Creation of a data commons for substance misuse related health research through privacy-preserving patient record linkage between hospitals and state agencies

被引:4
作者
Afshar, Majid [1 ,5 ]
Oguss, Madeline [1 ]
Callaci, Thomas A. [1 ]
Gruenloh, Timothy [1 ]
Gupta, Preeti [2 ]
Sun, Claire [1 ]
Afshar, Askar Safipour [1 ]
Cavanaugh, Joseph [1 ]
Churpek, Matthew M. [1 ]
Nyakoe-Nyasani, Edwin [3 ]
Nguyen-Hilfiger, Huong [3 ]
Westergaard, Ryan [1 ,3 ]
Salisbury-Afshar, Elizabeth [1 ,3 ]
Gussick, Megan [1 ]
Patterson, Brian [1 ]
Manneh, Claire [4 ]
Mathew, Jomol [1 ]
Mayampurath, Anoop [1 ]
机构
[1] Univ Wisconsin Madison, Sch Med & Publ Hlth, Madison, WI 53706 USA
[2] Univ Illinois, Div Pulm & Crit Care, Chicago, IL 60607 USA
[3] State Wisconsin Dept Hlth Serv, Madison, WI 53703 USA
[4] Datavant Inc, San Francisco, CA 94104 USA
[5] Univ Wisconsin Madison, Sch Med & Publ Hlth, Dept Med, 600 Highland Ave,CSC H4-616, Madison, WI 53792 USA
关键词
substance abuse; opioids; alcohol; health information exchange; data commons; OVERDOSES; SCIENCE; SYSTEM;
D O I
10.1093/jamiaopen/ooad092
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Objectives Substance misuse is a complex and heterogeneous set of conditions associated with high mortality and regional/demographic variations. Existing data systems are siloed and have been ineffective in curtailing the substance misuse epidemic. Therefore, we aimed to build a novel informatics platform, the Substance Misuse Data Commons (SMDC), by integrating multiple data modalities to provide a unified record of information crucial to improving outcomes in substance misuse patients.Materials and Methods The SMDC was created by linking electronic health record (EHR) data from adult cases of substance (alcohol, opioid, nonopioid drug) misuse at the University of Wisconsin hospitals to socioeconomic and state agency data. To ensure private and secure data exchange, Privacy-Preserving Record Linkage (PPRL) and Honest Broker services were utilized. The overlap in mortality reporting among the EHR, state Vital Statistics, and a commercial national data source was assessed.Results The SMDC included data from 36 522 patients experiencing 62 594 healthcare encounters. Over half of patients were linked to the statewide ambulance database and prescription drug monitoring program. Chronic diseases accounted for most underlying causes of death, while drug-related overdoses constituted 8%. Our analysis of mortality revealed a 49.1% overlap across the 3 data sources. Nonoverlapping deaths were associated with poor socioeconomic indicators.Discussion Through PPRL, the SMDC enabled the longitudinal integration of multimodal data. Combining death data from local, state, and national sources enhanced mortality tracking and exposed disparities.Conclusion The SMDC provides a comprehensive resource for clinical providers and policymakers to inform interventions targeting substance misuse-related hospitalizations, overdoses, and death. Substance misuse comprises a heterogeneous and complex set of conditions associated with high mortality and regional and demographic variation. Healthcare providers and public health agencies who design treatment and preventative interventions have focused primarily on fatal events. Recently, the Office of National Drug Control Policy recommended shifting focus to early warning signs-emergency department visits or hospitalizations-that lie on the path to fatality. To aid this transition, we constructed the Substance Misuse Data Commons (SMDC), a first-of-its-kind informatics platform that links hospital data from adult cases of substance (alcohol, opioid, nonopioid drug) misuse from a regional health system to census, national mortality, and state agency data. Our article describes our privacy-ensuring data-linking process and the characteristics of SMDC patients. Over half of the 36 522 SMDC patients had data from statewide ambulance and prescription drug databases. The majority of deaths were attributable to chronic diseases, more so than overdose deaths. There was a 49.1% overlap in death cases across the 3 mortality data sources, highlighting the value in our use of electronic health records, state vital records, and national death databases. With the SMDC, healthcare providers and policymakers may analyze a unified record of information that is useful for informing preventive strategies for both health systems and health departments.
引用
收藏
页数:8
相关论文
共 38 条
  • [1] Afshar M, 2022, LANCET DIGIT HEALTH, V4, pE426, DOI 10.1016/S2589-7500(22)00041-3
  • [2] External validation of an opioid misuse machine learning classifier in hospitalized adult patients
    Afshar, Majid
    Sharma, Brihat
    Bhalla, Sameer
    Thompson, Hale M.
    Dligach, Dmitriy
    Boley, Randy A.
    Kishen, Ekta
    Simmons, Alan
    Perticone, Kathryn
    Karnik, Niranjan S.
    [J]. ADDICTION SCIENCE & CLINICAL PRACTICE, 2021, 16 (01)
  • [3] Subtypes in patients with opioid misuse: A prognostic enrichment strategy using electronic health record data in hospitalized patients
    Afshar, Majid
    Joyce, Cara
    Dligach, Dmitriy
    Sharma, Brihat
    Kania, Robert
    Xie, Meng
    Swope, Kristin
    Salisbury-Afshar, Elizabeth
    Karnik, Niranjan S.
    [J]. PLOS ONE, 2019, 14 (07):
  • [4] Development and application of a high throughput natural language processing architecture to convert all clinical documents in a clinical data warehouse into standardized medical vocabularies
    Afshar, Majid
    Dligach, Dmitriy
    Sharma, Brihat
    Cai, Xiaoyuan
    Boyda, Jason
    Birch, Steven
    Valdez, Daniel
    Zelisko, Suzan
    Joyce, Cara
    Modave, Francois
    Price, Ron
    [J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2019, 26 (11) : 1364 - 1369
  • [5] Natural language processing and machine learning to identify alcohol misuse from the electronic health record in trauma patients: development and internal validation
    Afshar, Majid
    Phillips, Andrew
    Karnik, Niranjan
    Mueller, Jeanne
    To, Daniel
    Gonzalez, Richard
    Price, Ron
    Cooper, Richard
    Joyce, Cara
    Dligach, Dmitriy
    [J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2019, 26 (03) : 254 - 261
  • [6] Software as a Service for Data Scientists
    Allen, Bryce
    Bresnahan, John
    Childers, Lisa
    Foster, Ian
    Kandaswamy, Gopi
    Kettimuthu, Raj
    Kordas, Jack
    Link, Mike
    Martin, Stuart
    Pickett, Karl
    Tuecke, Steven
    [J]. COMMUNICATIONS OF THE ACM, 2012, 55 (02) : 81 - 88
  • [7] Anderson R N, 2001, Natl Vital Stat Rep, V49, P1
  • [8] Merging statewide data in a public/university collaboration to address opioid use disorder and overdose
    Becker, William C.
    Heimer, Robert
    Dormitzer, Catherine M.
    Doernberg, Molly
    D'Onofrio, Gail
    Grau, Lauretta E.
    Hawk, Kathryn
    Lin, Hsiu-Ju
    Secora, Alex M.
    Fiellin, David A.
    [J]. ADDICTION SCIENCE & CLINICAL PRACTICE, 2021, 16 (01)
  • [9] Real-World Matching Performance of Deidentified Record-Linking Tokens
    Bernstam, Elmer, V
    Applegate, Reuben Joseph
    Yu, Alvin
    Chaudhari, Deepa
    Liu, Tian
    Coda, Alex
    Leshin, Jonah
    [J]. APPLIED CLINICAL INFORMATICS, 2022, 13 (04): : 865 - 873
  • [10] Sharing Overdose Data Across State Agencies to Inform Public Health Strategies: A Case Study
    Cherico-Hsii, Sara
    Bankoski, Andrea
    Singal, Pooja
    Horon, Isabelle
    Beane, Eric
    Casey, Meghan
    Rebbert-Franklin, Kathleen
    Sharfstein, Joshua
    [J]. PUBLIC HEALTH REPORTS, 2016, 131 (02) : 258 - 263