Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Diabetes: Management and Pharmacotherapy

Diabetes: Management and Pharmacotherapy

The therapy for diabetes aims to alleviate hyperglycemia-related symptoms, prevent acute metabolic decompensation, and reduce chronic end-organ complications. Glycemic control is evaluated through short-term (self-monitoring, continuous glucose monitoring) and long-term (A1c, fructosamine) metrics, enabling near real-time tracking of blood glucose levels and reflecting glycemic control over specific time frames.
Insulin remains the cornerstone of treatment for most patients with type 1 and many...

Search research articles

Home
Stroke Management And Analysis Risk Tool (smart): An Interpretable Clinical Application For Diabetes-related Stroke Prediction.

Home
Stroke Management And Analysis Risk Tool (smart): An Interpretable Clinical Application For Diabetes-related Stroke Prediction.

Related Experiment Video

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Published on: September 26, 2018

Stroke Management and Analysis Risk Tool (SMART): An interpretable clinical application for diabetes-related stroke

Yumeng Sun¹, Jiaxi Li², Haiyang He³

¹Department of Pharmacy, China Pharmaceutical University Nanjing Drum Tower Hospital, #639 Longmian Avenue, Jiangning District, Nanjing, 211198, Jiangsu Province, China; School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, #639 Longmian Avenue, Jiangning District, Nanjing, 211198, Jiangsu Province, China.

Nutrition, Metabolism, and Cardiovascular Diseases : NMCD

|February 12, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Diabetic patients face a high risk of stroke. This study developed an interpretable stroke prediction model, SMART, using machine learning to identify key risk factors and improve patient outcomes.

Keywords:

Interpretability Machine learning Predictive models Stroke Type 2 diabetes mellitus

More Related Videos

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke

Published on: January 18, 2018

Related Experiment Videos

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis

Published on: September 26, 2018

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke

Optimized Management of Endovascular Treatment for Acute Ischemic Stroke

Published on: January 18, 2018

Area of Science:

Cardiovascular Medicine
Medical Informatics
Machine Learning in Healthcare

Background:

Diabetes and stroke represent a significant global health challenge.
Diabetic patients are at an elevated risk for stroke.
Accurate stroke risk prediction is crucial for timely intervention in this population.

Purpose of the Study:

To analyze factors contributing to stroke incidence in diabetic patients.
To develop an interpretable machine learning model for stroke risk prediction.
To create a clinically applicable tool for assessing stroke risk in individuals with diabetes.

Main Methods:

Utilized Electronic Health Record (EHR) data from 20,014 diabetic patients.
Employed feature engineering techniques including LASSO and SVM-RFE.

Trained and validated models using Random Forest (RF) and Deep Neural Networks (DNN), with class balancing via SMOTE.

Assessed model interpretability using SHAP values and developed the Stroke Management and Analysis Risk Tool (SMART).

Main Results:

Identified 11 key factors influencing stroke incidence in diabetic patients.
Achieved high predictive performance with RF (AUC=0.95) and DNN (AUC=0.91).
Demonstrated the model's interpretability and clinical practicality through SHAP values and a user interface.

Conclusions:

An interpretable stroke prediction model (SMART) was successfully developed for diabetic patients.
The model effectively predicts stroke risk using standard clinical and laboratory parameters.
This tool offers potential for improved stroke prevention strategies in diabetes management.