Predictive Model

The goal of this observational study is to develop and pre-validate a machine learning algorithm to predict early recovery of mobility in patients undergoing hip or knee joint replacement surgery. The primary research question is: Can a machine learning model accurately classify patients with faster versus slower recovery of autonomous mobility in the first days after joint replacement surgery? Patients who have undergone elective hip or knee arthroplasty and received post-operative physiotherapy will have their clinical and perioperative data collected retrospectively (2020-2023) and prospectively (March 2026-December 2027). The algorithm will be trained on retrospective data and tested prospectively to evaluate its predictive performance for early mobilization and length of hospital stay.

The integration of Artificial Intelligence (AI) in anesthesiology offers the potential to shift patient monitoring from reactive to predictive. Deep learning architectures, specifically Long Short-Term Memory (LSTM) networks, excel at processing complex, time-series data to forecast future clinical states. While standard PK/PD models (such as the state of the art Eleveld model for Propofol and Remifentanil) estimate target-site drug concentrations (Ce), they do not account for real-time, patient-specific dynamic responses. This study aims to deploy an AI framework designed to predict future physiological states.

The purpose of this 32-week study is to use an innovative experimental design known as SMART (Sequential Multiple Assignment Randomized Trial), which will allow us to determine the best way to sequence the delivery of teleexercise (referred to as an adaptive intervention), combined with predictive analytics on participant adherence in a stepped program of physical activity interventions. All 257 participants will have access to a library of recorded video exercise content, and a weekly wellness article. Some participants will receive health coaching calls (1st randomization). Analytic data will be used to determine which participants are responding or not responding to the intervention. Participants not responding after 4 weeks will receive either live one-on-one or group exercise training (2nd randomization). After 8 weeks, the participant will receive only pre-recorded exercise content and articles for a 24-week maintenance phase (weeks 9-32). The study outcomes are: The effectiveness of the adaptive interventions; Exploring mediating and moderating variables; Sensitivity analysis of the predictive analytics.