Predicting inpatient mortality in patients with inflammatory bowel disease: A machine learning approach.

BACKGROUND AND AIM: Data are lacking on predicting inpatient mortality (IM) in patients admitted for inflammatory bowel disease (IBD). IM is a critical outcome; however, difficulty in its prediction exists due to infrequent occurrence. We assessed IM predictors and developed a predictive model for IM using machine-learning (ML). METHODS: Using the National Inpatient Sample (NIS) database (2005-2017), we extracted adults admitted for IBD. After ML-guided predictor selection, we trained and internally validated multiple algorithms, targeting minimum sensitivity and positive likelihood ratio (+LR) ≥ 80% and ≥ 3, respectively. Diagnostic odds ratio (DOR) compared algorithm performance. The best performing algorithm was additionally trained and validated for an IBD-related surgery sub-cohort. External validation was done using NIS 2018. RESULTS: In 398 426 adult IBD admissions, IM was 0.32% overall, and 0.87% among the surgical cohort (n = 40 784). Increasing age, ulcerative colitis, IBD-related surgery, pneumonia, chronic lung disease, acute kidney injury, malnutrition, frailty, heart failure, blood transfusion, sepsis/septic shock and thromboembolism were associated with increased IM. The QLattice algorithm, provided the highest performance model (+LR: 3.2, 95% CI 3.0-3.3; area-under-curve [AUC]:0.87, 85% sensitivity, 73% specificity), distinguishing IM patients by 15.6-fold when comparing high to low-risk patients. The surgical cohort model (+LR: 8.5, AUC: 0.94, 85% sensitivity, 90% specificity), distinguished IM patients by 49-fold. Both models performed excellently in external validation. An online calculator (https://clinicalc.ai/im-ibd/) was developed allowing bedside model predictions. CONCLUSIONS: An online prediction-model calculator captured > 80% IM cases during IBD-related admissions, with high discriminatory effectiveness. This allows for risk stratification and provides a basis for assessing interventions to reduce mortality in high-risk patients.

Health care utilization in geriatric patients admitted with alcohol withdrawal from 2005 to 2014.

BACKGROUND: Alcohol-related and alcohol withdrawal (AW) hospitalizations are routinely underestimated in the geriatric population and can have a significant impact on healthcare resource utilization. OBJECTIVES: To examine various patient-characteristics, hospitalization-outcomes, and prevalence of AW related-hospitalizations. METHODS: In this retrospective study, we examined the objectives mentioned above over a 10-year period (2005 to 2014) using the Nationwide Inpatient Sample (NIS) in adults aged 65 years or older. National estimates of trends for AW prevalence and matched-regression analyses were conducted. RESULTS: Increased prevalence of hospitalizations for AW was observed (148-cases-per-100,000-discharges in 2005 to 283-cases-per-100,000-discharges in 2014). Of the overall nationwide hospital admissions in patients aged 65 and older (128,111,787), 0.21% (264,786) with documented AW were identified. Of these, those of age 65-74 years accounted for 72.7% of admissions with the highest prevalence amongst males (males accounted for 74%, women 26%) and individuals of Caucasian ethnicity (79.9%).On comparing AW to Non-AW related-hospitalizations, patients admitted with AW had a higher median length of stay (five vs. four days), more significant functional decline with only 44.2% discharges being discharged home (vs. 47.2%) and 34.4% AW related discharges requiring discharge to skilled nursing facilities (vs. 28.5%). Higher hospitalization costs totaling $4,000 more on bivariate analysis were observed for the AW group. CONCLUSIONS: The prevalence of admissions with AW has increased in the inpatient geriatric population, contributing to increased length of stay, higher hospitalization costs, and greater functional decline. Recognition of these findings and the development of programs supporting older adults with alcohol use disorder may improve patient outcomes.

Medical marijuana knowledge and attitudes amongst internal medicine residents.

BACKGROUND: Mounting evidence suggests the safety and efficacy of medical marijuana (MM) in treating chronic ailments, including chronic pain, epilepsy, and anorexia. Despite incremental use of medical and recreational cannabinoids, current limited evidence shows generalized unpreparedness of medical providers to discuss or recommend these substances to their patients. Herein, the present study aims to examine internal medicine residents' knowledge of marijuana and their attitude towards its medical use. METHODS: This is a descriptive cross-sectional study. A survey with 12 standardized queries was created and distributed among the internal medicine residents from Mount Sinai Morningside-West (MSMW) program from July 2020 to December 2020. Participants included preliminary and categorical residents from post-graduate years one to three. The survey consisted of self-assessment of residents' knowledge on the indication, contraindication, adverse effects of MM. RESULTS: Eighty-six (59%) out of 145 residents completed the questionnaire. Despite most trainees (70%) having considered certifying the use of MM for their patients, over 90% reported none to little knowledge on its use. Approximately 80% of the surveyed residents expressed willingness to receive an appropriate educational curriculum. CONCLUSION: To the best of our knowledge, this is the first study that indicated a critical lack of medical marijuana-related knowledge in surveyed internal medicine residents. In a population with growing cannabis consumption, physician training on the indication, toxicity, and drug interaction of cannabinoids is warranted.