Artificial intelligence methods for a Bayesian epistemology-powered evidence evaluation

Francesco DE PRETIS; Jürgen LANDES; William PEDEN

doi:10.1111/jep.13542

Artificial intelligence methods for a Bayesian epistemology-powered evidence evaluation

Francesco DE PRETIS, Jürgen LANDES, William PEDEN^*

^*Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

10 Citations (Scopus)

Abstract

Rationale, aims and objectives

The diversity of types of evidence (eg, case reports, animal studies and observational studies) makes the assessment of a drug's safety profile into a formidable challenge. While frequentist uncertain inference struggles in aggregating these signals, the more flexible Bayesian approaches seem better suited for this quest. Artificial Intelligence (AI) offers great promise to these approaches for information retrieval, decision support, and learning probabilities from data.

Methods

E-Synthesis is a Bayesian framework for drug safety assessments built on philosophical principles and considerations. It aims to aggregate all the available information, in order to provide a Bayesian probability of a drug causing an adverse reaction. AI systems are being developed for evidence aggregation in medicine, which increasingly are automated.

Results

We find that AI can help E-Synthesis with information retrieval, usability (graphical decision-making aids), learning Bayes factors from historical data, assessing quality of information and determining conditional probabilities for the so-called ‘indicators’ of causation for E-Synthesis. Vice versa, E-Synthesis offers a solid methodological basis for (semi-)automated evidence aggregation with AI systems.

Conclusions

Properly applied, AI can help the transition of philosophical principles and considerations concerning evidence aggregation for drug safety to a tool that can be used in practice.

Original language	English
Pages (from-to)	504-512
Number of pages	9
Journal	Journal of Evaluation in Clinical Practice
Volume	27
Issue number	3
DOIs	https://doi.org/10.1111/jep.13542
Publication status	Published - Jun 2021
Externally published	Yes

Bibliographical note

Francesco De Pretis and William Peden acknowledge funding from the European Research Council (PhilPharm—GA n. 639276) through the Marche Polytechnic University (Ancona, Italy). The Authors are grateful to Durham University for providing open access for this article. Jürgen Landes gratefully acknowledges funding from the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)—432308570 and 405961989.

Keywords

artificial intelligence
drug safety
E-Synthesis
evidence evaluation
pharmacosurveillance
pharmacovigilance

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1111/jep.13542Licence: CC BY

Cite this

@article{a912aaa26f444d7ba9d29fe523f9c883,

title = "Artificial intelligence methods for a Bayesian epistemology-powered evidence evaluation",

abstract = "Rationale, aims and objectivesThe diversity of types of evidence (eg, case reports, animal studies and observational studies) makes the assessment of a drug's safety profile into a formidable challenge. While frequentist uncertain inference struggles in aggregating these signals, the more flexible Bayesian approaches seem better suited for this quest. Artificial Intelligence (AI) offers great promise to these approaches for information retrieval, decision support, and learning probabilities from data. MethodsE-Synthesis is a Bayesian framework for drug safety assessments built on philosophical principles and considerations. It aims to aggregate all the available information, in order to provide a Bayesian probability of a drug causing an adverse reaction. AI systems are being developed for evidence aggregation in medicine, which increasingly are automated. ResultsWe find that AI can help E-Synthesis with information retrieval, usability (graphical decision-making aids), learning Bayes factors from historical data, assessing quality of information and determining conditional probabilities for the so-called {\textquoteleft}indicators{\textquoteright} of causation for E-Synthesis. Vice versa, E-Synthesis offers a solid methodological basis for (semi-)automated evidence aggregation with AI systems. ConclusionsProperly applied, AI can help the transition of philosophical principles and considerations concerning evidence aggregation for drug safety to a tool that can be used in practice.",

keywords = "artificial intelligence, drug safety, E-Synthesis, evidence evaluation, pharmacosurveillance, pharmacovigilance",

author = "{DE PRETIS}, Francesco and J{\"u}rgen LANDES and William PEDEN",

note = "Francesco De Pretis and William Peden acknowledge funding from the European Research Council (PhilPharm—GA n. 639276) through the Marche Polytechnic University (Ancona, Italy). The Authors are grateful to Durham University for providing open access for this article. J{\"u}rgen Landes gratefully acknowledges funding from the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)—432308570 and 405961989. ",

year = "2021",

month = jun,

doi = "10.1111/jep.13542",

language = "English",

volume = "27",

pages = "504--512",

journal = "Journal of Evaluation in Clinical Practice",

issn = "1356-1294",

publisher = "Wiley-Blackwell Publishing Ltd",

number = "3",

}

TY - JOUR

T1 - Artificial intelligence methods for a Bayesian epistemology-powered evidence evaluation

AU - DE PRETIS, Francesco

AU - LANDES, Jürgen

AU - PEDEN, William

N1 - Francesco De Pretis and William Peden acknowledge funding from the European Research Council (PhilPharm—GA n. 639276) through the Marche Polytechnic University (Ancona, Italy). The Authors are grateful to Durham University for providing open access for this article. Jürgen Landes gratefully acknowledges funding from the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)—432308570 and 405961989.

PY - 2021/6

Y1 - 2021/6

N2 - Rationale, aims and objectivesThe diversity of types of evidence (eg, case reports, animal studies and observational studies) makes the assessment of a drug's safety profile into a formidable challenge. While frequentist uncertain inference struggles in aggregating these signals, the more flexible Bayesian approaches seem better suited for this quest. Artificial Intelligence (AI) offers great promise to these approaches for information retrieval, decision support, and learning probabilities from data. MethodsE-Synthesis is a Bayesian framework for drug safety assessments built on philosophical principles and considerations. It aims to aggregate all the available information, in order to provide a Bayesian probability of a drug causing an adverse reaction. AI systems are being developed for evidence aggregation in medicine, which increasingly are automated. ResultsWe find that AI can help E-Synthesis with information retrieval, usability (graphical decision-making aids), learning Bayes factors from historical data, assessing quality of information and determining conditional probabilities for the so-called ‘indicators’ of causation for E-Synthesis. Vice versa, E-Synthesis offers a solid methodological basis for (semi-)automated evidence aggregation with AI systems. ConclusionsProperly applied, AI can help the transition of philosophical principles and considerations concerning evidence aggregation for drug safety to a tool that can be used in practice.

AB - Rationale, aims and objectivesThe diversity of types of evidence (eg, case reports, animal studies and observational studies) makes the assessment of a drug's safety profile into a formidable challenge. While frequentist uncertain inference struggles in aggregating these signals, the more flexible Bayesian approaches seem better suited for this quest. Artificial Intelligence (AI) offers great promise to these approaches for information retrieval, decision support, and learning probabilities from data. MethodsE-Synthesis is a Bayesian framework for drug safety assessments built on philosophical principles and considerations. It aims to aggregate all the available information, in order to provide a Bayesian probability of a drug causing an adverse reaction. AI systems are being developed for evidence aggregation in medicine, which increasingly are automated. ResultsWe find that AI can help E-Synthesis with information retrieval, usability (graphical decision-making aids), learning Bayes factors from historical data, assessing quality of information and determining conditional probabilities for the so-called ‘indicators’ of causation for E-Synthesis. Vice versa, E-Synthesis offers a solid methodological basis for (semi-)automated evidence aggregation with AI systems. ConclusionsProperly applied, AI can help the transition of philosophical principles and considerations concerning evidence aggregation for drug safety to a tool that can be used in practice.

KW - artificial intelligence

KW - drug safety

KW - E-Synthesis

KW - evidence evaluation

KW - pharmacosurveillance

KW - pharmacovigilance

UR - http://www.scopus.com/inward/record.url?scp=85100995170&partnerID=8YFLogxK

U2 - 10.1111/jep.13542

DO - 10.1111/jep.13542

M3 - Journal Article (refereed)

C2 - 33569874

AN - SCOPUS:85100995170

SN - 1356-1294

VL - 27

SP - 504

EP - 512

JO - Journal of Evaluation in Clinical Practice

JF - Journal of Evaluation in Clinical Practice

IS - 3

ER -

Artificial intelligence methods for a Bayesian epistemology-powered evidence evaluation

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this