Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study.

Early detection of diseases such as COVID-19 could be a critical tool in reducing disease transmission by helping individuals recognize when they should self-isolate, seek testing, and obtain early medical intervention. Consumer wearable devices that continuously measure physiological metrics hold promise as tools for early illness detection. We gathered daily questionnaire data and physiological data using a consumer wearable (Oura Ring) from 63,153 participants, of whom 704 self-reported possible COVID-19 disease. We selected 73 of these 704 participants with reliable confirmation of COVID-19 by PCR testing and high-quality physiological data for algorithm training to identify onset of COVID-19 using machine learning classification. The algorithm identified COVID-19 an average of 2.75 days before participants sought diagnostic testing with a sensitivity of 82% and specificity of 63%. The receiving operating characteristic (ROC) area under the curve (AUC) was 0.819 (95% CI [0.809, 0.830]). Including continuous temperature yielded an AUC 4.9% higher than without this feature. For further validation, we obtained SARS CoV-2 antibody in a subset of participants and identified 10 additional participants who self-reported COVID-19 disease with antibody confirmation. The algorithm had an overall ROC AUC of 0.819 (95% CI [0.809, 0.830]), with a sensitivity of 90% and specificity of 80% in these additional participants. Finally, we observed substantial variation in accuracy based on age and biological sex. Findings highlight the importance of including temperature assessment, using continuous physiological features for alignment, and including diverse populations in algorithm development to optimize accuracy in COVID-19 detection from wearables.

Can hospital adult code-teams and individual members perform high-quality CPR? A multicenter simulation-based study incorporating an educational intervention with CPR feedback.

AIMS: A multicenter simulation-based research study to assess the ability of interprofessional code-teams and individual members to perform high-quality CPR (HQ-CPR) at baseline and following an educational intervention with a CPR feedback device. METHODS: Five centers recruited ten interprofessional teams of AHA-certified adult code-team members with a goal of 200 participants. Baseline testing of chest compression (CC) quality was measured for all individuals. Teams participated in a baseline simulated cardiac arrest (SCA) where CC quality, chest compression fraction (CCF), and peri-shock pauses were recorded. Teams participated in a standardized HQ-CPR and abbreviated TeamSTEPPS® didactic, then engaged in deliberate practice with a CPR feedback device. Individuals were assessed to determine if they could achieve ≥80% combined rate and depth within 2020 AHA guidelines. Teams completed a second SCA and CPR metrics were recorded. Feedback was disabled for assessments except at one site where real-time CPR feedback was the institutional standard. Linear regression models were used to test for site effect and paired t-tests to evaluate significant score changes. Logistic univariate regression models were used to explore characteristics associated with the individual achieving competency. RESULTS: Data from 184 individuals and 45 teams were analyzed. Baseline HQ-CPR mean score across all sites was 18.5% for individuals and 13.8% for teams. Post-intervention HQ-CPR mean score was 59.8% for individuals and 37.0% for teams. There was a statistically significant improvement in HQ-CPR mean scores of 41.3% (36.1, 46.5) for individuals and 23.2% (17.1, 29.3) for teams (p < 0.0001). CCF increased at 3 out of 5 sites and there was a mean 5-s reduction in peri-shock pauses (p < 0.0001). Characteristics with a statistically significant association were height (p = 0.01) and number of times performed CPR (p = 0.01). CONCLUSION: Code-teams and individuals struggle to perform HQ-CPR but show improvement after deliberate practice with feedback as part of an educational intervention. Only one site that incorporated real-time CPR feedback devices routinely achieved ≥80% HQ-CPR.

Characterizing the learning curve of the VBLaST-PT(©) (Virtual Basic Laparoscopic Skill Trainer).

BACKGROUND: Mastering laparoscopic surgical skills requires considerable time and effort. The Virtual Basic Laparoscopic Skill Trainer (VBLaST-PT(©)) is being developed as a computerized version of the peg transfer task of the Fundamentals of Laparoscopic Surgery (FLS) system using virtual reality technology. We assessed the learning curve of trainees on the VBLaST-PT(©) using the cumulative summation (CUSUM) method and compared them with those on the FLS to establish convergent validity for the VBLaST-PT(©). METHODS: Eighteen medical students from were assigned randomly to one of three groups: control, VBLaST-training, and FLS-training. The VBLaST and the FLS groups performed a total of 150 trials of the peg-transfer task over a 3-week period, 5 days a week. Their CUSUM scores were computed based on predefined performance criteria (junior, intermediate, and senior levels). RESULTS: Of the six subjects in the VBLaST-training group, five achieved at least the "junior" level, three achieved the "intermediate" level, and one achieved the "senior" level of performance criterion by the end of the 150 trials. In comparison, for the FLS group, three students achieved the "senior" criterion and all six students achieved the "intermediate" and "junior" criteria by the 150th trials. Both the VBLaST-PT(©) and the FLS systems showed significant skill improvement and retention, albeit with system specificity as measured by transfer of learning in the retention test: The VBLaST-trained group performed better on the VBLaST-PT(©) than on FLS (p = 0.003), whereas the FLS-trained group performed better on the FLS than on VBLaST-PT(©) (p = 0.002). CONCLUSIONS: We characterized the learning curve for a virtual peg transfer task on the VBLaST-PT(©) and compared it with the FLS using CUSUM analysis. Subjects in both training groups showed significant improvement in skill performance, but the transfer of training between systems was not significant.