Identifying mental health status using deep neural network trained by visual metrics

• Main Authors: Somayeh B. Shafiei, Zaeem Lone, Ahmed S. Elsayed, Ahmed A. Hussein, Khurshid A. Guru
• Format: Article
• Language: English
• Published: Nature Publishing Group 2020-12-01
• Series: Translational Psychiatry
• Online Access: https://doi.org/10.1038/s41398-020-01117-5

Abstract Mental health is an integral part of the quality of life of cancer patients. It has been found that mental health issues, such as depression and anxiety, are more common in cancer patients. They may result in catastrophic consequences, including suicide. Therefore, monitoring mental health metrics (such as hope, anxiety, and mental well-being) is recommended. Currently, there is lack of objective method for mental health evaluation, and most of the available methods are limited to subjective face-to-face discussions between the patient and psychotherapist. In this study we introduced an objective method for mental health evaluation using a combination of convolutional neural network and long short-term memory (CNN-LSTM) algorithms learned and validated by visual metrics time-series. Data were recorded by the TobiiPro eyeglasses from 16 patients with cancer after major oncologic surgery and nine individuals without cancer while viewing18 artworks in an in-house art gallery. Pre-study and post-study questionnaires of Herth Hope Index (HHI; for evaluation of hope), anxiety State-Trait Anxiety Inventory for Adults (STAI; for evaluation of anxiety) and Warwick-Edinburgh Mental Wellbeing Scale (WEMWBS; for evaluation of mental well-being) were completed by participants. Clinical psychotherapy and statistical suggestions for cutoff scores were used to assign an individual’s mental health metrics level during each session into low (class 0), intermediate (class 1), and high (class 2) levels. Our proposed model was used to objectify evaluation and categorize HHI, STAI, and WEMWBS status of individuals. Classification accuracy of the model was 93.81%, 94.76%, and 95.00% for HHI, STAI, and WEMWBS metrics, respectively. The proposed model can be integrated into applications for home-based mental health monitoring to be used by patients after oncologic surgery to identify patients at risk.