Integration of feature vectors from raw laboratory, medication and procedure names improves the precision and recall of models to predict postoperative mortality and acute kidney injury.

Manuscripts that have successfully used machine learning (ML) to predict a variety of perioperative outcomes often use only a limited number of features selected by a clinician. We hypothesized that techniques leveraging a broad set of features for patient laboratory results, medications, and the surgical procedure name would improve performance as compared to a more limited set of features chosen by clinicians. Feature vectors for laboratory results included 702 features total derived from 39 laboratory tests, medications consisted of a binary flag for 126 commonly used medications, procedure name used the Word2Vec package for create a vector of length 100.

Acceptability and tolerability of a meal-based, rapid refeeding, behavioral weight restoration protocol for anorexia nervosa.

Objective: Safe, tolerable, effective approaches to weight restoration are needed for adults with anorexia nervosa (AN). We examined weight outcomes and patient satisfaction with an integrated, inpatient-partial hospitalization, meal-based behavioral program that rapidly weight restores a majority of patients.

Method: Consecutively discharged inpatients (N = 149) treated on weight gain protocol completed an anonymous questionnaire assessing treatment satisfaction at inpatient discharge.

Hospital course of underweight youth with ARFID treated with a meal-based behavioral protocol in an inpatient-partial hospitalization program for eating disorders.

Objective: Information on nutritional rehabilitation for underweight patients with avoidant/restrictive food intake disorder (ARFID) is scarce. This study characterized hospitalized youth with ARFID treated in an inpatient (IP)-partial hospitalization behavioral eating disorders (EDs) program employing an exclusively meal-based rapid refeeding protocol and compared weight restoration outcomes to those of patients with anorexia nervosa (AN).

Method: Data from retrospective chart review of consecutive underweight admissions (N = 275; age 11-26 years) with ARFID (n = 27) were compared to those with AN (n = 248) on clinical features, reason for discharge, and weight restoration variables.