Moving Biosurveillance Beyond Coded Data Using AI for Symptom Detection From Physician Notes: Retrospective Cohort Study.
Andrew J McMurryAmy R ZipurskyAlon GevaKaren L OlsonJames R JonesVladimir IgnatovTimothy A MillerKenneth D MandlPublished in: Journal of medical Internet research (2024)
This study establishes the value of AI-based NLP as a highly effective tool for real-time COVID-19 symptom detection in pediatric patients, outperforming traditional ICD-10 methods. It also reveals the evolving nature of symptom prevalence across different virus variants, underscoring the need for dynamic, technology-driven approaches in infectious disease surveillance.
Keyphrases
- infectious diseases
- artificial intelligence
- coronavirus disease
- loop mediated isothermal amplification
- patient reported
- sars cov
- real time pcr
- label free
- emergency department
- primary care
- big data
- copy number
- electronic health record
- gene expression
- machine learning
- deep learning
- dna methylation
- genome wide
- sensitive detection