Moving Biosurveillance Beyond Coded Data: AI for Symptom Detection from Physician Notes
Bibliographic record
Abstract
Abstract Background Real-time surveillance of emerging infectious diseases necessitates a dynamically evolving, computable case definition, which frequently incorporates symptom-related criteria. For symptom detection, both population health monitoring platforms and research initiatives primarily depend on structured data extracted from electronic health records. Objective To validate and test an artificial intelligence (AI) based Natural Language Processing (NLP) pipeline for detecting COVID-19 symptoms from physician notes. Methods Subjects in this retrospective cohort study are patients 21 years old and younger, who presented to a pediatric emergency department (ED) at a large academic children’s hospital between March 1, 2020 and May 31, 2022. ED notes for all patients were processed with an NLP pipeline tuned to detect the mention of 11 COVID-19 symptoms based on CDC criteria. For a gold standard, 3 subject matter experts labeled 226 ED notes and had strong agreement (F1=98.6; PPV=97.2; Recall=100.0). F1, PPV, and recall were used to compare the performance of both NLP and ICD-10 to the gold standard chart review. As a formative use case, variations in symptom patterns were measured across SARS-Cov2 variant eras. Results There were 85,678 ED encounters during the study period, 4.0% with patients with COVID-19. NLP was more accurate at identifying encounters with patients that had any of the COVID-19 symptoms (F1=79.6) than ICD-10 codes (F1=45.1%). NLP accuracy was higher for positive symptoms (recall=93%) than ICD-10 (recall=30%). However, ICD-10 accuracy was higher for negative symptoms (specificity=99.4%) than NLP (specificity=91.7%). Congestion or runny nose showed the highest accuracy difference: NLP F1=82.8%, ICD-10 F1=4.2%. Prevalence of NLP symptoms among patients with COVID-19 differed across variant eras. And patients with COVID-19 were more likely to have each symptom than patients without this disease. Effect sizes (odds ratios) varied across pandemic eras. Conclusions 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".