Pub Date : 2024-07-09eCollection Date: 2024-01-01DOI: 10.1515/em-2023-0039
Mark A van de Wiel, Matteo Amestoy, Jeroen Hoogland
Objectives: The addition of two-way interactions is a classic problem in statistics, and comes with the challenge of quadratically increasing dimension. We aim to a) devise an estimation method that can handle this challenge and b) to aid interpretation of the resulting model by developing computational tools for quantifying variable importance.
Methods: Existing strategies typically overcome the dimensionality problem by only allowing interactions between relevant main effects. Building on this philosophy, and aiming for settings with moderate n to p ratio, we develop a local shrinkage model that links the shrinkage of interaction effects to the shrinkage of their corresponding main effects. In addition, we derive a new analytical formula for the Shapley value, which allows rapid assessment of individual-specific variable importance scores and their uncertainties.
Results: We empirically demonstrate that our approach provides accurate estimates of the model parameters and very competitive predictive accuracy. In our Bayesian framework, estimation inherently comes with inference, which facilitates variable selection. Comparisons with key competitors are provided. Large-scale cohort data are used to provide realistic illustrations and evaluations. The implementation of our method in RStan is relatively straightforward and flexible, allowing for adaptation to specific needs.
Conclusions: Our method is an attractive alternative for existing strategies to handle interactions in epidemiological and/or clinical studies, as its linked local shrinkage can improve parameter accuracy, prediction and variable selection. Moreover, it provides appropriate inference and interpretation, and may compete well with less interpretable machine learners in terms of prediction.
{"title":"Linked shrinkage to improve estimation of interaction effects in regression models.","authors":"Mark A van de Wiel, Matteo Amestoy, Jeroen Hoogland","doi":"10.1515/em-2023-0039","DOIUrl":"10.1515/em-2023-0039","url":null,"abstract":"<p><strong>Objectives: </strong>The addition of two-way interactions is a classic problem in statistics, and comes with the challenge of quadratically increasing dimension. We aim to a) devise an estimation method that can handle this challenge and b) to aid interpretation of the resulting model by developing computational tools for quantifying variable importance.</p><p><strong>Methods: </strong>Existing strategies typically overcome the dimensionality problem by only allowing interactions between relevant main effects. Building on this philosophy, and aiming for settings with moderate n to p ratio, we develop a local shrinkage model that links the shrinkage of interaction effects to the shrinkage of their corresponding main effects. In addition, we derive a new analytical formula for the Shapley value, which allows rapid assessment of individual-specific variable importance scores and their uncertainties.</p><p><strong>Results: </strong>We empirically demonstrate that our approach provides accurate estimates of the model parameters and very competitive predictive accuracy. In our Bayesian framework, estimation inherently comes with inference, which facilitates variable selection. Comparisons with key competitors are provided. Large-scale cohort data are used to provide realistic illustrations and evaluations. The implementation of our method in RStan is relatively straightforward and flexible, allowing for adaptation to specific needs.</p><p><strong>Conclusions: </strong>Our method is an attractive alternative for existing strategies to handle interactions in epidemiological and/or clinical studies, as its linked local shrinkage can improve parameter accuracy, prediction and variable selection. Moreover, it provides appropriate inference and interpretation, and may compete well with less interpretable machine learners in terms of prediction.</p>","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11232106/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141581101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The prey-predator model provides a mathematical framework for understanding the population dynamics of interacting species, highlighting the delicate balance between predator and prey populations in ecological systems. The four-species predator-prey model extends the Lotka-Volterra framework to explore the dynamics of ecosystems with multiple interacting species. It provides a theoretical foundation for understanding how the populations of multiple prey and predator species influence each other over time. Apart from the traditional methods like direct approach for solving the non-linear system of equations, recent Fuzzy method approaches have been developed. The solution of non-linear systems using classical methods is not easy due to its non-linearity, analytical complexity, chaotic behavior, etc. and the T-S method is very much effective to analyze the non-linear models. In this study, we considered an eco-epidemic model with two populations of prey and one population of predator, with the only infectious disease infecting the first prey population. The four-dimensional Lotka-Volterra predator-prey system’s model stability has been examined using the Takagi-Sugeno (T-S) impulsive control model and the Fuzzy impulsive control model. Following the formulation of the model, the global stability and the Fuzzy solution are carried out through numerical simulations and graphical representations with appropriate discussion for a better understanding the dynamics of our proposed model. The Takagi-Sugeno method has diverse applications in modeling, control, pattern recognition, and decision-making in systems where uncertainty and non-linearity play a significant role. Its ability to combine fuzzy logic with traditional mathematical models provides a powerful tool for addressing complex real-world problems. The impulse control approach, what is considered within the foundation of fuzzy systems established on T-S model, is found to be suitable for extremely complex and non-linear systems with impulse effects.
{"title":"Population dynamic study of two prey one predator system with disease in first prey using fuzzy impulsive control","authors":"Khushbu Singh, K. Kolla","doi":"10.1515/em-2023-0037","DOIUrl":"https://doi.org/10.1515/em-2023-0037","url":null,"abstract":"\u0000 \u0000 \u0000 The prey-predator model provides a mathematical framework for understanding the population dynamics of interacting species, highlighting the delicate balance between predator and prey populations in ecological systems. The four-species predator-prey model extends the Lotka-Volterra framework to explore the dynamics of ecosystems with multiple interacting species. It provides a theoretical foundation for understanding how the populations of multiple prey and predator species influence each other over time. Apart from the traditional methods like direct approach for solving the non-linear system of equations, recent Fuzzy method approaches have been developed. The solution of non-linear systems using classical methods is not easy due to its non-linearity, analytical complexity, chaotic behavior, etc. and the T-S method is very much effective to analyze the non-linear models.\u0000 \u0000 \u0000 \u0000 In this study, we considered an eco-epidemic model with two populations of prey and one population of predator, with the only infectious disease infecting the first prey population. The four-dimensional Lotka-Volterra predator-prey system’s model stability has been examined using the Takagi-Sugeno (T-S) impulsive control model and the Fuzzy impulsive control model. Following the formulation of the model, the global stability and the Fuzzy solution are carried out through numerical simulations and graphical representations with appropriate discussion for a better understanding the dynamics of our proposed model.\u0000 \u0000 \u0000 \u0000 The Takagi-Sugeno method has diverse applications in modeling, control, pattern recognition, and decision-making in systems where uncertainty and non-linearity play a significant role. Its ability to combine fuzzy logic with traditional mathematical models provides a powerful tool for addressing complex real-world problems.\u0000 \u0000 \u0000 \u0000 The impulse control approach, what is considered within the foundation of fuzzy systems established on T-S model, is found to be suitable for extremely complex and non-linear systems with impulse effects.\u0000","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140525695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Determining the causal relationship between exposure and outcome is the goal of many observational studies. However, the selection of subjects into the study population, either voluntary or involuntary, may result in estimates that suffer from selection bias. To assess the robustness of the estimates as well as the magnitude of the bias, bounds for the bias can be calculated. Previous bounds for selection bias often require the specification of unknown relative risks, which might be difficult to provide. Here, alternative bounds based on observed data and unknown outcome probabilities are proposed. These unknown probabilities may be easier to specify than unknown relative risks. I derive alternative bounds from the definitions of the causal estimands using the potential outcomes framework, under specific assumptions. The bounds are expressed using observed data and unobserved outcome probabilities. The bounds are compared to previously reported bounds in a simulation study. Furthermore, a study of perinatal risk factors for type 1 diabetes is provided as a motivating example. I show that the proposed bounds are often informative when the exposure and outcome are sufficiently common, especially for the risk difference in the total population. It is also noted that the proposed bounds can be uninformative when the exposure and outcome are rare. Furthermore, it is noted that previously proposed assumption-free bounds are special cases of the new bounds when the sensitivity parameters are set to their most conservative values. Depending on the data generating process and causal estimand of interest, the proposed bounds can be tighter or wider than the reference bounds. Importantly, in cases with sufficiently common outcome and exposure, the proposed bounds are often informative, especially for the risk difference in the total population. It is also noted that, in some cases, the new bounds can be wider than the reference bounds. However, the proposed bounds based on unobserved probabilities may in some cases be easier to specify than the reference bounds based on unknown relative risks.
{"title":"Bounds for selection bias using outcome probabilities","authors":"Stina Zetterstrom","doi":"10.1515/em-2023-0033","DOIUrl":"https://doi.org/10.1515/em-2023-0033","url":null,"abstract":"\u0000 \u0000 \u0000 Determining the causal relationship between exposure and outcome is the goal of many observational studies. However, the selection of subjects into the study population, either voluntary or involuntary, may result in estimates that suffer from selection bias. To assess the robustness of the estimates as well as the magnitude of the bias, bounds for the bias can be calculated. Previous bounds for selection bias often require the specification of unknown relative risks, which might be difficult to provide. Here, alternative bounds based on observed data and unknown outcome probabilities are proposed. These unknown probabilities may be easier to specify than unknown relative risks.\u0000 \u0000 \u0000 \u0000 I derive alternative bounds from the definitions of the causal estimands using the potential outcomes framework, under specific assumptions. The bounds are expressed using observed data and unobserved outcome probabilities. The bounds are compared to previously reported bounds in a simulation study. Furthermore, a study of perinatal risk factors for type 1 diabetes is provided as a motivating example.\u0000 \u0000 \u0000 \u0000 I show that the proposed bounds are often informative when the exposure and outcome are sufficiently common, especially for the risk difference in the total population. It is also noted that the proposed bounds can be uninformative when the exposure and outcome are rare. Furthermore, it is noted that previously proposed assumption-free bounds are special cases of the new bounds when the sensitivity parameters are set to their most conservative values.\u0000 \u0000 \u0000 \u0000 Depending on the data generating process and causal estimand of interest, the proposed bounds can be tighter or wider than the reference bounds. Importantly, in cases with sufficiently common outcome and exposure, the proposed bounds are often informative, especially for the risk difference in the total population. It is also noted that, in some cases, the new bounds can be wider than the reference bounds. However, the proposed bounds based on unobserved probabilities may in some cases be easier to specify than the reference bounds based on unknown relative risks.\u0000","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140516970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sachin Kumar, S. Pal, Vijendra Pratap Singh, Priya Jaiswal
Abstract Objectives COVID-19 is frightening the health of billions of persons and speedily scattering worldwide. Medical studies have revealed that the majority of COVID-19 patients. X-ray of COVID-19 is extensively used because of their noticeably lower price than CT. This research article aims to spot the COVID-19 virus in the X-ray of the chest in less time and with better accuracy. Methods We have used the inception-v3 available on the cloud platform transfer learning model to classify COVID-19 infection. The online Inception v3 model can be reliable and efficient for COVID-19 disease recognition. In this experiment, we collected images of COVID-19-infected patients, then applied the online inception-v3 model to automatically extract features, and used a softmax classifier to classify the COVID-19 images. Finally, the experiment shows inception v3 is significant for COVID-19 image classification. Results Our results demonstrate that our proposed inception v3 model available on the cloud platform can detect 99.41% of COVID-19 cases between COVID-19 and Lung Mask diseases in 44 min only. We have also taken images of the normal chest for better outcomes. To estimate the computation power of the model, we collected 6018 COVID-19, Lung Masks, & Normal Chest images for experimentation. Our projected model offered a trustworthy COVID-19 classification by using chest X-rays. Conclusions In this research paper, the inception v3 model available on the cloud platform is used to categorize COVID-19 infection by X-ray images. The Inception v3 model available on the cloud platform is helpful to clinical experts to examine the enormous quantity of human chest X-ray images. Scientific and clinical experiments will be the subsequent objective of this paper.
{"title":"Energy- efficient model “Inception V3 based on deep convolutional neural network” using cloud platform for detection of COVID-19 infected patients","authors":"Sachin Kumar, S. Pal, Vijendra Pratap Singh, Priya Jaiswal","doi":"10.1515/em-2021-0046","DOIUrl":"https://doi.org/10.1515/em-2021-0046","url":null,"abstract":"Abstract Objectives COVID-19 is frightening the health of billions of persons and speedily scattering worldwide. Medical studies have revealed that the majority of COVID-19 patients. X-ray of COVID-19 is extensively used because of their noticeably lower price than CT. This research article aims to spot the COVID-19 virus in the X-ray of the chest in less time and with better accuracy. Methods We have used the inception-v3 available on the cloud platform transfer learning model to classify COVID-19 infection. The online Inception v3 model can be reliable and efficient for COVID-19 disease recognition. In this experiment, we collected images of COVID-19-infected patients, then applied the online inception-v3 model to automatically extract features, and used a softmax classifier to classify the COVID-19 images. Finally, the experiment shows inception v3 is significant for COVID-19 image classification. Results Our results demonstrate that our proposed inception v3 model available on the cloud platform can detect 99.41% of COVID-19 cases between COVID-19 and Lung Mask diseases in 44 min only. We have also taken images of the normal chest for better outcomes. To estimate the computation power of the model, we collected 6018 COVID-19, Lung Masks, & Normal Chest images for experimentation. Our projected model offered a trustworthy COVID-19 classification by using chest X-rays. Conclusions In this research paper, the inception v3 model available on the cloud platform is used to categorize COVID-19 infection by X-ray images. The Inception v3 model available on the cloud platform is helpful to clinical experts to examine the enormous quantity of human chest X-ray images. Scientific and clinical experiments will be the subsequent objective of this paper.","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74365959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Objectives Leishmaniasis is a parasitic disease whose transmission depends on climatic conditions and is more important in northeast Iran. This study aimed to investigate the time trend of leishmaniasis and present a prediction model using meteorological variables in Golestan province. Methods The 10-year data on leishmaniasis (2010–2019) were collected from the portal of the Ministry of Health and the National Meteorological Organization. First, the disease incidence (per 100,000 population) in different cities of the Golestan province was estimated. Then, the geographical distribution and disease clusters map were prepared at the province level. Finally, by using the Jenkins box model time series analysis method, the disease incidence was predicted for the period 2020 to 2023 of the total province. Results From 2010 to 2019, 8,871 patients with leishmaniasis were identified. The mean age of patients was 21.0 ± 18.4 years. The highest mean annual incidence was in Maravah-Tappeh city (188 per 100,000 population). The highest and lowest annual incidence was in 2018 and 2017, respectively. The average 10-year incidence was 48 per 100,000 population. The daily meteorological variables like monthly average wind speed, sunshine, temperature, and mean soil temperature at depth of 50 cm were significantly associated with the incidence of the disease. The estimated threshold for an epidemic was 40.3 per 100,000 population. Conclusions According to the results, leishmaniasis incidence cases apears in July and with a peak in November. The incidence rate was highest in Maravah-Tapeh and Gonbad-Kavous, and lowest in Kordkoy counties. The study showed that there were two peaks in 2010 and 2018 and also identified a downward trend in the disease between 2010 and 2013 with a clear decrease in the incidence. Climate conditions had an important effect on leishmaniasis incidence. These climate and epidemiological factors such as migration and overcrowding could provide important input to monitor and predict disease for control strategies.
{"title":"Incidence and trend of leishmaniasis and its related factors in Golestan province, northeastern Iran: time series analysis","authors":"M. Majidnia, A. Hosseinzadeh, Ahmad Khosravi","doi":"10.1515/em-2022-0124","DOIUrl":"https://doi.org/10.1515/em-2022-0124","url":null,"abstract":"Abstract Objectives Leishmaniasis is a parasitic disease whose transmission depends on climatic conditions and is more important in northeast Iran. This study aimed to investigate the time trend of leishmaniasis and present a prediction model using meteorological variables in Golestan province. Methods The 10-year data on leishmaniasis (2010–2019) were collected from the portal of the Ministry of Health and the National Meteorological Organization. First, the disease incidence (per 100,000 population) in different cities of the Golestan province was estimated. Then, the geographical distribution and disease clusters map were prepared at the province level. Finally, by using the Jenkins box model time series analysis method, the disease incidence was predicted for the period 2020 to 2023 of the total province. Results From 2010 to 2019, 8,871 patients with leishmaniasis were identified. The mean age of patients was 21.0 ± 18.4 years. The highest mean annual incidence was in Maravah-Tappeh city (188 per 100,000 population). The highest and lowest annual incidence was in 2018 and 2017, respectively. The average 10-year incidence was 48 per 100,000 population. The daily meteorological variables like monthly average wind speed, sunshine, temperature, and mean soil temperature at depth of 50 cm were significantly associated with the incidence of the disease. The estimated threshold for an epidemic was 40.3 per 100,000 population. Conclusions According to the results, leishmaniasis incidence cases apears in July and with a peak in November. The incidence rate was highest in Maravah-Tapeh and Gonbad-Kavous, and lowest in Kordkoy counties. The study showed that there were two peaks in 2010 and 2018 and also identified a downward trend in the disease between 2010 and 2013 with a clear decrease in the incidence. Climate conditions had an important effect on leishmaniasis incidence. These climate and epidemiological factors such as migration and overcrowding could provide important input to monitor and predict disease for control strategies.","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87085901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Objectives To dynamically measure COVID-19 transmissibility consistently normalized by population size in each country. Methods A reduced-form model enhanced from the classical SIR is proposed to stochastically represent the Reproduction Number and Mortality Rate, directly measuring the combined effects of viral evolution and population behavioral response functions. Results Evidences are shown that this e(hanced)-SIR model has the power to fit country-specific empirical data, produce interpretable model parameters to be used for generating probabilistic scenarios adapted to the still unfolding pandemic. Conclusions Stochastic processes embedded within compartmental epidemiological models can produce measurables and actionable information for surveillance and planning purposes.
{"title":"A country-specific COVID-19 model","authors":"G. Meissner, Hong Sherwin","doi":"10.2139/ssrn.4043977","DOIUrl":"https://doi.org/10.2139/ssrn.4043977","url":null,"abstract":"Abstract Objectives To dynamically measure COVID-19 transmissibility consistently normalized by population size in each country. Methods A reduced-form model enhanced from the classical SIR is proposed to stochastically represent the Reproduction Number and Mortality Rate, directly measuring the combined effects of viral evolution and population behavioral response functions. Results Evidences are shown that this e(hanced)-SIR model has the power to fit country-specific empirical data, produce interpretable model parameters to be used for generating probabilistic scenarios adapted to the still unfolding pandemic. Conclusions Stochastic processes embedded within compartmental epidemiological models can produce measurables and actionable information for surveillance and planning purposes.","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89060519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emily Riseberg, Rachel D Melamed, Katherine A James, Tanya L Alderete, Laura Corlin
Objectives: Specifying causal models to assess relationships among metal mixtures and cardiometabolic outcomes requires evidence-based models of the causal structures; however, such models have not been previously published. The objective of this study was to develop and evaluate a directed acyclic graph (DAG) diagraming metal mixture exposure and cardiometabolic outcomes.
Methods: We conducted a literature search to develop the DAG of metal mixtures and cardiometabolic outcomes. To evaluate consistency of the DAG, we tested the suggested conditional independence statements using linear and logistic regression analyses with data from the San Luis Valley Diabetes Study (SLVDS; n=1795). We calculated the proportion of statements supported by the data and compared this to the proportion of conditional independence statements supported by 1,000 DAGs with the same structure but randomly permuted nodes. Next, we used our DAG to identify minimally sufficient adjustment sets needed to estimate the association between metal mixtures and cardiometabolic outcomes (i.e., cardiovascular disease, fasting glucose, and systolic blood pressure). We applied them to the SLVDS using Bayesian kernel machine regression, linear mixed effects, and Cox proportional hazards models.
Results: From the 42 articles included in the review, we developed an evidence-based DAG with 74 testable conditional independence statements (43 % supported by SLVDS data). We observed evidence for an association between As and Mn and fasting glucose.
Conclusions: We developed, tested, and applied an evidence-based approach to analyze associations between metal mixtures and cardiometabolic health.
{"title":"Development and application of an evidence-based directed acyclic graph to evaluate the associations between metal mixtures and cardiometabolic outcomes.","authors":"Emily Riseberg, Rachel D Melamed, Katherine A James, Tanya L Alderete, Laura Corlin","doi":"10.1515/em-2022-0133","DOIUrl":"https://doi.org/10.1515/em-2022-0133","url":null,"abstract":"<p><strong>Objectives: </strong>Specifying causal models to assess relationships among metal mixtures and cardiometabolic outcomes requires evidence-based models of the causal structures; however, such models have not been previously published. The objective of this study was to develop and evaluate a directed acyclic graph (DAG) diagraming metal mixture exposure and cardiometabolic outcomes.</p><p><strong>Methods: </strong>We conducted a literature search to develop the DAG of metal mixtures and cardiometabolic outcomes. To evaluate consistency of the DAG, we tested the suggested conditional independence statements using linear and logistic regression analyses with data from the San Luis Valley Diabetes Study (SLVDS; n=1795). We calculated the proportion of statements supported by the data and compared this to the proportion of conditional independence statements supported by 1,000 DAGs with the same structure but randomly permuted nodes. Next, we used our DAG to identify minimally sufficient adjustment sets needed to estimate the association between metal mixtures and cardiometabolic outcomes (i.e., cardiovascular disease, fasting glucose, and systolic blood pressure). We applied them to the SLVDS using Bayesian kernel machine regression, linear mixed effects, and Cox proportional hazards models.</p><p><strong>Results: </strong>From the 42 articles included in the review, we developed an evidence-based DAG with 74 testable conditional independence statements (43 % supported by SLVDS data). We observed evidence for an association between As and Mn and fasting glucose.</p><p><strong>Conclusions: </strong>We developed, tested, and applied an evidence-based approach to analyze associations between metal mixtures and cardiometabolic health.</p>","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292771/pdf/em-12-1-em-2022-0133.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10352001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sachin Kumar, Vijendra Pratap Singh, S. Pal, Priya Jaiswal
Abstract Objective The outbreak of the coronavirus caused major problems in more than 151 countries around the world. An important step in the fight against coronavirus is the search for infected people. The goal of this article is to predict COVID-19 infectious patients. Methods We implemented DenseNet201, available on cloud platform, as a learning network. DenseNet201 is a 201-layer networkthat. is trained on ImageNet. The input size of pre-trained DenseNet201 images is 224 × 224 × 3. Results Implementation of DenseNet201 was effectively performed based on 80 % of the training X-rays and 20 % of the X-rays of the test phases, respectively. DenseNet201 shows a good experimental result with an accuracy of 99.24 % in 7.47 min. To measure the computational efficiency of the proposed model, we collected more than 6,000 noise-free data infected by tuberculosis, COVID-19, and uninfected healthy chests for implementation. Conclusions DenseNet201 available on the cloud platform has been used for the classification of COVID-19-infected patients. The goal of this article is to demonstrate how to achieve faster results.
{"title":"Energy-efficient model “DenseNet201 based on deep convolutional neural network” using cloud platform for detection of COVID-19 infected patients","authors":"Sachin Kumar, Vijendra Pratap Singh, S. Pal, Priya Jaiswal","doi":"10.1515/em-2021-0047","DOIUrl":"https://doi.org/10.1515/em-2021-0047","url":null,"abstract":"Abstract Objective The outbreak of the coronavirus caused major problems in more than 151 countries around the world. An important step in the fight against coronavirus is the search for infected people. The goal of this article is to predict COVID-19 infectious patients. Methods We implemented DenseNet201, available on cloud platform, as a learning network. DenseNet201 is a 201-layer networkthat. is trained on ImageNet. The input size of pre-trained DenseNet201 images is 224 × 224 × 3. Results Implementation of DenseNet201 was effectively performed based on 80 % of the training X-rays and 20 % of the X-rays of the test phases, respectively. DenseNet201 shows a good experimental result with an accuracy of 99.24 % in 7.47 min. To measure the computational efficiency of the proposed model, we collected more than 6,000 noise-free data infected by tuberculosis, COVID-19, and uninfected healthy chests for implementation. Conclusions DenseNet201 available on the cloud platform has been used for the classification of COVID-19-infected patients. The goal of this article is to demonstrate how to achieve faster results.","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76887951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuzi Zhang, Lin Ge, Lance A. Waller, Robert H. Lyles
Abstract In epidemiological studies, the capture-recapture (CRC) method is a powerful tool that can be used to estimate the number of diseased cases or potentially disease prevalence based on data from overlapping surveillance systems. Estimators derived from log-linear models are widely applied by epidemiologists when analyzing CRC data. The popularity of the log-linear model framework is largely associated with its accessibility and the fact that interaction terms can allow for certain types of dependency among data streams. In this work, we shed new light on significant pitfalls associated with the log-linear model framework in the context of CRC using real data examples and simulation studies. First, we demonstrate that the log-linear model paradigm is highly exclusionary. That is, it can exclude, by design, many possible estimates that are potentially consistent with the observed data. Second, we clarify the ways in which regularly used model selection metrics (e.g., information criteria) are fundamentally deceiving in the effort to select a “best” model in this setting. By focusing attention on these important cautionary points and on the fundamental untestable dependency assumption made when fitting a log-linear model to CRC data, we hope to improve the quality of and transparency associated with subsequent surveillance-based CRC estimates of case counts.
{"title":"On some pitfalls of the log-linear modeling framework for capture-recapture studies in disease surveillance","authors":"Yuzi Zhang, Lin Ge, Lance A. Waller, Robert H. Lyles","doi":"10.1515/em-2023-0019","DOIUrl":"https://doi.org/10.1515/em-2023-0019","url":null,"abstract":"Abstract In epidemiological studies, the capture-recapture (CRC) method is a powerful tool that can be used to estimate the number of diseased cases or potentially disease prevalence based on data from overlapping surveillance systems. Estimators derived from log-linear models are widely applied by epidemiologists when analyzing CRC data. The popularity of the log-linear model framework is largely associated with its accessibility and the fact that interaction terms can allow for certain types of dependency among data streams. In this work, we shed new light on significant pitfalls associated with the log-linear model framework in the context of CRC using real data examples and simulation studies. First, we demonstrate that the log-linear model paradigm is highly exclusionary. That is, it can exclude, by design, many possible estimates that are potentially consistent with the observed data. Second, we clarify the ways in which regularly used model selection metrics (e.g., information criteria) are fundamentally deceiving in the effort to select a “best” model in this setting. By focusing attention on these important cautionary points and on the fundamental untestable dependency assumption made when fitting a log-linear model to CRC data, we hope to improve the quality of and transparency associated with subsequent surveillance-based CRC estimates of case counts.","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135053775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sprockel Diaz Johm Jaime, Hector Fabio Restrepo Guerrero, J. J. Fernández
Abstract Objective To identify prognostic markers by applying machine learning strategies to the feature selection. Methods An observational, retrospective, multi-center study that included hospitalized patients with a confirmed diagnosis of COVID-19 in three hospitals in Colombia. Eight strategies were applied to select prognostic-related characteristics. Eight logistic regression models were built from each set of variables and the predictive ability of the outcome was evaluated. The primary endpoint was transfer to intensive care or in-hospital death. Results The database consisted of 969 patients of which 486 had complete data. The main outcome occurred in 169 cases. The development database included 220 patients, 137 (62.3%) were men with a median age of 58.2, 39 (17.7%) were diabetic, 62 (28.2%) had high blood pressure, and 32 (14.5%) had chronic lung disease. Thirty-three variables were identified as prognostic markers, and those selected most frequently were: LDH, PaO2/FIO2 ratio, CRP, age, neutrophil and lymphocyte counts, respiratory rate, oxygen saturation, ferritin, and HCO3. The eight logistic regressions developed were validated on 266 patients in whom similar results were reached (accuracy: 65.8–72.9%). Conclusions The combined use of strategies for selecting characteristics through machine learning techniques makes it possible to identify a broad set of prognostic markers in patients hospitalized for COVID-19 for death or hospitalization in intensive care.
{"title":"Application of machine learning tools for feature selection in the identification of prognostic markers in COVID-19","authors":"Sprockel Diaz Johm Jaime, Hector Fabio Restrepo Guerrero, J. J. Fernández","doi":"10.1515/em-2022-0132","DOIUrl":"https://doi.org/10.1515/em-2022-0132","url":null,"abstract":"Abstract Objective To identify prognostic markers by applying machine learning strategies to the feature selection. Methods An observational, retrospective, multi-center study that included hospitalized patients with a confirmed diagnosis of COVID-19 in three hospitals in Colombia. Eight strategies were applied to select prognostic-related characteristics. Eight logistic regression models were built from each set of variables and the predictive ability of the outcome was evaluated. The primary endpoint was transfer to intensive care or in-hospital death. Results The database consisted of 969 patients of which 486 had complete data. The main outcome occurred in 169 cases. The development database included 220 patients, 137 (62.3%) were men with a median age of 58.2, 39 (17.7%) were diabetic, 62 (28.2%) had high blood pressure, and 32 (14.5%) had chronic lung disease. Thirty-three variables were identified as prognostic markers, and those selected most frequently were: LDH, PaO2/FIO2 ratio, CRP, age, neutrophil and lymphocyte counts, respiratory rate, oxygen saturation, ferritin, and HCO3. The eight logistic regressions developed were validated on 266 patients in whom similar results were reached (accuracy: 65.8–72.9%). Conclusions The combined use of strategies for selecting characteristics through machine learning techniques makes it possible to identify a broad set of prognostic markers in patients hospitalized for COVID-19 for death or hospitalization in intensive care.","PeriodicalId":37999,"journal":{"name":"Epidemiologic Methods","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86505772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号