1
|
Naik K, Goyal RK, Foschini L, Chak CW, Thielscher C, Zhu H, Lu J, Lehár J, Pacanoswki MA, Terranova N, Mehta N, Korsbo N, Fakhouri T, Liu Q, Gobburu J. Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine. Clin Pharmacol Ther 2024; 115:673-686. [PMID: 38103204 DOI: 10.1002/cpt.3152] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Accepted: 11/28/2023] [Indexed: 12/18/2023]
Abstract
Technological innovations, such as artificial intelligence (AI) and machine learning (ML), have the potential to expedite the goal of precision medicine, especially when combined with increased capacity for voluminous data from multiple sources and expanded therapeutic modalities; however, they also present several challenges. In this communication, we first discuss the goals of precision medicine, and contextualize the use of AI in precision medicine by showcasing innovative applications (e.g., prediction of tumor growth and overall survival, biomarker identification using biomedical images, and identification of patient population for clinical practice) which were presented during the February 2023 virtual public workshop entitled "Application of Artificial Intelligence and Machine Learning for Precision Medicine," hosted by the US Food and Drug Administration (FDA) and University of Maryland Center of Excellence in Regulatory Science and Innovation (M-CERSI). Next, we put forward challenges brought about by the multidisciplinary nature of AI, particularly highlighting the need for AI to be trustworthy. To address such challenges, we subsequently note practical approaches, viz., differential privacy, synthetic data generation, and federated learning. The proposed strategies - some of which are highlighted presentations from the workshop - are for the protection of personal information and intellectual property. In addition, methods such as the risk-based management approach and the need for an agile regulatory ecosystem are discussed. Finally, we lay out a call for action that includes sharing of data and algorithms, development of regulatory guidance documents, and pooling of expertise from a broad-spectrum of stakeholders to enhance the application of AI in precision medicine.
Collapse
Affiliation(s)
- Kunal Naik
- Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, Maryland, USA
| | - Rahul K Goyal
- Center for Translational Medicine, University of Maryland School of Pharmacy, Baltimore, Maryland, USA
| | | | | | | | - Hao Zhu
- Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, Maryland, USA
| | - James Lu
- Modeling & Simulation/Clinical Pharmacology, Genentech Inc., South San Francisco, California, USA
| | | | - Michael A Pacanoswki
- Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, Maryland, USA
| | - Nadia Terranova
- Quantitative Pharmacology, Ares Trading S.A. (an affiliate of Merck KGaA, Darmstadt, Germany), Lausanne, Switzerland
| | - Neha Mehta
- Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, Maryland, USA
| | | | - Tala Fakhouri
- Office of Medical Policy, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, Maryland, USA
| | - Qi Liu
- Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, Maryland, USA
| | - Jogarao Gobburu
- Center for Translational Medicine, University of Maryland School of Pharmacy, Baltimore, Maryland, USA
| |
Collapse
|
2
|
Tachinardi U, Grannis SJ, Michael SG, Misquitta L, Dahlin J, Sheikh U, Kho A, Phua J, Rogovin SS, Amor B, Choudhury M, Sparks P, Mannaa A, Ljazouli S, Saltz J, Prior F, Baghal A, Gersing K, Embi PJ. Privacy-preserving record linkage across disparate institutions and datasets to enable a learning health system: The national COVID cohort collaborative (N3C) experience. Learn Health Syst 2024; 8:e10404. [PMID: 38249841 PMCID: PMC10797567 DOI: 10.1002/lrh2.10404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2023] [Revised: 12/06/2023] [Accepted: 12/06/2023] [Indexed: 01/23/2024] Open
Abstract
Introduction Research driven by real-world clinical data is increasingly vital to enabling learning health systems, but integrating such data from across disparate health systems is challenging. As part of the NCATS National COVID Cohort Collaborative (N3C), the N3C Data Enclave was established as a centralized repository of deidentified and harmonized COVID-19 patient data from institutions across the US. However, making this data most useful for research requires linking it with information such as mortality data, images, and viral variants. The objective of this project was to establish privacy-preserving record linkage (PPRL) methods to ensure that patient-level EHR data remains secure and private when governance-approved linkages with other datasets occur. Methods Separate agreements and approval processes govern N3C data contribution and data access. The Linkage Honest Broker (LHB), an independent neutral party (the Regenstrief Institute), ensures data linkages are robust and secure by adding an extra layer of separation between protected health information and clinical data. The LHB's PPRL methods (including algorithms, processes, and governance) match patient records using "deidentified tokens," which are hashed combinations of identifier fields that define a match across data repositories without using patients' clear-text identifiers. Results These methods enable three linkage functions: Deduplication, Linking Multiple Datasets, and Cohort Discovery. To date, two external repositories have been cross-linked. As of March 1, 2023, 43 sites have signed the LHB Agreement; 35 sites have sent tokens generated for 9 528 998 patients. In this initial cohort, the LHB identified 135 037 matches and 68 596 duplicates. Conclusion This large-scale linkage study using deidentified datasets of varying characteristics established secure methods for protecting the privacy of N3C patient data when linked for research purposes. This technology has potential for use with registries for other diseases and conditions.
Collapse
Affiliation(s)
- Umberto Tachinardi
- Department of Biomedical InformaticsUniversity of Cincinnati College of MedicineCincinnatiOhioUSA
| | - Shaun J. Grannis
- Center for Biomedical Informatics, Regenstrief InstituteDepartment of Family Medicine, IU School of MedicineRegenstrief Institute, Inc. and Indiana University School of MedicineIndianapolisIndianaUSA
| | - Sam G. Michael
- National Center for Advancing Translational ScienceNIHBethesdaMarylandUSA
| | - Leonie Misquitta
- National Center for Advancing Translational ScienceNIHBethesdaMarylandUSA
| | - Jayme Dahlin
- National Center for Advancing Translational ScienceNIHBethesdaMarylandUSA
| | - Usman Sheikh
- National Center for Advancing Translational ScienceNIHBethesdaMarylandUSA
| | - Abel Kho
- Department of MedicineNorthwestern University, Feinberg School of MedicineChicagoIllinoisUSA
- Public SectorDatavant, IncSan FranciscoCaliforniaUSA
| | - Jasmin Phua
- Public SectorDatavant, IncSan FranciscoCaliforniaUSA
| | | | - Benjamin Amor
- Federal HealthPalantir TechnologiesDenverColoradoUSA
| | | | - Philip Sparks
- Federal HealthPalantir TechnologiesDenverColoradoUSA
| | - Amin Mannaa
- Federal HealthPalantir TechnologiesDenverColoradoUSA
| | - Saad Ljazouli
- Federal HealthPalantir TechnologiesDenverColoradoUSA
| | - Joel Saltz
- School of MedicineStony Brook UniversityStony BrookNew YorkUSA
| | - Fred Prior
- COM Biomedical InformaticsUniversity of Arkansas for Medical SciencesLittle RockArkansasUSA
| | - Ahmen Baghal
- COM Biomedical InformaticsUniversity of Arkansas for Medical SciencesLittle RockArkansasUSA
| | - Kenneth Gersing
- National Center for Advancing Translational ScienceNIHBethesdaMarylandUSA
| | - Peter J. Embi
- Department of Biomedical InformaticsVanderbilt University Medical CenterNashvilleTennesseeUSA
| |
Collapse
|
3
|
Shah K, Patt D, Mullangi S. Use of Tokens to Unlock Greater Data Sharing in Health Care. JAMA 2023; 330:2333-2334. [PMID: 37983066 DOI: 10.1001/jama.2023.23720] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/21/2023]
Abstract
This Viewpoint discusses the use of privacy-preserving record linkage, a token-based record linkage system, as a promising avenue for building a data infrastructure system that bridges isolated data.
Collapse
Affiliation(s)
- Kanan Shah
- Department of Medicine, NYU Langone Medical Center, New York, New York
| | | | | |
Collapse
|
4
|
Waitman LR, Bailey LC, Becich MJ, Chung-Bridges K, Dusetzina SB, Espino JU, Hogan WR, Kaushal R, McClay JC, Merritt JG, Rothman RL, Shenkman EA, Song X, Nauman E. Avenues for Strengthening PCORnet's Capacity to Advance Patient-Centered Economic Outcomes in Patient-Centered Outcomes Research (PCOR). Med Care 2023; 61:S153-S160. [PMID: 37963035 PMCID: PMC10635342 DOI: 10.1097/mlr.0000000000001929] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2023]
Abstract
PCORnet, the National Patient-Centered Clinical Research Network, provides the ability to conduct prospective and observational pragmatic research by leveraging standardized, curated electronic health records data together with patient and stakeholder engagement. PCORnet is funded by the Patient-Centered Outcomes Research Institute (PCORI) and is composed of 8 Clinical Research Networks that incorporate at total of 79 health system "sites." As the network developed, linkage to commercial health plans, federal insurance claims, disease registries, and other data resources demonstrated the value in extending the networks infrastructure to provide a more complete representation of patient's health and lived experiences. Initially, PCORnet studies avoided direct economic comparative effectiveness as a topic. However, PCORI's authorizing law was amended in 2019 to allow studies to incorporate patient-centered economic outcomes in primary research aims. With PCORI's expanded scope and PCORnet's phase 3 beginning in January 2022, there are opportunities to strengthen the network's ability to support economic patient-centered outcomes research. This commentary will discuss approaches that have been incorporated to date by the network and point to opportunities for the network to incorporate economic variables for analysis, informed by patient and stakeholder perspectives. Topics addressed include: (1) data linkage infrastructure; (2) commercial health plan partnerships; (3) Medicare and Medicaid linkage; (4) health system billing-based benchmarking; (5) area-level measures; (6) individual-level measures; (7) pharmacy benefits and retail pharmacy data; and (8) the importance of transparency and engagement while addressing the biases inherent in linking real-world data sources.
Collapse
Affiliation(s)
- Lemuel R. Waitman
- Department of Biomedical Informatics, Biostatistics, and Medical Epidemiology, University of Missouri School of Medicine, Greater Plains Collaborative, PCORnet Clinical Research Network, Columbia, MO
| | | | | | | | | | | | | | - Rainu Kaushal
- Weill Cornell University School of Medicine, New York, NY
| | | | | | | | | | - Xing Song
- University of Missouri School of Medicine, Columbia, MO
| | | |
Collapse
|
5
|
Afshar M, Oguss M, Callaci TA, Gruenloh T, Gupta P, Sun C, Safipour Afshar A, Cavanaugh J, Churpek MM, Nyakoe-Nyasani E, Nguyen-Hilfiger H, Westergaard R, Salisbury-Afshar E, Gussick M, Patterson B, Manneh C, Mathew J, Mayampurath A. Creation of a data commons for substance misuse related health research through privacy-preserving patient record linkage between hospitals and state agencies. JAMIA Open 2023; 6:ooad092. [PMID: 37942470 PMCID: PMC10629613 DOI: 10.1093/jamiaopen/ooad092] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2023] [Revised: 10/04/2023] [Accepted: 10/16/2023] [Indexed: 11/10/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Majid Afshar
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Madeline Oguss
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Thomas A Callaci
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Timothy Gruenloh
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Preeti Gupta
- Division of Pulmonary and Critical Care, University of Illinois-Chicago, Chicago, IL 60607, United States
| | - Claire Sun
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Askar Safipour Afshar
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Joseph Cavanaugh
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Matthew M Churpek
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Edwin Nyakoe-Nyasani
- State of Wisconsin Department of Health Services, Madison, WI 53703, United States
| | | | - Ryan Westergaard
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
- State of Wisconsin Department of Health Services, Madison, WI 53703, United States
| | - Elizabeth Salisbury-Afshar
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
- State of Wisconsin Department of Health Services, Madison, WI 53703, United States
| | - Megan Gussick
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Brian Patterson
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Claire Manneh
- Datavant Incorporated, San Francisco, CA 94104, United States
| | - Jomol Mathew
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| | - Anoop Mayampurath
- School of Medicine and Public Health, University of Wisconsin-Madison, Madison, WI 53706, United States
| |
Collapse
|
6
|
Khurshid A, Hautala M, Oliveira E, Lakshminarayanan V, Abrol V, Collier J, Rosseau J, Granado L, Nallaparaju S, Mitra K, Sohail R. Social and Health Information Platform: Piloting a Standards-Based, Digital Platform Linking Social Determinants of Health Data into Clinical Workflows for Community-Wide Use. Appl Clin Inform 2023; 14:883-892. [PMID: 37940130 PMCID: PMC10632068 DOI: 10.1055/s-0043-1774819] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2023] [Accepted: 07/21/2023] [Indexed: 11/10/2023] Open
Abstract
BACKGROUND Social determinants of health (SDoH)a are increasingly recognized as a main contributor to clinical health outcomes, but the technologies and workflows within clinics make it difficult for health care providers to address SDoH needs during routine clinical visits. OBJECTIVES Our objectives were to pilot a digital platform that matches, links, and visualizes patient-level information and community-level deidentified data from across sectors; establish a technical infrastructure that is scalable, generalizable, and interoperable with new datasets or technologies; employ user-centered codesign principles to refine the platform's visualizations, dashboards, and alerts with community health workers, clinicians, and clinic administrators. METHODS We used privacy-preserving record linkage (PPRL) tools to ensure that all identifiable patient data were encrypted, only matched and displayed with consent, and never accessed or stored by the data intermediary. We used limited data sets (LDS) to share nonidentifiable patient data with the data intermediary through a health information exchange (HIE) to take advantage of existing partner agreements, technical infrastructure, and community clinical data. RESULTS The platform was successfully piloted in two Federally Qualified Health Clinics by 26 clinic staff. SDoH and demographic data from findhelp were successfully linked, matched, and displayed with clinical and demographic data from the HIE, Connxus. Pilot users tested the platform using real-patient data, guiding the refinement of the social and health information platform's visualizations and alerts. Users emphasized the importance of visuals and alerts that gave quick insights into individual patient SDoH needs, survey responses, and clinic-level trends in SDoH service referrals. CONCLUSION This pilot shows the importance of PPRL, LDS, and HIE-based data intermediaries in sharing data across sectors and service providers for scalable patient-level care coordination and community-level insights. Clinic staff are integral in designing, developing, and adopting health technologies that will enhance their ability to address SDoH needs within existing workflows without adding undue burdens or additional stress.
Collapse
Affiliation(s)
- Anjum Khurshid
- Department of Population Medicine, Harvard Medical School, Boston, Massachusetts
| | - Matti Hautala
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Eliel Oliveira
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Vidya Lakshminarayanan
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Vishal Abrol
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Joshua Collier
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Justin Rosseau
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Linda Granado
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Shreya Nallaparaju
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Kanishka Mitra
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| | - Rania Sohail
- Department of Population Health, Dell Medical School at The University of Texas at Austin, Texas
| |
Collapse
|
7
|
Graham RJ, Darras BT, Haselkorn T, Fisher D, Genetti CA, Miller W, Beggs AH. Real-world analysis of healthcare resource utilization by patients with X-linked myotubular myopathy (XLMTM) in the United States. Orphanet J Rare Dis 2023; 18:138. [PMID: 37280644 PMCID: PMC10242920 DOI: 10.1186/s13023-023-02733-2] [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: 11/18/2022] [Accepted: 05/14/2023] [Indexed: 06/08/2023] Open
Abstract
BACKGROUND X-linked myotubular myopathy (XLMTM) is a rare, life-threatening congenital myopathy with multisystem involvement, often requiring invasive ventilator support, gastrostomy tube feeding, and wheelchair use. Understanding healthcare resource utilization in patients with XLMTM is important for development of targeted therapies but data are limited. METHODS We analyzed individual medical codes as governed by Healthcare Common Procedure Coding System, Current Procedural Terminology, and International Classification of Diseases, 10th Revision (ICD-10) for a defined cohort of XLMTM patients within a US medical claims database. Using third-party tokenization software, we defined a cohort of XLMTM patient tokens from a de-identified dataset in a research registry of diagnostically confirmed XLMTM patients and de-identified data from a genetic testing company. After approval of an ICD-10 diagnosis code for XLMTM (G71.220) in October 2020, we identified additional patients. RESULTS A total of 192 males with a diagnosis of XLMTM were included: 80 patient tokens and 112 patients with the new ICD-10 code. From 2016 to 2020, the annual number of patients with claims increased from 120 to 154 and the average number of claims per patient per year increased from 93 to 134. Of 146 patients coded with hospitalization claims, 80 patients (55%) were first hospitalized between 0 and 4 years of age. Across all patients, 31% were hospitalized 1-2 times, 32% 3-9 times, and 14% ≥ 10 times. Patients received care from multiple specialty practices: pulmonology (53%), pediatrics (47%), neurology (34%), and critical care medicine (31%). The most common conditions and procedures related to XLMTM were respiratory events (82%), ventilation management (82%), feeding difficulties (81%), feeding support (72%), gastrostomy (69%), and tracheostomy (64%). Nearly all patients with respiratory events had chronic respiratory claims (96%). The most frequent diagnostic codes were those investigating hepatobiliary abnormalities. CONCLUSIONS This innovative medical claims analysis shows substantial healthcare resource use in XLMTM patients that increased over the last 5 years. Most patients required respiratory and feeding support and experienced multiple hospitalizations throughout childhood and beyond for those that survived. This pattern delineation will inform outcome assessments with the emergence of novel therapies and supportive care measures.
Collapse
Affiliation(s)
- Robert J Graham
- Division of Critical Care Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| | - Basil T Darras
- Department of Neurology, Neuromuscular Program, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA
| | | | | | - Casie A Genetti
- Division of Genetics and Genomics, The Manton Center for Orphan Disease Research, Boston Children's Hospital, Harvard Medical School, 3 Blackfan Circle - BCH3150, Boston, MA, 02115, USA
| | - Weston Miller
- Formerly of Astellas Gene Therapies, San Francisco, CA, USA
| | - Alan H Beggs
- Division of Genetics and Genomics, The Manton Center for Orphan Disease Research, Boston Children's Hospital, Harvard Medical School, 3 Blackfan Circle - BCH3150, Boston, MA, 02115, USA.
| |
Collapse
|
8
|
Marsolo K, Kiernan D, Toh S, Phua J, Louzao D, Haynes K, Weiner M, Angulo F, Bailey C, Bian J, Fort D, Grannis S, Krishnamurthy AK, Nair V, Rivera P, Silverstein J, Zirkle M, Carton T. Assessing the impact of privacy-preserving record linkage on record overlap and patient demographic and clinical characteristics in PCORnet®, the National Patient-Centered Clinical Research Network. J Am Med Inform Assoc 2022; 30:447-455. [PMID: 36451264 PMCID: PMC9933062 DOI: 10.1093/jamia/ocac229] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2022] [Revised: 11/03/2022] [Accepted: 11/16/2022] [Indexed: 12/02/2022] Open
Abstract
OBJECTIVE This article describes the implementation of a privacy-preserving record linkage (PPRL) solution across PCORnet®, the National Patient-Centered Clinical Research Network. MATERIAL AND METHODS Using a PPRL solution from Datavant, we quantified the degree of patient overlap across the network and report a de-duplicated analysis of the demographic and clinical characteristics of the PCORnet population. RESULTS There were ∼170M patient records across the responding Network Partners, with ∼138M (81%) of those corresponding to a unique patient. 82.1% of patients were found in a single partner and 14.7% were in 2. The percentage overlap between Partners ranged between 0% and 80% with a median of 0%. Linking patients' electronic health records with claims increased disease prevalence in every clinical characteristic, ranging between 63% and 173%. DISCUSSION The overlap between Partners was variable and depended on timeframe. However, patient data linkage changed the prevalence profile of the PCORnet patient population. CONCLUSIONS This project was one of the largest linkage efforts of its kind and demonstrates the potential value of record linkage. Linkage between Partners may be most useful in cases where there is geographic proximity between Partners, an expectation that potential linkage Partners will be able to fill gaps in data, or a longer study timeframe.
Collapse
Affiliation(s)
- Keith Marsolo
- Corresponding Author: Keith Marsolo, PhD, Department of Population Health Sciences, Duke University School of Medicine, 215 Morris Street, Durham, NC 27710, USA;
| | - Daniel Kiernan
- Department of Population Medicine, Harvard Medical School and Harvard Pilgrim Health Care Institute, Boston, Massachusetts, USA
| | - Sengwee Toh
- Department of Population Medicine, Harvard Medical School and Harvard Pilgrim Health Care Institute, Boston, Massachusetts, USA
| | | | - Darcy Louzao
- Duke Clinical Research Institute, Duke University School of Medicine, Durham, North Carolina, USA
| | - Kevin Haynes
- Scientific Affairs, HealthCore, Inc., Wilmington, Delaware, USA
| | - Mark Weiner
- Department of Medicine, Weill Cornell Medicine, New York, New York, USA
| | - Francisco Angulo
- Department of Medicine, Cook County Health and Hospital System, Chicago, Illinois, USA
| | - Charles Bailey
- Department of Pediatrics, Applied Clinical Research Center, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
| | - Jiang Bian
- Department of Health Outcomes and Bioinformatics, College of Medicine, University of Florida, Gainesville, Florida, USA
| | - Daniel Fort
- Center for Outcomes and Health Services Research, Ochsner Health, New Orleans, Louisiana, USA
| | - Shaun Grannis
- Regenstrief Institute, Indiana University, Indianapolis, Indiana, USA
| | | | | | | | - Jonathan Silverstein
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | | | - Thomas Carton
- Louisiana Public Health Institute, New Orleans, Louisiana, USA
| |
Collapse
|