1
|
Zinzuwadia AN, Mineeva O, Li C, Farukhi Z, Giulianini F, Cade B, Chen L, Karlson E, Paynter N, Mora S, Demler O. Tailoring Risk Prediction Models to Local Populations. JAMA Cardiol 2024:2823894. [PMID: 39292486 PMCID: PMC11411452 DOI: 10.1001/jamacardio.2024.2912] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/19/2024]
Abstract
Importance Risk estimation is an integral part of cardiovascular care. Local recalibration of guideline-recommended models could address the limitations of existing tools. Objective To provide a machine learning (ML) approach to augment the performance of the American Heart Association's Predicting Risk of Cardiovascular Disease Events (AHA-PREVENT) equations when applied to a local population while preserving clinical interpretability. Design, Setting, and Participants This cohort study used a New England-based electronic health record cohort of patients without prior atherosclerotic cardiovascular disease (ASCVD) who had the data necessary to calculate the AHA-PREVENT 10-year risk of developing ASCVD in the event period (2007-2016). Patients with prior ASCVD events, death prior to 2007, or age 79 years or older in 2007 were subsequently excluded. The final study population of 95 326 patients was split into 3 nonoverlapping subsets for training, testing, and validation. The AHA-PREVENT model was adapted to this local population using the open-source ML model (MLM) Extreme Gradient Boosting model (XGBoost) with minimal predictor variables, including age, sex, and AHA-PREVENT. The MLM was monotonically constrained to preserve known associations between risk factors and ASCVD risk. Along with sex, race and ethnicity data from the electronic health record were collected to validate the performance of ASCVD risk prediction in subgroups. Data were analyzed from August 2021 to February 2024. Main Outcomes and Measures Consistent with the AHA-PREVENT model, ASCVD events were defined as the first occurrence of either nonfatal myocardial infarction, coronary artery disease, ischemic stroke, or cardiovascular death. Cardiovascular death was coded via government registries. Discrimination, calibration, and risk reclassification were assessed using the Harrell C index, a modified Hosmer-Lemeshow goodness-of-fit test and calibration curves, and reclassification tables, respectively. Results In the test set of 38 137 patients (mean [SD] age, 64.8 [6.9] years, 22 708 [59.5]% women and 15 429 [40.5%] men; 935 [2.5%] Asian, 2153 [5.6%] Black, 1414 [3.7%] Hispanic, 31 400 [82.3%] White, and 2235 [5.9%] other, including American Indian, multiple races, unspecified, and unrecorded, consolidated owing to small numbers), MLM-PREVENT had improved calibration (modified Hosmer-Lemeshow P > .05) compared to the AHA-PREVENT model across risk categories in the overall cohort (χ23 = 2.2; P = .53 vs χ23 > 16.3; P < .001) and sex subgroups (men: χ23 = 2.1; P = .55 vs χ23 > 16.3; P < .001; women: χ23 = 6.5; P = .09 vs. χ23 > 16.3; P < .001), while also surpassing a traditional recalibration approach. MLM-PREVENT maintained or improved AHA-PREVENT's calibration in Asian, Black, and White individuals. Both MLM-PREVENT and AHA-PREVENT performed equally well in discriminating risk (approximate ΔC index, ±0.01). Using a clinically significant 7.5% risk threshold, MLM-PREVENT reclassified a total of 11.5% of patients. We visualize the recalibration through MLM-PREVENT ASCVD risk charts that highlight preserved risk associations of the original AHA-PREVENT model. Conclusions and Relevance The interpretable ML approach presented in this article enhanced the accuracy of the AHA-PREVENT model when applied to a local population while still preserving the risk associations found by the original model. This method has the potential to recalibrate other established risk tools and is implementable in electronic health record systems for improved cardiovascular risk assessment.
Collapse
Affiliation(s)
| | | | - Chunying Li
- Brigham & Women's Hospital, Boston, Massachusetts
| | - Zareen Farukhi
- Brigham & Women's Hospital, Boston, Massachusetts
- Massachusetts General Hospital, Boston
| | | | - Brian Cade
- Brigham & Women's Hospital, Boston, Massachusetts
| | - Lin Chen
- Brigham & Women's Hospital, Boston, Massachusetts
| | | | - Nina Paynter
- Brigham & Women's Hospital, Boston, Massachusetts
| | - Samia Mora
- Brigham & Women's Hospital, Boston, Massachusetts
| | - Olga Demler
- Brigham & Women's Hospital, Boston, Massachusetts
- ETH Zurich, Zurich, Switzerland
| |
Collapse
|
2
|
Coon H, Shabalin A, DiBlasi E, Monson ET, Han S, Kaufman EA, Chen D, Kious B, Molina N, Yu Z, Staley M, Crockett DK, Colbert SM, Mullins N, Bakian AV, Docherty AR, Keeshin B. Absence of nonfatal suicidal behavior preceding suicide death reveals differences in clinical risks. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.06.05.24308493. [PMID: 38883733 PMCID: PMC11177925 DOI: 10.1101/2024.06.05.24308493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/18/2024]
Abstract
Nonfatal suicidality is the most robust predictor of suicide death. However, only ~10% of those who survive an attempt go on to die by suicide. Moreover, ~50% of suicide deaths occur in the absence of prior known attempts, suggesting risks other than nonfatal suicide attempt need to be identified. We studied data from 4,000 population-ascertained suicide deaths and 26,191 population controls to improve understanding of risks leading to suicide death. This study included 2,253 suicide deaths and 3,375 controls with evidence of nonfatal suicidality (SUI_SI/SB and CTL_SI/SB) from diagnostic codes and natural language processing of electronic health records notes. Characteristics of these groups were compared to 1,669 suicides with no prior nonfatal SI/SB (SUI_None) and 22,816 controls with no lifetime suicidality (CTL_None). The SUI_None and CTL_None groups had fewer diagnoses and were older than SUI_SI/SB and CTL_SI/SB. Mental health diagnoses were far less common in both the SUI_None and CTL_None groups; mental health problems were less associated with suicide death than with presence of SI/SB. Physical health diagnoses were conversely more often associated with risk of suicide death than with presence of SI/SB. Pending replication, results indicate highly significant clinical differences among suicide deaths with versus without prior nonfatal SI/SB.
Collapse
Affiliation(s)
- Hilary Coon
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Andrey Shabalin
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Emily DiBlasi
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Eric T. Monson
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Seonggyun Han
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Erin A. Kaufman
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Danli Chen
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Brent Kious
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | | | - Zhe Yu
- Pedigree & Population Resource, Huntsman Cancer Institute, University of Utah, Salt Lake City, UT
| | - Michael Staley
- Utah State Office of the Medical Examiner, Utah Department of Health and Human Services, Salt Lake City, UT
| | | | - Sarah M. Colbert
- Department of Psychiatry, Mount Sinai School of Medicine, New York, NY
| | - Niamh Mullins
- Department of Psychiatry, Mount Sinai School of Medicine, New York, NY
| | - Amanda V. Bakian
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Anna R. Docherty
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
| | - Brooks Keeshin
- Department of Psychiatry & Huntsman Mental Health Institute, University of Utah School of Medicine, Salt Lake City, UT, USA
- Department of Pediatrics, University of Utah, Salt Lake City, UT
- Primary Children’s Hospital Center for Safe and Healthy Families, Salt Lake City, UT
| |
Collapse
|
3
|
Huang RJ, Huang ES, Mudiganti S, Chen T, Martinez MC, Ramrakhiani S, Han SS, Hwang JH, Palaniappan LP, Liang SY. Risk of Gastric Adenocarcinoma in a Multiethnic Population Undergoing Routine Care: An Electronic Health Records Cohort Study. Cancer Epidemiol Biomarkers Prev 2024; 33:547-556. [PMID: 38231023 PMCID: PMC10990787 DOI: 10.1158/1055-9965.epi-23-1200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 12/05/2023] [Accepted: 01/12/2024] [Indexed: 01/18/2024] Open
Abstract
BACKGROUND Gastric adenocarcinoma (GAC) is often diagnosed at advanced stages and portends a poor prognosis. We hypothesized that electronic health records (EHR) could be leveraged to identify individuals at highest risk for GAC from the population seeking routine care. METHODS This was a retrospective cohort study, with endpoint of GAC incidence as ascertained through linkage to an institutional tumor registry. We utilized 2010 to 2020 data from the Palo Alto Medical Foundation, a large multispecialty practice serving Northern California. The analytic cohort comprised individuals ages 40-75 receiving regular ambulatory care. Variables collected included demographic, medical, pharmaceutical, social, and familial data. Electronic phenotyping was based on rule-based methods. RESULTS The cohort comprised 316,044 individuals and approximately 2 million person-years (p-y) of observation. 157 incident GACs occurred (incidence 7.9 per 100,000 p-y), of which 102 were non-cardia GACs (incidence 5.1 per 100,000 p-y). In multivariable analysis, male sex [HR: 2.2, 95% confidence interval (CI): 1.6-3.1], older age, Asian race (HR: 2.5, 95% CI: 1.7-3.7), Hispanic ethnicity (HR: 1.9, 95% CI: 1.1-3.3), atrophic gastritis (HR: 4.6, 95% CI: 2.2-9.3), and anemia (HR: 1.9, 95% CI: 1.3-2.6) were associated with GAC risk; use of NSAID was inversely associated (HR: 0.3, 95% CI: 0.2-0.5). Older age, Asian race, Hispanic ethnicity, atrophic gastritis, and anemia were associated with non-cardia GAC. CONCLUSIONS Routine EHR data can stratify the general population for GAC risk. IMPACT Such methods may help triage populations for targeted screening efforts, such as upper endoscopy.
Collapse
Affiliation(s)
- Robert J Huang
- Division of Gastroenterology and Hepatology, Stanford University School of Medicine, Stanford, California
| | - Edward S Huang
- Department of Gastroenterology, Palo Alto Medical Foundation, San Jose, California
| | - Satish Mudiganti
- Palo Alto Medical Foundation Research Institute, Palo Alto Medical Foundation, Palo Alto, California
| | - Tony Chen
- Palo Alto Medical Foundation Research Institute, Palo Alto Medical Foundation, Palo Alto, California
| | - Meghan C Martinez
- Palo Alto Medical Foundation Research Institute, Palo Alto Medical Foundation, Palo Alto, California
| | - Sanjay Ramrakhiani
- Department of Gastroenterology, Palo Alto Medical Foundation, San Jose, California
| | - Summer S Han
- Department of Neurosurgery, Stanford University School of Medicine, Stanford, California
| | - Joo Ha Hwang
- Division of Gastroenterology and Hepatology, Stanford University School of Medicine, Stanford, California
| | - Latha P Palaniappan
- Division of Cardiovascular Medicine, Stanford University School of Medicine, Stanford, California
| | - Su-Ying Liang
- Palo Alto Medical Foundation Research Institute, Palo Alto Medical Foundation, Palo Alto, California
| |
Collapse
|
4
|
Al-Sahab B, Leviton A, Loddenkemper T, Paneth N, Zhang B. Biases in Electronic Health Records Data for Generating Real-World Evidence: An Overview. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2024; 8:121-139. [PMID: 38273982 PMCID: PMC10805748 DOI: 10.1007/s41666-023-00153-2] [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: 06/30/2023] [Revised: 09/05/2023] [Accepted: 11/07/2023] [Indexed: 01/27/2024]
Abstract
Electronic Health Records (EHR) are increasingly being perceived as a unique source of data for clinical research as they provide unprecedentedly large volumes of real-time data from real-world settings. In this review of the secondary uses of EHR, we identify the anticipated breadth of opportunities, pointing out the data deficiencies and potential biases that are likely to limit the search for true causal relationships. This paper provides a comprehensive overview of the types of biases that arise along the pathways that generate real-world evidence and the sources of these biases. We distinguish between two levels in the production of EHR data where biases are likely to arise: (i) at the healthcare system level, where the principal source of bias resides in access to, and provision of, medical care, and in the acquisition and documentation of medical and administrative data; and (ii) at the research level, where biases arise from the processes of extracting, analyzing, and interpreting these data. Due to the plethora of biases, mainly in the form of selection and information bias, we conclude with advising extreme caution about making causal inferences based on secondary uses of EHRs.
Collapse
Affiliation(s)
- Ban Al-Sahab
- Department of Family Medicine, College of Human Medicine, Michigan State University, B100 Clinical Center, 788 Service Road, East Lansing, MI USA
| | - Alan Leviton
- Department of Neurology, Harvard Medical School, Boston, MA USA
- Department of Neurology, Boston Children’s Hospital, Boston, MA USA
| | - Tobias Loddenkemper
- Department of Neurology, Harvard Medical School, Boston, MA USA
- Department of Neurology, Boston Children’s Hospital, Boston, MA USA
| | - Nigel Paneth
- Department of Epidemiology and Biostatistics, College of Human Medicine, Michigan State University, East Lansing, MI USA
- Department of Pediatrics and Human Development, College of Human Medicine, Michigan State University, East Lansing, MI USA
| | - Bo Zhang
- Department of Neurology, Boston Children’s Hospital, Boston, MA USA
- Biostatistics and Research Design, Institutional Centers of Clinical and Translational Research, Boston Children’s Hospital, Boston, MA USA
- Harvard Medical School, Boston, MA USA
| |
Collapse
|
5
|
Gullón P, Fontán-Vela M, Díez J, Nieuwenhuijsen M, Rojas-Rueda D, Escobar F, Franco M. Who benefits from green spaces? Surrounding greenness and incidence of cardiovascular disease in a population-based electronic medical records cohort in Madrid. Int J Hyg Environ Health 2023; 252:114221. [PMID: 37421937 DOI: 10.1016/j.ijheh.2023.114221] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Revised: 05/06/2023] [Accepted: 07/03/2023] [Indexed: 07/10/2023]
Abstract
The objective was to study the association between surrounding greenness and the incidence of cardiovascular diseases (CVD) with a four years follow-up in almost half a million high CVD-risk women and men, as well as its differential effect by area-level deprivation in Madrid. We analyzed 2015-2018 primary healthcare electronic medical records for 437,513 high CVD risk individuals representing more than 95% of the population of that age range residing in Madrid. The outcome variable was any cardiovascular event. We measured surrounding residence greenness at 200 m, 300 m, 500 m, and 1000 m through the Normalized Difference Vegetation Index (NDVI). We assessed socioeconomic deprivation through a census-based deprivation index. We estimated the 4-year relative risk of CVD by an increase in 0.1 units of NDVI and then stratified the models by quintiles of deprivation (Q5 the most deprived). We found that for every increase in 0.1 units of NDVI at 1000 m there was a 16% decrease in CVD risk (RR = 0.84 95% CI 0.75-0.94). CVD risk for the remaining distance exposures (at 200 m, 300 m, and 500 m) were none statistically significant. In general, the protective effect of green spaces was present in medium-deprivation areas and males, but the associations were inconsistent across deprivation levels. This study highlights the relevance of evaluating the interaction between physical and social urban components to further understand possible population prevention approaches for cardiovascular diseases. Future studies should focus on the mechanisms of context-specific interactions between social inequalities and green spaces' effects on health.
Collapse
Affiliation(s)
- Pedro Gullón
- Public Health and Epidemiology Research Group, School of Medicine and Health Sciences, Universidad de Alcala, Alcala de Henares, 28871, Madrid, Spain; Centre for Urban Research, RMIT University, Melbourne, Australia.
| | - Mario Fontán-Vela
- Public Health and Epidemiology Research Group, School of Medicine and Health Sciences, Universidad de Alcala, Alcala de Henares, 28871, Madrid, Spain; Instituto de Lengua, Literatura y Antropología, Centro Superior de Investigaciones Sociológicas, Ministerio de Ciencia e Innovación, Spain
| | - Julia Díez
- Public Health and Epidemiology Research Group, School of Medicine and Health Sciences, Universidad de Alcala, Alcala de Henares, 28871, Madrid, Spain
| | - Mark Nieuwenhuijsen
- ISGlobal, Center for Research in Environmental Epidemiology (CREAL), 08036, Barcelona, Spain; Universitat Pompeu Fabra (UPF), 08002, Barcelona, Spain; Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública (CIBERESP), Madrid, Spain
| | - David Rojas-Rueda
- Department of Environmental and Radiological Health Sciences, Colorado State University, Fort Collins, CO, USA; Colorado School of Public Health, Colorado State University, Fort Collins, CO, USA
| | - Francisco Escobar
- Department of Geology, Geography and Environmental Sciences, University of Alcalá, Calle Colegios 2, Alcalá de Henares, 28801, Madrid, Spain
| | - Manuel Franco
- Public Health and Epidemiology Research Group, School of Medicine and Health Sciences, Universidad de Alcala, Alcala de Henares, 28871, Madrid, Spain; Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, Md, 21205-2217, USA
| |
Collapse
|
6
|
Koutsouleris N, Hauser TU, Skvortsova V, De Choudhury M. From promise to practice: towards the realisation of AI-informed mental health care. THE LANCET DIGITAL HEALTH 2022; 4:e829-e840. [DOI: 10.1016/s2589-7500(22)00153-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/28/2022] [Revised: 07/14/2022] [Accepted: 07/27/2022] [Indexed: 11/07/2022]
|