AI predicts mental health needs in cancer patients

Credit: Unsplash+

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.

This AI, utilizing advanced neural networks and natural language processing, analyzes oncologists’ notes from initial consultations to detect subtle indicators of a patient’s potential mental health requirements.

The AI’s ability to interpret the nuances of medical language enables it to identify patients who might benefit from early psychiatric or counseling interventions.

Recently published findings in Communications Medicine reveal that this 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.

Dr. John-Jose Nunez, a psychiatrist and clinical research fellow at UBC’s Mood Disorders Centre and BC Cancer, emphasized the significance of this development. He explained that cancer treatment is not only physically demanding but also emotionally and mentally challenging.

The AI acts like a personal assistant to oncologists, helping them recognize mental health needs sooner and ensuring that patients receive necessary support quickly.

Research indicates that mental health significantly affects cancer treatment outcomes and overall quality of life. Patients struggling with depression and anxiety often have poorer survival rates, likely due to difficulties in adhering to treatment plans and managing side effects.

Despite the critical need, only about 15% of cancer patients currently access psychiatric services, while another 45% would benefit from counseling.

Barriers such as stigma, lack of service awareness, and the challenge of diagnosing mental health conditions contribute to this underutilization.

Dr. Nunez is now looking to collaborate with oncologists and patients to explore practical applications of this AI tool, which could range from prompting oncologists to discuss mental health care options with their patients to sending patients tailored emails listing available services.

This AI was developed by a multidisciplinary team, combining expertise from computer science, medical oncology, and psychiatry.

The team trained the model using data from 59,800 patients across all six BC Cancer locations in British Columbia. To ensure confidentiality, all patient data was securely stored and anonymized.

The researchers have also made strides in AI interpretability, a significant advancement given the complexity of neural models.

By developing techniques that allow them to understand how the AI makes its predictions, they identified common indicators linked to higher needs for mental health services, such as family cancer history, substance use patterns, and certain aggressive cancer types.

Study co-author Dr. Raymond Ng, a professor in UBC’s Department of Computer Science, highlighted the importance of these interpretability advances.

He noted that understanding how AI models synthesize data from multiple documents could significantly enhance both research and clinical practice, especially in the complex interplay between oncology and mental health.

Looking forward, the team envisions expanding this AI tool’s application beyond oncology to other medical fields where psychosocial factors greatly impact patient outcomes.

This expansion could revolutionize how healthcare providers approach early intervention and patient care across various disciplines.

If you care about depression, please read studies about how dairy foods may influence depression risk, and B vitamins could help prevent depression and anxiety.

For more information about mental health, please see recent studies that ultra-processed foods may make you feel depressed, and extra-virgin olive oil could reduce depression symptoms.

The research findings can be found in Communications Medicine.

Copyright © 2024 Knowridge Science Report. All rights reserved.