Key result
A machine learning model utilizing vital signs and activity metrics from wearable sensors obtained high predictive performance for continuous recovery profiles in perioperative oncology patients.
Why the study?
Postoperative recovery is difficult to assess and predict because current methods involve high subjectivity, measure recovery at only a single time point, and end at discharge.
Does a machine learning model using wearable sensor data predict continuous recovery scores in oncology patients in perioperative care?
Population
Oncology patients in perioperative care
Design
Prediction model development study using XGBoost
Authors
Loading...
May support recovery monitoring in perioperative oncology; leaves open prospective validation before clinical adoption.
Does a machine learning model using wearable sensor data predict continuous recovery scores in oncology patients in perioperative care?
A machine learning model utilizing wearable sensor data can objectively predict continuous postoperative recovery profiles in oncology patients, potentially aiding in discharge planning and complication detection.
Eijnden et al. (2023) studied Oncology patients in perioperative care. Machine learning model using wearable sensor data was evaluated on Continuous recovery scores. A machine learning model utilizing vital signs and activity metrics from wearable sensors obtained high predictive performance for continuous recovery profiles in perioperative oncology patients.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: