Related Experiment Video
Updated: Nov 11, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Improving Stroke Risk Prediction in the General Population: A Comparative Assessment of Common Clinical Rules, a New
Gregory Y H Lip1, Ash Genaidy2, George Tran3
1Liverpool Centre for Cardiovascular Science, University of Liverpool and Liverpool Heart and Chest Hospital, Liverpool, United Kingdom.
Insights
Machine learning models significantly improve stroke risk prediction in patients with multiple health conditions. This approach offers better clinical utility than existing methods for dynamic risk stratification and patient management.
Area of Science:
- Cardiology
- Medical Informatics
- Epidemiology
Background:
- Few large-scale studies predict cardiovascular and noncardiovascular comorbidities' impact on stroke risk.
- Investigating stroke risks in a large prospective cohort with multimorbidity is crucial.
Purpose of the Study:
- To compare the predictive performance of machine learning (ML) algorithms against traditional clinical rules for stroke risk in multimorbid patients.
- To assess the clinical utility of ML-based stroke risk prediction.
Main Methods:
- A prospective U.S. cohort of over 3.4 million patients was analyzed over 2 years.
- Stroke outcomes were evaluated against diverse multimorbid conditions, demographics, and risk factors using ML.
- ML models were compared with two common clinical risk scores (CHADS2, CHA2DS2-VASc) and a clinical multimorbidity index.
Main Results:
- ML-based algorithms, particularly logistic regression, demonstrated superior discriminant validity (c-index 0.866) compared to clinical scores (c-index ~0.81) and multimorbidity index (c-index 0.850).
- ML models showed satisfactory calibration and superior clinical utility over existing tools and the 'treat all' strategy.
- The ML approach effectively accounted for the dynamic nature of changing multimorbidity risk factors.
Conclusions:
- Machine learning uncovers complex comorbidity relationships, significantly enhancing stroke risk prediction in dynamic multimorbidity scenarios.
- ML facilitates automated, dynamic risk stratification, aiding decision-making for integrated patient management.
- This approach holds promise for improving stroke risk assessment and holistic care for multimorbid individuals.
Background:
There are few large studies examining and predicting the diversified cardiovascular/noncardiovascular comorbidity relationships with stroke. We investigated stroke risks in a very large prospective cohort of patients with multimorbidity, using two common clinical rules, a clinical multimorbid index and a machine-learning (ML) approach, accounting for the complex relationships among variables, including the dynamic nature of changing risk factors.
Methods:
We studied a prospective U.S. cohort of 3,435,224 patients from medical databases in a 2-year investigation. Stroke outcomes were examined in relationship to diverse multimorbid conditions, demographic variables, and other inputs, with ML accounting for the dynamic nature of changing multimorbidity risk factors, two clinical risk scores, and a clinical multimorbid index.
Results:
Common clinical risk scores had moderate and comparable c indices with stroke outcomes in the training and external validation samples (validation-CHADS2: c index 0.812, 95% confidence interval [CI] 0.808-0.815; CHA2DS2-VASc: c index 0.809, 95% CI 0.805-0.812). A clinical multimorbid index had higher discriminant validity values for both the training/external validation samples (validation: c index 0.850, 95% CI 0.847-0.853). The ML-based algorithms yielded the highest discriminant validity values for the gradient boosting/neural network logistic regression formulations with no significant differences among the ML approaches (validation for logistic regression: c index 0.866, 95% CI 0.856-0.876). Calibration of the ML-based formulation was satisfactory across a wide range of predicted probabilities. Decision curve analysis demonstrated that clinical utility for the ML-based formulation was better than that for the two current clinical rules and the newly developed multimorbid tool. Also, ML models and clinical stroke risk scores were more clinically useful than the "treat all" strategy.
Conclusion:
Complex relationships of various comorbidities uncovered using a ML approach for diverse (and dynamic) multimorbidity changes have major consequences for stroke risk prediction. This approach may facilitate automated approaches for dynamic risk stratification in the significant presence of multimorbidity, helping in the decision-making process for risk assessment and integrated/holistic management.
Related Concept Videos
01:10Pre-Procedural Guidelines for Assessing Blood Pressure
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT