1
|
Kafka JM, Schleimer JP, Toomet O, Chen K, Ellyson A, Rowhani-Rahbar A. Measuring interpersonal firearm violence: natural language processing methods to address limitations in criminal charge data. J Am Med Inform Assoc 2024:ocae082. [PMID: 38607336 DOI: 10.1093/jamia/ocae082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2024] [Revised: 03/27/2024] [Accepted: 04/02/2024] [Indexed: 04/13/2024] Open
Abstract
OBJECTIVE Firearm violence constitutes a public health crisis in the United States, but comprehensive data infrastructure is lacking to study this problem. To address this challenge, we used natural language processing (NLP) to classify court record documents from alleged violent crimes as firearm-related or non-firearm-related. MATERIALS AND METHODS We accessed and digitized court records from the state of Washington (n = 1472). Human review established a gold standard label for firearm involvement (yes/no). We developed a key term search and trained supervised machine learning classifiers for this labeling task. Results were evaluated in a held-out test set. RESULTS The decision tree performed best (F1 score: 0.82). The key term list had perfect recall (1.0) and a modest F1 score (0.65). DISCUSSION AND CONCLUSION This case report highlights the accuracy, feasibility, and potential time-saved by using NLP to identify firearm involvement in alleged violent crimes based on digitized narratives from court documents.
Collapse
Affiliation(s)
- Julie M Kafka
- Firearm Injury & Policy Research Program, University of Washington, Seattle, WA 98195, United States
- Department of Pediatrics, School of Medicine, University of Washington, Seattle, WA 98195, United States
| | - Julia P Schleimer
- Firearm Injury & Policy Research Program, University of Washington, Seattle, WA 98195, United States
- Department of Epidemiology, School of Public Health, University of Washington, Seattle, WA 98195, United States
| | - Ott Toomet
- Information School, University of Washington Seattle, WA 98195, United States
| | - Kaidi Chen
- Information School, University of Washington Seattle, WA 98195, United States
| | - Alice Ellyson
- Firearm Injury & Policy Research Program, University of Washington, Seattle, WA 98195, United States
- Department of Pediatrics, School of Medicine, University of Washington, Seattle, WA 98195, United States
| | - Ali Rowhani-Rahbar
- Firearm Injury & Policy Research Program, University of Washington, Seattle, WA 98195, United States
- Department of Epidemiology, School of Public Health, University of Washington, Seattle, WA 98195, United States
| |
Collapse
|
2
|
Bond AE, Moceri-Brooks J, Rodriguez TR, Semenza D, Anestis MD. Determining who healthcare providers screen for firearm access in the United States. Prev Med 2023; 169:107476. [PMID: 36870571 DOI: 10.1016/j.ypmed.2023.107476] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Revised: 02/21/2023] [Accepted: 02/27/2023] [Indexed: 03/06/2023]
Abstract
Healthcare providers are well positioned to screen for firearm access to reduce risk of suicides, yet there is a limited understanding of how often and for whom firearm access screening occurs. The present study examined the extent to which providers screen for firearm access and sought to identify who has been screened in the past. The representative sample included 3510 residents from five US states who reported whether they have been asked about their access to firearms by a healthcare provider. The findings demonstrate that most participants have never been asked by a provider about firearm access. People who have been asked were more likely to be White, male, and firearm owners. Those with children under 17 years old in the home, that have been in mental health treatment, and report a history of suicidal ideation were more likely to be screened for firearm access. Although there are interventions for mitigating firearm related risks in healthcare settings, many providers may be missing the opportunity to implement these because they do not ask about firearm access.
Collapse
Affiliation(s)
- Allison E Bond
- The New Jersey Gun Violence Research Center, Rutgers University, United States of America; Department of Psychology, Rutgers University, United States of America; Department of Sociology, Anthropology, and Criminal Justice, Rutgers University - Camden, United States of America.
| | - Jayna Moceri-Brooks
- The New Jersey Gun Violence Research Center, Rutgers University, United States of America; School of Public Health, Rutgers University, United States of America
| | - Taylor R Rodriguez
- The New Jersey Gun Violence Research Center, Rutgers University, United States of America; Department of Psychology, Rutgers University, United States of America
| | - Daniel Semenza
- The New Jersey Gun Violence Research Center, Rutgers University, United States of America; Department of Sociology, Anthropology, and Criminal Justice, Rutgers University - Camden, United States of America
| | - Michael D Anestis
- The New Jersey Gun Violence Research Center, Rutgers University, United States of America; School of Public Health, Rutgers University, United States of America
| |
Collapse
|
3
|
Goulet JL, Warren AR, Workman TE, Skanderson M, Farmer MM, Gordon KS, Abel EA, Akgün KM, Bean-Mayberry B, Zeng-Treitler Q, Haderlein TP, Haskell SG, Bastian LA, Womack JA, Post LA, Hwang U, Brandt CA. Variation in firearm screening and access by LGBT status. Acad Emerg Med 2023; 30:420-423. [PMID: 36661348 DOI: 10.1111/acem.14664] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Revised: 01/10/2023] [Accepted: 01/13/2023] [Indexed: 01/21/2023]
Affiliation(s)
- Joseph L Goulet
- Department of Emergency Medicine, Yale School of Medicine, New Haven, Connecticut, USA.,VA Connecticut Healthcare System, West Haven, Connecticut, USA
| | - Allison R Warren
- VA Connecticut Healthcare System, West Haven, Connecticut, USA.,Department of Psychiatry, Yale School of Medicine, New Haven, Connecticut, USA
| | - T Elizabeth Workman
- Biomedical Informatics Center, The George Washington University, Washington, DC, USA
| | | | - Melissa M Farmer
- Center for the Study of Healthcare Innovation, Implementation & Policy (CSHIIP), Los Angeles, California, USA.,VA Greater Los Angeles Healthcare System, Los Angeles, California, USA
| | - Kirsha S Gordon
- VA Connecticut Healthcare System, West Haven, Connecticut, USA.,Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Erica A Abel
- VA Connecticut Healthcare System, West Haven, Connecticut, USA.,Department of Psychiatry, Yale School of Medicine, New Haven, Connecticut, USA
| | - Kathleen M Akgün
- VA Connecticut Healthcare System, West Haven, Connecticut, USA.,Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Bevanne Bean-Mayberry
- Center for the Study of Healthcare Innovation, Implementation & Policy (CSHIIP), Los Angeles, California, USA.,VA Greater Los Angeles Healthcare System, Los Angeles, California, USA.,Department of Medicine, UCLA-David Geffen School of Medicine, Los Angeles, California, USA
| | - Qing Zeng-Treitler
- Biomedical Informatics Center, The George Washington University, Washington, DC, USA.,Washington DC VA Medical Center, Washington, DC, USA
| | - Taona P Haderlein
- Center for the Study of Healthcare Innovation, Implementation & Policy (CSHIIP), Los Angeles, California, USA.,VA Greater Los Angeles Healthcare System, Los Angeles, California, USA.,Department of Veterans Affairs, Veterans Emergency Management Evaluation Center (VEMEC), North Hills, California, USA
| | - Sally G Haskell
- VA Connecticut Healthcare System, West Haven, Connecticut, USA.,Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Lori A Bastian
- VA Connecticut Healthcare System, West Haven, Connecticut, USA.,Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Julie A Womack
- Department of Emergency Medicine, Yale School of Medicine, New Haven, Connecticut, USA.,Yale School of Nursing, VA Connecticut, West Haven, Connecticut, USA
| | - Lori A Post
- Northwestern University, Chicago, Illinois, USA
| | - Ula Hwang
- Department of Emergency Medicine, Yale School of Medicine, New Haven, Connecticut, USA.,Geriatric Research, Education and Clinical Center, James J. Peters VAMC, Bronx, New York, USA
| | - Cynthia A Brandt
- Department of Emergency Medicine, Yale School of Medicine, New Haven, Connecticut, USA.,VA Connecticut Healthcare System, West Haven, Connecticut, USA
| |
Collapse
|
4
|
A case for developing domain-specific vocabularies for extracting suicide factors from healthcare notes. J Psychiatr Res 2022; 151:328-338. [PMID: 35533516 DOI: 10.1016/j.jpsychires.2022.04.009] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/04/2022] [Revised: 04/09/2022] [Accepted: 04/18/2022] [Indexed: 11/23/2022]
Abstract
The onset and persistence of life events (LE) such as housing instability, job instability, and reduced social connection have been shown to increase risk of suicide. Predictive models for suicide risk have low sensitivity to many of these factors due to under-reporting in structured electronic health records (EHR) data. In this study, we show how natural language processing (NLP) can help identify LE in clinical notes at higher rates than reported medical codes. We compare domain-specific lexicons formulated from Unified Medical Language System (UMLS) selection, content analysis by subject matter experts (SME) and the Gravity Project, to data-driven expansion through contextual word embedding using Word2Vec. Our analysis covers EHR from the Veterans Affairs (VA) Corporate Data Warehouse (CDW) and measures the prevalence of LE across time for patients with known underlying cause of death in the National Death Index (NDI). We found that NLP methods had higher sensitivity of detecting LE relative to structured EHR (S-EHR) variables. We observed that, on average, suicide cases had higher rates of LE over time when compared to patients who died of non-suicide related causes with no previous history of diagnosed mental illness. When used to discriminate these outcomes, the inclusion of NLP derived variables increased the concentration of LE along the top 0.1%, 0.5% and 1% of predicted risk. LE were less informative when discriminating suicide death from non-suicide related death for patients with diagnosed mental illness.
Collapse
|