1
|
McMurry AJ, Zipursky AR, Geva A, Olson KL, Jones JR, Ignatov V, Miller TA, Mandl KD. Moving Biosurveillance Beyond Coded Data Using AI for Symptom Detection From Physician Notes: Retrospective Cohort Study. J Med Internet Res 2024; 26:e53367. [PMID: 38573752 PMCID: PMC11027052 DOI: 10.2196/53367] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2023] [Revised: 11/30/2023] [Accepted: 02/27/2024] [Indexed: 04/05/2024] Open
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 This study sought to validate and test an artificial intelligence (AI)-based natural language processing (NLP) pipeline for detecting COVID-19 symptoms from physician notes in pediatric patients. We specifically study patients presenting to the emergency department (ED) who can be sentinel cases in an outbreak. METHODS Subjects in this retrospective cohort study are patients who are 21 years of age and younger, who presented to a pediatric ED at a large academic children's hospital between March 1, 2020, and May 31, 2022. The ED notes for all patients were processed with an NLP pipeline tuned to detect the mention of 11 COVID-19 symptoms based on Centers for Disease Control and Prevention (CDC) criteria. For a gold standard, 3 subject matter experts labeled 226 ED notes and had strong agreement (F1-score=0.986; positive predictive value [PPV]=0.972; and sensitivity=1.0). F1-score, PPV, and sensitivity were used to compare the performance of both NLP and the International Classification of Diseases, 10th Revision (ICD-10) coding to the gold standard chart review. As a formative use case, variations in symptom patterns were measured across SARS-CoV-2 variant eras. RESULTS There were 85,678 ED encounters during the study period, including 4% (n=3420) with patients with COVID-19. NLP was more accurate at identifying encounters with patients that had any of the COVID-19 symptoms (F1-score=0.796) than ICD-10 codes (F1-score =0.451). NLP accuracy was higher for positive symptoms (sensitivity=0.930) than ICD-10 (sensitivity=0.300). However, ICD-10 accuracy was higher for negative symptoms (specificity=0.994) than NLP (specificity=0.917). Congestion or runny nose showed the highest accuracy difference (NLP: F1-score=0.828 and ICD-10: F1-score=0.042). For encounters with patients with COVID-19, prevalence estimates of each NLP symptom differed across variant eras. Patients with COVID-19 were more likely to have each NLP symptom detected 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.
Collapse
Affiliation(s)
- Andrew J McMurry
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - Amy R Zipursky
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Division of Pediatric Emergency Medicine, Department of Pediatrics, The Hospital for Sick Children, Toronto, ON, Canada
| | - Alon Geva
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Division of Critical Care Medicine, Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, United States
- Department of Anaesthesia, Harvard Medical School, Boston, MA, United States
| | - Karen L Olson
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - James R Jones
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
| | - Vladimir Ignatov
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
| | - Timothy A Miller
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
| | - Kenneth D Mandl
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, United States
- Department of Pediatrics, Harvard Medical School, Boston, MA, United States
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States
| |
Collapse
|
2
|
Miller TA, McMurry AJ, Jones J, Gottlieb D, Mandl KD. The SMART Text2FHIR Pipeline. AMIA ... ANNUAL SYMPOSIUM PROCEEDINGS. AMIA SYMPOSIUM 2024; 2023:514-520. [PMID: 38222416 PMCID: PMC10785871] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 01/16/2024]
Abstract
Objective: To implement an open source, free, and easily deployable high throughput natural language processing module to extract concepts from clinician notes and map them to Fast Healthcare Interoperability Resources (FHIR). Materials and Methods: Using a popular open-source NLP tool (Apache cTAKES), we create FHIR resources that use modifier extensions to represent negation and NLP sourcing, and another extension to represent provenance of extracted concepts. Results: The SMART Text2FHIR Pipeline is an open-source tool, released through standard package managers, and publicly available container images that implement the mappings, enabling ready conversion of clinical text to FHIR. Discussion: With the increased data liquidity because of new interoperability regulations, NLP processes that can output FHIR can enable a common language for transporting structured and unstructured data. This framework can be valuable for critical public health or clinical research use cases. Conclusion: Future work should include mapping more categories of NLP-extracted information into FHIR resources and mappings from additional open-source NLP tools.
Collapse
Affiliation(s)
- Timothy A Miller
- Boston Children's Hospital, Boston, MA
- Harvard Medical School, Boston, MA
| | - Andrew J McMurry
- Boston Children's Hospital, Boston, MA
- Harvard Medical School, Boston, MA
| | - James Jones
- Boston Children's Hospital, Boston, MA
- Harvard Medical School, Boston, MA
| | - Daniel Gottlieb
- Boston Children's Hospital, Boston, MA
- Harvard Medical School, Boston, MA
| | - Kenneth D Mandl
- Boston Children's Hospital, Boston, MA
- Harvard Medical School, Boston, MA
| |
Collapse
|