Machine Learning Prediction Models for Recovery After Colorectal Cancer Surgery Using Wearable Device Data, Air Quality Data, and Clinical Evaluation Data (Preprint)

Abstract

With the advancement of medical technology, minimally invasive surgery has gradually replaced traditional surgery as the primary treatment for colorectal cancer because of its more minor wound and shortened length of hospitalization. The subject of our research is how to investigate the postoperative recovery status further on this basis.

The study hopes to use the physiological and clinical data combined with the patient's lifestyle indicators and use machine learning models to predict the patient's postoperative recovery.

A total of 85 patients, data had been collected from National Taiwan University Hospital and National Taiwan University Hospital Hsinchu Branch, undergoing minimally invasive surgery for colorectal cancer. We use wearable devices to collect the participant's step count data, select the nearest station according to their location to collect the PM2.5 in the air quality index of the day as environmental data and merge the two lifestyle indicators above with physiological and clinical data to predict. We use postoperative complications, defined by the Clavien-Dindo classification, as the basis for judging the situation of postoperative recovery. Four data pre-processing methods and six machine learning classification models were used to predict, and each feature was discussed in an interpretable model SHAP.

In each data set and machine learning model, the performance of the third data set trained with Random Forest and the performance of the fourth data set trained with XgBoost are better. Based on the results, we found that the model tended to predict a good recovery on the participants with more steps/day than 2,000 and low sub-index of PM2.5 in their living environment.

Combined with the patient's physiological and clinical data, step counts, and air quality data, through the data pre-processing, machine learning prediction, and interpretable model analysis, the merged data are used to classify the participants' postoperative recovery status. We found that if the patient had a daily essential exercise (based on the number of steps, more than 2,000 steps per day) in an environment where PM2.5 is low (PM2.5 sub-index is less than 36), it would help Postoperative recovery.