Development and temporal validation of an explainable machine-learning model for identifying anxiety symptoms in adults with sudden sensorineural hearing loss

Sudden sensorineural hearing loss (SSNHL) may be accompanied by substantial psychological distress, yet machine-learning studies have focused mainly on hearing recovery rather than anxiety during acute care. OBJECTIVE: To develop, internally validate, temporally evaluate, and interpret machine-learning models for identifying anxiety symptoms in adults hospitalized with first-episode SSNHL after initial treatment and...

Continue reading at PubMed →

No actionable change yet — the model is at development/validation stage and has not been prospectively deployed; clinicians should remain alert to anxiety in SSNHL patients but cannot apply this tool outside a research setting.

Psychological distress is under-screened in sudden sensorineural hearing loss care, and an explainable, validated ML model could systematically close that gap if translated to clinical workflows.

1. 01ML model developed and temporally validated to flag anxiety in adults with sudden sensorineural hearing loss (SSNHL).
2. 02Model uses explainability features, allowing clinicians to see which factors drove each prediction.
3. 03Psychological screening is not routine in most SSNHL clinical pathways, highlighting a care gap.
4. 04Temporal validation (testing on later patients) strengthens generalizability compared to random split validation.
5. 05Study published in Frontiers in Public Health (2026).

PMID

42996158

DOI

10.3389/fpubh.2026.2003468.

Journal

Frontiers in Public Health

Publication type

research_article

Evidence level

2b

Population

Adults with sudden sensorineural hearing loss

Intervention

Explainable machine-learning model for anxiety symptom identification