Comparative Evaluation of Machine Learning Algorithms for Predicting Spinal Anesthesia Termination Time

What this Trial Is About

This research aims to evaluate the use of machine learning (ML) algorithms to predict how long spinal anesthesia will last and when patients will be ready to move after total knee arthroplasty. Spinal anesthesia offers benefits over general anesthesia, such as less blood loss, faster recovery, and fewer complications. Predicting its duration accurately is important for patient safety and better postoperative care. This study investigates how ML models can use patient, surgical, and anesthetic data to provide these predictions and improve perioperative management. Patients in this study will undergo total knee replacement surgery using spinal anesthesia with bupivacaine. Before the procedure, patients are monitored with ECG, blood pressure, and oxygen saturation measurements, and an intravenous line is set up. The spinal anesthesia is administered via a needle between specific vertebrae, injecting bupivacaine to induce numbness for surgery. The study focuses on observing anesthesia duration and patient recovery, using ML models trained on collected clinical data. Participants will be monitored from the time of spinal injection until they fully regain motor function, within about 6 hours. Researchers will assess anesthesia duration and pain levels using scales like the Visual Analogue Scale. Data collected includes vital signs, drug dosages, and surgical details. The study aims to measure how well ML predictions match actual anesthesia duration and patient readiness for mobilization, supporting safer and more personalized care during and after surgery.

Machine Learning for Predicting Spinal Anesthesia Duration