Association of the medication protocols and longitudinal change of COVID-19 symptoms: a hospital-based mixed-statistical methods study.

The objective of this study was to identify the relationship between hospitalization treatment strategies leading to change in symptoms during 12-week follow-up among hospitalized patients during the COVID-19 outbreak. In this article, data from a prospective cohort study on COVID-19 patients admitted to Khorshid Hospital, Isfahan, Iran, from February 2020 to February 2021, were analyzed and reported. Patient characteristics, including socio-demographics, comorbidities, signs and symptoms, and treatments during hospitalization, were investigated. Also, to investigate the treatment effects adjusted by other confounding factors that lead to symptom change during follow-up, the binary classification trees, generalized linear mixed model, machine learning, and joint generalized estimating equation methods were applied. This research scrutinized the effects of various medications on COVID-19 patients in a prospective hospital-based cohort study, and found that heparin, methylprednisolone, ceftriaxone, and hydroxychloroquine were the most frequently prescribed medications. The results indicate that of patients under 65 years of age, 76% had a cough at the time of admission, while of patients with Cr levels of 1.1 or more, 80% had not lost weight at the time of admission. The results of fitted models showed that, during the follow-up, women are more likely to have shortness of breath (OR = 1.25; P-value: 0.039), fatigue (OR = 1.31; P-value: 0.013) and cough (OR = 1.29; P-value: 0.019) compared to men. Additionally, patients with symptoms of chest pain, fatigue and decreased appetite during admission are at a higher risk of experiencing fatigue during follow-up. Each day increase in the duration of ceftriaxone multiplies the odds of shortness of breath by 1.15 (P-value: 0.012). With each passing week, the odds of losing weight increase by 1.41 (P-value: 0.038), while the odds of shortness of breath and cough decrease by 0.84 (P-value: 0.005) and 0.56 (P-value: 0.000), respectively. In addition, each day increase in the duration of meropenem or methylprednisolone decreased the odds of weight loss at follow-up by 0.88 (P-value: 0.026) and 0.91 (P-value: 0.023), respectively (among those who took these medications). Identified prognostic factors can help clinicians and policymakers adapt management strategies for patients in any pandemic like COVID-19, which ultimately leads to better hospital decision-making and improved patient quality of life outcomes.

Bayesian second-order sensitivity of longitudinal inferences to non-ignorability: an application to antidepressant clinical trial data.

Incomplete data is a prevalent complication in longitudinal studies due to individuals' drop-out before intended completion time. Currently available methods via commercial software for analyzing incomplete longitudinal data at best rely on the ignorability of the drop-outs. If the underlying missing mechanism was non-ignorable, potential bias arises in the statistical inferences. To remove the bias when the drop-out is non-ignorable, joint complete-data and drop-out models have been proposed which involve computational difficulties and untestable assumptions. Since the critical ignorability assumption is unverifiable based on the observed part of the sample, some local sensitivity indices have been proposed in the literature. Specifically, Eftekhari Mahabadi (Second-order local sensitivity to non-ignorability in Bayesian inferences. Stat Med 2018;59:55-95) proposed a second-order local sensitivity tool for Bayesian analysis of cross-sectional studies and show its better performance for handling bias compared with the first-order ones. In this paper, we aim to extend this index for the Bayesian sensitivity analysis of normal longitudinal studies with drop-outs. The index is driven based on a selection model for the drop-out mechanism and a Bayesian linear mixed-effect complete-data model. The presented formulas are calculated using the posterior estimation and draws from the simpler ignorable model. The method is illustrated via some simulation studies and sensitivity analysis of a real antidepressant clinical trial data. Overall, the numerical analysis showed that when repeated outcomes are subject to missingness, regression coefficient estimates are nearly approximated well by a linear function in the neighbourhood of MAR model, but there are a considerable amount of second-order sensitivity for the error term and random effect variances in Bayesian linear mixed-effect model framework.

Traffic violation analysis using time series, clustering and panel zero-truncated one-inflated mixed model.

Traffic rules violations in urban areas, which can cause traffic crashes and unsafe situations, are a major issue nowadays. The present paper aims to analyze the frequency of traffic violations in Tehran city, Iran, over a five-year period (March 2016- March 2021). The data is obtained via road traffic violation monitoring system which can capture and process various traffic violations. This database, containing about 97 million violations committed by about 16 million drivers, is explored applying three statistical approaches. In the first approach, some multiplicative SARIMA and Bayesian Spatio-temporal models are fitted to the monthly violations. Also, in the second approach, the K-means clustering algorithm is applied to discover homogeneous districts of Tehran Municipality regarding their number of violations and their number of violations per camera towers meter during the study. Finally, in the third approach, a random-effect zero-truncated one-inflated Poisson model is proposed to study factors affecting driver's number of violations over time.

Second-order local sensitivity to non-ignorability in Bayesian inferences.

The sensitivity of Bayesian inferences to non-ignorability is an important issue which should be carefully handled when analyzing incomplete data sets. Generally, sensitivity analysis quantifies the effect that non-ignorability parameter variations have on model outputs or inferences. This sensitivity can be achieved locally around the ignorable model. Previously, some local sensitivity measures to assess the impact of non-ignorable coarsening on Bayesian inferences have been established based on the first-order derivation of the posterior expectations. This may not be adequate to show potential sensitivity when there is a considerable amount of curvature around the ignorable model estimate. Specifically, it becomes more important when the posterior expectation is U-shaped near the ignorable estimate so that the first-order sensitivity index is approximately zero even if the posterior mean might be highly curved around the ignorable model and hence sensitive to the ignorability assumption. In this paper, we present a method for determining the second-order sensitivity to non-ignorability of Bayesian inferences locally around the ignorable model in GLMs which perform equally well when the impact of non-ignorability is locally linear. Calculation of the proposed second-order sensitivity index only requires some posterior covariances of the simple ignorable model and is conducted efficiently and with minimal computational overhead compared with the first-order sensitivity index. To show the need for the second-order sensitivity index as a more precise screening tool, some simulation studies are conducted. Also, the approach is applied to analyze a real data example with CD4 cell counts as an incomplete response variable.