Aid of a machine learning algorithm can improve clinician predictions of patient quality of life during breast cancer treatments

BackgroundProper and well-timed interventions may improve breast cancer patient adaptation and quality of life (QoL) through treatment and recovery. The challenge is to identify those patients who would benefit most from a particular intervention. The aim of this study was to measure whether the machine learning prediction incorporated in the clinical decision support system (CDSS) improves clinicians' performance to predict patients' QoL during treatment process.MethodsWe conducted two user experiments in which clinicians used a CDSS to predict QoL of breast cancer patients. In both experiments each patient was evaluated both with and without the aid of a machine learning (ML) prediction. In Experiment I, 60 breast cancer patients were evaluated by 6 clinicians. In Experiment II, 90 patients were evaluated by 9 clinicians. The task of clinicians was to predict the patient's quality of life at either 6 (Experiment I) or 12 months post-diagnosis (Experiment II).ResultsTaking into account input from the machine learning prediction considerably improved clinicians' prediction accuracy. Accuracy of clinicians for predicting QoL of patients at 6 months post-diagnosis was .745 (95% CI .668-.821) with the aid of the prediction provided by the ML model and .696 (95% CI .608-.781) without the aid. Clinicians' prediction accuracy at 12 months was .739 (95% CI .667-.812) with the aid and .709 (95% CI .633-.783) without the aid.ConclusionThe results show that the machine learning model integrated into the CDSS can improve clinicians' performance in predicting patients' quality of life.

Automated summary

This study aimed to examine whether machine learning can improve the prediction accuracy of clinicians in assessing breast cancer patients' quality of life. The results showed that incorporating machine learning into the clinical decision support system significantly enhanced clinicians' ability to predict patients' QoL.