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] [What about the content of this article? (0)] [Affiliation(s)] [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
|
Malik FS, Liese AD, Ellyson A, Reid LA, Reboussin BA, Sauder KA, Frongillo EA, Pihoker C, Dabelea D, Reynolds K, Jensen ET, Marcovina S, Bowlby DA, Mendoza JA. Household food insecurity and associations with hemoglobin A 1c and acute diabetes-related complications in youth and young adults with type 1 diabetes: The SEARCH for diabetes in youth study. Diabetes Res Clin Pract 2024:111608. [PMID: 38574894 DOI: 10.1016/j.diabres.2024.111608] [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] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/25/2023] [Revised: 02/20/2024] [Accepted: 03/06/2024] [Indexed: 04/06/2024]
Abstract
AIMS To examine, among youth and young adults (YYA) with type 1 diabetes (T1D), the association of household food insecurity (HFI) with: 1) HbA1c and 2) episodes of diabetic ketoacidosis (DKA) and severe hypoglycemia. METHODS HFI was assessed using the U.S. Household Food Security Survey Module in SEARCH for Diabetes in Youth participants with T1D between 2016 and 2019. Linear and logistic regression models adjusted for age, diabetes duration, sex, race, ethnicity, clinic site, parent/participant education, household income, health insurance, and diabetes technology use. RESULTS Of 1830 participants (mean age 20.8 ± 5.0 years, 70.0 % non-Hispanic White), HbA1c was collected for 1060 individuals (mean HbA1c 9.2 % ± 2.0 %). The prevalence of HFI was 16.4 %. In the past 12 months, 18.2 % and 9.9 % reported an episode of DKA or severe hypoglycemia, respectively. Compared to participants who were food secure, HFI was associated with a 0.33 % (95 % CI 0.003, 0.657) higher HbA1c level. Those with HFI had 1.58 (95 % CI 1.13, 2.21) times the adjusted odds of an episode of DKA and 1.53 (95 % CI 0.99, 2.37) times the adjusted odds of an episode of severe hypoglycemia as those without HFI. CONCLUSIONS HFI is associated with higher HbA1c levels and increased odds of DKA in YYA with T1D.
Collapse
Affiliation(s)
- Faisal S Malik
- Department of Pediatrics, University of Washington School of Medicine, Seattle, United States; Seattle Children's Research Institute, Seattle, United States.
| | | | - Alice Ellyson
- Department of Pediatrics, University of Washington School of Medicine, Seattle, United States; Seattle Children's Research Institute, Seattle, United States
| | - Lauren A Reid
- University of South Carolina, Columbia, United States; South College, Atlanta, United States
| | - Beth A Reboussin
- Wake Forest University School of Medicine, Winston-Salem, United States
| | | | | | - Catherine Pihoker
- Department of Pediatrics, University of Washington School of Medicine, Seattle, United States; Seattle Children's Research Institute, Seattle, United States
| | - Dana Dabelea
- University of Colorado Anschutz Medical Campus, Aurora, United States
| | - Kristi Reynolds
- Kaiser Permanente Southern California, Pasadena, United States
| | | | | | | | - Jason A Mendoza
- Department of Pediatrics, University of Washington School of Medicine, Seattle, United States; Seattle Children's Research Institute, Seattle, United States; Fred Hutchinson Cancer Center, Seattle, United States
| |
Collapse
|
3
|
Conrick KM, Adhia A, Ellyson A, Haviland MJ, Lyons VH, Mills B, Rowhani-Rahbar A. Race, structural racism and racial disparities in firearm homicide victimisation. Inj Prev 2023; 29:290-295. [PMID: 36564165 DOI: 10.1136/ip-2022-044788] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Accepted: 12/06/2022] [Indexed: 12/25/2022]
Abstract
OBJECTIVES To identify an approach in measuring the association between structural racism and racial disparities in firearm homicide victimisation focusing on racism, rather than race. METHODS We examined associations of six measures of structural racism (Black/white disparity ratios in poverty, education, labour force participation, rental housing, single-parent households and index crime arrests) with state-level Black-white disparities in US age-adjusted firearm homicide victimisation rates 2010-2019. We regressed firearm homicide victimisation disparities on four specifications of independent variables: (1) absolute measure only; (2) absolute measure and per cent Black; (3) absolute measure and Black-white disparity ratio and (4) absolute measure, per cent Black and disparity ratio. RESULTS For all six measures of structural racism the optimal specification included the absolute measure and Black-white disparity ratio and did not include per cent Black. Coefficients for the Black-white disparity were statistically significant, while per cent Black was not. CONCLUSIONS In the presence of structural racism measures, the inclusion of per cent Black did not contribute to the explanation of firearm homicide disparities in this study. Findings provide empiric evidence for the preferred use of structural racism measures instead of race.
Collapse
Affiliation(s)
- Kelsey M Conrick
- School of Social Work, University of Washington, Seattle, Washington, USA
- Firearm Injury & Policy Research Program, University of Washington, Seattle, Washington, USA
| | - Avanti Adhia
- Firearm Injury & Policy Research Program, University of Washington, Seattle, Washington, USA
- Department of Child, Family, and Population Health Nursing, School of Nursing, University of Washington, Seattle, Washington, USA
| | - Alice Ellyson
- Firearm Injury & Policy Research Program, University of Washington, Seattle, Washington, USA
- Center for Child Health, Behavior and Development, Seattle Children's Research Institute, Seattle, Washington, USA
| | - Miriam Joan Haviland
- Firearm Injury & Policy Research Program, University of Washington, Seattle, Washington, USA
| | - Vivian H Lyons
- Social Development Research Group, School of Social Work, Department of Psychiatry, University of Washington Allies in Healthier Systems for Health & Abundance in Youth, Seattle, Washington, USA
| | - Brianna Mills
- Firearm Injury & Policy Research Program, University of Washington, Seattle, Washington, USA
- Department of Epidemiology, School of Public Health, University of Washington, Seattle, Washington, USA
| | - Ali Rowhani-Rahbar
- Department of Epidemiology, School of Public Health, University of Washington, Seattle, Washington, USA
| |
Collapse
|
4
|
Schleimer JP, Gause E, Dalve K, Ellyson A, Rowhani-Rahbar A. Rural-Urban Variation in the Association of Adolescent Violence and Handgun Carrying in the United States, 2002-2019. JAMA Netw Open 2023; 6:e231153. [PMID: 36853603 PMCID: PMC9975933 DOI: 10.1001/jamanetworkopen.2023.1153] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/11/2022] [Accepted: 01/15/2023] [Indexed: 03/01/2023] Open
Abstract
Importance Adolescent handgun carrying is associated with increased risk of firearm-related violence. Most evidence on adolescent handgun carrying is from urban areas, but these findings may not generalize to rural areas. Objective To examine differences in associations of adolescent interpersonal violence with handgun carrying across the rural-urban continuum. Design, Setting, and Participants This cross-sectional study used nationally representative data from the US National Survey on Drug Use and Health among adolescents aged 12 to 17 years from 2002 to 2019 to estimate time-varying prevalence ratios (PRs) and prevalence differences (PDs) between interpersonal violence and handgun carrying across the rural-urban continuum. Analyses were conducted in April to July 2022. Exposures Any past-year serious fighting, group fighting, and attacking with intent to harm. Main Outcomes and Measures Any past-year handgun carrying. Associations were estimated within county rural-urban strata using the US Department of Agriculture's Rural-Urban Continuum Codes. Results In each year, the sample included a weighted count of almost 25 million adolescents, with 50.9% (95% CI, 50.2%-51.6%) males and 24.7% (95% CI, 23.8%-25.6%) Hispanic adolescents, 13.5% (95% CI, 12.8%-14.2%) non-Hispanic Black adolescents, and 51.8% (95% CI, 50.8%-52.8%) non-Hispanic White adolescents in 2019. More rural counties had less racial and ethnic diversity. For example, 81.1% (95% CI, 75.9%-85.4%) of adolescents were non-Hispanic White in the most rural counties vs 43.1% (95% CI, 41.7%-44.6%) of adolescents were non-Hispanic White in the most urban counties in 2019. Adolescent handgun carrying increased over time, with the largest increases in the most rural counties, where the prevalence of adolescent handgun carrying increased from 5.2% (95% CI, 3.8%-7.0%) in 2003 to 12.4% (95% CI, 8.9%-16.9%) in 2019. PRs for the association of violence and handgun carrying were greater in more urban counties. For example, in the most urban counties in 2019, adolescents involved in a group fight had 3.7 (95% CI, 2.9-4.8) times the prevalence of handgun carrying vs those not involved in a group fight; this PR was 3.1 (95% CI, 1.6-5.6) in the most rural counties. PDs were similar and, in some cases, larger in rural areas. For example, in the most urban counties in 2019, handgun carrying prevalence was 7.5% (95% CI, 5.7%-9.5%) higher among adolescents who were involved in a group fight compared with those who were not; this PD was 21.8% (95% CI, 8.2%-37.8%) in the most rural counties, where handgun carrying was more common. Conclusions and Relevance This cross-sectional study found that associations of interpersonal violence with handgun carrying were stronger in relative terms in urban areas than in rural areas; however, a higher percentage of rural than urban adolescents carried handguns, resulting in a greater absolute prevalence of handgun carrying associated with violence in rural areas than in urban areas. These findings suggest opportunities for preventing handgun carrying-related harms may differ between rural and urban communities.
Collapse
Affiliation(s)
- Julia P. Schleimer
- Department of Epidemiology, University of Washington, Seattle
- Firearm Injury and Policy Research Program, University of Washington, Seattle
| | - Emma Gause
- Department of Epidemiology, University of Washington, Seattle
- Firearm Injury and Policy Research Program, University of Washington, Seattle
| | - Kimberly Dalve
- Department of Epidemiology, University of Washington, Seattle
- Firearm Injury and Policy Research Program, University of Washington, Seattle
| | - Alice Ellyson
- Firearm Injury and Policy Research Program, University of Washington, Seattle
- Department of Pediatrics, University of Washington, Seattle
- Center for Child Health, Behavior, and Development, Seattle Children’s Research Institute, Seattle, Washington
| | - Ali Rowhani-Rahbar
- Department of Epidemiology, University of Washington, Seattle
- Firearm Injury and Policy Research Program, University of Washington, Seattle
- Department of Pediatrics, University of Washington, Seattle
| |
Collapse
|
5
|
Prater LC, Ellyson A, Fihn SD. Incentivizing Firearm Safety and Storage Counseling in the US Health Care System: a Path Forward. J Gen Intern Med 2021; 36:3568-3570. [PMID: 33904041 PMCID: PMC8075276 DOI: 10.1007/s11606-021-06800-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/26/2021] [Accepted: 04/01/2021] [Indexed: 12/01/2022]
Affiliation(s)
- Laura C Prater
- Harborview Injury Prevention and Research Center, Harborview Medical Center, University of Washington, 401 Broadway Suite 2075, Seattle, WA, 98104, USA. .,Department of Epidemiology, School of Public Health, University of Washington, Seattle, WA, USA.
| | - Alice Ellyson
- Harborview Injury Prevention and Research Center, Harborview Medical Center, University of Washington, 401 Broadway Suite 2075, Seattle, WA, 98104, USA.,Department of Pediatrics, University of Washington, Seattle, WA, USA
| | - Stephan D Fihn
- Department of Medicine, University of Washington, Seattle, WA, USA.,Department of Health Services, School of Public Health, University of Washington, Seattle, WA, USA
| |
Collapse
|
6
|
Lyons VH, Haviland MJ, Azrael D, Adhia A, Bellenger MA, Ellyson A, Rowhani-Rahbar A, Rivara FP. Firearm purchasing and storage during the COVID-19 pandemic. Inj Prev 2020; 27:87-92. [DOI: 10.1136/injuryprev-2020-043872] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2020] [Revised: 08/19/2020] [Accepted: 08/22/2020] [Indexed: 11/04/2022]
Abstract
To better understand motivations behind purchase and storage of firearms during the COVID-19 pandemic, we used Amazon Mechanical Turk to conduct an online survey of individuals who did and did not purchase a firearm since 1 January 2020 in response to COVID-19. The survey was fielded between 1 and 5 May 2020. We asked about motivations for purchase, changes in storage practices and concern for themselves or others due to COVID-19. There were 1105 survey respondents. Most people who purchased a firearm did so to protect themselves from people. Among respondents who had purchased a firearm in response to COVID-19 without prior household firearm ownership, 39.7% reported at least one firearm was stored unlocked. Public health efforts to improve firearm-related safety during COVID-19 should consider increasing access to training and framing messages around the concerns motivating new firearm purchase.
Collapse
|