Machine Learning Prediction Model for Dyslipidemia and Its Association With Atherothrombotic Events in 3 Independent Cohorts From South Korea, Japan, and the United Kingdom: Algorithm Development and Validation Study - Scorecard - MDSpire
Advertisement
Machine Learning Prediction Model for Dyslipidemia and Its Association With Atherothrombotic Events in 3 Independent Cohorts From South Korea, Japan, and the United Kingdom: Algorithm Development and Validation Study
Clinical Scorecard: Development and Validation of a Machine Learning Model for Predicting Dyslipidemia and Its Link to Atherothrombotic Events Across Three Distinct Cohorts in South Korea, Japan, and the United Kingdom
At a Glance
Category
Detail
Condition
Dyslipidemia
Key Mechanisms
Abnormal lipid profile characterized by elevated LDL cholesterol or triglycerides or reduced HDL cholesterol.
Target Population
Individuals aged 19 and older from South Korea, Japan, and the United Kingdom.
Care Setting
Population-based health screenings and claims data.
Key Highlights
ML model developed to predict dyslipidemia within 5 years using routine health data.
Validated across diverse cohorts from South Korea, Japan, and the UK.
Model associated with risk of atherothrombotic events like myocardial infarction.
Guideline-Based Recommendations
Diagnosis
Dyslipidemia diagnosed through blood tests and ICD-10 codes.
Management
Proactive early intervention based on risk prediction.
Monitoring & Follow-up
Longitudinal assessment of atherothrombotic events using predicted probabilities.
Risks
Increased risk of cardiovascular disease associated with dyslipidemia.
Patient & Prescribing Data
Individuals undergoing health screenings, aged 19 and older.
Focus on managing lipid profiles to mitigate health risks.
Clinical Best Practices
Utilize machine learning for risk prediction in dyslipidemia.
Implement routine health screenings for early detection.
