Reduction of preventable hospital readmissions that result from chronic or acute conditions like stroke, heart failure, myocardial infarction and pneumonia remains a significant challenge for improving the outcomes and decreasing the cost of healthcare delivery in the United States. Patient readmission rates are relatively high for conditions like heart failure (HF) despite the implementation of high-quality healthcare delivery operation guidelines created by regulatory authorities. Multiple predictive models are currently available to evaluate potential 30-day readmission rates of patients. Most of these models are hypothesis driven and repetitively assess the predictive abilities of the same set of biomarkers as predictive features. In this manuscript, we discuss our attempt to develop a data-driven, electronic-medical record-wide (EMR-wide) feature selection approach and subsequent machine learning to predict readmission probabilities. We have assessed a large repertoire of variables from electronic medical records of heart failure patients in a single center. The cohort included 1,068 patients with 178 patients were readmitted within a 30-day interval (16.66% readmission rate). A total of 4,205 variables were extracted from EMR including diagnosis codes (n=1,763), medications (n=1,028), laboratory measurements (n=846), surgical procedures (n=564) and vital signs (n=4). We designed a multistep modeling strategy using the Naïve Bayes algorithm. In the first step, we created individual models to classify the cases (readmitted) and controls (non-readmitted). In the second step, features contributing to predictive risk from independent models were combined into a composite model using a correlation-based feature selection (CFS) method. All models were trained and tested using a 5-fold cross-validation method, with 70% of the cohort used for training and the remaining 30% for testing. Compared to existing predictive models for HF readmission rates (AUCs in the range of 0.6–0.7), results from our EMR-wide predictive model (AUC=0.78; Accuracy=83.19%) and phenome-wide feature selection strategies are encouraging and reveal the utility of such data-driven machine learning. Fine tuning of the model, replication using multi-center cohorts and prospective clinical trial to evaluate the clinical utility would help the adoption of the model as a clinical decision system for evaluating readmission status.

Chronic pain is common in HIV, but incompletely characterized, including its underlying etiologies, its effect on healthcare utilization, and the characteristics of affected patients in the HIV primary care setting. These data are needed to design and justify appropriate clinic-based pain management services. Using a clinical data warehouse, we analyzed one year of data from 638 patients receiving standard-of-care antiretroviral therapy in a large primary care HIV clinic, located in the Harlem neighborhood of New York City. We found that 40% of patients carried one or more chronic pain diagnoses. The most common diagnoses were degenerative musculoskeletal disorders (eg, degenerative spinal disease and osteoarthritis), followed by neuropathic pain and headache disorders. Many patients (16%) had multiple chronic pain diagnoses. Women, older patients, and patients with greater burdens of medical illness, and psychiatric and substance use comorbidities were disproportionately represented among those with chronic pain diagnoses. Controlling for overall health status, HIV patients with chronic pain had greater healthcare utilization including emergency department visits and radiology procedures. In summary, our study demonstrates the high prevalence of chronic pain disorders in the primary care HIV clinic. Colocated interventions for chronic pain in this setting should not only focus on musculoskeletal pain but also account for complex multifaceted pain syndromes, and address the unique biopsychosocial features of this population. Furthermore, because chronic pain is prevalent in HIV and associated with increased healthcare utilization, developing clinic-based pain management programs could be cost-effective.

BackgroundWorldwide, over 14% of individuals hospitalized for psychiatric reasons have readmissions to hospitals within 30 days after discharge. Predicting patients at risk and leveraging accelerated interventions can reduce the rates of early readmission, a negative clinical outcome (i.e., a treatment failure) that affects the quality of life of patient. To implement individualized interventions, it is necessary to predict those individuals at highest risk for 30-day readmission. In this study, our aim was to conduct a data-driven investigation to find the pharmacological factors influencing 30-day all-cause, intra- and interdepartmental readmissions after an index psychiatric admission, using the compendium of prescription data (prescriptome) from electronic medical records (EMR).MethodsThe data scientists in the project received a deidentified database from the Mount Sinai Data Warehouse, which was used to perform all analyses. Data was stored in a secured MySQL database, normalized and indexed using a unique hexadecimal identifier associated with the data for psychiatric illness visits. We used Bayesian logistic regression models to evaluate the association of prescription data with 30-day readmission risk. We constructed individual models and compiled results after adjusting for covariates, including drug exposure, age, and gender. We also performed digital comorbidity survey using EMR data combined with the estimation of shared genetic architecture using genomic annotations to disease phenotypes.ResultsUsing an automated, data-driven approach, we identified prescription medications, side effects (primary side effects), and drug-drug interaction-induced side effects (secondary side effects) associated with readmission risk in a cohort of 1275 patients using prescriptome analytics. In our study, we identified 28 drugs associated with risk for readmission among psychiatric patients. Based on prescription data, Pravastatin had the highest risk of readmission (OR = 13.10; 95% CI (2.82, 60.8)). We also identified enrichment of primary side effects (n = 4006) and secondary side effects (n = 36) induced by prescription drugs in the subset of readmitted patients (n = 89) compared to the non-readmitted subgroup (n = 1186). Digital comorbidity analyses and shared genetic analyses further reveals that cardiovascular disease and psychiatric conditions are comorbid and share functional gene modules (cardiomyopathy and anxiety disorder: shared genes (n = 37; P = 1.06815E-06)).ConclusionsLarge scale prescriptome data is now available from EMRs and accessible for analytics that could improve healthcare outcomes. Such analyses could also drive hypothesis and data-driven research. In this study, we explored the utility of prescriptome data to identify factors driving readmission in a psychiatric cohort. Converging digital health data from EMRs and systems biology investigations reveal a subset of patient populations that have significant comorbidities with cardiovascular diseases are more likely to be readmitted. Further, the...

No abstract

Background: Indications for inferior vena cava filter (IVCF) placement are controversial. This study assesses the proportion of different indications for IVCF placement and the associated 30-day event rates and predictors for all-cause mortality, deep vein thrombosis (DVT), pulmonary embolism, and bleeding after IVCF placement. Method: In this 5-year retrospective cohort observational study in a quaternary care center, consecutive patients with IVCF placement were identified through cross-matching of 3 database sets and classified into 3 indication groups defined as “standard” in patients with venous thromboembolism (VTE) and contraindication to anticoagulants, “extended” in patients with VTE but no contraindication to anticoagulants, and “prophylactic” in patients without VTE. Results: We identified 1248 IVCF placements, that is, 238 (19.1%) IVCF placements for standard indications, 583 (46.7%) IVCF placements for extended indications, and 427 (34.2%) IVCF placements for prophylactic indications. Deep vein thrombosis rates [95% confidence interval] were higher in the extended (8.06% [5.98-10.58]) and prophylactic (7.73% [5.38-10.68]) groups than in the standard group (3.36% [1.46-6.52]). Mortality rates were higher in the standard group (12.18% [8.31-17.03]) than in the extended group (7.55% [5.54-9.99]) and the prophylactic (5.85% [3.82-8.52]) group. Bleeding rates were higher in the standard group (4.62% [2.33-8.12]) than in the prophylactic group (2.11% [0.97-3.96]). Best predictors for VTE were acute medical conditions; best predictors for mortality were age, acute medical conditions, cancer, and Medicare health insurance. Conclusions: Prophylactic and extended indications account for the majority of IVCF placements. The standard indication is associated with the lowest VTE rate that may be explained by the competing risk of mortality higher in this group and related to the underlying medical conditions and bleeding risk. In the prophylactic group (no VTE at baseline), the exceedingly high DVT rate may be related to the IVCF placement.