Machine Learning Models for Prediction of Diabetic Microvascular Complications
Kanbour, Sarah ; Harris, Catharine ; Lalani, Benjamin ; Wolf, Risa M ; Fitipaldi, Hugo LU ; Gomez, Maria F LU
and Mathioudakis, Nestoras
(2024)
In Journal of diabetes science and technology
- Abstract
IMPORTANCE AND AIMS: Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN).
METHODS: A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics.
RESULTS: Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the... (More)
IMPORTANCE AND AIMS: Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN).
METHODS: A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics.
RESULTS: Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the use of ML for predicting microvascular complications, mainly driven by DKD research across 27 countries. A more modest increase in ML research on DR and DN was observed, with publications from fewer countries. For all microvascular complications, predictive models achieved a mean (standard deviation) c-statistic of 0.79 (0.09) on internal validation and 0.72 (0.12) on external validation. Diabetic kidney disease models had the highest discrimination, with c-statistics of 0.81 (0.09) on internal validation and 0.74 (0.13) on external validation, respectively. Few studies externally validated prediction of DN. The prediction horizon, outcome definitions, number and type of predictors, and ML technique significantly influenced model performance.
CONCLUSIONS AND RELEVANCE: There is growing global interest in using ML for predicting diabetic microvascular complications. Research on DKD is the most advanced in terms of publication volume and overall prediction performance. Both DR and DN require more research. External validation and adherence to recommended guidelines are crucial.
(Less)
- author
- Kanbour, Sarah
; Harris, Catharine
; Lalani, Benjamin
; Wolf, Risa M
; Fitipaldi, Hugo
LU
; Gomez, Maria F
LU
and Mathioudakis, Nestoras
- organization
- publishing date
- 2024-01-08
- type
- Contribution to journal
- publication status
- epub
- subject
- in
- Journal of diabetes science and technology
- publisher
- Diabetes Technology Society
- external identifiers
-
- scopus:85181655342
- pmid:38189280
- ISSN
- 1932-2968
- DOI
- 10.1177/19322968231223726
- language
- English
- LU publication?
- yes
- id
- cb55a23d-47a7-4209-b081-cb754227c95d
- date added to LUP
- 2024-01-08 21:54:27
- date last changed
- 2024-04-24 20:20:58
@article{cb55a23d-47a7-4209-b081-cb754227c95d,
abstract = {{<p>IMPORTANCE AND AIMS: Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN).</p><p>METHODS: A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics.</p><p>RESULTS: Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the use of ML for predicting microvascular complications, mainly driven by DKD research across 27 countries. A more modest increase in ML research on DR and DN was observed, with publications from fewer countries. For all microvascular complications, predictive models achieved a mean (standard deviation) c-statistic of 0.79 (0.09) on internal validation and 0.72 (0.12) on external validation. Diabetic kidney disease models had the highest discrimination, with c-statistics of 0.81 (0.09) on internal validation and 0.74 (0.13) on external validation, respectively. Few studies externally validated prediction of DN. The prediction horizon, outcome definitions, number and type of predictors, and ML technique significantly influenced model performance.</p><p>CONCLUSIONS AND RELEVANCE: There is growing global interest in using ML for predicting diabetic microvascular complications. Research on DKD is the most advanced in terms of publication volume and overall prediction performance. Both DR and DN require more research. External validation and adherence to recommended guidelines are crucial.</p>}},
author = {{Kanbour, Sarah and Harris, Catharine and Lalani, Benjamin and Wolf, Risa M and Fitipaldi, Hugo and Gomez, Maria F and Mathioudakis, Nestoras}},
issn = {{1932-2968}},
language = {{eng}},
month = {{01}},
publisher = {{Diabetes Technology Society}},
series = {{Journal of diabetes science and technology}},
title = {{Machine Learning Models for Prediction of Diabetic Microvascular Complications}},
url = {{http://dx.doi.org/10.1177/19322968231223726}},
doi = {{10.1177/19322968231223726}},
year = {{2024}},
}