Romero‐Brufau, Santiago

Abstract Objective Artificial intelligence (AI) models may propagate harmful biases in performance and hence negatively affect the underserved. We aimed to assess the degree to which data quality of electronic health records (EHRs) affected by inequities related to low socioeconomic status (SES), results in differential performance of AI models across SES. Materials and Methods This study utilized existing machine learning models for predicting asthma exacerbation in children with asthma. We compared balanced error rate (BER) against different SES levels measured by HOUsing-based SocioEconomic Status measure (HOUSES) index. As a possible mechanism for differential performance, we also compared incompleteness of EHR information relevant to asthma care by SES. Results Asthmatic children with lower SES had larger BER than those with higher SES (eg, ratio = 1.35 for HOUSES Q1 vs Q2–Q4) and had a higher proportion of missing information relevant to asthma care (eg, 41% vs 24% for missing asthma severity and 12% vs 9.8% for undiagnosed asthma despite meeting asthma criteria). Discussion Our study suggests that lower SES is associated with worse predictive model performance. It also highlights the potential role of incomplete EHR data in this differential performance and suggests a way to mitigate this bias. Conclusion The HOUSES index allows AI researchers to assess bias in predictive model performance by SES. Although our case study was based on a small sample size and a single-site study, the study results highlight a potential strategy for identifying bias by using an innovative SES measure.

Abstract Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop simple yet useful models for 12-hour census prediction and design a dashboard application to display this output to our hospital’s decision-makers. Specifically, we found that linear models with ElasticNet regularization performed well for this task with relative 95% error of +/− 3.4% and that this work could be completed in approximately 7 months.

Abstract Objective Electronic health record documentation by intensive care unit (ICU) clinicians may predict patient outcomes. However, it is unclear whether physician and nursing notes differ in their ability to predict short-term ICU prognosis. We aimed to investigate and compare the ability of physician and nursing notes, written in the first 48 hours of admission, to predict ICU length of stay and mortality using 3 analytical methods. Materials and Methods This was a retrospective cohort study with split sampling for model training and testing. We included patients ≥18 years of age admitted to the ICU at Beth Israel Deaconess Medical Center in Boston, Massachusetts, from 2008 to 2012. Physician or nursing notes generated within the first 48 hours of admission were used with standard machine learning methods to predict outcomes. Results For the primary outcome of composite score of ICU length of stay ≥7 days or in-hospital mortality, the gradient boosting model had better performance than the logistic regression and random forest models. Nursing and physician notes achieved area under the curves (AUCs) of 0.826 and 0.796, respectively, with even better predictive power when combined (AUC, 0.839). Discussion Models using only nursing notes more accurately predicted short-term prognosis than did models using only physician notes, but in combination, the models achieved the greatest accuracy in prediction. Conclusions Our findings demonstrate that statistical models derived from text analysis in the first 48 hours of ICU admission can predict patient outcomes. Physicians’ and nurses’ notes are both uniquely important in mortality prediction and combining these notes can produce a better predictive model.

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: Burnout syndrome is very prevalent among healthcare residents. Initiatives addressing workload conditions have had limited impact on burnout. The present study aims to explore the contribution of two emotion regulation strategies, namely emotion suppression and cognitive reevaluation, to residents’ burnout, while accounting for workload factors. Methods: Participants were 105 residents (68.6% women; mean age = 27.5, SD = 3.0). They completed measures of workload, burnout, and emotion regulation. The study was cross-sectional. Results: Emotional suppression was associated with higher burnout (depersonalization scale; β = 0.20, p < 0.05, CI 0.15–2.48) and cognitive revaluation was linked to lower burnout (higher personal accomplishment; β = 0.35, p < 0.01, CI 0.16–2.56), even after controlling for demographic and workload factors. We found interaction effects between workload variables (supervisor support and number of patient hours) and emotion regulation (p < 0.05). Conclusions: The relationship between workload, emotion regulation, and burnout seems to be complex. That is, similar work conditions might generate different levels of burnout depending on the resident’s emotional regulation strategies. This might partly explain why existing initiatives based on workload changes have had a modest impact on burnout. Results also support including emotion regulation training in prevention and treatment programs targeting burnout during residency.

Abstract Background Hospital readmissions are a key quality metric, which has been tied to reimbursement. One strategy to reduce readmissions is to direct resources to patients at the highest risk of readmission. This strategy necessitates a robust predictive model coupled with effective, patient-centered interventions. Objective The aim of this study was to reduce unplanned hospital readmissions through the use of artificial intelligence-based clinical decision support. Methods A commercially vended artificial intelligence tool was implemented at a regional hospital in La Crosse, Wisconsin between November 2018 and April 2019. The tool assessed all patients admitted to general care units for risk of readmission and generated recommendations for interventions intended to decrease readmission risk. Similar hospitals were used as controls. Change in readmission rate was assessed by comparing the 6-month intervention period to the same months of the previous calendar year in exposure and control hospitals. Results Among 2,460 hospitalizations assessed using the tool, 611 were designated by the tool as high risk. Sensitivity and specificity for risk assignment were 65% and 89%, respectively. Over 6 months following implementation, readmission rates decreased from 11.4% during the comparison period to 8.1% (p < 0.001). After accounting for the 0.5% decrease in readmission rates (from 9.3 to 8.8%) at control hospitals, the relative reduction in readmission rate was 25% (p < 0.001). Among patients designated as high risk, the number needed to treat to avoid one readmission was 11. Conclusion We observed a decrease in hospital readmission after implementing artificial intelligence-based clinical decision support. Our experience suggests that use of artificial intelligence to identify patients at the highest risk for readmission can reduce quality gaps when coupled with patient-centered interventions.

The need for multiple transducer positions, especially from right parasternal windows, is consistently mentioned in the recommendations for the accurate measurement of peak velocities across a stenotic aortic valve, but yet poorly adopted. We performed a subanalysis of the largest prospective series on the right parasternal acoustic windows in patients with aortic stenosis (330 consecutive) to calculate the degree of misalignment and estimate the potential outcome implication of this often-forgotten approach. The right parasternal view was highly feasible with an average estimated misalignment from the apical view of 14 ± 16 degree; in 10 cases, an estimated misalignment >40 degree. Right parasternal assessment (vs. apical alone) provided a significant reclassification from moderate to severe or even very-severe aortic valve stenosis. Considering a wellestablished survival benefit provided by either percutaneous or surgical valve replacement in patients with severe aortic stenosis the reclassification would result in approximately 1 life-year saved for every 30–35 patients in whom parasternal view were effectively utilized.

Objective.: The Dizziness Handicap Inventory (DHI) is a 25-item self-report questionnaire developed to measure the disabling and handicapping impact of dizziness. The present investigation was conducted in an effort to re-assess the factor structure of the DHI. Study Design.: Retrospective study. Setting.: Tertiary care center. Patients.: Subjects were 1,991 patients who were evaluated in the Mayo Clinic-Rochester Vestibular and Balance Laboratory. Main Outcome Measures.: Exploratory factor analysis: an exploratory bifactor analysis (EFA) with bifactor rotation was used to analyze a random sample of 999 patients. Analyses were used to determine the dominance of the general factor (i.e., total score) relative to the group factor (i.e., subscales). Confirmatory factor analysis: a confirmatory bifactor graded response model was fit with appropriate item-to-group relationships that was discovered by our exploratory analyses. To validate the bifactor model that was identified with the exploratory analyses, a bifactor model with three grouping factors (i.e., Physical manifestations, Catastrophic impact of dizziness, and the Emotional impact of dizziness) were fit to a different random sample of 992 patients using the new item-to-group factor specifications. Results.: In the confirmatory analyses, all items had a positive factor loading on the general factor. There were 14 items that loaded on the general factor only. The rest of the items (n = 11) loaded on both the general factor and one of three group factors. Conclusions.: Conclusions of the study revealed several findings: 1) reporting the result as a total score (i.e., a single general factor) is warranted, and, 2) there is statistical support for the existence of three subscales representing: the Physical manifestations, Catastrophic impact, and Emotional impact of dizziness and vertigo.

Abstract Introduction Identification of hospitalized patients with suddenly unfavorable clinical course remains challenging. Models using objective data elements from the electronic health record may miss important sources of information available to nurses. Methods We recorded nurses’ perception of patient potential for deterioration in 2 medical and 2 surgical adult hospital units using a 5-point score at the start of the shift (the Worry Factor [WF]), and any time a change or an increase was noted by the nurse. Cases were evaluated by three reviewers. Intensive care unit (ICU) transfers were also tracked. Results 31 159 patient-shifts were recorded for 3185 unique patients during 3551 hospitalizations, with 169 total outcome events. Out of 492 potential deterioration events identified, 380 (77%) were confirmed by reviewers as true deterioration events. Likelihood ratios for ICU transfer were 17.8 (15.2–20.9) in the 24 hours following a WF &gt; 2, and 40.4 (27.1–60.1) following a WF &gt; 3. Accuracy rates were significantly higher in nurses with over a year of experience (68% vs 79%, P = 0.04). The area under the receiver operator characteristic curve (AUROC) was 0.92 for the prediction of ICU transfer within 24 hours. Discussion This is a higher accuracy than most published early warning scores. Conclusion Nurses’ pattern recognition and sense of worry can provide important information for the detection of acute physiological deterioration and should be included in the electronic medical record.