In-hospital mortality, readmission, and prolonged length of stay risk prediction leveraging historical electronic patient records

Objective This study aimed to investigate the predictive capabilities of historical patient records to predict patient adverse outcomes such as mortality, readmission, and prolonged length of stay (PLOS). Methods Leveraging a de-identified dataset from a tertiary care university hospital, we developed an eXplainable Artificial Intelligence (XAI) framework combining tree-based and traditional machine learning (ML) models with interpretations and statistical analysis of predictors of mortality, readmission, and PLOS. Results Our framework demonstrated exceptional predictive performance with a notable area under the receiver operating characteristic (AUROC) of 0.9625 and an area under the precision-recall curve (AUPRC) of 0.8575 for 30-day mortality at discharge and an AUROC of 0.9545 and AUPRC of 0.8419 at admission. For the readmission and PLOS risk, the highest AUROC achieved were 0.8198 and 0.9797, respectively. The tree-based models consistently outperformed the traditional ML models in all 4 prediction tasks. The key predictors were age, derived temporal features, routine laboratory tests, and diagnostic and procedural codes. Conclusion The study underscores the potential of leveraging medical history for enhanced hospital predictive analytics. We present an accurate and intuitive framework for early warning models that can be easily implemented in the current and developing digital health platforms to predict adverse outcomes accurately. Lay Summary This study investigates using historical electronic patient records to predict adverse hospital outcomes such as mortality, readmission, and prolonged length of stay (PLOS). Using data from St Olavs University Hospital in Trondheim, Norway, we developed a framework that combines machine learning models with eXplainable Artificial Intelligence techniques. The study focused on patients suspected of bloodstream infections, leveraging their comprehensive medical histories to enhance prediction accuracy. Our framework demonstrated high predictive performance, especially for 30-day mortality and PLOS. Key predictors included age, laboratory test results, hospital codes, and cumulative hospital length of stay, referring to the cumulative length of all previous hospital admissions up to but not including the current hospital admission. Our approach ensures that healthcare professionals can understand and trust the predictions by providing clear model explanations, ultimately supporting better clinical decision-maki