Researchers at the University of British Columbia (UBC) and BC Cancer have developed a groundbreaking artificial intelligence (AI) model designed to predict mental health service needs among cancer patients.
Utilizing advanced neural networks and natural language processing, this AI analyzes oncologists’ notes from initial consultations to detect subtle indicators of a patient’s potential mental health requirements. By interpreting the nuances of medical language, it identifies patients who might benefit from early psychiatric or counseling interventions.
Published findings in Communications Medicine reveal that the AI model can predict with over 70% accuracy whether a cancer patient will require psychiatric or counseling services within a year of their first consultation.
According to Dr. John-Jose Nunez, a psychiatrist and clinical research fellow at UBC’s Mood Disorders Centre and BC Cancer, cancer treatment is physically demanding and emotionally challenging. Mental health significantly impacts treatment outcomes and quality of life, with patients struggling with depression and anxiety experiencing poorer survival rates.
Despite the critical need, only around 15% of cancer patients currently access psychiatric services, while another 45% could benefit from counseling. Barriers such as stigma and lack of service awareness contribute to this underutilization.
Developed by a multidisciplinary team, the AI was trained using data from 59,800 patients across all six BC Cancer locations, ensuring confidentiality and anonymization of patient data. The team is now exploring practical applications of this AI tool in collaboration with oncologists and patients to enhance patient care and early intervention.
AI interpretability advances are also being made to understand how the AI makes its predictions, identifying common indicators linked to higher needs for mental health services.
Dr. Raymond Ng highlighted the importance of these advances, emphasizing how they could enhance research and clinical practice in the intricate interplay between oncology and mental health. The team envisions expanding the AI tool’s application beyond oncology to revolutionize patient care across various medical fields impacted by psychosocial factors.
