Facial Expression Recognition With Machine Learning and Assessment of Distress in Patients With Cancer

Objectives: To estimate the effectiveness of combining facial expression recognition and machine learning for better detection of distress.

Sample & Setting: 232 patients with cancer in Sichuan University West China Hospital in Chengdu, China.

Methods & Variables: The Distress Thermometer (DT) and Hospital Anxiety and Depression Scale (HADS) were used as instruments. The HADS included scores for anxiety (HADS-A), depression (HADS-D), and total score (HADS-T). Distressed patients were defined by the DT cutoff score of 4, the HADS-A cutoff score of 8 or 9, the HADS-D cutoff score of 8 or 9, or the HADS-T cutoff score of 14 or 15. The authors applied histogram of oriented gradients to extract facial expression features from face images, and used a support vector machine as the classifier.

Results: The facial expression features showed feasible differentiation ability on cases classified by DT and HADS.

Implications for Nursing: Facial expression recognition could serve as a supplementary screening tool for improving the accuracy of distress assessment and guide strategies for treatment and nursing.