ABSTRACT
Background: Hypertension and diabetes are common comorbidities in patients with COVID-19 and could be influencing the mortality of such patients. The present study aimed to evaluate the effects of hypertension alone and in comorbidity with diabetes on the death within 30 days among inpatients with COVID-19 in presence of well-known determinates of COVID-19 death.Study Design: A case-control study.Methods: Four groups of COVID-19 inpatients including controls, diabetes alone, hypertension alone, and hypertension and diabetes comorbidities were defined. Each study groups did not have underlying diseases other than hypertension and diabetes. Demographic and general characteristics, underlying diseases, and hospital course events were extracted from medical records. The outcome of interest was alive at discharge/ death within 30 days after admission. Multivariable binary logistic analysis was employed to estimate the effect measures.Results: The number of death within 30 days among controls (n = 1359), diabetes alone (159), hypertension alone (406) and hypertension and diabetes comorbidities (188) were 12.68%, 15.72%, 20.74% and 26.74%, respectively. According to three multivariable analyses after adjusting older age, hospital length of stay, and intensive care unit (ICU) admission separately, the odds of death within 30 days in COVID-19 patients with having hypertension and diabetes comorbidities was 1.58, 2.13 and 1.91 times of patients without such comorbidities, respectively (P < 0.015). The effect of hypertension alone was also significant after adjusting hospital length of stay and ICU admission but not for older age.Conclusion: Our results suggest that comorbidities, such as hypertension and diabetes may be associated with COVID-19-related deaths independent of other underlying diseases, older age, and adverse hospital course events.
ABSTRACT
Survival data with a multi-state structure are frequently observed in follow-up studies. An analytic approach based on a multi-state model (MSM) should be used in longitudinal health studies in which a patient experiences a sequence of clinical progression events. One main objective in the MSM framework is variable selection, where attempts are made to identify the risk factors associated with the transition hazard rates or probabilities of disease progression. The usual variable selection methods, including stepwise and penalized methods, do not provide information about the importance of variables. In this context, we present a two-step algorithm to evaluate the importance of variables formulti-state data. Three differentmachine learning approaches (randomforest, gradient boosting, and neural network) as themost widely usedmethods are considered to estimate the variable importance in order to identify the factors affecting disease progression and rank these factors according to their importance. The performance of our proposed methods is validated by simulation and applied to the COVID-19 data set. The results revealed that the proposed two-stage method has promising performance for estimating variable importance.
ABSTRACT
Survival data with a multi-state structure are frequently observed in follow-up studies. An analytic approach based on a multi-state model (MSM) should be used in longitudinal health studies in which a patient experiences a sequence of clinical progression events. One main objective in the MSM framework is variable selection, where attempts are made to identify the risk factors associated with the transition hazard rates or probabilities of disease progression. The usual variable selection methods, including stepwise and penalized methods, do not provide information about the importance of variables. In this context, we present a two-step algorithm to evaluate the importance of variables for multi-state data. Three different machine learning approaches (random forest, gradient boosting, and neural network) as the most widely used methods are considered to estimate the variable importance in order to identify the factors affecting disease progression and rank these factors according to their importance. The performance of our proposed methods is validated by simulation and applied to the COVID-19 data set. The results revealed that the proposed two-stage method has promising performance for estimating variable importance. © 2023 Tech Science Press. All rights reserved.
ABSTRACT
Survival data with a multi-state structure are frequently observed in follow-up studies. An analytic approach based on a multi-state model (MSM) should be used in longitudinal health studies in which a patient experiences a sequence of clinical progression events. One main objective in the MSM framework is variable selection, where attempts are made to identify the risk factors associated with the transition hazard rates or probabilities of disease progression. The usual variable selection methods, including stepwise and penalized methods, do not provide information about the importance of variables. In this context, we present a two-step algorithm to evaluate the importance of variables for multi-state data. Three different machine learning approaches (random forest, gradient boosting, and neural network) as the most widely used methods are considered to estimate the variable importance in order to identify the factors affecting disease progression and rank these factors according to their importance. The performance of our proposed methods is validated by simulation and applied to the COVID-19 data set. The results revealed that the proposed two-stage method has promising performance for estimating variable importance.