Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review
Authors' conclusion
Neural network with 76.6% precision, 88.06% sensitivity, and area under the curve (AUC) of 0.91 was found to be the most reliable algorithm in developing prediction model for cardiovascular disease among type 2 diabetes patients.
Study context
- Population
- Studies of machine learning (ML) prediction models for cardiovascular disease (CVD) risk among T2D patients; Scopus and Web of Science10 studies
- Outcome
- Most reliable algorithm for CVD prediction in T2D
Methodological detailsPROBAST risk of bias assessment, TRIPOD reporting assessment
- PROBAST risk of bias assessment
- TRIPOD reporting assessment
Pooled result
As reported in the abstract
| Group | Precision | Sensitivity | AUC |
|---|---|---|---|
| Neural network | 76.6% | 88.06% | 0.91 |
Neural network
Precision76.6%
Sensitivity88.06%
AUC0.91
Further pooled results
Risk of bias and applicability (PROBAST)
- Studies with high risk of bias (ROB)
- 2 of 10
- ROB of other studies unknown due to lack of information
- Overall concern of applicability low
Adherence to TRIPOD reporting standard
- Overall TRIPOD score
- 53.75%
Original publication
Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review. Cardiovasc Diabetol. Published 19 January 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →