A LightGBM machine learning model predicted one-year mortality following orthopedic hospitalization with 93% accuracy and an AUC of 0.93, outperforming traditional statistical methods.
Observational (n=3,132)
No
Does a LightGBM machine learning model accurately predict one-year mortality in patients undergoing orthopedic procedures?
A LightGBM machine learning model accurately predicts one-year mortality following orthopedic hospitalization, with emergency admission time being the strongest predictor.
Effect estimate: Accuracy 93%, AUC 0.93
• LightGBM model predicts one-year mortality post-orthopedic surgery with 93% accuracy. • Emergency admission time is the strongest predictor of mortality risk. • Age and pre-operative days are significant factors in mortality prediction. • SHAP analysis provides insights into the model’s decision-making process. • Model has potential to enhance risk stratification and inform clinical decisions. Predicting mortality risk following orthopedic surgery is crucial for informed decision-making and patient care. This study aims to develop and validate a machine learning model for predicting one-year mortality risk after orthopedic hospitalization and to create a personalized risk prediction tool for clinical use. We analyzed data from 3,132 patients who underwent orthopedic procedures at the Central Lisbon University Hospital Center from 2021 to 2023. Using the LightGBM algorithm, we developed a predictive model incorporating various clinical and administrative variables. We employed SHAP (SHapley Additive exPlanations) values for model interpretation and created a personalized risk prediction tool for individual patient assessment. Our model achieved an accuracy of 93% and an area under the ROC curve of 0.93 for predicting one-year mortality. Notably, ’EMERGENCY ADMISSION DATE TIME’ emerged as the most influential predictor, followed by age and pre-operative days. The model demonstrated robust performance across different patient subgroups and outperformed traditional statistical methods. The personalized risk prediction tool provides clinicians with real-time, patient-specific risk assessments and insights into contributing factors. Our study presents a highly accurate model for predicting one-year mortality following orthopedic hospitalization. The significance of ’EMERGENCY ADMISSION DATE TIME’ as the primary predictor highlights the importance of admission timing in patient outcomes. The accompanying personalized risk prediction tool offers a practical means of implementing this model in clinical settings, potentially improving risk stratification and patient care in orthopedic practice.
Carvalho et al. (Fri,) conducted a observational in Orthopedic hospitalization (n=3,132). LightGBM predictive model vs. Traditional statistical methods was evaluated on One-year mortality (Accuracy 93%, AUC 0.93). A LightGBM machine learning model predicted one-year mortality following orthopedic hospitalization with 93% accuracy and an AUC of 0.93, outperforming traditional statistical methods.