Search

Self-harm risk prediction models developed using health system data (electronic health records and insurance claims information) often use patient information from up to several years prior to the index visit when the prediction is made. Measurements from some time periods may not be available for all patients. Using the framework of algorithm-agnostic variable importance, we study the predictive potential of variables corresponding to different time horizons prior to the index visit and demonstrate the application of variable importance techniques in the biomedical informatics setting. We use variable importance to quantify the potential of recent (up to three months before the index visit) and distant (more than one year before the index visit) patient mental health information for predicting self-harm risk using data from seven health systems. We quantify importance as the decrease in predictiveness when the variable set of interest is excluded from the prediction task. We define predictiveness using discriminative metrics: area under the receiver operating characteristic curve (AUC), sensitivity, and positive predictive value. Mental health predictors corresponding to the three months prior to the index visit show strong signal of importance; in one setting, excluding these variables decreased AUC from 0.85 to 0.77. Predictors corresponding to more distant information were less important. Predictors from the months immediately preceding the index visit are highly important. Implementation of self-harm prediction models may be challenging in settings where recent data are not completely available (e.g., due to lags in insurance claims processing) at the time a prediction is made. Clinically derived variables from different time frames exhibit varying levels of importance for predicting self-harm. Variable importance analyses can inform whether and how to implement risk prediction models into clinical practice given real-world data limitations. These analyses be applied more broadly in biomedical informatics research to provide insight into general clinical risk prediction tasks. [Display omitted] [ABSTRACT FROM AUTHOR]

Background: COVID-19 has been observed to be associated with venous and arterial thrombosis. The inflammatory disease prolongs hospitalization, and preexisting comorbidities can intensify thrombotic burden in COVID-19 patients. However, venous thromboembolism, arterial thrombosis, and other vascular complications may go unnoticed in critical care settings. Early risk stratification is paramount in the COVID-19 patient population for proactive monitoring of thrombotic complications.Objective: This exploratory research seeks to characterize thrombotic complication risk factors associated with COVID-19 using information from Electronic Health Record (EHR) databases and insurance claims databases. The goal is to develop an approach for analysis using real-world data evidence that can be generalized to characterize thrombotic complications and additional conditions in other clinical settings as well, such as pneumonia or acute respiratory distress syndrome in COVID-19 patients or in ICU settings.Methods: We extracted deidentified patient data from the insurance claims database, IBM MarketScan, and formulated hypotheses on thrombotic complications in COVID-19 patients with respect to patient demographic and clinical factors using logistic regression. The analysis then verified the hypotheses with deidentified patient data from the Mass General Brigham (MGB) patient EHR database, the Research Patient Data Registry (RPDR). A combination of odds ratios, 95% confidence intervals (CI), and P-values were obtained via the statistical analysis.Results: The analysis identified significant predictors (with P-value <.001) for thrombotic complications in 184,831 COVID-19 patients out of the millions of records from IBM MarketScan and MGB RPDR. With respect to age groups, patients 60 years old and older had higher odds (4.866 in Marketscan and 6.357 in RPDR) to have thrombotic complications than those under 60 years old. In terms of gender, men were more likely (odds ratio of 1.245 in Marketscan and 1.693 in RPDR) to have thrombotic complications than women. Among the pre-existing comorbidities, heart disease, cerebrovascular diseases, hypertension, and personal history of thrombosis all had significantly higher odds of developing a thrombotic complication. Cancer and obesity had odds greater than 1 as well. The results from RPDR validated the IBM MarketScan findings. They are largely consistent and afford mutual enrichment.Conclusions: The analysis approach can work across heterogeneous databases from diverse organizations and thus facilitates collaboration. Searching through millions of patient records, the analysis helped identify factors influencing a phenotype. Use of thrombotic complications in COVID-19 patients is just a case study, and the same design can be used across other disease areas by extracting corresponding disease specific patient data from the databases.Clinicaltrial: [ABSTRACT FROM AUTHOR]

Abstract: Purpose: Epilepsy is well known as a disorder in poststroke patients. However, studies that have investigated the association between epilepsy and the risk of subsequent stroke are limited. This population-based study investigated the incidence and risk of stroke in patients with epilepsy by using the Taiwan National Health Insurance claims data. Methods: We identified 3812 patients newly diagnosed with epilepsy in 2000–2008 and 15,248 nonepilepsy comparisons frequency matched according to sex, age, and index year. We searched for subsequent stroke diagnoses in both cohorts until the end of 2009. The incidence rates and hazard ratios of stroke were estimated based on sex, age, the average defined daily doses (DDDs) of antiepilepsy drugs, and comorbidity. Results: The stroke incidence of the epilepsy cohort was 3-fold higher than that of the comparison cohort. The age-specific results indicated that in the epilepsy cohort and the comparison cohort, the risk was the highest for the youngest group (20–39 years). Conclusion: The patients with epilepsy exhibited a higher incidence of cerebral stroke than the general population did. In addition, younger patients with epilepsy and patients who took a high doses of antiepileptic drugs exhibited a high risk of stroke. [Copyright &y& Elsevier]

Adults with congenital (cerebral palsy or spina bifida (CP/SB)) or acquired disabilities (spinal cord injury (SCI) or multiple sclerosis (MS)) have higher incidence of age-related health conditions. There is a gap in the literature about the risk of dementia among adults living with these disabilities. This study aimed to examine time to incidence of Alzheimer's disease and related dementia (ADRD) among these disability cohorts. Incidence of ADRD was compared at 4-years. Cox Regression was used to estimate adjusted hazard ratios (aHR) for incident early and late onset ADRD. Using national private payer claims data from 2007-2017, we identified adults (45+) with diagnosis of CP/SB (n=7,226), SCI (n=6,083), and MS (n=6,025). Adults without disability diagnosis were included as controls. Using age, sex, race/ethnicity, cardiometabolic, psychologic, and musculoskeletal chronic conditions, and socioeconomic variables, we propensity score matched persons with and without disabilities. We identified adults (45+) with diagnosis of CP/SB (n=7,226), SCI (n=6,083), and MS (n=6,025). Adults without disability diagnosis were included as controls. The exposure variable was diagnosis with either congenital or acquired disability. Main outcome variable was incident Alzheimer's disease and related dementia. Incidence of early and late onset ADRD were substantially higher among people with disabilities compared to their non-disabled counterparts. Adults with CP, SCI, and MS had higher risk for early [CP/SB: aHR= 3.35 (95% CI: 2.18-5.14); SCI: aHR=1.93 (95% CI:1.06-3.51); and MS: aHR=4.49 (95% CI:2.62-7.69)] and late [CP: aHR=1.68 (95% CI:1.38-2.03); SCI: aHR: 1.77 (95% CI:1.55-2.02); and MS: aHR=1.26 (95% CI:1.04, 1.54)] onset ADRD. Risk of ADRD was higher among adults with CP/SB, SCI, and MS compared to their matched cohort without disability. Investment in early screening and use of therapeutic or rehabilitative services that may help preserving cognitive function among these patient cohorts is warranted. There is no conflict of interest to disclose. [ABSTRACT FROM AUTHOR]