A scoping review of artificial intelligence-based methods for diabetes risk prediction

<p dir="ltr">The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Farida Mohsen (16994682) (author)
مؤلفون آخرون: Hamada R. H. Al-Absi (16726299) (author), Noha A. Yousri (1392577) (author), Nady El Hajj (686554) (author), Zubair Shah (231886) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513520757899264
author Farida Mohsen (16994682)
author2 Hamada R. H. Al-Absi (16726299)
Noha A. Yousri (1392577)
Nady El Hajj (686554)
Zubair Shah (231886)
author2_role author
author
author
author
author_facet Farida Mohsen (16994682)
Hamada R. H. Al-Absi (16726299)
Noha A. Yousri (1392577)
Nady El Hajj (686554)
Zubair Shah (231886)
author_role author
dc.creator.none.fl_str_mv Farida Mohsen (16994682)
Hamada R. H. Al-Absi (16726299)
Noha A. Yousri (1392577)
Nady El Hajj (686554)
Zubair Shah (231886)
dc.date.none.fl_str_mv 2023-10-25T09:00:00Z
dc.identifier.none.fl_str_mv 10.1038/s41746-023-00933-5
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_scoping_review_of_artificial_intelligence-based_methods_for_diabetes_risk_prediction/26776468
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Public health
Type 2 Diabetes Mellitus (T2DM)
Predictive Models
Early Diagnosis
Artificial Intelligence (AI)
Machine Learning (ML)
Electronic Health Records (EHR)
Risk Prediction
dc.title.none.fl_str_mv A scoping review of artificial intelligence-based methods for diabetes risk prediction
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration.</p><h2>Other Information</h2><p dir="ltr">Published in: npj Digital Medicine<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41746-023-00933-5" target="_blank">https://dx.doi.org/10.1038/s41746-023-00933-5</a></p>
eu_rights_str_mv openAccess
id Manara2_40f63eea7fe15bd22b632f827bdcbb80
identifier_str_mv 10.1038/s41746-023-00933-5
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26776468
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A scoping review of artificial intelligence-based methods for diabetes risk predictionFarida Mohsen (16994682)Hamada R. H. Al-Absi (16726299)Noha A. Yousri (1392577)Nady El Hajj (686554)Zubair Shah (231886)Biomedical and clinical sciencesClinical sciencesHealth sciencesHealth services and systemsPublic healthType 2 Diabetes Mellitus (T2DM)Predictive ModelsEarly DiagnosisArtificial Intelligence (AI)Machine Learning (ML)Electronic Health Records (EHR)Risk Prediction<p dir="ltr">The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration.</p><h2>Other Information</h2><p dir="ltr">Published in: npj Digital Medicine<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41746-023-00933-5" target="_blank">https://dx.doi.org/10.1038/s41746-023-00933-5</a></p>2023-10-25T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1038/s41746-023-00933-5https://figshare.com/articles/journal_contribution/A_scoping_review_of_artificial_intelligence-based_methods_for_diabetes_risk_prediction/26776468CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/267764682023-10-25T09:00:00Z
spellingShingle A scoping review of artificial intelligence-based methods for diabetes risk prediction
Farida Mohsen (16994682)
Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Public health
Type 2 Diabetes Mellitus (T2DM)
Predictive Models
Early Diagnosis
Artificial Intelligence (AI)
Machine Learning (ML)
Electronic Health Records (EHR)
Risk Prediction
status_str publishedVersion
title A scoping review of artificial intelligence-based methods for diabetes risk prediction
title_full A scoping review of artificial intelligence-based methods for diabetes risk prediction
title_fullStr A scoping review of artificial intelligence-based methods for diabetes risk prediction
title_full_unstemmed A scoping review of artificial intelligence-based methods for diabetes risk prediction
title_short A scoping review of artificial intelligence-based methods for diabetes risk prediction
title_sort A scoping review of artificial intelligence-based methods for diabetes risk prediction
topic Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Public health
Type 2 Diabetes Mellitus (T2DM)
Predictive Models
Early Diagnosis
Artificial Intelligence (AI)
Machine Learning (ML)
Electronic Health Records (EHR)
Risk Prediction