Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review

Prediction model has been the focus of studies since the last century in the diagnosis and prognosis of various diseases. With the advancement in computational technology, machine learning (ML) has become the widely used tool to develop a prediction model. This review is to investigate the current development of prediction model for the risk of cardiovascular disease (CVD) among type 2 diabetes (T2DM) patients using machine learning. A systematic search on Scopus and Web of Science (WoS) was conducted to look for relevant articles based on the research question. The risk of bias (ROB) for all articles were assessed based on the Prediction model Risk of Bias Assessment Tool (PROBAST) statement. 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. The overall concern of applicability of all included studies is low. While two out of 10 studies were shown to have high ROB, another studies ROB are unknown due to the lack of information. The adherence to reporting standards was conducted based on the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) standard where the overall score is 53.75%. It is highly recommended that future model development should adhere to the PROBAST and TRIPOD assessment to reduce the risk of bias and ensure its applicability in clinical settings. Potential lipid peroxidation marker is also recommended in future cardiovascular disease prediction model to improve overall model applicability. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12933-023-01741-7.