scholarly journals Learning longitudinal patterns and identifying subtypes of pediatric Crohn disease treated with infliximab via trajectory cluster analysis of electronic health records

2021 ◽  
Author(s):  
Andrew Chen ◽  
Ronen Stein ◽  
Robert N. Baldassano ◽  
Jing Huang
Keyword(s):  
Electronic Health Records ◽  
Disease Activity ◽  
Crohn Disease ◽  
Cross Sectional ◽  
Health Records ◽  
Disease Evolution ◽  
Current Classification ◽  
Electronic Health ◽  
Over Time

ABSTRACTBackgroundThe current classification of pediatric CD is mainly based on cross-sectional data. The objective of this study is to identify subgroups of pediatric CD through trajectory cluster analysis of disease activity using data from electronic health records.MethodsWe conducted a retrospective study of pediatric CD patients who had been treated with infliximab. The evolution of disease over time was described using trajectory analysis of longitudinal data of C-Reactive Protein (CRP). Patterns of disease evolution were extracted through functional principal components analysis and subgroups were identified based on those patterns using the Gaussian mixture model. We compared patient characteristics, a biomarker for disease activity, received treatments, and long-term surgical outcomes across subgroups.ResultsWe identified four subgroups of pediatric CD patients with differential relapse-and-remission risk profiles. They had significantly different disease phenotype (p < 0.001), CRP (p < 0.001) and calprotectin (p = 0.037) at diagnosis, with increasing percentage of inflammatory phenotype and declining CRP and fecal calprotectin levels from Subgroup 1 through 4. The risk of colorectal surgery within 10 years after diagnosis was significantly different between groups (p < 0.001). We did not find statistical significance in gender or age at diagnosis across subgroups, but the BMI z-score was slightly smaller in subgroup 1 (p =0.055).ConclusionsReadily available longitudinal data from electronic health records can be leveraged to provide a deeper characterization of pediatric Crohn disease. The identified subgroups captured novel forms of variation in pediatric Crohn disease that were not explained by baseline measurements and treatment information.SummaryThe current classification of pediatric Crohn disease mainly relies on cross-sectional data, e.g., the Paris classification. However, the phenotypic classification may evolve over time after diagnosis. Our study utilized longitudinal measures from the electronic health records and stratified pediatric Crohn disease patients with differential relapse-and-remission risk profiles based on patterns of disease evolution. We found trajectories of well-maintained low disease activity were associated with less severe disease at baseline, early initiation of infliximab treatment, and lower risk of surgery within 10 years of diagnosis, but the difference was not fully explained by phenotype at diagnosis.

scholarly journals Physician Specialty and Variations in Adoption of Electronic Health Records

2013 ◽  
Vol 04 (02) ◽  
pp. 225-240 ◽  
Author(s):  
S. Banerjee ◽  
R. Kaushal ◽  
L.M. Kern ◽  
Z. M. Grinspan
Keyword(s):  
Electronic Health Records ◽  
Reference Group ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Physician Specialty ◽  
Cross Sectional ◽  
Health Records ◽  
Ehr Adoption ◽  
Electronic Health ◽  
Over Time

SummaryObjective: Efforts to promote adoption of electronic health records (EHRs) have focused on primary care physicians, who are now expected to exchange data electronically with other providers, including specialists. However, the variation of EHR adoption among specialists is underexplored.Methods: We conducted a retrospective cross-sectional study to determine the association between physician specialty and the prevalence of EHR adoption, and a retrospective serial cross-sectional study to determine the association of physician specialty and the rate of EHR adoption over time. We used the 2005–2009 National Ambulatory Medical Care Survey. We considered fourteen specialties, and four definitions of EHR adoption (any EHR, basic EHR, full EHR, and a novel definition of EHR sophistication). We used multivariable logistic regression, and adjusted for several covariates (geography, practice characteristics, revenue characteristics, physician degree).Results: Physician specialty was significantly associated with EHR adoption, regardless of the EHR definition, after adjusting for covariates. Psychiatrists, dermatologists, pediatricians, ophthalmologists, and general surgeons were significantly less likely to adopt EHRs, compared to the reference group of family medicine / general practitioners. After adjustment for covariates, these specialties were 44 – 94% less likely to adopt EHRs than the reference group. EHR adoption increased in all specialties, by approximately 40% per year. The rate of EHR adoption over time did not significantly vary by specialty.Conclusions: Although EHR adoption is increasing in all specialties, adoption varies widely by specialty. In order to insure each individual’s network of providers can electronically share data, widespread adoption of EHRs is needed across all specialties.Citation: Grinspan ZM, Banerjee S, Kaushal R, Kern LM. Physician specialty and variations in adoption of electronic health records. Appl Clin Inf 2013; 4: 225–240http://dx.doi.org/10.4338/ACI-2013-02-RA-0015

scholarly journals Leveraging electronic health records data to predict multiple sclerosis disease activity

2021 ◽  
Vol 8 (4) ◽  
pp. 800-810
Author(s):  
Yuri Ahuja ◽  
Nicole Kim ◽  
Liang Liang ◽  
Tianrun Cai ◽  
Kumar Dahal ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Electronic Health Records ◽  
Disease Activity ◽  
Health Records ◽  
Multiple Sclerosis Disease ◽  
Electronic Health

Association Between Meaningful Use and Florida Counties’ COVID-19 Case and Death Rates Among Medicaid Providers (Preprint)

2021 ◽  
Author(s):  
Katherine Freeman ◽  
Judith P. Monestime
Keyword(s):  
Electronic Health Records ◽  
Cumulative Incidence ◽  
Meaningful Use ◽  
County Level ◽  
Cross Sectional ◽  
Health Records ◽  
Death Rates ◽  
Public Health Reporting ◽  
Electronic Health ◽  
Population Demographic

BACKGROUND Although the Health Information Technology for Economic and Clinical Health (HITECH) Act has accelerated the adoption of Meaningful Use of Electronic Health Records (EHRs) among Medicaid providers, only about half achieve Meaningful Use. Furthermore, the validity of public health reporting of COVID-19 outcomes, which relies on Meaningful Use advanced functions, remains unknown. OBJECTIVE This study aims to examine the difference between Medicaid providers who did and did not achieve Meaningful Use regarding Florida county-level incidence rates of COVID-19 cases and deaths, accounting for county-level race/ethnicity, unemployment, income, prevalence of respiratory diseases, age, poverty, and healthcare environment. METHODS This cross-sectional ecologic study examined the association between Meaningful Use achievement by Medicaid providers and COVID-19 cases and death rates from 67 Florida counties as of November 19, 2020. Provider information was obtained from the publicly available database from the Florida Medicaid Promoting Interoperability Program, formerly Electronic Health Record Incentive Program. The database includes the Area Health Resources File, capturing provider characteristics and population demographic and socioeconomic characteristics at the county level. Cumulative COVID-19 cases and deaths were obtained from the Florida Department of Health Open Data (FDOH) for zip codes which were aggregated by county. Rates were obtained by dividing cumulative incidence or prevalence by the U.S. Census County population. RESULTS As of November 19, 2020, the cumulative incidence rate of COVID-19 deaths was significantly different between Medicaid providers who achieved Meaningful Use and those who did not (P=.0131), with relatively more deaths reported for those not achieving Meaningful Use. County-level characteristics associated with increased COVID-19 death rates in hierarchical models include greater concentrations of persons of African American or Black race (P<.0001), lower median household income (P<.0001), higher unemployment (P<.0001), and higher concentrations of those living in poverty (P<.0001) and without health insurance (P<.0001). CONCLUSIONS Although Federal subsidies successfully influenced the adoption of Electronic Health Records, our findings suggest an emerging further digital "advanced use" divide among patients cared for by Medicaid providers. Policy interventions need to be reevaluated to address disparities in COVID-19 clinical outcomes which appear exacerbated by the limited use of advanced Electronic Health Records functions. CLINICALTRIAL not applicable

scholarly journals Incorporating natural language processing to improve classification of axial spondyloarthritis using electronic health records

Rheumatology ◽  
2019 ◽  
Vol 59 (5) ◽  
pp. 1059-1065 ◽  
Author(s):  
Sizheng Steven Zhao ◽  
Chuan Hong ◽  
Tianrun Cai ◽  
Chang Xu ◽  
Jie Huang ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Predictive Value ◽  
Area Under The Curve ◽  
Free Text ◽  
Text Data ◽  
Health Records ◽  
Disease Concepts ◽  
Icd Codes ◽  
Electronic Health

Abstract Objectives To develop classification algorithms that accurately identify axial SpA (axSpA) patients in electronic health records, and compare the performance of algorithms incorporating free-text data against approaches using only International Classification of Diseases (ICD) codes. Methods An enriched cohort of 7853 eligible patients was created from electronic health records of two large hospitals using automated searches (⩾1 ICD codes combined with simple text searches). Key disease concepts from free-text data were extracted using NLP and combined with ICD codes to develop algorithms. We created both supervised regression-based algorithms—on a training set of 127 axSpA cases and 423 non-cases—and unsupervised algorithms to identify patients with high probability of having axSpA from the enriched cohort. Their performance was compared against classifications using ICD codes only. Results NLP extracted four disease concepts of high predictive value: ankylosing spondylitis, sacroiliitis, HLA-B27 and spondylitis. The unsupervised algorithm, incorporating both the NLP concept and ICD code for AS, identified the greatest number of patients. By setting the probability threshold to attain 80% positive predictive value, it identified 1509 axSpA patients (mean age 53 years, 71% male). Sensitivity was 0.78, specificity 0.94 and area under the curve 0.93. The two supervised algorithms performed similarly but identified fewer patients. All three outperformed traditional approaches using ICD codes alone (area under the curve 0.80–0.87). Conclusion Algorithms incorporating free-text data can accurately identify axSpA patients in electronic health records. Large cohorts identified using these novel methods offer exciting opportunities for future clinical research.

scholarly journals Contribution of Different Patient Information Sources to Create the Best Possible Medication History

2020 ◽  
Vol 33 (6) ◽  
pp. 384 ◽  
Author(s):  
Joelizy Oliveira ◽  
Ana Cristina Cabral ◽  
Marta Lavrador ◽  
Filipa A. Costa ◽  
Filipe Félix Almeida ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Medical Records ◽  
Data Sources ◽  
Sources Of Information ◽  
Medication History ◽  
Cross Sectional ◽  
Health Records ◽  
Hospital Medical ◽  
Time Periods ◽  
Electronic Health

Introduction: Obtaining the best possible medication history is the crucial step in medication reconciliation. Our aim was to evaluate the potential contributions of the main data sources available – patient/caregiver, hospital medical records, and shared electronic health records – to obtain an accurate ‘best possible medication history’.Material and Methods: An observational cross-sectional study was conducted. Adult patients taking at least one medicine were included. Patient interview was performed upon admission and this information was reconciled with hospital medical records and shared electronic health records, assessed retrospectively. Concordance between sources was assessed. In the shared electronic health records, information was collected for four time-periods: the preceding three, six, nine and 12-months. The proportion of omitted data between time-periods was analysed.Results: A total of 148 patients were admitted, with a mean age of 54.6 ± 16.3 years. A total of 1639 medicines were retrieved. Only 29% were collected simultaneously in the three sources of information, 40% were only obtained in shared electronic health records and only 5% were obtained exclusively from patients. The total number of medicines gathered in shared electronic health records considering the different time frames were 778 (three-months), 1397 (six-months), 1748 (nine-months), and 1933 (12-months).Discussion: The use of shared electronic health records provides data that were omitted in the other data sources available and retrieving the information at six months is the most efficient procedure to establish the basis of the best possible medication history.Conclusion: Shared electronic health records should be the preferred source of information to supplement the patient or caregiver interview in order to increase the accuracy of best possible medication history of the patient, particularly if collected within the prior six months.

Five analytic challenges in working with electronic health records data to support clinical trials with some solutions

2020 ◽  
Vol 17 (4) ◽  
pp. 370-376
Author(s):  
Benjamin A Goldstein
Keyword(s):  
Clinical Trials ◽  
Electronic Health Records ◽  
Large Scale ◽  
Point Of Care ◽  
Cross Sectional ◽  
Health Records ◽  
Data Resource ◽  
Electronic Health ◽  
Data Elements ◽  
Data Efficiency

Electronic health records data are becoming a key data resource in clinical research. Owing to issues of data efficiency, electronic health records data are being used for clinical trials. This includes both large-scale pragmatic trails and smaller—more focused—point-of-care trials. While electronic health records data open up a number of scientific opportunities, they also present a number of analytic challenges. This article discusses five particular challenges related to organizing electronic health records data for analytic purposes. These are as follows: (1) data are not organized for research purposes, (2) data are both densely and irregularly observed, (3) we don’t have all data elements we may want or need, (4) data are both cross-sectional and longitudinal, and (5) data may be informatively observed. While laying out these challenges, the article notes how many of these challenges can be addressed by careful and thoughtful study design as well as by integration of clinicians and informaticians into the analytic team.

scholarly journals Soft clustering using real-world data for the identification of multimorbidity patterns in an elderly population: cross-sectional study in a Mediterranean population

BMJ Open ◽  
2019 ◽  
Vol 9 (8) ◽  
pp. e029594 ◽  
Author(s):  
Concepción Violán ◽  
Quintí Foguet-Boreu ◽  
Sergio Fernández-Bertolín ◽  
Marina Guisado-Clavero ◽  
Margarita Cabrera-Bean ◽  
...  
Keyword(s):  
Cluster Analysis ◽  
Electronic Health Records ◽  
Cross Sectional Study ◽  
Secondary Outcome ◽  
Sectional Study ◽  
Cross Sectional ◽  
Health Records ◽  
Soft Clustering ◽  
Fuzzy C Means ◽  
Electronic Health

ObjectivesThe aim of this study was to identify, with soft clustering methods, multimorbidity patterns in the electronic health records of a population ≥65 years, and to analyse such patterns in accordance with the different prevalence cut-off points applied. Fuzzy cluster analysis allows individuals to be linked simultaneously to multiple clusters and is more consistent with clinical experience than other approaches frequently found in the literature.DesignA cross-sectional study was conducted based on data from electronic health records.Setting284 primary healthcare centres in Catalonia, Spain (2012).Participants916 619 eligible individuals were included (women: 57.7%).Primary and secondary outcome measuresWe extracted data on demographics, International Classification of Diseases version 10 chronic diagnoses, prescribed drugs and socioeconomic status for patients aged ≥65. Following principal component analysis of categorical and continuous variables for dimensionality reduction, machine learning techniques were applied for the identification of disease clusters in a fuzzy c-means analysis. Sensitivity analyses, with different prevalence cut-off points for chronic diseases, were also conducted. Solutions were evaluated from clinical consistency and significance criteria.ResultsMultimorbidity was present in 93.1%. Eight clusters were identified with a varying number of disease values: nervous and digestive; respiratory, circulatory and nervous; circulatory and digestive; mental, nervous and digestive, female dominant; mental, digestive and blood, female oldest-old dominant; nervous, musculoskeletal and circulatory, female dominant; genitourinary, mental and musculoskeletal, male dominant; and non-specified, youngest-old dominant. Nuclear diseases were identified for each cluster independently of the prevalence cut-off point considered.ConclusionsMultimorbidity patterns were obtained using fuzzy c-means cluster analysis. They are clinically meaningful clusters which support the development of tailored approaches to multimorbidity management and further research.

scholarly journals Provider and Patient Determinants of Generic Levothyroxine Prescribing: An Electronic Health Records–Based Study

2017 ◽  
Vol 51 (8) ◽  
pp. 640-648 ◽  
Author(s):  
Robert J. Romanelli ◽  
Vani Nimbal ◽  
Sarah K. Dutcher ◽  
Xia Pu ◽  
Jodi B. Segal
Keyword(s):  
Electronic Health Records ◽  
Intraclass Correlation ◽  
Fixed Effect ◽  
Cross Sectional ◽  
Mixed Effect ◽  
Health Records ◽  
Residual Variation ◽  
Generic Prescribing ◽  
Electronic Health ◽  
To Receive

Background: Despite the availability of generic levothyroxine products for more than a decade, uptake of these products is poor. Objective: We sought to evaluate determinants of generic prescribing of levothyroxine. Methods: In a cross-sectional analysis of electronic health records data between 2010 and 2013, we identified adult patients with a levothyroxine prescription from a primary-care physician (PCP) or endocrinologist. We used mixed-effect logistic regression models with random intercepts for prescribing provider to examine predictors of generic levothyroxine prescribing. Models include patient, prescription, and provider fixed-effect covariates. Odds ratios (ORs) and 95% CIs were generated. Between-provider random variation was quantified by the intraclass correlation coefficient (ICC). Results: Study patients (n = 63 838) were clustered among 941 prescribing providers within 25 ambulatory care clinics. The overall prevalence of generic prescribing of levothyroxine was 73%. In the multivariable mixed-effect model, patients were significantly less likely to receive generic levothyroxine from an endocrinologist than a PCP (OR = 0.43; 95% CI = 0.33-0.55; P < 0.001). Women were less likely to receive generic levothyroxine than men from endocrinologists (OR = 0.68; 95% CI = 0.59-0.78; P < 0.001) but not from PCPs. Between-provider variation in generic prescribing was 18.3% in the absence of fixed-effect covariates and could be explained marginally by patient, prescription, and provider factors (ICC = 15.9%). Conclusions: Generic levothyroxine prescribing differed by PCPs and endocrinologists. Residual variation in generic prescribing, after accounting for measurable factors, indicates the need for provider interventions or patient education aimed at improving levothyroxine generic uptake.

Sign in / Sign up

Export Citation Format

Share Document