Comparison of static and rolling logistic regression models on predicting invasive mechanical ventilation or death from COVID-19-A retrospective, multicentre study.

INTRODUCTION: COVID-19 virus has undergone mutations, and the introduction of vaccines and effective treatments have changed its clinical severity. We hypothesized that models that evolve may better predict invasive mechanical ventilation or death than do static models. METHODS: This retrospective study of adult patients with COVID-19 from six Michigan hospitals analysed 20 demographic, comorbid, vital sign and laboratory factors, one derived factor and nine factors representing changes in vital signs or laboratory values with time for their ability to predict death or invasive mechanical ventilation within the next 4, 8 or 24 h. Static logistic regression was constructed on the initial 300 patients and tested on the remaining 6741 patients. Rolling logistic regression was similarly constructed on the initial 300 patients, but then new patients were added, and older patients removed. Each new construction model was subsequently tested on the next patient. Static and rolling models were compared with receiver operator characteristic and precision-recall curves. RESULTS: Of the 7041 patients, 534 (7.6%) required invasive mechanical ventilation or died within 14 days of arrival. Rolling models improved discrimination (0.865 ± 0.010, 0.856 ± 0.007 and 0.843 ± 0.005 for the 4, 8 and 24-h models, respectively; all p < 0.001 compared with the static logistic regressions with 0.827 ± 0.011, 0.794 ± 0.012 and 0.735 ± 0.012, respectively). Similarly, the areas under the precision-recall curves improved from 0.006, 0.010 and 0.021 with the static models to 0.030, 0.045 and 0.076 for the 4-, 8- and 24-h rolling models, respectively, all p < 0.001. CONCLUSION: Rolling models with contemporaneous data maintained better metrics of performance than static models, which used older data.

Frequency and Analysis of Unplanned Extubation in Coronavirus Disease 2019 Patients.

OBJECTIVES: To determine if patients with coronavirus disease 2019 had a greater number of unplanned extubations resulting in reintubations than in patients without coronavirus disease 2019. DESIGN: Retrospective cohort study comparing the frequency of unplanned extubations resulting in reintubations in a group of coronavirus disease 2019 patients to a historical (noncoronavirus disease 2019) control group. SETTING: This study was conducted at Henry Ford Hospital, an academic medical center in Detroit, MI. The historical noncoronavirus disease 2019 patients were treated in the 68 bed medical ICU. The coronavirus disease 2019 patients were treated in the coronavirus disease ICU, which included the 68 medical ICU beds, 18 neuro-ICU beds, 32 surgical ICU beds, and 40 cardiovascular ICU beds, as the medical ICU was expanded to these units at the peak of the pandemic in Detroit, MI. PATIENTS: The coronavirus disease 2019 cohort included patients diagnosed with coronavirus disease 2019 who were intubated for respiratory failure from March 12, 2020, to April 13, 2020. The historic control (noncoronavirus disease 2019) group consisted of patients who were admitted to the medical ICU in the year spanning from November 1, 2018 to October 31, 2019, with a need for mechanical ventilation that was not related to surgery or a neurologic reason. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: To identify how many patients in each cohort had unplanned extubations, an electronic medical records query for patients with two intubations within 30 days was performed, in addition to a review of our institutional quality and safety database of reported self-extubations. Medical charts were manually reviewed by board-certified anesthesiologists to confirm each event was an unplanned extubation followed by a reintubation within 24 hours. There was a significantly greater incidence of unplanned extubations resulting in reintubation events in the coronavirus disease 2019 cohort than in the noncoronavirus disease 2019 cohort (coronavirus disease 2019 cohort: 167 total admissions with 22 events-13.2%; noncoronavirus disease 2019 cohort: 326 total admissions with 14 events-4.3%; p < 0.001). When the rate of unplanned extubations was expressed per 100 intubated days, there was not a significant difference between the groups (0.88 and 0.57, respectively; p = 0.269). CONCLUSIONS: Coronavirus disease 2019 patients have a higher incidence of unplanned extubation that requires reintubation than noncoronavirus disease 2019 patients. Further study is necessary to evaluate the variables that contribute to this higher incidence and clinical strategies that can reduce it.