Imagine walking into a hospital, unaware of the costs that lie ahead. But what if machines could predict these costs with uncanny accuracy? A recent study has made significant strides in developing explainable AI-based machine learning models to forecast hospital stay and treatment costs in cardiovascular patients.
## A Global Health Concern
Cardiovascular disease (CVD) is the leading cause of mortality worldwide, with substantial economic implications for healthcare systems. Among hospitalized CVD patients, procedures like angioplasty and coronary artery bypass grafting (CABG) are associated with prolonged hospital stays and elevated treatment costs. The need for robust predictive tools to support clinical and administrative decision-making is, therefore, paramount.
## A Study of Epic Proportions
This applied, retrospective predictive modeling study was conducted in 2024 at a specialized cardiovascular clinic in Tehran, Iran. A cohort of 7,685 adult inpatients who underwent angioplasty or CABG between 2022 and 2023 was analyzed. Eight regression-based machine learning algorithms were developed to predict four outcomes: hospital length of stay (LOS), patient out-of-pocket (OOP) expenses, insurer payment, and total treatment cost.
The study employed XGBoost, a high-performing model that consistently outshone its counterparts across all prediction tasks. On the test set, XGBoost achieved R^2 values of 0.7802 for LOS, 0.8473 for patient OOP, 0.8946 for insurer payment, and 0.6437 for total cost. SHAP analysis revealed LOS, intervention type, age, and comorbidities as key predictors.
## A Clinically Implementable Solution
The study presents a comprehensive, explainable, and clinically implementable machine learning framework for predicting LOS and treatment costs in cardiovascular care. By integrating high-performing models with explainable AI and real-world application, this approach offers a scalable solution for enhancing hospital resource planning and optimizing patient outcomes.
Future work should focus on external validation of the models across multiple hospitals and healthcare systems to enhance their generalizability. Additionally, integrating broader clinical and socioeconomic variables may further improve the predictive performance and expand the applicability of the developed decision support tool.
