A Two-Step Algorithm to Estimate Variable Importance for Multi-State Data: An Application to COVID-19

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.

A Two-Step Algorithm to Estimate Variable Importance for Multi-State Data: An Application to COVID-19

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.

A Two-Step Algorithm to Estimate Variable Importance for Multi-State Data: An Application to COVID-19

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.

Mixed-frequency machine learning: Nowcasting and backcasting weekly initial claims with daily internet search volume data

We propose an out-of-sample prediction approach that combines unrestricted mixed-data sampling with machine learning (mixed-frequency machine learning, MFML). We use the MFML approach to generate a sequence of nowcasts and backcasts of weekly unemployment insurance initial claims based on a rich trove of daily Google Trends search volume data for terms related to unemployment. The predictions are based on linear models estimated via the LASSO and elastic net, nonlinear models based on artificial neural networks, and ensembles of linear and nonlinear models. Nowcasts and backcasts of weekly initial claims based on models that incorporate the information in the daily Google Trends search volume data substantially outperform those based on models that ignore the information. Predictive accuracy increases as the nowcasts and backcasts include more recent daily Google Trends data. The relevance of daily Google Trends data for predicting weekly initial claims is strongly linked to the COVID-19 crisis.

The influence of financial literacy on financial resilience - New evidence from Europe during the COVID-19 crisis

Purpose This study examines the importance of financial literacy in explaining financial resilience in four continental European countries during the coronavirus disease 2019 (COVID-19) crisis while controlling for a wide set of additional determinants. Design/methodology/approach Variable importance may vary with the technique applied. Therefore, different classification techniques, such as logistic regression, partial proportional odds regression, and conditional random forest, have been employed. The analysis relies on the Survey of Health, Ageing and Retirement in Europe in the context of COVID-19, collecting 4,781 observations from France, Germany, Italy, and Spain. Findings In line with previous studies, financial resilience is found to increase with financial literacy that consistently ranks in the midfield in terms of variable importance among all explanatory variables. Practical implications The findings reveal the most important features that improve financial resilience. Financial literacy is one of the few determinants of financial resilience that can be actively shaped. To increase preparedness for future crises, a policy mix of financial education, regulation, and nudging may help increase financial literacy and, subsequently, financial resilience. Originality/value The better the financial literacy, the more protected individuals are from macroeconomic shocks. However, most previous studies do not rely on data samples that cover such crises. Moreover, most of the previous studies rely on single classification techniques, while this study applied traditional and data-mining techniques to assess feature importance.

Identification of Risk Factors Associated With Mortality Among Patients With COVID-19 Using Random Forest Model: A Historical Cohort Study

There is conflicting evidence about factors associated with Clinical course and risk factors for mortality of adult inpatients. We aimed to identify the demographic, clinical, treatment, and laboratory data factors associated with mortality in the Khoy district. We performed a retrospective cohort study including COVID-19 infected patients who were admitted to Qamar-Bani Hashim hospital from 2 November 2020 to 4 December 2020. We used random forest methods to explore the risk factors associated with death. The applied method was evaluated using sensitivity, specificity, accuracy, and the area under the curve. Age, pulmonary symptoms, patients need a ventilator, brain symptoms, nasal airway, job were the most important risk factors for mortality of COVID-19 in the random forest (RF) method. The RF method showed the highest accuracy, 82.9 and 79.3, for training and testing samples, respectively. However, this method resulted in the highest specificity (89.5% for training and 95.7% for testing sample) and the highest sensitivity (91.9% for training and 94.5% for testing sample). The potential risk factors consisting of older age, pulmonary symptoms, the use of a ventilator, brain symptoms, nasal airway, and the job could help clinicians to identify patients with poor prognosis at an early stage.

Spatio-temporal modeling of COVID-19 prevalence and mortality using artificial neural network algorithms.

The outbreak of coronavirus disease (COVID-19) has become one of the most challenging global concerns in recent years. Due to inadequate worldwide studies on spatio-temporal modeling of COVID-19, this research aims to examine the relative significance of potential explanatory variables (n = 75) concerning COVID-19 prevalence and mortality using multilayer perceptron artificial neural network topology. We utilized ten variable importance analysis methods to identify the relative importance of the explanatory variables. The main findings indicated that several variables were persistently among the most influential variables in all periods. Regarding COVID-19 prevalence, unemployment and population density were among the most influential variables with the highest importance scores. While for COVID-19 mortality, health-related variables such as diabetes prevalence and number of hospital beds were among the most significant variables. The obtained findings from this study might provide general insights for public health policymakers to monitor the spread of disease and support decision-making.