JMIR Publications

ABSTRACT

Background:

Cancer survivors often experience disorders from the depressive spectrum, which remain largely unrecognized and overlooked. Even though screening for depression is recognized as essential, several barriers prevent its successful implementation. This is leading the question of whether a better option can be developed. New possibilities are opening up by advances in artificial intelligence and increasing knowledge on the connection of observable cues and psychological states.

Objective:

The aim of this scoping meta-review was to identify observable features of depression that can be intercepted using artificial intelligence in order to provide a stepping stone towards better recognition of depression among cancer survivors.

Methods:

Methodological framework for scoping reviews was followed. SCOPUS and Web of Science were searched for relevant papers on the topic. Data were extracted from the papers complying with inclusion criteria and analysed by the method of thematic analysis within three predefined categories of depression (i.e., language, speech, and facial expression cues).

Results:

The search yielded 1023 papers of which 9 complied with the inclusion criteria. Analysis of their findings resulted in several well-supported cues of depression in language, speech, and facial expression domains, providing a comprehensive list of observable features potentially suited to be intercepted by artificial intelligence for an early detection of depression.

Conclusions:

This review provides a synthesis of behavioral features of depression, while translating this knowledge into the context of artificial intelligence supported screening for depression in cancer survivors, bringing closer new possibilities of aiding cancer survivors.