Prospective validation of a dynamic prognostic model for identifying COVID-19 patients at high risk of rapid deterioration.

BACKGROUND: We sought to develop and prospectively validate a dynamic model that incorporates changes in biomarkers to predict rapid clinical deterioration in patients hospitalized for COVID-19. METHODS: We established a retrospective cohort of hospitalized patients aged ≥18 years with laboratory-confirmed COVID-19 using electronic health records (EHR) from a large integrated care delivery network in Massachusetts including > 40 facilities from March to November 2020. A total of 71 factors, including time-varying vital signs and laboratory findings during hospitalization were screened. We used elastic net regression and tree-based scan statistics for variable selection to predict rapid deterioration, defined as progression by two levels of a published severity scale in the next 24 hours. The development cohort included the first 70% of patients identified chronologically in calendar time; the latter 30% served as the validation cohort. A cut-off point was estimated to alert clinicians of high risk of imminent clinical deterioration. RESULTS: Overall, 3,706 patients (2,587 in the development and 1,119 in the validation cohort) met the eligibility criteria with a median of 6 days of follow-up. Twenty-four variables were selected in the final model, including 16 dynamic changes of laboratory results or vital signs. Area under the ROC curve was 0.81 (95% CI, 0.79 - 0.82) in the development set and 0.74 (95% CI, 0.71-0.78) in the validation set. The model was well calibrated (slope = 0.84 and intercept = -0.07 on the calibration plot in the validation set). The estimated cut-off point, with a positive predictive value of 83%, was 0.78. CONCLUSIONS: Our prospectively validated dynamic prognostic model demonstrated temporal generalizability in a rapidly evolving pandemic and can be used to inform day-to-day treatment and resource allocation decisions based on dynamic changes in biophysiological factors. This article is protected by copyright. All rights reserved.

Gastrointestinal prophylaxis for COVID-19: an illustration of severe bias arising from inappropriate comparators in observational studies.

OBJECTIVES: We aimed to use setting-appropriate comparisons to estimate the effects of different gastrointestinal (GI) prophylaxis pharmacotherapies for patients hospitalized with COVID-19 and setting-inappropriate comparisons to illustrate how improper design choices could result in biased results. STUDY DESIGN AND SETTING: We identified 3,804 hospitalized patients aged ≥ 18 years with COVID-19 from March to November 2020. We compared the effects of different gastroprotective agents on clinical improvement of COVID-19, as measured by a published severity scale. We used propensity score-based fine-stratification for confounding adjustment. Based on guidelines, we prespecified comparisons between agents with clinical equipoise and inappropriate comparisons of users vs. nonusers of GI prophylaxis in the intensive care unit (ICU). RESULTS: No benefit was detected when comparing oral famotidine to omeprazole in patients treated in the general ward or ICUs. We also found no associations when comparing intravenous famotidine to intravenous pantoprazole. For inappropriate comparisons of users vs. nonusers in the ICU, the probability of improvement was reduced by 32%-45% in famotidine users and 21%-48% in omeprazole or pantoprazole users. CONCLUSION: We found no evidence that GI prophylaxis improved outcomes for patients hospitalized with COVID-19 in setting-appropriate comparisons. An improper comparator choice can lead to spurious associations in critically ill patients.

Applying Machine Learning in Distributed Data Networks for Pharmacoepidemiologic and Pharmacovigilance Studies: Opportunities, Challenges, and Considerations.

Increasing availability of electronic health databases capturing real-world experiences with medical products has garnered much interest in their use for pharmacoepidemiologic and pharmacovigilance studies. The traditional practice of having numerous groups use single databases to accomplish similar tasks and address common questions about medical products can be made more efficient through well-coordinated multi-database studies, greatly facilitated through distributed data network (DDN) architectures. Access to larger amounts of electronic health data within DDNs has created a growing interest in using data-adaptive machine learning (ML) techniques that can automatically model complex associations in high-dimensional data with minimal human guidance. However, the siloed storage and diverse nature of the databases in DDNs create unique challenges for using ML. In this paper, we discuss opportunities, challenges, and considerations for applying ML in DDNs for pharmacoepidemiologic and pharmacovigilance studies. We first discuss major types of activities performed by DDNs and how ML may be used. Next, we discuss practical data-related factors influencing how DDNs work in practice. We then combine these discussions and jointly consider how opportunities for ML are affected by practical data-related factors for DDNs, leading to several challenges. We present different approaches for addressing these challenges and highlight efforts that real-world DDNs have taken or are currently taking to help mitigate them. Despite these challenges, the time is ripe for the emerging interest to use ML in DDNs, and the utility of these data-adaptive modeling techniques in pharmacoepidemiologic and pharmacovigilance studies will likely continue to increase in the coming years.

Hydroxychloroquine early in pregnancy and risk of birth defects.

BACKGROUND: Hydroxychloroquine is generally considered safe in pregnancy for the treatment of rheumatic conditions, but studies have been too small to evaluate teratogenicity. Quantifying the risk of congenital malformations associated with early pregnancy exposure to hydroxychloroquine is important in both the context of its ongoing use for rheumatological disorders and its potential future use for coronavirus disease 2019 prophylaxis, for which a number of clinical trials are ongoing despite initial trials for coronavirus disease 2019 treatment having been negative. OBJECTIVE: The study objective was to evaluate the risk of major congenital malformations associated with exposure to hydroxychloroquine during the first trimester of pregnancy, the period of organogenesis. STUDY DESIGN: We performed a population-based cohort study nested in the Medicaid Analytic eXtract (MAX, 2000-2014) and IBM MarketScan Research Database (MarketScan, 2003-2015). The source cohort included 2045 hydroxychloroquine-exposed pregnancies and 3,198,589 pregnancies not exposed to hydroxychloroquine continuously enrolled in their respective insurance program for 3 months before the last menstrual period through at least 1 month after delivery; infants were enrolled for at least 3 months after birth. We compared the risk of congenital malformations in women using hydroxychloroquine during the first trimester of pregnancy with that of those not using hydroxychloroquine, restricting the cohort to women with rheumatic disorders and using propensity score matching to control for indication, demographics, medical comorbidities, and concomitant medications (1867 hydroxychloroquine-exposed pregnancies and 19,080 pregnancies not exposed to hydroxychloroquine). The outcomes considered included major congenital malformations diagnosed during the first 90 days after delivery and specific malformation types for which there were at least 5 exposed events: oral cleft, cardiac, respiratory, gastrointestinal, genital, urinary, musculoskeletal, and limb defects. RESULTS: Overall, 54.8 per 1000 infants exposed to hydroxychloroquine were born with a major congenital malformation versus 35.3 per 1000 unexposed infants, corresponding to an unadjusted relative risk of 1.51 (95% confidence interval, 1.27-1.81). Patient characteristics were balanced in the restricted, propensity score-matched cohort. The adjusted relative risk was 1.26 (95% confidence interval, 1.04-1.54); it was 1.33 (95% confidence interval, 1.08-1.65) for a daily dose of ≥400 mg and 0.95 (95% confidence interval, 0.60-1.50) for a daily dose of <400 mg. Among the different malformation groups considered, more substantial increases in the risk of oral clefts, respiratory anomalies, and urinary defects were observed, although estimates were imprecise. No pattern of malformation was identified. CONCLUSION: Our findings suggest a small increase in the risk of malformations associated with first-trimester hydroxychloroquine use. For most patients with autoimmune rheumatic disorders, the benefits of treatment during pregnancy will likely outweigh this risk. If hydroxychloroquine were shown to be effective for coronavirus disease 2019 prophylaxis in ongoing trials, the risk of malformations would need to be balanced against such benefits.