Predicting control of cardiovascular disease risk factors in South Asia using machine learning
Anna Reuter1,2, Mohammed K Ali3, Viswanathan Mohan4,5
1German Federal Institute of Population Research, Wiesbaden, Germany.
Insights
Machine learning models can identify individuals with diabetes at high risk of poor cardiovascular disease (CVD) risk factor control. This approach aids targeted interventions in resource-limited settings.
Area of Science:
- Cardiovascular disease research
- Diabetes management
- Machine learning in healthcare
Background:
- Many patients at risk of cardiovascular disease (CVD) do not achieve adequate control of their risk factors.
- Clinicians currently lack structured methods for identifying high-risk patients needing intervention.
- Diabetes significantly increases the risk of cardiovascular disease.
Purpose of the Study:
- To develop and validate machine learning models for predicting CVD risk factor control failure in individuals with diabetes.
- To identify patients likely to not achieve target goals or meaningful improvements in HbA1c, SBP, and LDL levels within one year.
- To assess the feasibility of integrating predictive models into routine clinical care for targeted resource allocation.
Main Methods:
- Longitudinal data from 1502 individuals with diabetes in India and Pakistan from two randomized controlled trials were analyzed.
- Machine learning algorithms were employed to predict the risk of failing to achieve CVD risk factor control goals or meaningful improvements at one year.
- Model performance was evaluated using precision metrics for specific risk factors (HbA1c, SBP, LDL).
Main Results:
- The models achieved a precision of 73% for predicting failure to meet HbA1c goals and 88% for meaningful HbA1c improvement.
- For SBP, precision was 30% for goal achievement and 87% for meaningful improvement.
- LDL prediction precision was 24% for goal achievement and 85% for meaningful improvement.
Conclusions:
- Machine learning models can effectively identify individuals with diabetes at high risk of poor cardiovascular disease risk factor control.
- These predictive models demonstrate potential for enhancing the efficiency and targeting of healthcare resources, particularly in resource-constrained environments.
- Integration into routine care could facilitate proactive management and improve patient outcomes for cardiovascular disease prevention.
Abstract:
A substantial share of patients at risk of developing cardiovascular disease (CVD) fail to achieve control of CVD risk factors, but clinicians lack a structured approach to identify these patients. We applied machine learning to longitudinal data from two completed randomized controlled trials among 1502 individuals with diabetes in urban India and Pakistan. Using commonly available clinical data, we predict each individual's risk of failing to achieve CVD risk factor control goals or meaningful improvements in risk factors at one year after baseline. When classifying those in the top quartile of predicted risk scores as at risk of failing to achieve goals or meaningful improvements, the precision for not achieving goals was 73% for HbA1c, 30% for SBP, and 24% for LDL, and for not achieving meaningful improvements 88% for HbA1c, 87% for SBP, and 85% for LDL. Such models could be integrated into routine care and enable efficient and targeted delivery of health resources in resource-constrained settings.
More Related Videos
07:51Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
Related Concept Videos
01:18Steps in Outbreak Investigation
01:28Factors affecting Blood pressure
Physiological Factors:
01:10Pre-Procedural Guidelines for Assessing Blood Pressure
01:11Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...
01:23Assessment of the Cardiovascular System I: Subjective Data
Initial Enquiry
Ask the patient about their primary concern and thoroughly explore all reported symptoms.
Medical History
Investigate past illnesses affecting the cardiovascular system, such as angina, anemia, rheumatic fever, congenital heart disease, stroke, thrombophlebitis, dysrhythmias, varicosities
Inquire about symptoms...
01:25Errors occurring during blood pressure monitoring
Several factors...