Developing and Validating a Prediction Model For Death or Critical Illness in Hospitalized Adults, an Opportunity for Human-Computer Collaboration.

Hospital early warning systems that use machine learning (ML) to predict clinical deterioration are increasingly being used to aid clinical decision-making. However, it is not known how ML predictions complement physician and nurse judgment. Our objective was to train and validate a ML model to predict patient deterioration and compare model predictions with real-world physician and nurse predictions. DESIGN: Retrospective and prospective cohort study. SETTING: Academic tertiary care hospital. PATIENTS: Adult general internal medicine hospitalizations. MEASUREMENTS AND MAIN RESULTS: We developed and validated a neural network model to predict in-hospital death and ICU admission in 23,528 hospitalizations between April 2011 and April 2019. We then compared model predictions with 3,374 prospectively collected predictions from nurses, residents, and attending physicians about their own patients in 960 hospitalizations between April 30, and August 28, 2019. ML model predictions achieved clinician-level accuracy for predicting ICU admission or death (ML median F1 score 0.32 [interquartile range (IQR) 0.30-0.34], AUC 0.77 [IQ 0.76-0.78]; clinicians median F1-score 0.33 [IQR 0.30-0.35], AUC 0.64 [IQR 0.63-0.66]). ML predictions were more accurate than clinicians for ICU admission. Of all ICU admissions and deaths, 36% occurred in hospitalizations where the model and clinicians disagreed. Combining human and model predictions detected 49% of clinical deterioration events, improving sensitivity by 16% compared with clinicians alone and 24% compared with the model alone while maintaining a positive predictive value of 33%, thus keeping false alarms at a clinically acceptable level. CONCLUSIONS: ML models can complement clinician judgment to predict clinical deterioration in hospital. These findings demonstrate important opportunities for human-computer collaboration to improve prognostication and personalized medicine in hospital.

Nurses' death anxiety, comfort level during communication with patients and families regarding death, and exposure to communication education: a quantitative study.

The first purpose of this study was to determine if a nurse's death anxiety is related to the comfort level of the nurse during communication with patients and families regarding death. The second purpose was to explore whether nurses reported having been exposed to communication education regarding dealing with difficult subjects such as death and whether this exposure was related to comfort level of the nurse during communication with patients and families regarding death. Findings of this study benefit nurse educators and nurses involved in staff development because the results indicate that comfort level of the nurse during communication with patients and families is adversely affected by an increase in the nurse's own death anxiety, and positively affected by exposure to communication education. Thus, these results indicate a need for education in this area. The next step is to identify the most effective type, objectives, and content of this type of education.

What do nurses know about teaching patients?

A quasiexperimental study was conducted to ascertain what nurses know about teaching patients and whether a planned education offering could increase the knowledge nurses have about the teaching process in patient education. A convenience sample of 44 nurses participated in a pretest/posttest and 1- to 2-month follow-up test on the teaching process. Knowledge deficit was present and learning evident. Nurse educators should instruct staff on the teaching process, giving nurses the necessary skills to deliver effective patient education.