IMPORTANCE Readmission penalties have catalyzed efforts to improve care transitions, but few programs have incorporated viewpoints of patients and health care professionals to determine readmission preventability or to prioritize opportunities for care improvement. OBJECTIVES To determine preventability of readmissions and to use these estimates to prioritize areas for improvement. DESIGN, SETTING, AND PARTICIPANTS An observational study was conducted of 1000 general medicine patients readmitted within 30 days of discharge to 12 US academic medical centers between April 1, 2012, and March 31, 2013. We surveyed patients and physicians, reviewed documentation, and performed 2-physician case review to determine preventability of and factors contributing to readmission. We used bivariable statistics to compare preventable and nonpreventable readmissions, multivariable models to identify factors associated with potential preventability, and baseline risk factor prevalence and adjusted odds ratios (aORs) to determine the proportion of readmissions affected by individual risk factors. MAIN OUTCOME AND MEASURE Likelihood that a readmission could have been prevented. RESULTS The study cohort comprised 1000 patients (median age was 55 years). Of these, 269 (26.9%) were considered potentially preventable. In multivariable models, factors most strongly associated with potential preventability included emergency department decision making regarding the readmission (aOR, 9.13; 95% CI, 5.23–15.95), failure to relay important information to outpatient health care professionals (aOR, 4.19; 95% CI, 2.17–8.09), discharge of patients too soon (aOR, 3.88; 95% CI, 2.44–6.17), and lack of discussions about care goals among patients with serious illnesses (aOR, 3.84; 95% CI, 1.39–10.64). The most common factors associated with potentially preventable readmissions included emergency department decision making (affecting 9.0%; 95% CI, 7.1%−10.3%), inability to keep appointments after discharge (affecting 8.3%; 95% CI, 4.1%−12.0%), premature discharge from the hospital (affecting 8.7%; 95% CI, 5.8%–11.3%), and patient lack of awareness of whom to contact after discharge (affecting 6.2%; 95% CI, 3.5%–8.7%). CONCLUSIONS AND RELEVANCE Approximately one-quarter of readmissions are potentially preventable when assessed using multiple perspectives. High-priority areas for improvement efforts include improved communication among health care teams and between health care professionals and patients, greater attention to patients’ readiness for discharge, enhanced disease monitoring, and better support for patient self-management.

ObjectivesWe validate a machine learning-based sepsis-prediction algorithm (InSight) for the detection and prediction of three sepsis-related gold standards, using only six vital signs. We evaluate robustness to missing data, customisation to site-specific data using transfer learning and generalisability to new settings.DesignA machine-learning algorithm with gradient tree boosting. Features for prediction were created from combinations of six vital sign measurements and their changes over time.SettingA mixed-ward retrospective dataset from the University of California, San Francisco (UCSF) Medical Center (San Francisco, California, USA) as the primary source, an intensive care unit dataset from the Beth Israel Deaconess Medical Center (Boston, Massachusetts, USA) as a transfer-learning source and four additional institutions’ datasets to evaluate generalisability.Participants684 443 total encounters, with 90 353 encounters from June 2011 to March 2016 at UCSF.InterventionsNone.Primary and secondary outcome measuresArea under the receiver operating characteristic (AUROC) curve for detection and prediction of sepsis, severe sepsis and septic shock.ResultsFor detection of sepsis and severe sepsis, InSight achieves an AUROC curve of 0.92 (95% CI 0.90 to 0.93) and 0.87 (95% CI 0.86 to 0.88), respectively. Four hours before onset, InSight predicts septic shock with an AUROC of 0.96 (95% CI 0.94 to 0.98) and severe sepsis with an AUROC of 0.85 (95% CI 0.79 to 0.91).ConclusionsInSight outperforms existing sepsis scoring systems in identifying and predicting sepsis, severe sepsis and septic shock. This is the first sepsis screening system to exceed an AUROC of 0.90 using only vital sign inputs. InSight is robust to missing data, can be customised to novel hospital data using a small fraction of site data and retains strong discrimination across all institutions.

No abstract

KeywordsMedical order entry systems, clinical decision support systems, medication errors/prevention and control, drug interactions, physician's practice patterns SummaryBackground: Interruptive drug interaction alerts may reduce adverse drug events and are required for Stage I Meaningful Use attestation. For the last decade override rates have been very high. Despite their widespread use in commercial EHR systems, previously described interventions to improve alert frequency and acceptance have not been well studied. Objectives: (1) To measure override rates of inpatient medication alerts within a commercial clinical decision support system, and assess the impact of local customization efforts. (2) To compare override rates between drug-drug interaction and drug-allergy interaction alerts, between attending and resident physicians, and between public and academic hospitals. (3) To measure the correlation between physicians' individual alert quantities and override rates as an indicator of potential alert fatigue. Methods: We retrospectively analyzed physician responses to drug-drug and drug-allergy interaction alerts, as generated by a common decision support product in a large teaching hospital system. Results: (1) Over four days, 461 different physicians entered 18,354 medication orders, resulting in 2,455 visible alerts; 2,280 alerts (93%) were overridden. (2) The drug-drug alert override rate was 95.1%, statistically higher than the rate for drug-allergy alerts (90.9%) (p < 0.001). There was no significant difference in override rates between attendings and residents, or between hospitals. (3) Physicians saw a mean of 1.3 alerts per day, and the number of alerts per physician was not significantly correlated with override rate (R2 = 0.03, p = 0.41). Conclusions: Despite intensive efforts to improve a commercial drug interaction alert system and to reduce alerting, override rates remain as high as reported over a decade ago. Alert fatigue does not seem to contribute. The results suggest the need to fundamentally question the premises of drug interaction alert systems.