Machine learning model predicted long-term risks and avoidable health care costs after acute coronary syndromes (ACS), according to a recent study published in Value Health (2020;23[12]:1570-1579. doi:10.1016/j.jval.2020.08.2091).
“Traditional risk scores improved the definition of the initial therapeutic strategy in [ACS], but they were not designed for predicting long-term individual risks and costs,” wrote Luiz Sérgio Fernandes de Carvalho, MD, MSc, PhD, Clarity Healthcare Intelligence, Jundiaí, Brazil, and colleagues.
“In parallel, attempts to directly predict costs from clinical variables in ACS had limited success. Thus, novel approaches to predict cardiovascular risk and health expenditure are urgently needed,” they continued.
This study aimed to predict the risk of major/minor adverse cardiovascular events (MACE) and estimate assistance-related costs.
Researchers used a 2-step approach to predict outcomes with a common pathophysiological substrate (MACE) by using machine learning or logistic regression and compare with existing risk scores and derive costs associated with noncardiovascular deaths, dialysis, ambulatory-care-sensitive-hospitalizations (ACSH), strokes, and MACE.
Consecutive ACS individuals (n = 1089) from 2 cohorts were included; 80% of the population were trained in and 20% were tested in using a 4-fold cross-validation framework. The 29-variable model included socioeconomic, clinical/lab, and coronarography variables. Costs were estimated based on cause-specific hospitalization from the Brazilian Health Ministry perspective.
After 12 years of follow-up, the machine model was superior to logistic regression.
High-risk patients presented increased HbA1c and LDL-C both at <24 hours post-ACS and 1-year follow-up. Additionally, high-risk patients accounted for 33.5% of total costs and displayed 4.96-fold (95% CI 3.71-5.48, P <.00001) greater per capita costs compared with low-risk patients, most of which were avoidable.
“ML could be useful to select individuals at higher risk for clinical events and who are more likely to incur higher costs in the long term,” wrote Dr Fernandes de Carvalho.—Lisa Kuhns
