1
|
Eyre H, Alba PR, Gibson CJ, Gatsby E, Lynch KE, Patterson OV, DuVall SL. Bridging information gaps in menopause status classification through natural language processing. JAMIA Open 2024; 7:ooae013. [PMID: 38419670 PMCID: PMC10901606 DOI: 10.1093/jamiaopen/ooae013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 01/22/2024] [Accepted: 02/06/2024] [Indexed: 03/02/2024] Open
Abstract
Objective To use natural language processing (NLP) of clinical notes to augment existing structured electronic health record (EHR) data for classification of a patient's menopausal status. Materials and methods A rule-based NLP system was designed to capture evidence of a patient's menopause status including dates of a patient's last menstrual period, reproductive surgeries, and postmenopause diagnosis as well as their use of birth control and menstrual interruptions. NLP-derived output was used in combination with structured EHR data to classify a patient's menopausal status. NLP processing and patient classification were performed on a cohort of 307 512 female Veterans receiving healthcare at the US Department of Veterans Affairs (VA). Results NLP was validated at 99.6% precision. Including the NLP-derived data into a menopause phenotype increased the number of patients with data relevant to their menopausal status by 118%. Using structured codes alone, 81 173 (27.0%) are able to be classified as postmenopausal or premenopausal. However, with the inclusion of NLP, this number increased 167 804 (54.6%) patients. The premenopausal category grew by 532.7% with the inclusion of NLP data. Discussion By employing NLP, it became possible to identify documented data elements that predate VA care, originate outside VA networks, or have no corresponding structured field in the VA EHR that would be otherwise inaccessible for further analysis. Conclusion NLP can be used to identify concepts relevant to a patient's menopausal status in clinical notes. Adding NLP-derived data to an algorithm classifying a patient's menopausal status significantly increases the number of patients classified using EHR data, ultimately enabling more detailed assessments of the impact of menopause on health outcomes.
Collapse
Affiliation(s)
- Hannah Eyre
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT 84113, United States
- Department of Internal Medicine, School of Medicine, University of Utah, Salt Lake City, UT 84112, United States
| | - Patrick R Alba
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT 84113, United States
- Department of Internal Medicine, School of Medicine, University of Utah, Salt Lake City, UT 84112, United States
| | - Carolyn J Gibson
- San Francisco VA Healthcare System, San Francisco, CA 94121, United States
- University of California, San Francisco, San Francisco, CA 94115, United States
| | - Elise Gatsby
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT 84113, United States
| | - Kristine E Lynch
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT 84113, United States
- Department of Internal Medicine, School of Medicine, University of Utah, Salt Lake City, UT 84112, United States
| | - Olga V Patterson
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT 84113, United States
- Department of Internal Medicine, School of Medicine, University of Utah, Salt Lake City, UT 84112, United States
| | - Scott L DuVall
- VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT 84113, United States
- Department of Internal Medicine, School of Medicine, University of Utah, Salt Lake City, UT 84112, United States
| |
Collapse
|
2
|
Young-Xu Y, Korves C, Zwain G, Satram S, Drysdale M, Reyes C, Cheng MM, Bonomo RA, Epstein L, Marconi VC, Ginde AA. Effectiveness of Sotrovimab in Preventing COVID-19-Related Hospitalizations or Deaths Among US Veterans During Omicron BA.1. Open Forum Infect Dis 2023; 10:ofad605. [PMID: 38152625 PMCID: PMC10751450 DOI: 10.1093/ofid/ofad605] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2023] [Accepted: 11/29/2023] [Indexed: 12/29/2023] Open
Abstract
Background The real-world clinical effectiveness of sotrovimab in preventing coronavirus disease 2019 (COVID-19)-related hospitalization or mortality among high-risk patients diagnosed with COVID-19, particularly after the emergence of the Omicron variant, needs further research. Method Using data from the US Department of Veterans Affairs (VA) health care system, we adopted a target trial emulation design in our study. Veterans aged ≥18 years, diagnosed with COVID-19 between December 1, 2021, and April 4, 2022, were included. Patients treated with sotrovimab (n = 2816) as part of routine clinical care were compared with all eligible but untreated patients (n = 11,250). Cox proportional hazards modeling estimated the hazard ratios (HRs) and 95% CIs for the association between receipt of sotrovimab and outcomes. Results Most (90%) sotrovimab recipients were ≥50 years old, and 64% had ≥2 mRNA vaccine doses or ≥1 dose of Ad26.COV2. During the period that BA.1 was dominant, compared with patients not treated, sotrovimab-treated patients had a 70% lower risk of hospitalization or mortality within 30 days (HR, 0.30; 95% CI, 0.23-0.40). During BA.2 dominance, sotrovimab-treated patients had a 71% (HR, 0.29; 95% CI, 0.08-0.98) lower risk of 30-day COVID-19-related hospitalization, emergency room visits, or urgent care visits (defined as severe COVID-19) compared with patients not treated. Conclusions Using national real-world data from high-risk and predominantly vaccinated veterans, administration of sotrovimab, compared with contemporary standard treatment regimens, was associated with reduced risk of 30-day COVID-19-related hospitalization or all-cause mortality during the Omicron BA.1 period.
Collapse
Affiliation(s)
- Yinong Young-Xu
- US Department of Veterans Affairs, PBM, Center for Medication Safety, Hines, Illinois, USA
- Geisel School of Medicine at Dartmouth, Hanover, New Hampshire, USA
| | - Caroline Korves
- US Department of Veterans Affairs, PBM, Center for Medication Safety, Hines, Illinois, USA
- White River Junction Veterans Affairs Medical Center, White River Junction, Vermont
| | - Gabrielle Zwain
- US Department of Veterans Affairs, PBM, Center for Medication Safety, Hines, Illinois, USA
- White River Junction Veterans Affairs Medical Center, White River Junction, Vermont
| | - Sacha Satram
- Vir Biotechnology, San Francisco, California, USA
| | | | | | | | - Robert A Bonomo
- US Department of Veterans Affairs, VA SHIELD, Veterans Affairs Northeast Ohio Healthcare System, Cleveland, Ohio, USA
- Case Western Reserve University, Cleveland, Ohio, USA
| | - Lauren Epstein
- Atlanta Veterans Affairs Medical Center, Decatur, Georgia, USA
- Division of Infectious Diseases, Emory University School of Medicine, Atlanta, Georgia, USA
| | - Vincent C Marconi
- Atlanta Veterans Affairs Medical Center, Decatur, Georgia, USA
- Division of Infectious Diseases, Emory University School of Medicine, Atlanta, Georgia, USA
- Department of Global Health, Rollins School of Public Health, Emory University, Atlanta, Georgia, USA
| | - Adit A Ginde
- Department of Emergency Medicine, University of Colorado School of Medicine, Aurora, Colorado, USA
| |
Collapse
|