Prediction of outpatient rehabilitation patient preferences and optimization of graded diagnosis and treatment based on XGBoost machine learning algorithm

Enhancing patient rehabilitation outcomes: artificial intelligence-driven predictive modeling for home discharge in neurological and orthopedic conditions

In recent years, the fusion of the medical and computer science domains has gained significant traction in the scientific research landscape. Progress in both fields has enabled the generation of a vast amount of data used for making predictions and identifying interesting clusters and pathways. The Machine Learning (ML) model's application in the medical domain is one of the most compelling and challenging topics to explore, bridging the gap between Artificial Intelligence (AI) and healthcare. The combination of AI and medical information offers the possibility to create tools that can benefit both healthcare providers and physicians. This enables the enhancement of rehabilitation therapy and patient care. In the rehabilitation context, this work provides an alternative perspective: prediction of patients' home discharge upon completing the rehabilitation protocol. Demographic and clinical data were collected on 7282 inpatients from electronic Medical Record, each record was categorized into Neurological Patients (NP, N = 3222) or Orthopedic Patients (OP, N = 4060). To identify the most suitable machine learning model, an extensive data preprocessing phase was conducted. This process involved variables recoding, scaling, and the evaluation of different dataset balancing methods to optimize model performance. Following a thorough review and comparison of algorithms commonly employed in the clinical-rehabilitative field, the Random Over Sampling (ROS) technique, in combination with the Random Forest (RF) machine learning model, was selected. Subsequently, a comprehensive hyperparameter tuning phase was performed using a grid search approach. The optimized model achieved an average accuracy of 98% for OP and 96% for NP, based on 10-fold cross-validation applied to the balanced training set (unrealistic scenario). When tested on the unbalanced dataset (real-world condition), the RF model maintained strong generalization performance, achieving 90% accuracy for OP and 83% for NP. This work points out the increasing importance of AI in medicine, especially in the realm of personalized rehabilitation. The use of such approaches could signify a transformative shift in healthcare. The integration of machine learning not only enhances the precision of treatment but also opens new possibilities for patient-centered care, improving outcomes and quality of care for individuals undergoing rehabilitation.