Revisiting the dynamic risk profile of cardiovascular/non‐cardiovascular multimorbidity in incident atrial fibrillation patients and five cardiovascular/non‐cardiovascular outcomes: A machine‐learning approach

Abstract

Background Patients with atrial fibrillation (AF) usually have a heterogeneous co‐morbid history, with dynamic changes in risk factors impacting on multiple adverse outcomes. We investigated a large prospective cohort of patients with multimorbidity, using a machine‐learning approach, accounting for the dynamic nature of comorbidity risks and incident AF. Methods Using machine‐learning, we studied a prospective US cohort using medical/pharmacy databases of 1 091 911 patients, with an incident AF cohort of 14 078 and non‐AF cohort of 1 077 833 enrolled in the 4‐year study. Five incident clinical outcomes (heart failure, stroke, myocardial infarction, major bleeding, and cognitive impairment) were examined in relationship to AF status (AF vs non‐AF), diverse multi‐morbid (conditions and medications) history, and demographic parameters (age and gender), with supervised machine‐learning techniques. Results Complex inter‐relationships of various comorbidities were uncovered for AF cases, leading to 6‐fold higher risk of heart failure relative to the non‐AF cohort (OR 6.02, 95% CI 5.72‐6.33), followed by myocardial infarction (OR=2.68), stroke (OR=2.19), and major bleeding (OR=1.36). Supervised machine learning algorithms on the original populations yielded comparable results for both neural network and logistic regression algorithms in terms of discriminant validity, with c‐indexes for incident adverse outcomes: heart failure (0.924, 95%CI 0.923‐0.925), stroke (0.871, 95%CI 0.869‐0.873), myocardial infarction (0.901, 95% CI 0.899‐0.903), major bleeding (0.700, 95%CI 0.697‐0.703), and cognitive impairment (0.919, 95% CI 0.9170.921). External calibration of all models demonstrated a good fit between the predicted probabilities and observed events. Decision curve analysis demonstrated that the obtained models were much more clinically useful than the “treat all” strategy. Conclusions Complex multimorbidity relationships uncovered using a machine learning approach for incident AF cases have major consequences for integrated care management, with implications for risk stratification and adverse clinical outcomes. This approach may facilitate automated approaches in the presence of multimorbidity, potentially helping decision making.

Incident and recurrent myocardial infarction (MI) in relation to comorbidities: Prediction of outcomes using machine‐learning algorithms

“…This is in keeping with the increasing literature showing how ML models provide clear improvement over risk prediction based on clinical factors alone in various disease states 7–10 . Indeed, ML has been used to aid diagnosis and predict complications following presentation with acute coronary syndromes 9–12 . One novel aspect in the present study is our use of two parametric (i.e., neural network and logistic regression) and non‐parametric (i.e., decision tree and gradient boosting) ML methods accounting for dynamic changes in risk including newly acquired incident risk factors and comorbidities.…”

“…[7][8][9][10] Indeed, ML has been used to aid diagnosis and predict complications following presentation with acute coronary syndromes. [9][10][11][12] One novel aspect in the present study is our use of two parametric (i.e., neural network and logistic regression) and non-parametric (i.e., decision tree and gradient boosting) ML methods accounting for dynamic changes in risk including newly acquired incident risk factors and comorbidities.…”

Rhythm- or rate-control strategies according to 4S-AF characterization scheme and long-term outcomes in atrial fibrillation patients: the FAMo (Fibrillazione Atriale in Modena) cohort

“…It is well known that comorbidities have a major impact on outcome also in AF patients [27,[45][46][47][48][49] and they are more commonly present in daily practice, as compared with trials [29,50]. In a Canadian registry [51] age, heart failure, prior myocardial infarction or need of revascularization, left ventricular hypertrophy, and mitral regurgitation were factors significantly affecting all-cause mortality and they may be more critical for the management of patients in daily practice than for patients selected in trials.…”

Atrial fibrillation, a contemporary sign of multimorbidity and irregular social inequity

“…On the contrary, the natural history of ageing and accumulation of cardiovascular risk factors (which change in a dynamic way) may play an essential role in the increased risk of AF and its complications such as stroke. 7 , 8 The continuously aging population, together with associated multimorbidity and the lower thresholds of hypertension diagnosis, have led to an increase in AF prevalence. Similarly, comorbidities such as diabetes mellitus, chronic kidney disease and obesity which increased over time, may also contribute to the increasing prevalence of AF.…”