PMID- 37880301
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20231123
IS  - 2398-6352 (Electronic)
IS  - 2398-6352 (Linking)
VI  - 6
IP  - 1
DP  - 2023 Oct 25
TI  - A scoping review of artificial intelligence-based methods for diabetes risk 
      prediction.
PG  - 197
LID - 10.1038/s41746-023-00933-5 [doi]
LID - 197
AB  - 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.
CI  - (c) 2023. Springer Nature Limited.
FAU - Mohsen, Farida
AU  - Mohsen F
AD  - College of Science and Engineering, Hamad Bin Khalifa University, Qatar 
      Foundation, 34110, Doha, Qatar.
FAU - Al-Absi, Hamada R H
AU  - Al-Absi HRH
AUID- ORCID: 0000-0002-5636-7632
AD  - College of Science and Engineering, Hamad Bin Khalifa University, Qatar 
      Foundation, 34110, Doha, Qatar.
FAU - Yousri, Noha A
AU  - Yousri NA
AUID- ORCID: 0000-0003-1918-0331
AD  - Genetic Medicine, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar.
AD  - College of Health and Life Sciences, Hamad Bin Khalifa University, Qatar 
      Foundation, 34110, Doha, Qatar.
AD  - Computer and Systems Engineering, Alexandria University, Alexandria, Egypt.
FAU - El Hajj, Nady
AU  - El Hajj N
AUID- ORCID: 0000-0003-3420-8531
AD  - College of Science and Engineering, Hamad Bin Khalifa University, Qatar 
      Foundation, 34110, Doha, Qatar.
AD  - College of Health and Life Sciences, Hamad Bin Khalifa University, Qatar 
      Foundation, 34110, Doha, Qatar.
FAU - Shah, Zubair
AU  - Shah Z
AD  - College of Science and Engineering, Hamad Bin Khalifa University, Qatar 
      Foundation, 34110, Doha, Qatar. zshah@hbku.edu.qa.
LA  - eng
PT  - Journal Article
PT  - Review
DEP - 20231025
PL  - England
TA  - NPJ Digit Med
JT  - NPJ digital medicine
JID - 101731738
PMC - PMC10600138
COIS- The authors declare no competing interests.
EDAT- 2023/10/26 00:42
MHDA- 2023/10/26 00:43
PMCR- 2023/10/25
CRDT- 2023/10/25 23:30
PHST- 2023/03/25 00:00 [received]
PHST- 2023/09/25 00:00 [accepted]
PHST- 2023/10/26 00:43 [medline]
PHST- 2023/10/26 00:42 [pubmed]
PHST- 2023/10/25 23:30 [entrez]
PHST- 2023/10/25 00:00 [pmc-release]
AID - 10.1038/s41746-023-00933-5 [pii]
AID - 933 [pii]
AID - 10.1038/s41746-023-00933-5 [doi]
PST - epublish
SO  - NPJ Digit Med. 2023 Oct 25;6(1):197. doi: 10.1038/s41746-023-00933-5.