Naessens, James

Abstract Objective We aimed to develop a model for accurate prediction of general care inpatient deterioration. Materials and Methods Training and internal validation datasets were built using 2-year data from a quaternary hospital in the Midwest. Model training used gradient boosting and feature engineering (clinically relevant interactions, time-series information) to predict general care inpatient deterioration (resuscitation call, intensive care unit transfer, or rapid response team call) in 24 hours. Data from a tertiary care hospital in the Southwest were used for external validation. C-statistic, sensitivity, positive predictive value, and alert rate were calculated for different cutoffs and compared with the National Early Warning Score. Sensitivity analysis evaluated prediction of intensive care unit transfer or resuscitation call. Results Training, internal validation, and external validation datasets included 24 500, 25 784 and 53 956 hospitalizations, respectively. The Mayo Clinic Early Warning Score (MC-EWS) demonstrated excellent discrimination in both the internal and external validation datasets (C-statistic = 0.913, 0.937, respectively), and results were consistent in the sensitivity analysis (C-statistic = 0.932 in external validation). At a sensitivity of 73%, MC-EWS would generate 0.7 alerts per day per 10 patients, 45% less than the National Early Warning Score. Discussion Low alert rates are important for implementation of an alert system. Other early warning scores developed for the general care ward have achieved lower discrimination overall compared with MC-EWS, likely because MC-EWS includes both nursing assessments and extensive feature engineering. Conclusions MC-EWS achieved superior prediction of general care inpatient deterioration using sophisticated feature engineering and a machine learning approach, reducing alert rate.

Background: Managing the safety climate in health care is a promising tool for improving employee and patient safety in the health care work environment. Gaps in the theoretical and conceptual underpinnings of safety climate, as well as the evidence base for its practical application in health care remain. The purpose of this study was to evaluate the number of work injuries occurring in health care work units and associated safety climate beliefs. Methods: A retrospective analysis was conducted utilizing organizational staff survey data collected by a large medical hospital in the Midwest in 2015. Employees ( n = 32,327) were invited to identify safety climate perceptions via survey. Injuries, days restricted, and days absent were identified through the Hospital’s Occupational Safety and Health Administration (OSHA) log. Zero inflated negative binomial regressions used injuries as dependent variables and safety climate perceptions as independent variables. Findings: In all, 23,599 employees completed the survey (73% response rate) across 1,805 employee work units which were defined as groupings of employees reporting to a single supervisor. We found that there was an association between fewer injuries and health care workers indicating that they share responsibility for compliance with safety rules and procedures (relative risk [RR] = 0.98, 95% confidence interval [CI] = [0.98, 0.99]). Conclusion/Application to Practice: This study supports the use of a safety climate measure to assess working units’ perceptions of employee safety. A continued focus on the health and safety of employees who interact directly with patients is warranted, as well as employees who do not provide direct patient care.

Background: This paper assesses obesity- and smoking-related incremental healthcare costs for the employees and dependents of a large U.S. employer. Objectives: Unlike previous studies, this study evaluates the distributional effects of obesity and smoking on healthcare cost distribution using a recently developed econometric framework: the unconditional quantile regression (UQR). Methods: Results were compared with the traditional conditional quantile regression (CQR), and the generalized linear modeling (GLM) framework that is commonly used for modeling healthcare cost. Results: The study found strong evidence of association of healthcare costs with obesity and smoking. More importantly, the study found that these effects are substantially higher in the upper quantiles of the healthcare cost distribution than in the lower quantiles. The insights on the heterogeneity of impacts of obesity and smoking on healthcare costs would not have been captured by traditional mean-based approaches. The study also found that UQR impact estimates were substantially different from CQR impact estimates in the upper quantiles of the cost distribution. Conclusions: These results suggest the potential role that smoking cessation and weight management programs can play in arresting the growth in healthcare costs. Specifically, given the finding that obesity and smoking have markedly higher impacts on high-cost patients, such programs appear to have significant cost saving potential if targeted toward high-cost patients.

PURPOSE: Quality payment programs aim to adjust payments on the basis of quality and cost; however, few quality metrics exist in radiation oncology. This study evaluates and predicts the top spenders (TS) after radiation therapy (RT). MATERIALS AND METHODS: Patient characteristics, cancer details, treatments, toxicity, and survival data were collected for patients treated with RT at Mayo Clinic from 2007 to 2016. Standardized costs were obtained and adjusted for inflation. TSs were identified as those with greater than 93rd percentile costs (≥ $120,812). Prediction models were developed to predict TSs using training and validation sets using information available at consultation, after RT, and at last follow-up. RESULTS: A total of 15,131 patients were included and 1,065 TSs identified. Mean cost overall was $55,290 (median, $39,996) for all patients. Prediction models 1, 2, and 3 had concordance statistics of 0.83 to 0.83, 0.85 to 0.85, and 0.87 to 0.88, respectively in training and validation, indicating excellent prediction of TSs. Factors that were most predictive of TSs included stage N/A and stage 4 ( v stage 0; odds ratio [OR], 18.23 and 8.44, respectively; P < .001); hematologic, upper GI, skin and lung cancers ( v breast; OR, 11.45, 7.69, 3.81, and 2.43, respectively; P < .01); immunotherapy, surgery, and chemotherapy use (OR, 4.36, 2.51, and 1.61, respectively; P < .01); hospitalizations within 90 days of RT (OR, 2.26; P < .01); or death during the episode (OR, 1.56; P < .01). CONCLUSION: This is the first study of its kind to predict with high accuracy the highest spenders in radiation oncology. These patients may benefit from pre-emptive management to mitigate costs, or may require exclusion or adjustment from quality payment programs.

Abstract Background: Laparoscopy and more recently robotics are increasingly used for colorectal cancer surgery in the United States. We examined the current trends of minimally invasive surgical resections for colorectal cancer in Florida. Methods: The Florida Inpatient Discharge Dataset was used to examine the clinical data of patients who underwent elective surgery for colorectal cancer during 2013–2015. Multivariate analyses were performed to compare patient characteristics associated with the use of open and minimally invasive surgeries. Results: A total of 10,513 patients were analyzed; 5451 (52%) had open surgery, 4403 (42%) laparoscopy, and 659 (6%) robotic surgery. The rates of minimally invasive surgery (MIS) increased from 46.95% in 2013 to 48.72% in 2015. Among minimally invasive surgical procedures, the use of robotics increased from 9.82% in 2013 to 15.48% in 2015. Metastatic cancer (odds ratio [OR] 0.61, confidence interval [CI] 0.55–0.67), Elixhauser score of 3–5 (OR 0.85, CI 0.76–0.95) or more than 5 (OR 0.78, CI 0.63–0.97), Medicaid insurance (OR 0.73, CI 0.6–0.89), Black race (OR 0.88, CI 0.77–0.99), and rural residence (OR 0.83, CI 0.69–0.99) were associated with lower odds of MIS than open surgery. Conclusions: This study demonstrates that the overall rates of MIS for colorectal cancer in Florida increased from 2013 to 2015. Socially deprived and very sick patient populations with colorectal cancer are less likely to undergo MIS.

AbstractRational, aims, and objectivesUnderstanding of barriers and successes associated with the implementation of electronic patient self‐reported measures (ePSRMs) within clinical settings are limited and have not been pursued utilizing implementation science frameworks. This qualitative study is designed to assess staff perceptions of an ePSRM implementation.MethodsThe study took place in an academic hospital's Consultation Liaison Psychiatry practice. Qualitative interviews were conducted with the staff and clinicians from the practice. Participants were directly involved with the implementation and use of the ePSRM system within the Psychiatry practice. Interviews were structured around the Reach, Effectiveness, Adoption, Implementation, Maintenance (RE‐AIM) framework.ResultsParticipants reported increased patient engagement as well as efficiency and time savings. The intervention was perceived to be more challenging for older patients. Facilitators include communicating the ePSRM to patients prior to the care visit, having enough trained staff or super‐users who can assist with technical problems, and having a shorter questionnaire.ConclusionsOverall, assessment of the ePSRM implementation was positive. Staff and clinicians indicated benefits in time, effectiveness, and improvements in patient treatment. Results indicate that defining how the system would fit within the clinical workflow was key, as was a flexible and user‐friendly technology platform. The ePSRM implementation was dependent upon clinical involvement and interest in adoption, while barriers were associated with technical challenges as well as some patient difficulties, such as cognitive impairment. The use of the RE‐AIM framework is valuable as it allows for systematic assessment of the implementation and identifies areas in that implementation has succeeded or is lacking.