Multi-horizon predictive models for guiding extracorporeal resource allocation in critically ill COVID-19 patients.

OBJECTIVE: Extracorporeal membrane oxygenation (ECMO) resource allocation tools are currently lacking. We developed machine learning (ML) models for predicting COVID-19 patients at risk of receiving ECMO to guide patient triage and resource allocation. MATERIAL AND METHODS: We included COVID-19 patients admitted to intensive care units for >24 h from March 2020 to October 2021, divided into training and testing development and testing-only holdout cohorts. We developed ECMO deployment timely prediction model ForecastECMO using Gradient Boosting Tree (GBT), with pre-ECMO prediction horizons from 0 to 48 h, compared to PaO2/FiO2 ratio, Sequential Organ Failure Assessment score, PREdiction of Survival on ECMO Therapy score, logistic regression, and 30 pre-selected clinical variables GBT Clinical GBT models, with area under the receiver operator curve (AUROC) and precision recall curve (AUPRC) metrics. RESULTS: ECMO prevalence was 2.89% and 1.73% in development and holdout cohorts. ForecastECMO had the best performance in both cohorts. At the 18-h prediction horizon, a potentially clinically actionable pre-ECMO window, ForecastECMO, had the highest AUROC (0.94 and 0.95) and AUPRC (0.54 and 0.37) in development and holdout cohorts in identifying ECMO patients without data 18 h prior to ECMO. DISCUSSION AND CONCLUSIONS: We developed a multi-horizon model, ForecastECMO, with high performance in identifying patients receiving ECMO at various prediction horizons. This model has potential to be used as early alert tool to guide ECMO resource allocation for COVID-19 patients. Future prospective multicenter validation would provide evidence for generalizability and real-world application of such models to improve patient outcomes.

Natural trajectory of recovery of COVID-19 associated olfactory loss.

IMPORTANCE: Prevalence of post-viral olfactory loss has increased dramatically due to the frequency and severity of olfactory dysfunction associated with infection by the SARS-CoV-2 virus. OBJECTIVE: To determine the trajectory of COVID-19 olfactory loss over a six-month period. A key secondary objective is to assess predictive factors associated with the recovery of olfaction. DESIGN: Longitudinal repeated-measures study that enrolled from May 5, 2020 to February 2, 2021, with the last date of data collection on June 15, 2021. SETTING: Barnes-Jewish HealthCare/Washington University School of Medicine facilities (Saint Louis, Missouri, USA). PARTICIPANTS: Individuals who tested positive for SARS-CoV-2 by real-time polymerase chain reaction on nasopharyngeal swab and indicated olfactory loss on COVID-19 screening questionnaire. Individuals were excluded if they had previously diagnosed history of olfactory loss, neurodegenerative disorders, <18 years of age, admitted to hospital service, unable to read, write, and understand English, or lacked computer or internet access. INTERVENTIONS/EXPOSURES: Watch and wait for spontaneous recovery. MAIN OUTCOME(S) AND MEASURE(S): Participants completed olfactory assessments every 30 days for six months. Each assessment consisted of the University of Pennsylvania Smell Identification Test (UPSIT), an objective "scratch-and-sniff" test, and Clinical Global Impressions (CGI), a subjective Likert rating scale. RESULTS: The mean age was 41 years old (SD = 16). 39 (80 %) were female and 42 (86 %) white. At baseline assessment of objective olfaction, 18 (36 %) participants had anosmia or severe hyposmia. Subjective, complete recovery at six months was 81 % (95 % CI 74 % to 88 %). Likelihood of recovery was associated with age <50 years (aHR = 8.1 (95 % CI 1.1 to 64.1)) and mild olfactory loss at baseline (UPSIT = 30-33 for males and 31-34 for females) (aHR 6.2 (95 % CI 1.2 to 33.0)). CONCLUSIONS AND RELEVANCE: The trajectory of olfactory recovery among adults with COVID-19 olfactory loss illustrated rapid recovery within 2-3 weeks of infection, and by six months 81 % had recovered based on self-report. Age <50 years old and mild severity of olfactory loss at baseline were associated with increased likelihood of recovery of olfaction. These findings can be used to inform shared decision-making with patients.

Post-acute sensory neurological sequelae in patients with severe acute respiratory syndrome coronavirus 2 infection: the COVID-PN observational cohort study.

ABSTRACT: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection can cause neurological sequelae after the resolution of symptomatic COVID-19 illness, but the occurrence of peripheral neuropathy symptoms and cranial nerve dysfunction is unknown. This study aimed to characterize the occurrence and severity of pain and peripheral neuropathy symptoms in patients with SARS-CoV-2 infection. An observational cohort study included adults tested for a SARS-CoV-2 infection at an academic medical center (assigned as CV+ or control, based on test results). Thirty to 90 days after the index SARS-CoV-2 test, patients completed a web-based questionnaire assessing pain, peripheral neuropathy-related sensory symptoms, and symptoms in the distribution of cranial nerves (current symptoms, symptoms at testing and 2 weeks thereafter). Univariate analyses compared the outcomes between the groups. Multivariable analysis was used to determine the odds for neuropathy symptoms after adjusting for key baseline variables. A total of 1556 participants were included: 542 CV+ patients and 1014 control subjects. CV+ patients reported a higher occurrence of peripheral neuropathy symptoms in the extremities anytime within 90 days postinfection (28.8% vs 12.9%, odds ratio [OR] [95% confidence interval] = 2.72 [2.10-3.54]), as well as such symptoms persisting up to 90 days after infection (6.1% vs 1.9%, OR = 3.39 [1.91-6.03]). The occurrence of pain in the extremities was higher in the CV+ group (24.2% vs 9.8%, OR = 2.95 [2.21-3.91]). SARS-CoV-2 infection was also associated with higher occurrence of peripheral neuropathy symptoms, after adjusting for the history of chronic pain and neuropathy (OR = 3.19 [2.37-4.29]). The results suggest that SARS-CoV-2 infection was independently associated with an increased risk of pain and peripheral neuropathy symptoms.

Hospital trajectories and early predictors of clinical outcomes differ between SARS-CoV-2 and influenza pneumonia.

BACKGROUND: A comparison of pneumonias due to SARS-CoV-2 and influenza, in terms of clinical course and predictors of outcomes, might inform prognosis and resource management. We aimed to compare clinical course and outcome predictors in SARS-CoV-2 and influenza pneumonia using multi-state modelling and supervised machine learning on clinical data among hospitalised patients. METHODS: This multicenter retrospective cohort study of patients hospitalised with SARS-CoV-2 (March-December 2020) or influenza (Jan 2015-March 2020) pneumonia had the composite of hospital mortality and hospice discharge as the primary outcome. Multi-state models compared differences in oxygenation/ventilatory utilisation between pneumonias longitudinally throughout hospitalisation. Differences in predictors of outcome were modelled using supervised machine learning classifiers. FINDINGS: Among 2,529 hospitalisations with SARS-CoV-2 and 2,256 with influenza pneumonia, the primary outcome occurred in 21% and 9%, respectively. Multi-state models differentiated oxygen requirement progression between viruses, with SARS-CoV-2 manifesting rapidly-escalating early hypoxemia. Highly contributory classifier variables for the primary outcome differed substantially between viruses. INTERPRETATION: SARS-CoV-2 and influenza pneumonia differ in presentation, hospital course, and outcome predictors. These pathogen-specific differential responses in viral pneumonias suggest distinct management approaches should be investigated. FUNDING: This project was supported by NIH/NCATS UL1 TR002345, NIH/NCATS KL2 TR002346 (PGL), the Doris Duke Charitable Foundation grant 2015215 (PGL), NIH/NHLBI R35 HL140026 (CSC), and a Big Ideas Award from the BJC HealthCare and Washington University School of Medicine Healthcare Innovation Lab and NIH/NIGMS R35 GM142992 (PS).

Association of Male Hypogonadism With Risk of Hospitalization for COVID-19.

Importance: Male sex is associated with severe COVID-19. It is not known whether the risk of hospitalization differs between men with hypogonadism, men with eugonadism, and those receiving testosterone therapy (TTh). Objective: To compare COVID-19 hospitalization rates for men with hypogonadism who were not receiving TTh, men with eugonadism, and men receiving TTh. Design, Setting, and Participants: This cohort study was conducted in 2 large academic health systems in St Louis, Missouri, among 723 men with a history of COVID-19 who had testosterone concentrations measured between January 1, 2017, and December 31, 2021. Exposures: The primary exposure was gonadal status (hypogonadism, eugonadism, and TTh). Hypogonadism was defined as a total testosterone concentration below the limit of normal provided by the laboratory (which varied from 175 to 300 ng/dL [to convert to nanomoles per liter, multiply by 0.0347]). Main Outcomes and Measures: The primary outcome was rate of hospitalization for COVID-19. Statistical adjustments were made for group differences in age, body mass index, race and ethnicity, immunosuppression, and comorbid conditions. Results: Of the 723 study participants (mean [SD] age, 55 [14] years; mean [SD] body mass index, 33.5 [7.3]), 116 men had hypogonadism, 427 had eugonadism, and 180 were receiving TTh. Men with hypogonadism were more likely than men with eugonadism to be hospitalized with COVID-19 (52 of 116 [45%] vs 53 of 427 [12%]; P < .001). After multivariable adjustment, men with hypogonadism had higher odds than men with eugonadism of being hospitalized (odds ratio, 2.4; 95% CI, 1.4-4.4; P < .003). Men receiving TTh had a similar risk of hospitalization as men with eugonadism (odds ratio, 1.3; 95% CI, 0.7-2.3; P = .35). Men receiving inadequate TTh (defined as subnormal testosterone concentrations while receiving TTh) had higher odds of hospitalization compared with men who had normal testosterone concentrations while receiving TTh (multivariable adjusted odds ratio, 3.5; 95% CI, 1.5-8.6; P = .003). Conclusions and Relevance: This study suggests that men with hypogonadism were more likely to be hospitalized after COVID-19 infection compared with those with eugonadism, independent of other known risk factors. This increased risk was not observed among men receiving adequate TTh. Screening and appropriate therapy for hypogonadism need to be evaluated as a strategy to prevent severe COVID-19 outcomes among men.

Effects of Persistent Exposure to COVID-19 on Mental Health Outcomes Among Trainees: a Longitudinal Survey Study.

BACKGROUND: The rapid spread of the coronavirus disease 2019 (COVID-19) has created considerable strain on the physical and mental health of healthcare workers around the world. The effects have been acute for physician trainees-a unique group functioning simultaneously as learners and care providers with limited autonomy. OBJECTIVE: To investigate the longitudinal effects of physician trainee exposure to patients being tested for COVID-19 on stress, anxiety, depression, and burnout using three surveys conducted during the early phase of the pandemic. DESIGN: Longitudinal survey study. PARTICIPANTS: All physician trainees (N = 1375) at an academic medical center. MAIN MEASURE: Assess the relationship between repeated exposure to patients being tested for COVID-19 and stress, anxiety, depression, and burnout. KEY RESULTS: Three hundred eighty-nine trainees completed the baseline survey (28.3%). Of these, 191 and 136 completed the ensuing surveys. Mean stress, anxiety, and burnout decreased by 21% (95% confidence interval (CI): - 28 to - 12%; P < 0.001), 25% (95% CI: - 36 to - 11%; P < 0.001), and 13% (95% CI: - 18 to - 7%; P < 0.001), respectively, per survey. However, for each survey time point, there was mean increase in stress, anxiety, and burnout per additional exposure: stress [24% (95% CI: + 12 to + 38%; P < 0.001)], anxiety [22% (95% CI: + 2 to + 46%; P = 0.026)], and burnout [18% (95% CI: + 10 to + 28%; P < 0.001)]. For depression, the association between exposure was strongest for the third survey, where mean depression scores increased by 33% per additional exposure (95% CI: + 18 to + 50%; P < 0.001). CONCLUSIONS: Training programs should adapt to address the detrimental effects of the "pileup" of distress associated with persistent exposure through adaptive programs that allow flexibility for time off and recovery.

Impact of Changes in EHR Use during COVID-19 on Physician Trainee Mental Health.

OBJECTIVES: This article investigates the association between changes in electronic health record (EHR) use during the coronavirus disease 2019 (COVID-19) pandemic on the rate of burnout, stress, posttraumatic stress disorder (PTSD), depression, and anxiety among physician trainees (residents and fellows). METHODS: A total of 222 (of 1,375, 16.2%) physician trainees from an academic medical center responded to a Web-based survey. We compared the physician trainees who reported that their EHR use increased versus those whose EHR use stayed the same or decreased on outcomes related to depression, anxiety, stress, PTSD, and burnout using univariable and multivariable models. We examined whether self-reported exposure to COVID-19 patients moderated these relationships. RESULTS: Physician trainees who reported increased use of EHR had higher burnout (adjusted mean, 1.48 [95% confidence interval [CI] 1.24, 1.71] vs. 1.05 [95% CI 0.93, 1.17]; p = 0.001) and were more likely to exhibit symptoms of PTSD (adjusted mean = 15.09 [95% CI 9.12, 21.05] vs. 9.36 [95% CI 7.38, 11.28]; p = 0.035). Physician trainees reporting increased EHR use outside of work were more likely to experience depression (adjusted mean, 8.37 [95% CI 5.68, 11.05] vs. 5.50 [95% CI 4.28, 6.72]; p = 0.035). Among physician trainees with increased EHR use, those exposed to COVID-19 patients had significantly higher burnout (2.04, p < 0.001) and depression scores (14.13, p = 0.003). CONCLUSION: Increased EHR use was associated with higher burnout, depression, and PTSD outcomes among physician trainees. Although preliminary, these findings have implications for creating systemic changes to manage the wellness and well-being of trainees.

Cohort study protocol to characterize the incidence and severity of neuropathic pain in patients with severe acute respiratory syndrome coronavirus 2 infection.

INTRODUCTION AND OBJECTIVES: The coronavirus disease 2019 (COVID-19) pandemic has resulted in patients experiencing symptoms that include neurological dysfunction. As many viral infections are associated with neuropathy, the aim of the study is to characterize the incidence and severity of neuropathic pain in patients with COVID-19. METHODS: A cohort study will be conducted in adult (≥18 years) patients who were tested for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) at Washington University/Barnes-Jewish Hospital. Participants who are deceased, with incomplete test results, or who cannot be contacted will be excluded. Approximately 1320 participants will be recruited in a 1:2 ratio of those with a positive-to-negative SARS-CoV-2 test result. Each participant will be invited to complete a survey to assess their symptoms related to neuropathy, 30 to 90 days after their initial SARS-CoV-2 test. Survey responses, demographics, and clinical data from the electronic health record will be used for analysis. The primary outcome is the incidence of new symptoms of neuropathic pain. The self-reported DN4 and Neuropathic Pain Symptom Inventory questionnaires (Appendix 1, http://links.lww.com/PR9/A103) will be used for neuropathic pain screening and severity assessment, respectively. Exploratory analyses will be performed to investigate other potential clinical endpoints and trends. RESULTS/CONCLUSION: Similar to previous coronavirus infections, an increased incidence of new-onset neuropathic pain after COVID-19 disease is expected, along with an increase in the severity experienced by patients with COVID-19 with pre-existing chronic pain. Comprehensive understanding of how COVID-19 affects the nervous system can provide a better framework for managing pain in this disease.

Risk factors associated with physician trainee concern over missed educational opportunities during the COVID-19 pandemic.

BACKGROUND: The COVID-19 pandemic resulted in a transformation of clinical care practices to protect both patients and providers. These changes led to a decrease in patient volume, impacting physician trainee education due to lost clinical and didactic opportunities. We measured the prevalence of trainee concern over missed educational opportunities and investigated the risk factors leading to such concerns. METHODS: All residents and fellows at a large academic medical center were invited to participate in a web-based survey in May of 2020. Participants responded to questions regarding demographic characteristics, specialty, primary assigned responsibility during the previous 2 weeks (clinical, education, or research), perceived concern over missed educational opportunities, and burnout. Multivariable logistic regression was used to assess the relationship between missed educational opportunities and the measured variables. RESULTS: 22% (301 of 1375) of the trainees completed the survey. 47% of the participants were concerned about missed educational opportunities. Trainees assigned to education at home had 2.85 [95%CI 1.33-6.45] greater odds of being concerned over missed educational opportunities as compared with trainees performing clinical work. Trainees performing research were not similarly affected [aOR = 0.96, 95%CI (0.47-1.93)]. Trainees in pathology or radiology had 2.51 [95%CI 1.16-5.68] greater odds of concern for missed educational opportunities as compared with medicine. Trainees with greater concern over missed opportunities were more likely to be experiencing burnout (p = 0.038). CONCLUSIONS: Trainees in radiology or pathology and those assigned to education at home were more likely to be concerned about their missed educational opportunities. Residency programs should consider providing trainees with research or at home clinical opportunities as an alternative to self-study should future need for reduced clinical hours arise.

Correction: Work-Related and Personal Factors Associated With Mental Well-Being During the COVID-19 Response: Survey of Health Care and Other Workers.

[This corrects the article DOI: 10.2196/21366.].

Exposure to COVID-19 patients increases physician trainee stress and burnout.

The coronavirus disease 2019 (COVID-19) pandemic has put considerable physical and emotional strain on frontline healthcare workers. Among frontline healthcare workers, physician trainees represent a unique group-functioning simultaneously as both learners and caregivers and experiencing considerable challenges during the pandemic. However, we have a limited understanding regarding the emotional effects and vulnerability experienced by trainees during the pandemic. We investigated the effects of trainee exposure to patients being tested for COVID-19 on their depression, anxiety, stress, burnout and professional fulfillment. All physician trainees at an academic medical center (n = 1375) were invited to participate in an online survey. We compared the measures of depression, anxiety, stress, burnout and professional fulfillment among trainees who were exposed to patients being tested for COVID-19 and those that were not, using univariable and multivariable models. We also evaluated perceived life stressors such as childcare, home schooling, personal finances and work-family balance among both groups. 393 trainees completed the survey (29% response rate). Compared to the non-exposed group, the exposed group had a higher prevalence of stress (29.4% vs. 18.9%), and burnout (46.3% vs. 33.7%). The exposed group also experienced moderate to extremely high perceived stress regarding childcare and had a lower work-family balance. Multivariable models indicated that trainees who were exposed to COVID-19 patients reported significantly higher stress (10.96 [95% CI, 9.65 to 12.46] vs 8.44 [95% CI, 7.3 to 9.76]; P = 0.043) and were more likely to be burned out (1.31 [95% CI, 1.21 to1.41] vs 1.07 [95% CI, 0.96 to 1.19]; P = 0.002]. We also found that female trainees were more likely to be stressed (P = 0.043); while unmarried trainees were more likely to be depressed (P = 0.009), and marginally more likely to have anxiety (P = 0.051). To address these challenges, wellness programs should focus on sustaining current programs, develop new and targeted mental health resources that are widely accessible and devise strategies for creating awareness regarding these resources.

Work-Related and Personal Factors Associated With Mental Well-Being During the COVID-19 Response: Survey of Health Care and Other Workers.

BACKGROUND: The response to the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has created an unprecedented disruption in work conditions. This study describes the mental health and well-being of workers both with and without clinical exposure to patients with coronavirus disease (COVID-19). OBJECTIVE: The aim of this study is to measure the prevalence of stress, anxiety, depression, work exhaustion, burnout, and decreased well-being among faculty and staff at a university and academic medical center during the SARS-CoV-2 pandemic and describe work-related and personal factors associated with their mental health and well-being. METHODS: All faculty, staff, and postdoctoral fellows of a university, including its medical school, were invited in April 2020 to complete an online questionnaire measuring stress, anxiety, depression, work exhaustion, burnout, and decreased well-being. We examined associations between these outcomes and factors including work in high-risk clinical settings and family/home stressors. RESULTS: There were 5550 respondents (overall response rate of 34.3%). Overall, 34% of faculty and 14% of staff (n=915) were providing clinical care, while 61% of faculty and 77% of staff were working from home. Among all workers, anxiety (prevalence ratio 1.37, 95% CI 1.09-1.73), depression (prevalence ratio 1.28, 95% CI 1.03-1.59), and high work exhaustion (prevalence ratio 1.24, 95% CI 1.13-1.36) were independently associated with community or clinical exposure to COVID-19. Poor family-supportive behaviors by supervisors were also associated with these outcomes (prevalence ratio 1.40, 95% CI 1.21-1.62; prevalence ratio 1.69, 95% CI 1.48-1.92; and prevalence ratio 1.54, 95% CI 1.44-1.64, respectively). Age <40 years and a greater number of family/home stressors were also associated with these poorer outcomes. Among the subset of clinicians, caring for patients with COVID-19 and working in high-risk clinical settings were additional risk factors. CONCLUSIONS: Our findings suggest that the pandemic has had negative effects on the mental health and well-being of both clinical and nonclinical employees. Mitigating exposure to COVID-19 and increasing supervisor support are modifiable risk factors that may protect mental health and well-being for all workers.

When past is not a prologue: Adapting informatics practice during a pandemic.

Data and information technology are key to every aspect of our response to the current coronavirus disease 2019 (COVID-19) pandemic-including the diagnosis of patients and delivery of care, the development of predictive models of disease spread, and the management of personnel and equipment. The increasing engagement of informaticians at the forefront of these efforts has been a fundamental shift, from an academic to an operational role. However, the past history of informatics as a scientific domain and an area of applied practice provides little guidance or prologue for the incredible challenges that we are now tasked with performing. Building on our recent experiences, we present 4 critical lessons learned that have helped shape our scalable, data-driven response to COVID-19. We describe each of these lessons within the context of specific solutions and strategies we applied in addressing the challenges that we faced.

Digital Translucence: Adapting Telemedicine Delivery Post-COVID-19

In nearly 1 month, with a rapidly expanding corona virus disease 2019 (COVID-19), telemedicine has been transformed into an essential service for delivering routine clinical care. This transformation occurred as a crisis management response-driven by the need to provide care for patients with physical distancing measures in place. However, the current rapid adoption of telemedicine presents a transitional state between one that existed before the pandemic and one that could potentially be better aligned with the delivery of a personalized model of care. Using the conceptual framework of digital translucence-situating virtual encounters with more nuanced information regarding patients-we describe the role of integrated remote monitoring and virtual care tools aligned with the patient's electronic health record for adapting telemedicine delivery post-COVID-19.