I am a pediatric cardiologist and have cared for children with heart disease for the past three decades. In addition, I have an educational background in business and finance as well as healthcare administration and global health – I gained a Masters Degree in Public Health from UCLA and taught Global Health there after I completed the program.
“Mental health problems don’t define who you are. They are something you experience. You walk in the rain and you feel the rain, but you are not the rain.”
Matt Haig, author of Reasons to Stay Alive
The pandemic has affected the mental health of many, and particularly the most vulnerable segments of our population: children and adolescents, the chronically-ill, and older people. While the acute health issues of pulmonary and cardiac conditions are most prominently discussed in the media, the mental health conditions of our population are just starting to surface as the next health dimension to be impacted by the pandemic.
The ubiquity of smartphones and the emergence of sensors and wearables along with existing large datasets render the deployment of artificial intelligence a unique opportunity to improve mental health in our fragile population.
Mental health is one of the first domains in healthcare to discuss the use of artificial intelligence to improve diagnosis and treatment. This timely work by Rene et al, published in Frontiers of Psychiatry late last year, espouses an interprofessional perspective on applications of artificial intelligence for geriatric mental health research and care. The authors propose using AI to learn about patterns in large multimodal datasets within and across individuals to help improve our understanding of both present clinical status and future clinical outcome. This capability of AI can impact on diagnosis, treatment, and therefore clinical decision making for the mental health care of the older population.
The authors emphasize the importance of this data rich domain not to be used only by the data scientists, but also by stakeholders and practitioners so that interprofessional collaboration can impact on the pragmatic issues in clinical practice. This schism exists in other healthcare areas, so a reminder for data scientists and clinicians (clinical geropsychology and geriatric nursing) to bridge this divide is always welcomed.
The field of geriatric mental health encompasses acute and chronic physical illness, neurodegeneration and cognitive impairment, and mental disorders in people over 65 years of age. The authors opine that AI is ideally situated to advance this field of geriatric mental health for two reasons: AI can enable precision care with real-world multimodal data, and it can improve access to mental health due to cost, time, distance and stigma barriers for mental health delivery.
The authors also review the three main clinical domains relevant to geriatric mental health care:
1) assessment, symptom recognition, and diagnosis; 2) treatment and treatment monitoring; and 3) clinical decision-making, provider training and support. They conclude with a relevant section on the challenges and opportunities of AI solutions in geriatric mental health that are unique for this clinical area.
