PERCEPTION OF UNDERGRADUATE STUDENTS ON THE FEASIBILITY OF USING ARTIFICIAL INTELLIGENCE TO SELF-DIAGNOSE AND MANAGE DEPRESSION, IN THE UNIVERSITY OF IBADAN, OYO STATE.

Abstract

Poor mental health especially depression constitutes a significant source of morbidity in Africa, especially among undergraduate students. Early treatment reduces the risk of suicide, but this requires access to accurate and timely diagnosis. Unfortunately, most sufferers do not use formal health systems to seek diagnosis and follow-up for treatment thus accentuating thoughts of suicide. The use of Artificial Intelligence (AI) for students’ self-diagnosis of depression is a promising alternative to the current low-level diagnostic approach. The objective of this study was to explore a novel approach in the use of artificial intelligence to improve self-diagnosis of depression among undergraduate students in Nigeria. This cross-sectional study was conducted among 350 undergraduate students from the University of Ibadan, Nigeria using both qualitative and quantitative methods. Multi-stage sampling technique was used to select the study participants. The assessment on students’ perception and knowledge of AI and attitude to its use in self-diagnosing depression was conducted using self-administered questionnaires and interviews.Quantitative data was analysed using inferential and descriptive statistics. The manual qualitative thematic analysis method was used for the analysis of all transcribed interviews. Themes and categories were closely examined to identify common themes while subsequent information gathered were fitted into new categories. Respondents’ age was 20.6±2.4 years and 59.1% were females. Majority (82%) of the respondents were of Yoruba ethnicity. Over half (70.6%) of the respondents knew that depression is a state of sadness that extends over two weeks. Almost all (99.1%) of the respondents had good knowledge of depression with knowledge score of 8.8±0.8. More than half (59.4%) of the respondents said they are not at risk of depression while 52% confirmed to have been depressed while in the institution. Twenty (5.7%) respondents were previously diagnosed for depression. It took an average of 3 days for diagnosis to be done and result obtained across the 20 respondents. Of those diagnosed, treatment was obtained by 63.6% respondents with27.3% choosing their treatment type. Advice was the most (50%) received form of treatment for respondents. Poor access to professional mental health therapist was found to be a significant barrier to getting diagnosis(60.5%), followed by unavailability of mental health professional (50.3%) and stigmatization (50.0%). Respondents had good knowledge about depression and artificial intelligence, respondents’ knowledge was not significantly different across age and gender. Although the perception of respondents of AI was positive, it was however identified that data availability and addiction to the tool may pose an area of concern. Based on findings from this study, it is recommended that advocacy should be made for the development of AI for students’ self-diagnosis and management of depression in the university setting. Secondly, An AI tool that features complete diagnosis and recovery monitoring should also be designed. Thirdly, sensitization on stigmatisation should be carried out for mental health professionals working in tertiary institutions.