Domain-Aware Interpretable Machine Learning Model for Predicting Postoperative Hospital Length of Stay from...

Postoperative hospital length of stay (LOS) reflects surgical recovery and resource demand but remains difficult to predict due to heterogeneous perioperative trajectories. We aimed to develop and validate an interpretable machine learning framework that integrates multimodal perioperative data to accurately predict LOS and uncover clinically meaningful drivers of prolonged hospitalization.

We studied 97,937 adult surgical cases from a large perioperative registry. Routinely collected perioperative data included patient demographics, comorbid conditions, preoperative laboratory values, intraoperative physiologic summaries, and procedural characteristics. Length of stay was modeled using a supervised regression approach with internal cross-validation and independent holdout evaluation. Model performance was assessed at both the cohort and individual levels, and explanatory analyses were performed to quantify the contribution of clinically defined perioperative domains.

The model achieved R² = 0.61 and MAE ≈ 1.34 days on the holdout set, with nearly identical cross-validation performance (R² = 0.60, MAE ≈ 1.34 days). Operative duration, diagnostic complexity, intraoperative hemodynamic variability, and preoperative laboratory indices-particularly albumin and hematocrit-emerged as the strongest determinants of postoperative stay. Patients with shorter recoveries typically had brief operations, stable physiology, and normal laboratory profiles, whereas prolonged hospitalization was linked to complex procedures, malignant or respiratory diagnoses, and lower albumin levels.

Interpretable machine learning enables accurate and generalizable estimation of postoperative LOS while revealing clinically actionable perioperative domains. Such frameworks may facilitate more efficient perioperative planning, improved allocation of hospital resources, and personalized recovery strategies.