BACKGROUND: Diversified cardiovascular/non-cardiovascular multimorbid risk and efficient machine learning algorithms may facilitate improvements in stroke risk prediction, especially in newly diagnosed non-anticoagulated atrial fibrillation (AF) patients where initial decision-making on stroke prevention is needed.
OBJECTIVE: sTo update common clinical risk assessment for stroke risk prediction in AF/non-AF cohorts with cardiovascular/non-cardiovascular multimorbid conditions; second, to improve stroke risk prediction using machine learning approaches; and third, to compare the improved clinical prediction rules for multi-morbid conditions using machine learning algorithms.
DATA DESIGN: We used cohort data from two health plans with 6,457,412 males/females contributing 14,188,679 person-years of data.
PREDICTIVE MODELING: The model inputs consisted of diversified list of comorbidities/demographic/temporal exposure variables, with the outcome capturing stroke event incidences. Machine learning algorithms used two parametric and two non-parametric techniques.
RESULTS: The best prediction model was derived on the basis of non-linear formulations using machine learning criteria, with the highest c-index was obtained for logistic regression (0.892; 95%CI 0.886-0.898), with consistency on external validation (0.891; 95%CI 0.882-0.9). These were significantly higher than those based on the conventional stroke risk scores (CHADS2: 0.7488, 95% CI 0.746-0.7516; CHA2DS2-VASc: 0.7801, 95% CI 0.7772-0.7831) and multimorbid index (0.8508, 95% CI 0.8483-0.8532). The machine learning algorithm had good internal and external calibration, and net benefit values.
CONCLUSION: In this large cohort of newly diagnosed non-anticoagulated AF/non-AF patients, large improvements in stroke risk prediction can be shown with a cardiovascular/non-cardiovascular multimorbid index and a machine learning approach incorporating changes in risk related to ageing and incident comorbidities.
|Journal||European heart journal. Quality of care & clinical outcomes|
|Publication status||E-pub ahead of print - 17 May 2021|