Machine Learning for Predicting Medical Error Risks in Greek Surgery Departments

Patient safety remains a global priority, with surgical errors, including in-hospital infections, procedural mishaps, and delays in diagnosis or treatment, causing over 7 million adverse events and 1 million deaths annually. This study evaluates machine learning (ML) to predict the risk of medical errors in the general surgery department of a Greek tertiary university hospital. Medical error risk was operationalized using several proxy indicators derived from prolonged hospitalization and elevated treatment costs, validated against diagnosis-related complication codes. Using a 10-year dataset of 19,965 anonymized patient records (13.5% error cases, n = 2700), we applied ensemble ML algorithms via WEKA, achieving 94.3% accuracy (Random Forest) in detecting errors such as healthcare-associated infections (HAIs), medication errors, and equipment failures. Given the clinical importance of minimizing missed adverse events, model evaluation prioritized both sensitivity and AUC-ROC in addition to overall accuracy. Key predictors were hospitalization duration (ranked #1 via information gain) and initial diagnosis, enabling early risk flagging (e.g., post-op day 5). Further exploratory analyses excluding hospitalization duration from the predictor set demonstrated a moderate reduction in predictive performance while preserving clinically meaningful discriminative capability, suggesting that model performance was not exclusively dependent on hospitalization duration. Compared to US benchmarks like ACS NSQIP (90% accuracy), our model outperformed by 4.3%, filling a gap in EU/Greek studies amid data silos and resource constraints. Integration with tools like the WHO Surgical Safety Checklist could enable proactive interventions, such as enhanced monitoring for prolonged stays. However, the proposed framework should be interpreted as identifying high adverse-event risk patterns rather than directly detecting clinically adjudicated preventable medical errors. Limitations include retrospective biases and workflow integration challenges; ethical issues like data privacy and algorithmic fairness were addressed via anonymization and ethics approval. Future work will focus on multi-center validation, calibration analysis, longitudinal modeling, and integration of explainable artificial intelligence (XAI) techniques to improve transparency and clinical trust. By blending ML with clinician expertise, this approach shifts healthcare from reactive to proactive error mitigation, improving outcomes and reducing costs.