Clinical notes used to flag mental-health risk in chronic illness
Original title: Beyond Physical Illness: Can Clinical Narratives Reveal Emerging Mental Health Risks in Chronically Ill Patients?
A weakly supervised MIMIC-III cohort of about 4,000 patients tracks risk from day-wise narratives.
The study asks whether latent mental-health risk in chronically ill patients hospitalized mainly for physical illness can be inferred from longitudinal clinical notes. A weakly supervised cohort of around 4,000 MIMIC-III patients is built from mental-health evidence in discharge summaries, covering risks such as depression, dementia, and suicidal ideation. A hierarchical state-space model turns day-wise narratives into representations and tracks them over the stay. Preliminary results show better binary risk prediction and distinct trajectories for risk and no-risk groups.
Unconfirmed: Results are described as preliminary.
- The cohort is about 4,000 patients drawn from MIMIC-III.
- Labels come from mental-health evidence in discharge summaries.
- The model estimates risk throughout hospitalization, not only at discharge.
- Preliminary results separate risk and no-risk trajectory patterns.
From the original article
1 min read at arxiv.orgMental-health risks such as depression, dementia, and suicidal ideation can emerge during hospitalization among chronically ill patients and may worsen without timely recognition and intervention. However, most existing mental health studies focus on patients with established psychiatric conditions rather than patients hospitalized primarily for physical illness.
By Sudeshna Jana · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.