Adverse Healthcare Utilization Research Articles

Prediction of Readmission in Geriatric Patients From Clinical Notes: Retrospective Text Mining Study.

BackgroundPrior literature suggests that psychosocial factors adversely impact health and health care utilization outcomes. However, psychosocial factors are typically not captured by the structured data in electronic medical records (EMRs) but are rather recorded as free text in different types of clinical notes.ObjectiveWe here propose a text-mining approach to analyze EMRs to identify older adults with key psychosocial factors that predict adverse health care utilization outcomes, measured by 30-day readmission. The psychological factors were appended to the LACE (Length of stay, Acuity of the admission, Comorbidity of the patient, and Emergency department use) Index for Readmission to improve the prediction of readmission risk.MethodsWe performed a retrospective analysis using EMR notes of 43,216 hospitalization encounters in a hospital from January 1, 2017 to February 28, 2019. The mean age of the cohort was 67.51 years (SD 15.87), the mean length of stay was 5.57 days (SD 10.41), and the mean intensive care unit stay was 5% (SD 22%). We employed text-mining techniques to extract psychosocial topics that are representative of these patients and tested the utility of these topics in predicting 30-day hospital readmission beyond the predictive value of the LACE Index for Readmission.ResultsThe added text-mined factors improved the area under the receiver operating characteristic curve of the readmission prediction by 8.46% for geriatric patients, 6.99% for the general hospital population, and 6.64% for frequent admitters. Medical social workers and case managers captured more of the psychosocial text topics than physicians.ConclusionsThe results of this study demonstrate the feasibility of extracting psychosocial factors from EMR clinical notes and the value of these notes in improving readmission risk prediction. Psychosocial profiles of patients can be curated and quantified from text mining clinical notes and these profiles can be successfully applied to artificial intelligence models to improve readmission risk prediction.

Racial Disparities in Healthcare Utilization Among Individuals with Cardiometabolic Risk Factors and Comorbid Anxiety Disorder.

This study addresses racial/ethnic differences in adverse health care utilization among individuals with comorbid anxiety disorder and cardiometabolic syndrome (CMetS) risk factors. Utilizing 2011-2015 Medical Expenditure Panel Survey (MEPS) data, logistic regression models were estimated to determine the likelihood of receiving CMetS-related medical treatment in the emergency department (ED) or via inpatient services and to determine if the likelihood is associated with race/ethnicity. Adjusted models controlled for age, sex, and insurance type. Significant racial-ethnic differences were observed for utilization (any emergency department and/or inpatient visit). The odds of non-Hispanic Black respondents reporting emergency department and/or inpatient utilization was 2.39 (p < 0.05) times the odds of non-Hispanic White respondents. Racial-ethnic variation in adverse healthcare utilization suggests an opportunity to improve care and outcomes for persons diagnosed with comorbid anxiety disorder and cardiometabolic syndrome. Integrated interventions could simultaneously improve mental health and facilitate CMetS disease self-management.

The patient-centered oncology care on health care utilization and cost: A systematic review and meta-analysis.

Optimal cancer care entails coordination among multiple providers and continued follow-up and surveillance over time. The patient-centered care brings opportunities to improve the delivery of cancer care. The adoption of patient-centered oncology care (PCOC) is in its infancy. Evidence synthesis on the model's effectiveness is scant. This is the first systemic review and meta-analysis on associations of PCOC with cancer patients' adverse health care utilization, cost, patient satisfaction, and quality of care. Our study was guided by the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) framework. Quality appraisal was performed using Downs and Black's quality checklist. Study-level effect sizes of adverse health care utilization were computed using Cohen's d and summarized using forest plots. Funnel plots were constructed to examine publication bias. Of 334 studies that were reviewed, 10 met eligibility criteria and were included into the final analysis. Many included studies implemented almost all six of patient-centered care core attributes, plus three additional attributes that specifically addressed cancer patients' needs, including triage pathways, standardized and evidence-based symptom management, as well as support patient navigation. PCOC patients had lower utilization of inpatient care (standardized means difference [SMD] = -0.027, p = .049). Overall positive effect of PCOC on emergency department use was small and not significant (SMD = -0.023, p = .103). With regard to cost and quality of care, our narrative summaries showed an overall positive direction, though we found limitations in individual study quality that precluded a meta-analysis. The results showed that it is possible to utilize patient-centered model to support best practice of cancer care. Early evidence shows that the PCOC model has potential to improve health care utilization, cost, and quality of care, but limited numbers of included articles and heterogeneity of those studies implied that more rigorous research is expected to further investigate the model's effects.