American journal of epidemiology最新文献

筛选
英文 中文
Assessing residential neighborhood exposomes and their associations with cancer incidence: rationale, study design, and methods. 评估居民区暴露体及其与癌症发病率的关系:理论基础、研究设计和方法。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf096
Resa M Jones, Inkyu Han, John Hughes, Erik J Nelson
{"title":"Assessing residential neighborhood exposomes and their associations with cancer incidence: rationale, study design, and methods.","authors":"Resa M Jones, Inkyu Han, John Hughes, Erik J Nelson","doi":"10.1093/aje/kwaf096","DOIUrl":"10.1093/aje/kwaf096","url":null,"abstract":"<p><p>Geographic and racial/ethnic disparities in cancer outcomes exist but are not fully explained. As neighborhood context significantly influences these disparities, understanding factors related to neighborhood disadvantage (ND), including historical and structural injustice, will identify key areas that could eliminate disparities. This study will address three important limitations to understanding the role of neighborhood factors on cancer outcomes, the: (1) timing of exposures during the life course, (2) identification of the most important ND variables, and (3) comprehensive assessment of several domains of neighborhood-based exposures. The neighborhood exposome comprises four domains over the life course: socioeconomic deprivation, racial segregation, environmental pollutants, and built environment. To elucidate the relationship between ND and cancer risk, we will use Virginia and Pennsylvania state cancer registry data, case and control residential histories, and data documenting multiple historical and current ND exposure indicators. The aims of this project are to determine the effects of different ND exposure domains for colorectal, lung, and female breast cancer incidence cumulatively over time using residential histories. The expected outcomes of this research will be (1) new methods for estimating ND effects over time and (2) identification of previously undetected historic ND exposures associated with significant cancer risk.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2977-2985"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12527257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143951416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A hypothetical intervention on the use of hearing aids for the risk of dementia in people with hearing loss in UK Biobank. 英国生物银行对听力损失人群中使用助听器对痴呆风险的假设干预。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwae452
Jure Mur, Matthias Klee, Helen R Wright, Alina Solomon, Christine Johnson, Thomas J Littlejohns, Graciela Muniz-Terrera, Anja K Leist
{"title":"A hypothetical intervention on the use of hearing aids for the risk of dementia in people with hearing loss in UK Biobank.","authors":"Jure Mur, Matthias Klee, Helen R Wright, Alina Solomon, Christine Johnson, Thomas J Littlejohns, Graciela Muniz-Terrera, Anja K Leist","doi":"10.1093/aje/kwae452","DOIUrl":"10.1093/aje/kwae452","url":null,"abstract":"<p><p>Observational studies have reported that hearing aid (HA) use is associated with a reduced risk of dementia diagnosis, suggesting a possible protective effect. However, extant observational studies do not explicitly model causal effects, while randomized controlled trials on the effect of HA on dementia exhibit short follow-up. Here we used self-report, hearing tests, and healthcare records in UK Biobank to design a hypothetical intervention for the effect of HA use on the risk of dementia diagnosis in people with incident hearing loss. HA users exhibited a higher risk of dementia diagnosis than nonusers (risk ratio: 1.43; 95% CI, 1.08-1.88). Associations between HA use and dementia diagnosis were robust across sensitivity analyses (risk ratio: 1.34-1.59), but adjustment for primary healthcare use (risk ratio: 0.77; 95% CI, 0.44-1.33) or primary and secondary care use (risk ratio: 0.68; 95% CI, 0.39-1.18) substantially decreased the observed effect. The decrease in effect estimates upon adjustment for primary (risk ratio: 1.30; 95% CI, 0.95-1.78), and primary and secondary healthcare use (1.30, 0.94-1.78) was smaller when participants with relatively early diagnoses of hearing loss were included in the sample compared to when they were not. While the findings are not conclusive, they suggest residual confounding by healthcare use and dating of hearing loss diagnosis in participants without primary care data in UK Biobank.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2844-2852"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12527245/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142826927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Association of childhood and adult socioeconomic status with adult social connection: a mediation analysis. 儿童和成人社会经济地位与成人社会联系的关联:中介分析。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf106
Laura Cachón-Alonso, Laura Pulkki-Råback, Christian Hakulinen, Katja Pahkala, Suvi Rovio, Olli T Raitakari, Nina Hutri, Kaisla Komulainen, Marko Elovainio
{"title":"Association of childhood and adult socioeconomic status with adult social connection: a mediation analysis.","authors":"Laura Cachón-Alonso, Laura Pulkki-Råback, Christian Hakulinen, Katja Pahkala, Suvi Rovio, Olli T Raitakari, Nina Hutri, Kaisla Komulainen, Marko Elovainio","doi":"10.1093/aje/kwaf106","DOIUrl":"10.1093/aje/kwaf106","url":null,"abstract":"<p><p>In this prospective cohort study, we explored associations of childhood socioeconomic status (SES) with social connection in adulthood, and to which extent these associations can be explained by SES in adulthood. We used data from the longitudinal Young Finns Study (n = 1775, 3-18 years at baseline). Childhood SES was assessed through parental income and educational attainment in 1980, and participants' own adult SES through income and educational attainment in 2007. The outcomes were 3 indicators of social connection measured in 2018-2020: (1) loneliness, (2) perceived social support, and (3) frequency of social contact. SES indicators were analyzed separately using regression models and causal mediation analysis via marginal structural models. In the mediation analyses, low parental income was associated with higher loneliness, lower perceived social support, and less frequent social contact in adulthood while adjusting for parental and own educational attainment. The associations with loneliness and perceived social support were partially mediated by participants' income in adulthood. Conversely, the associations between parental educational attainment and social connection in adulthood were smaller, with confidence intervals including the null. These results emphasize that poor family financial conditions during childhood may have long-lasting implications for the development and maintenance of social connection throughout the lifespan.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"3018-3027"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12527292/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144109397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Health-related quality of life in the UK Biobank Experience of Pain follow-up study: a comparison with general population norms. 英国生物银行中与健康相关的生活质量疼痛体验随访研究:与一般人群标准的比较
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf113
Nigel R Armfield, Scott F Farrell, Belinda J Gabbe, Rachel A Elphinston, Shamini Kosgallana, Luke B Connelly, Michele Sterling
{"title":"Health-related quality of life in the UK Biobank Experience of Pain follow-up study: a comparison with general population norms.","authors":"Nigel R Armfield, Scott F Farrell, Belinda J Gabbe, Rachel A Elphinston, Shamini Kosgallana, Luke B Connelly, Michele Sterling","doi":"10.1093/aje/kwaf113","DOIUrl":"10.1093/aje/kwaf113","url":null,"abstract":"<p><p>The UK Biobank (UKB) is a population-based resource of genetic, health, lifestyle, sociodemographic, and linked clinical data for approximately 500 000 volunteers. Previous analyses of health determinants have shown that the UKB is not representative of the population from which it is drawn. However, representativeness from a general health-outcomes perspective is unknown, but could be assessed using health-related quality of life (HRQoL) questionnaire responses and expected population norms. The HRQoL responses, collected using the EuroQoL EQ-5D-5L instrument, were available for participants who completed the experience of pain follow-up survey (n = 167 199). We comprehensively characterized follow-up participant HRQoL and made age and sex-specific comparisons with normative data derived from the nationally representative Health Survey for England (2014). The pattern of reported problems mirrored those of the expected population norms, but with differences in magnitude: for both sexes, at all ages (except >74 years) the prevalence/odds of problems were greater for UKB participants. Compared with the norms, HRQoL of participants in this subsample did not follow a pattern of decline as expected with increasing age. While we did find differences in patterns between the EoPQ cohort and expected population HRQoL, the absolute differences were only modest, and this should provide reassurance for users of the data.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2954-2967"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12527277/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144155484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Family criminal legal system exposure and early adolescents' pubertal development: the mediating role of family strain. 家庭刑事法律制度与青少年青春期发育:家庭压力的中介作用。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwae457
Juan Del Toro, Michael Roettger, Dylan B Jackson, Sylia Wilson
{"title":"Family criminal legal system exposure and early adolescents' pubertal development: the mediating role of family strain.","authors":"Juan Del Toro, Michael Roettger, Dylan B Jackson, Sylia Wilson","doi":"10.1093/aje/kwae457","DOIUrl":"10.1093/aje/kwae457","url":null,"abstract":"<p><p>Pubertal trends, wherein adolescents today are experiencing puberty earlier than prior generations, have coincided with the expansion of the criminal legal system, which is disproportionately affecting communities of color. However, whether pubertal development and criminal legal system exposure among adolescents are interrelated is unknown. We tested whether family members' criminal legal system exposure predicted adolescents' pubertal development, whether family strain explained the relation between criminal legal system exposure and pubertal development, and whether race/ethnicity moderated our results. We used 3 yearly waves of longitudinal data among a national sample of 9518 adolescents. Results indicated that 40% of Black, 20% of Latinx, 16% of adolescents of other races or ethnicities, and 10% of White adolescents experienced 1 or more family criminal legal system exposures. In structural equation models within a case-crossover design controlling for measured confounders and unmeasured confounders that do not change over time, including neighborhood-level socioeconomic status and crime, family criminal legal system exposure predicted adolescents' advanced pubertal development, and family strain explained this relation between family criminal legal system exposure and pubertal development. The approach to law and order in the United States has public health implications that may be perpetuating health inequities, as accelerated pubertal development can have downstream consequences across the life course.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2870-2878"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12527266/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Validation of diagnosis codes for low birth weight and small for gestational age in the Medicaid Analytic eXtract database. 医疗补助分析提取数据库中低出生体重和小胎龄诊断代码的验证。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwae472
Xi Wang, Yehua Wang, Yanmin Zhu, Diana Montoya-Williams, Joshua Brown, Amie J Goodin, Ellen Zimmerman, Almut G Winterstein
{"title":"Validation of diagnosis codes for low birth weight and small for gestational age in the Medicaid Analytic eXtract database.","authors":"Xi Wang, Yehua Wang, Yanmin Zhu, Diana Montoya-Williams, Joshua Brown, Amie J Goodin, Ellen Zimmerman, Almut G Winterstein","doi":"10.1093/aje/kwae472","DOIUrl":"10.1093/aje/kwae472","url":null,"abstract":"<p><p>The accuracy of low birth weight (LBW) and small for gestational age (SGA) in administrative health care records is crucial for perinatal studies but there are few published validity studies. Using 1999-2010 Medicaid Analytic eXtract (MAX) data linked to birth certificates (BCs), we identified mother-infant dyads (≥30 days enrollment after delivery, with valid gestational age [GA] and birth weight [BW] data). We identified LBW and SGA according to International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes. Infants with BW < 10% of the US reference were flagged as SGA. For LBW group diagnoses, we imputed BW using median, mean BW from BCs, and ICD code boundaries of infants in the same LBW group. We calculated the sensitivity, specificity, and positive and negative predictive values to assess performance. We identified 1 536 272 live births. All LBW groups had low Ses and high SPs and NPVs, whereas PPVs varied. Among infants with SGA diagnoses based on GA/BW from the BC, SE of the SGA codes was 13.36%, SP was 99.01%, and PPV was 67.37%. Combining imputation with LBW codes increased SE up to 22.09% (lower boundary) but decreased PPV to 41.53% (lower boundary). The ICD-9-CM codes from administrative health care records had low SE but high SP. Imputation based on GA and BW did not add much value to SGA identification.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2887-2895"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142998419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Associations of social network size and perceived level of social support with age acceleration estimated by a proteomic aging clock: the Atherosclerosis Risk in Communities Study. 社会网络规模和感知到的社会支持水平与蛋白质组老化时钟估计的年龄加速的关系:社区研究中的动脉粥样硬化风险。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf125
Eri Eguchi, Anna Prizment, Shuo Wang, Sanaz Sedaghat, Mako Nagayoshi, Susan A Everson-Rose, Kevin J Sullivan, Ganga Bey, Anna Kucharska-Newton, Weihua Guan, Pamela L Lutsey
{"title":"Associations of social network size and perceived level of social support with age acceleration estimated by a proteomic aging clock: the Atherosclerosis Risk in Communities Study.","authors":"Eri Eguchi, Anna Prizment, Shuo Wang, Sanaz Sedaghat, Mako Nagayoshi, Susan A Everson-Rose, Kevin J Sullivan, Ganga Bey, Anna Kucharska-Newton, Weihua Guan, Pamela L Lutsey","doi":"10.1093/aje/kwaf125","DOIUrl":"10.1093/aje/kwaf125","url":null,"abstract":"<p><p>We examined the associations of social network size and social support with biological age acceleration using a protein-based aging clock. A total of 11 719 participants (mean age, 57.1 ± 5.7 years; 55.6% female) of the Atherosclerosis Risk in Communities (ARIC) study Visit 2 (1990-1992) were included. Biological age was calculated using a proteomic aging clock (PAC), and age acceleration was defined as the residuals after regressing the PAC on chronological age. The associations of self-reported social network size and level of support with standardized mean age acceleration were examined using multivariable linear regression. Size of social networks and level of support were inversely associated with age acceleration. The age accelerations of small, medium, and large social networks were 0.24, 0.08, and -0.05 (P for trend = 0.003), while for low, moderate, and high levels of support the age accelerations were 0.33, 0.19, and -0.06 (P for trend < 0.0001), respectively. Associations were modestly attenuated after adjusting for social and lifestyle factors. Findings of the benefit of social networks and support to biological aging processes provide evidence of potential physiological underpinnings of social interactions on health outcomes.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2905-2914"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144289370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The health-related impact of disruptions in cancer care and the Waiting Time Paradox. 癌症治疗中断对健康的影响和等待时间悖论。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf128
Parker R Tope, Bronner P Gonçalves, Mariam El-Zein, Eduardo L Franco
{"title":"The health-related impact of disruptions in cancer care and the Waiting Time Paradox.","authors":"Parker R Tope, Bronner P Gonçalves, Mariam El-Zein, Eduardo L Franco","doi":"10.1093/aje/kwaf128","DOIUrl":"10.1093/aje/kwaf128","url":null,"abstract":"<p><p>Healthcare system disruptions, such as that caused by the COVID-19 pandemic, can lead to delays in, or lag time to, cancer diagnosis and treatment. In order to quantify the negative impact of disruptions such as this on the health of populations, a better grasp on biases that might affect estimation of effects of diagnosis or treatment delays on clinical outcomes is needed. Here, we discuss some of the methodological difficulties in these analyses, including those posed by what has been referred to as the Waiting Time Paradox. In doing so, we define the effect of lag time using potential outcomes, describe evidence for the Waiting Time Paradox, and present directed acyclic graphs to characterize different contexts when it might occur. Although our discussion is motivated by disruptions in cancer care, accurate quantification of lag time's effect would be valuable for the study of other medical conditions and different types of medical service inefficiencies, as well as in settings where policy changes to minimize waiting time are considered.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2928-2935"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144289377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Evaluating the generalizability of commercial healthcare claims data. 评估商业医疗保健索赔数据的普遍性。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf142
Alex Dahlen, Yaowei Deng, Vivek Charu
{"title":"Evaluating the generalizability of commercial healthcare claims data.","authors":"Alex Dahlen, Yaowei Deng, Vivek Charu","doi":"10.1093/aje/kwaf142","DOIUrl":"10.1093/aje/kwaf142","url":null,"abstract":"<p><p>Commercial healthcare claims datasets area nonrandom sample of the US population, affecting generalizability. Rigorous comparisons of claims-derived results to ground-truth data that quantify external validity bias are lacking. Our goal is to (1) quantify external validity of commercial healthcare claims data and (2) to evaluate how socioeconomic/demographic factors are related to the bias. We analyzed inpatient discharge records occurring between January 1, 2019 and December 31, 2019 in five states: California, Iowa, Maryland, Massachusetts, and New Jersey, and compared rates (per person-year) of the 250 most common inpatient procedures between claims and reference data for each target population. We used Merative MarketScan Commercial Database for the claims data and State Inpatient Databases and the US Census as reference. For a target population of all Americans, commercial healthcare claims underestimate the rate of overall inpatient discharges by 23.1%. The extent of bias varied across procedures, with the rates of ~25% of procedures being underestimated by a factor of 2. Socioeconomic factors were significantly associated with the magnitude of bias (${R}^2=69.4%,$P < .001). When the target population was restricted to commercially insured Americans, the bias decreased substantially (1.4% of procedures were biased by more than factor of 2), but some variation across procedures remained.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":"2999-3006"},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12527232/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144551667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Improving classification of myocardial infarction with machine learning in a diverse population. 用机器学习改进不同人群中心肌梗死的分类。
IF 4.8 2区 医学
American journal of epidemiology Pub Date : 2025-10-07 DOI: 10.1093/aje/kwaf223
Alicia Chen, Chuan Hong, Yuk Lam Ho, Nicholas Link, Jacqueline P Honerlaw, Vidisha Tanukonda, Ariela R Orkaby, Saadia Qazi, Connor Melley, Ashley Galloway, Lauren Costa, Monika Maripuri, Xuan Wang, Yichi Zhang, Petra Schubert, Tianrun Cai, Zeling He, Vidul A Panickan, Morgan Rosser, Laura Tarko, Sharon Dowell, Candace Feldman, Gail Kerr, J Michael Gaziano, Peter W F Wilson, Kelly Cho, Tianxi Cai, Katherine P Liao
{"title":"Improving classification of myocardial infarction with machine learning in a diverse population.","authors":"Alicia Chen, Chuan Hong, Yuk Lam Ho, Nicholas Link, Jacqueline P Honerlaw, Vidisha Tanukonda, Ariela R Orkaby, Saadia Qazi, Connor Melley, Ashley Galloway, Lauren Costa, Monika Maripuri, Xuan Wang, Yichi Zhang, Petra Schubert, Tianrun Cai, Zeling He, Vidul A Panickan, Morgan Rosser, Laura Tarko, Sharon Dowell, Candace Feldman, Gail Kerr, J Michael Gaziano, Peter W F Wilson, Kelly Cho, Tianxi Cai, Katherine P Liao","doi":"10.1093/aje/kwaf223","DOIUrl":"https://doi.org/10.1093/aje/kwaf223","url":null,"abstract":"<p><p>Phenotype classification with electronic health record (EHR) data is increasingly performed with ML, however their performance in diverse populations remains understudied. We compared an ICD-based algorithm with an ML phenotyping pipeline to classify myocardial infarction (MI) in a general and self-reported Black population. We determined the impact of differential performance by replicating a published MI risk factor study with MI defined by the ICD or ML algorithms. Individuals followed in the Veterans Health Administration (VHA) EHR with data from 2002 to 2019 were examined: 11,523,175 Veterans, mean age 67.5 years, 93.8% male, 14.3% Black, 79.1% White. MI was classified using a published rule-based ICD algorithm and an ML pipeline, PheCAP which incorporates natural language processing. Algorithms were trained and validated against n=403 Veterans randomly selected and chart-reviewed for MI (gold standard), oversampled for self-reported Black. Among chart-reviewed Veterans, the ICD algorithm had high PPV and low sensitivity (all race, PPV:0.97, sensitivity:0.17; Black Veterans, PPV:0.94, sensitivity:0.24). PheCAP MI had good PPV and higher sensitivity (all race, PPV:0.90, sensitivity:0.66; Black, PPV:0.81, sensitivity:0.79). Applying PheCAP MI to the entire VHA population to classify MI provided increased power to replicate findings from the published MI risk factor study compared to the ICD algorithm.</p>","PeriodicalId":7472,"journal":{"name":"American journal of epidemiology","volume":" ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145237569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信