2.2 Challenges
The challenges are as follows:
— Creation of models that balance the level of abstraction with comprehensiveness to make modelling
efforts reproducible and reusable (abstraction versus size).
— Development of prediction models that can be adopted easily to individual patient profiles.
— Efficient parameter estimation tools to cope with population and disease heterogeneity.
— Overfitting of the model to the experimental/patient data and optimization methods for model
predictions in a realistic parametric uncertainty.
— Flexibility in models to cope with missing data (e.g. diverse patient profiles).
— Scaling from cellular to organ and to organism levels (e.g. high clinical relevance, high hurdles for
regulatory acceptancy).
5
© ISO 2023 – All rights reserved
---------------------- Page: 10 ----------------------
ISO/DTS 9491-1:2023(E)
4.2.3 Risk prediction for common diseases
4.2.3.1 General
Predictive models stratify patients into distinct subgroups at different levels of risk for clinical
outcomes (risk prediction for disease). By training the algorithm on clinical data, phenotypic or
genotypic, subgroups can be identified which have identifiably different patterns of clinical markers.
By then identifying which patterns a patient fits best, the model can place a particular patient within
the most similar trajectory, thereby also stratifying the patient to a particular level of risk. Clinical
markers used in such models can be any health feature, tokenized as to be analysable by the model,
from phenotypic data such as disease history symptoms, treatment and other exposure data, family
history, laboratory data, etc., to genetic data.
4.2.3.2 Challenges
The challenges are as follows:
— Understanding the possible implication to patients at an individual level. What can be inferred?
How to test the inference made?
— Limited replication of genetic associations and poor application of diverse populations (e.g. too
poorly represented to be of interest for specific analyses), specifically of mixed or non-European
ancestry.
— Varying transparency of methodological choices and reproducibility.
— Limited cellular/tissue context and harmonized functional data availability across populations/
studies.
— Missing environmental information coupled to genetic data.
4.2.4 Disease course and therapy response prediction
4.2.4.1 General
Prediction of the disease behaviour (mild versus severe, stable versus progressive) early in the disease
course based on specific molecular biomarkers can allow an improved timing of therapy introduction,
[28]
as well as the choice of therapy scheme (targeted therapy). Ideally, these models can provide a
prediction of multi-factorial diseases at unprecedented resolution, in a way that clinicians can use the
information in their daily decision-making.
4.2.4.2 Challenges
The challenges are as follows:
— Harmonization and standardization of clinical information for measuring the disease of interest.
— Developing transparent and quality-controlled workflows for molecular data generation and
interpretation in clinical settings.
— Harmonization and application of existing and upcoming pre-examination workflow standards
(including specimen collection, storage and nucleic acid isolation), as well as developing feasible
ring trial formats and external quality assurance (EQA) schemes for given molecular analysis types.
— Transparent reduction of contents and definition of appropriate marker sets and dynamic models to
foster clinical translation.
— Developing intuitive visualization results and insights into molecular
...
© ISO 2023 – All rights reserved
ISO/DTS 9491-1:20222023(E)
Date: 2023-02-17
ISO/TC 276/WG 5
Secretariat: DIN
Biotechnology — Recommendations and requirements for
Predictivepredictive computational models in
personalisedpersonalized medicine research — Part 1: Guidelines
for constructingConstructing, verifying and validating models
Biotechnologie - Recommandations et exigences relatives aux modèles informatiques prédictifs dans la
recherche sur la médecine personnalisée – Partie 1: Lignes directrices pour la construction, la vérification et la
validation des modèles
DTS stage
---------------------- Page: 1 ----------------------
ISO/DTS 9491-1:2023(E)
© ISO 2023
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of
this publication may be reproduced or utilized otherwise in any form or by any means, electronic or
mechanical, including photocopying, or posting on the internet or an intranet, without prior written
permission. Permission can be requested from either ISO at the address below or ISO’s member body in the
country of the requester.
ISO Copyright Office
CP 401 • CH-1214 Vernier, Geneva
Phone: + 41 22 749 01 11
Email: copyright@iso.org
Website: www.iso.org
Published in Switzerland.
ii © ISO 2023 – All rights reserved
---------------------- Page: 2 ----------------------
ISO/DTS 9491-1:2023(E)
Contents
Foreword . iv
Introduction . v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Principles . 4
4.1 General . 4
4.2 Computational models in personalized medicine . 5
4.2.1 General . 5
4.2.2 Cellular systems biology models . 6
4.2.3 Risk prediction for common diseases . 6
4.2.4 Disease course and therapy response prediction . 7
4.2.5 Pharmacokinetic/-dynamic modelling and in silico trial simulations . 7
4.2.6 Artificial intelligence models . 8
4.3 Standardization needs for computational models . 8
4.3.1 General . 8
4.3.2 Challenges . 9
4.3.3 Common standards relevant for personalized medicine . 9
4.4 Data preparation for integration into computer models . 10
4.4.1 General . 10
4.4.2 Sampling data . 10
4.4.3 Data formatting . 11
4.4.4 Data description . 12
4.4.5 Data annotation (semantics) . 12
4.4.6 Data interoperability requirements across subdomains . 13
4.4.7 Data integration . 14
4.4.8 Data provenance information . 15
4.4.9 Data access . 15
4.5 Model formatting . 16
4.6 Model validation . 17
4.6.1 General . 17
4.6.2 Specific recommendations for model validation . 17
4.7 Model simulation . 20
4.7.1 General . 20
4.7.2 Requirements for capturing and sharing simulation set-ups . 21
4.7.3 Requirements for capturing and sharing simulation results . 21
4.8 Requirements for model storing and sharing . 22
4.9 Application of models in clinical trials and research . 22
4.9.1 General . 22
4.9.2 Specific recommendations . 23
4.10 Ethical requirements for modelling in personalized medicine . 23
Annex A (informative) Common standards relevant for personalized medicine and in silico
approaches . 25
Annex B (informative) Information on modelling approaches relevant for personalized
medicine . 29
Bibliography . 31
© ISO 2023 – All rights reserved iii
---------------------- Page: 3 ----------------------
ISO/DTS 9491-1:2023(E)
Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work. ISO
collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www.iso.org/directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of any
patent rights identified during the development of the document will be in the Introduction and/or on
the ISO list of patent declarations received (see www.iso.org/patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and
expressions related to conformity assessment, as well as information about ISO’s adherence to the World
Trade Organization (WTO) principles in the Technical Barriers to Trade (TBT), see
www.iso.org/iso/foreword.html.
This document was prepared by Technical Committee ISO/TC 276, Biotechnology.
A list of all parts in the ISO 9491 series can be found on the ISO website.
Any feedback or questions on this document should be directed to the user’s national standards body. A
complete listing of these bodies can be found at www.iso.org/members.html.
iv © ISO 2023 – All rights reserved
---------------------- Page: 4 ----------------------
ISO/DTS 9491-1:2023(E)
Introduction
The capacity to generate data in Life Scienceslife sciences and Healthhealth research has greatly
increased many orders of magnitude in the last decade. In combination with patient/personal-derived
data, such as electronic health records, patient registries and -databases, as well as life stylelifestyle
information, this Big Databig data holds an immense potential for clinical applications, especially for
computer-based models with predictive capacities in personalisedpersonalized medicine. However, and
despite the ever-progressing technological advances in producing data, the exploitation of Big Databig
data to generate new knowledge for medical benefits, while guaranteeing data privacy and security, is
lacking behind its full potential. A reason for this obstacle is the inherent heterogeneity of Big Databig
data and the lack of broadly accepted standards allowing interoperable integration of heterogeneous
health data to perform analysis and interpretation for predictive modelling approaches in health
research, such as personalisedpersonalized medicine.
Common standards lead to a mutual understanding and improve information exchange within and across
research communities and are indispensable for collaborative work. HeterogeneousIn order to setup
computer models in personalized medicine, data integration from heterogeneous and different sources
and recorded at different times shall be integrated in order to setup computer models in personalised
medicineplays a key role. Consistent documentation of data, models and simulation results based on basic
1 2
guiding principles for data management practices, such as FAIR or ALCOA , (findable, accessible,
[7]
interoperable, reusable) or ALCOA (attributable, legible, contemporaneous, original, accurate), and
standards can ensure that the data and the corresponding metadata (data describing the data and its
context), as well as the models, methods and visualizations, are of reliable high quality.
Hence, standards for biomedical and clinical data, simulation models, and data exchange are a
prerequisite for reliable integration of health-related data. Such standards, together with
harmonisedharmonized ways to describe their metadata, ensure the interoperability of tools used for
data integration and modelling, as well as the reproducibility of the simulation results. In this sense,
modelling standards are agreed ways of consistently structuring, describing, and associating models and
data, their respective parts, and their graphical visualisationvisualization, as well as the information
about applied methods and the outcome of model simulations. Such standards also assist in describing
how constituent parts interact, or are linked together, and how they are embedded in their physiological
context.
Major challenges in the field of personalisedpersonalized medicine are to (1) harmonise:
a) harmonize the standardization efforts that refer to different data types, approaches and technologies,
as well as to (2) ;
b) make the standards interoperable, so that the data can be compared and integrated into models.
An overall goal is to (3) FAIRify data and processes in order to improve data integration and reuse. An
additional challenge is to ensure a legal and ethical framework enabling interoperability.
This document presents modelling requirements and recommendations and requirements for research
in the field of personalisedpersonalized medicine, especially with focus on collaborative research, such
that health-related data can be optimally used for translational research and personalisedpersonalized
medicine world-wideworldwide.
1
FAIR: Findable, Accessible, Interoperable, Reusable
2
ALCOA: Attributable, Legible, Contemporaneous, Original, Accurate
© ISO 2023 – All rights reserved v
---------------------- Page: 5 ----------------------
TECHNICAL SPECIFICATION ISO/DTS 9491-1:2023(E)
Biotechnology — Recommendations and requirements for
predictivePredictive computational models in
personalisedpersonalized medicine research — Guidelines for
constructingConstructing, verifying and validating models
1 Scope
This document specifies requirements and recommendations for the design, development and
establishment of predictive computational models for research purposes in the field personalisedof
personalized medicine. It addresses the set-up, formatting, validation, simulation, storing and sharing of
computational models used for personalisedpersonalized medicine. Requirements and
recommendations for data used to construct or required for validating such models are also addressed.
This includes rules for formatting, descriptions, annotations, interoperability, integration, access and
provenance of such data. Computational models used in clinical, diagnostic or therapeutic purposes are
excluded.
This document does not apply to computational models used in clinical, diagnostic or therapeutic
purposes.
2 Normative references
The following documents are referred to in the text in such a way that some or all of their content
constitutes requirements of this document. For dated references, only the edition cited applies. For
undated references, the latest edition of the referenced document (including any amendments) applies.
ISO 20691:2022, Biotechnology — Requirements for data formatting and description in the life sciences
ISO/DTS 23494-1, Biotechnology — Provenance information model for biological material and data —
Part 1: Design concepts and general requirements
ISO 14155:2020, Clinical investigation of medical devices for human subjects — Good clinical practice
ISO 26000, Guidance on social responsibility
ISO 20916:2019, In vitro diagnostic medical devices — Clinical performance studies using specimens from
human subjects — Good study practice
ISO 20186-1:2019, Molecular in vitro diagnostic examinations — Specifications for pre-examination
processes for venous whole blood — Part 1: Isolated cellular RNA
ISO/TS 20658:2017, Medical laboratories — Requirements for collection, transport, receipt, and handling
of samples
ISO 13972:2022, Health informatics — Clinical information models — Characteristics, structures and
requirements
103 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
© ISO 2023 – All rights reserved 1
---------------------- Page: 6 ----------------------
ISO/DTS 9491-1:2023(E)
ISO and IEC maintain terminologicalterminology databases for use in standardization at the following
addresses:
— ISO Online browsing platform: available at https://www.iso.org/obp
— IEC Electropedia: available at https://www.electropedia.org/
3.1
artificial intelligence
AI
capability to acquire, process, create and apply knowledge, held in the form of a model, to
conduct one or more given tasks
[SOURCE: ISO/IEC TR 24030:2021, 3.1]
3.2
molecular biomarker
biomarker
molecular marker
detectable and/or quantifiable molecule or group of molecules used to indicate a biological condition,
state, identity or characteristic or an organism, e.g. but not limited to, nucleic acid sequences, proteins,
small molecules such as metabolites and other molecules such as lipids and polysaccharides
EXAMPLE Nucleic acid sequences, proteins, small molecules such as metabolites, other molecules such as
lipids and polysaccharides.
[SOURCE: ISO 16577:20162022, 3.1144.28]
3.3
big data in health
high volume, high diversity biological, clinical, environmental, and lifestyle information collected from
single individuals to large cohorts, in relation to their health and wellness status, at one or several time
points
[SOURCE: Reference [8]]
3.4
community standard
standard that reflects the results of a grass-roots standardization effort from a specific user group, and
that is created by individual organizations or communities
3.5
computational model
in silico model
description of a system in a mathematical expression and/or graphical form highlighting objects and their
interfaces ; object distributed processing (ODP) concept
Note 1Note 1 to entry: An object distributed processing (ODP) concept.
Note 2 to entry: The computational model is similar to OMT ad UML notion of a class diagram when using the
graphical form.
Note 2 to entry: This definition is based on ISO/IEC 16500-8:1999, 3.6.
[SOURCE: ISO/IEC 16500-8:1999, 3.6, modified — Admitted term added. “mathematical expression
and/or” added, and “as such it is similar to the OMT and UML notion of a class Diagram” deleted from the
2 © ISO 2023 – All rights reserved
---------------------- Page: 7 ----------------------
ISO/DTS 9491-1:2023(E)
definition. “An object distributed processing (ODP) concept” moved to Note 1 to entry. Note 2 to entry
added.]
3.6
data-driven model
model developed through the use of data derived from tests or from the output of investigated process
[SOURCE: ISO 15746-1:2015, 2.4]
3.7
data harmonization
technical process of bringing together different data types to make them processable in the same
computational framework
3.8
data integration
systematic combining of data from different independent and potentially heterogeneous sources, to
create a more compatible, unified view of these data for research purpose
[SOURCE: ISO 5127:2017, 3.1.11.24]
3.9
genome-wide association studies
GWAS
testing of genetic variants across the genomes of many individuals to identify genotype–phenotype
associations
3.10
in silico clinical trial
use of individualisedindividualized computer simulation in the development or regulatory evaluation of
a medicinal product, medical device, or medical intervention
Note 1 to entry: definition according to: Avicenna roadmap .
[SOURCE: Reference [9]]
3.11
in silico experimentapproach
computer-executable analyses of mathematical model(s) (3.13) to study and simulate a biological system
3.12
machine learning
ML
computer technology with the ability to automatically learn and improve from experience without being
explicitly programmed
EXAMPLE : Speech recognition, predictive text, spam detection, artificial intelligence.
[SOURCE: ISO 20252:2019, 3.52], modified — Abbreviated term “ML” added.]
3.13
mathematical model
sets of equations that describes the behaviour of a physical system
[SOURCE ISO 16730-1:2015, 3.11]
© ISO 2023 – All rights reserved 3
---------------------- Page: 8 ----------------------
ISO/DTS 9491-1:2023(E)
3.14
mechanism-based (models)
approach in computational modelling that aims for a structural representation
3.15
model validation
comparison between the output of the calibrated model and the measured data, independent of the data
set used for calibration
[SOURCE: ISO 14837-1:2005, 3.7]
3.16
model verification
confirmation that the mathematical elements of the model behave as intended
[SOURCE: ISO 14837-1:2005, 3.8]
3.17
personalisedpersonalized medicine
medical model using characterization of individuals’ phenotypes and genotypes for tailoring the right
therapeutic strategy for the right person at the right time, and/or to determine the predisposition to
disease and/or to deliver timely and targeted prevention
Note 1 to entry: Based on the EU Health Ministers in their Council conclusions on personalised medicine for
patients.
Note 2 to entry: Examples for individuals’ phenotypes and genotypes are molecular profiling, medical imaging,
and lifestyle data.
Note 32 to entry: Medical decisions, prevention strategies and therapies in personalisedpersonalized medicine are
based on this individuality.
[10]
[SOURCE: EU 2015/C 421/03 ]
3.18
raw data
data in its originally acquired, direct form from its source before subsequent processing
[SOURCE: ISO 5127:2017, 3.1.10.04]
114 Principles
11.14.1 General
Research in the field of personalisedpersonalized medicine is highly dependent on the exchange of data
from different sources, as well as harmonisedharmonized integrative analysis of large-scale
personalisedpersonalized medicine data (big data in health). Computational modelling approaches play
a key role for understanding, simulating and predicting the molecular processes and pathways that
characterisecharacterize human biology. Modelling approaches in biomedical research also lead to a
more profound understanding of the mechanisms and factors that drive disease, and later on
consequently allow for adapting personalisedpersonalized treatment strategies that are guided by
central clinical questions. Patients can greatly benefit from this development in research that equips
personalisedpersonalized medicine with predictive capabilities to simulate in silico clinically relevant
questions, such as the effect of therapies, the response to drug treatments, or the progression of disease.
4 © ISO 2023 – All rights reserved
---------------------- Page: 9 ----------------------
ISO/DTS 9491-1:2023(E)
11.24.2 Computational models in personalisedpersonalized medicine
11.2.14.2.1 General
Computational models have the potential to translate in vitro, non-clinical and clinical results (and their
related uncertainty) into descriptive or predictive expressions. The added value of such models in
medicine and pharmacology has increasingly been recognisedrecognized by the scientific community
[11][12][13][14]
([4], [5], [6], [7]),, as well as by regulatory bodies such as the European Medicines Agency (e.g.
3 [15] [16][17]
EMA guideline on PBPK reporting ), ), or the US Food and Drug Administration (FDA) [8], [9].).
Computational models are integrated in different fields in medicine and drug development expanding
from disease modelling, molecular biomarker research to assessment of drug efficacy and safety. In silico
[18][19]
approaches are also expanding in neighbouring fields, such as pharmacoeconomics ([10], [11]),,
[20][21] [22][23]
analytical chemistry ([12], [13]) and biology that are out of scope of this document [14], [15]. .
Model creation starts with a clinical question and the collection of data (see Figure 1). The data employed
need harmonized approaches for data integration to start the model construction. The initial model
usually undergoes several refinement and improvement iterations to enhance predictive capabilities.
Common standards (see 4.3.3) should be used for the model building and curation process. Accuracy
measurements and validation processes are key, and should be transparent, while model output and
function should ideally be interpretable or explainable.
A number of computational modelling approaches in pre-clinical and clinical research already address
these questions in detail (see 4.2.2 to 4.2.6) and, therefore, play a leading role for the future development
of personalisedpersonalized medicine.
Figure 1 — Modelling approach for personalisedpersonalized medicine
3
https://www.ema.europa.eu/en/reporting-physiologically-based-pharmacokinetic-pbpk-modelling-simulation
© ISO 2023 – All rights reserved 5
---------------------- Page: 10 ----------------------
ISO/DTS 9491-1:2023(E)
11.2.24.2.2 Cellular systems biology models
11.2.2.14.2.2.1 General
For the simulation of complex dynamic biological processes and networks, models can be either data-
driven (“bottom-up”) or mechanism-based (“top-down”).
Mechanism-based concepts aim for a structural representation of the governing physiological processes
based on model equations with limited amount of data, which are required for the base model
[24] [25][26]
establishment [16 or, alternatively, on static interacting networks [17], [18]. Data-driven
[11][27]
approaches [4], [19 require sufficiently rich and quantitative time-course data to train and to
validate the model. Due to its often black-box nature, the model validation process in data-driven
approaches relies on performance tests against known results.
11.2.2.24.2.2.2 Challenges
The challenges are as follows:
— Creation of models that balance the level of abstraction with comprehensiveness to make modelling
efforts reproducible and reusable (abstraction vsversus size).
— Development of prediction models that can be adopted easily to individual patient profiles.
— Efficient parameter estimation tools to cope with population and disease heterogeneity.
— Overfitting of the model to the experimental/patient data and optimization methods for model
predictions in a realistic parametric uncertainty.
— Flexibility in models to cope with missing data (e.g.,. diverse patient profiles).
— Scaling from cellular to organ and to organism levels (e.g.,. high clinical relevance, high hurdles for
regulatory acceptancy).
11.2.34.2.3 Risk prediction for common diseases
11.2.3.14.2.3.1 General
Predictive models stratify patients into distinct subgroups at different levels of risk for clinical outcomes
(risk prediction for disease). By training the algorithm on clinical data, phenotypic or genotypic, one can
identify subgroups can be identified which have identifiably different patterns of clinical markers and by.
By then identifying which patterns a patient fits best, the model can place a particular patient within the
most similar trajectory, thereby also stratifying the patient to a particular level of risk. Clinical markers
used in such models can be any health feature, tokenisedtokenized as to be analysable by the model, from
phenotypic data such as disease history symptoms, treatment and other exposure data, family history,
lablaboratory data and so on,, etc., to genetic data.
11.2.3.24.2.3.2 Challenges
The challenges are as follows:
— Understanding the possible implication to patients at an individual -level, what. What can be
inferred? How to test the inference made?
— Limited replication of genetic associations and poor application of diverse populations (e.g.,. too
poorly represented to be of interest for specific analyses), specifically of mixed or non-European
ancestry.
— Varying transparency of methodological choices and reproducibility.
6 © ISO 2023 – All rights reserved
---------------------- Page: 11 ----------------------
ISO/DTS 9491-1:2023(E)
— Limited cellular/tissue context and harmonized functional data availability across
populations/studies.
— Missing environmental information coupled to genetic data.
11.2.44.2.4 Disease course and therapy response prediction
11.2.4.14.2.4.1 General
Prediction of the disease behaviour (mild vs.versus severe, stable vs.versus progressive) early in the
disease course based on specific molecular biomarkers can allow an improved timing of therapy
[28]
introduction, as well as the choice of therapy scheme (targeted therapy) [24].). Ideally, these models
can provide a prediction of ‘multi-factorial’ diseases at unprecedented resolution, in a way that clinicians
can use the information in their daily decision-making.
11.2.4.24.2.4.2 Challenges
The challenges are as follows:
— Harmonization and standardization of clinical information for measuring the disease of interest.
— Developing transparent and quality-controlled workflows for molecular data generation and
interpretation in clinical settings.
— Harmonization and application of existing and upcoming pre-examination workflow standards
(including specimen collection, storage and nucleic acid isolation), as well as developing feasible ring
trial formats and External Qual
...
Questions, Comments and Discussion
Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.