PLoS ONE最新文献

筛选
英文 中文
Efficient quantification of Parkinson's disease severity using augmented time-series data.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0319826
Hua Huo, Shupei Jiao, Dongfang Li, Lan Ma, Ningya Xu
{"title":"Efficient quantification of Parkinson's disease severity using augmented time-series data.","authors":"Hua Huo, Shupei Jiao, Dongfang Li, Lan Ma, Ningya Xu","doi":"10.1371/journal.pone.0319826","DOIUrl":"https://doi.org/10.1371/journal.pone.0319826","url":null,"abstract":"<p><p>The diagnosis of Parkinson's disease relies heavily on the subjective assessment of physicians, which depends on their individual experience and training, potentially leading to inconsistent diagnostic results. Therefore, developing an objective and efficient diagnostic method is essential to improve the accuracy and timeliness of Parkinson's disease diagnosis. In this study, we utilized the PhysioNet dataset, a time-series dataset comprising data from 93 Parkinson's patients and 73 healthy individuals. The dataset contains vertical ground reaction forces recorded from 16 sensors (8 per foot) during a 2-minute test at a sampling rate of 100 Hz. To address challenges such as limited dataset size, high labeling noise, and high intra-class variability, we performed data preprocessing and applied various data augmentation techniques, including jittering, scaling, rotation, permutation, magnitude warping, time warping, cropping, and linear residuals. These methods were evaluated using one-dimensional-convolutional neural network (1D-ConvNet) and one-dimensional Transformer networks. By conducting 10-fold cross-validation, we observed significant improvements in classification performance. The best data augmentation strategy achieved 90.8% accuracy, 92.0% precision, 91.0% recall, and a 91.0% F1 score in assessing disease severity. These results highlight the importance of selecting appropriate data augmentation techniques for time-series data to improve model generalization and diagnostic reliability, while also offering new insights for researchers working with sensor device data. Our results demonstrate that data-enhanced methods can significantly boost the performance of machine-learning models in the field of Parkinson's disease diagnosis.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0319826"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
"You take care of people, people will take care of you": Moral Economies and an Unpredictable Drug Market.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0320423
Erin E Gould, Siddhi S Ganesh, Anthony J DiMario, Jimi Huh, Ricky N Bluthenthal, Rachel Carmen Ceasar
{"title":"\"You take care of people, people will take care of you\": Moral Economies and an Unpredictable Drug Market.","authors":"Erin E Gould, Siddhi S Ganesh, Anthony J DiMario, Jimi Huh, Ricky N Bluthenthal, Rachel Carmen Ceasar","doi":"10.1371/journal.pone.0320423","DOIUrl":"https://doi.org/10.1371/journal.pone.0320423","url":null,"abstract":"<p><strong>Introduction: </strong>Fentanyl is the leading cause of opioid-related overdose deaths in the United States. Given the exogenous market shock of fentanyl and subsequent transition in the illicit opioid supply, our analysis sought to explore the social and relational experiences of people who use opioids (PWUO).</p><p><strong>Methods: </strong>We conducted qualitative interviews with 30 PWUO (n = 30) in Los Angeles, CA from July 2021 to April 2022. To be eligible for this study, participants had to report being 18 years of age or older and any self-reported opioid, cannabis, and injection drug use within the past 30 days. We used constructivist grounded theory to analyze the contexts that contribute to lived experiences surrounding opioid use behaviors within social networks.</p><p><strong>Results: </strong>Within an unpredictable drug market contaminated by fentanyl, participants reported: 1) avoiding opioid withdrawal symptoms by sharing financial and material resources within social networks, 2) securing and cultivating known, predictable social ties to prioritize safe/ safer supply of opioids, and 3) avoiding and mitigating risk of overdose fatality by using opioids within peer groups.</p><p><strong>Conclusions: </strong>Our findings emphasize that while peer support plays a critical role in safety within moral economies of PWUO, structural changes are needed to address the additional harms from an unregulated drug supply. Harm reduction interventions such as fentanyl test strip and naloxone distribution, as well as medication for opioid use disorders may improve safety. However, with a fentanyl-contaminated drug supply increasing risk for PWUO, safer opioid distribution of pharmaceutical-grade opioids and overdose prevention programs are needed to effectively address the burden of withdrawal, overdose, and fatality prevention within peer groups.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0320423"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Integrating virtual reality, electroencephalography, and transcranial magnetic stimulation to study the neural correlates of awe experiences: The SUBRAIN protocol.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0302762
Elena Bondi, Flavia Carbone, Marta Pizzolante, Giandomenico Schiena, Adele Ferro, Maddalena Mazzocut-Mis, Andrea Gaggioli, Alice Chirico, Paolo Brambilla, Eleonora Maggioni
{"title":"Integrating virtual reality, electroencephalography, and transcranial magnetic stimulation to study the neural correlates of awe experiences: The SUBRAIN protocol.","authors":"Elena Bondi, Flavia Carbone, Marta Pizzolante, Giandomenico Schiena, Adele Ferro, Maddalena Mazzocut-Mis, Andrea Gaggioli, Alice Chirico, Paolo Brambilla, Eleonora Maggioni","doi":"10.1371/journal.pone.0302762","DOIUrl":"https://doi.org/10.1371/journal.pone.0302762","url":null,"abstract":"<p><strong>Introduction: </strong>Awe is a complex emotion unveiling a positive and mixed nature, which resembles the Romantic feeling of the Sublime. It has increasingly become the object of scientific investigation in the last twenty years. However, its underlying brain mechanisms are still unclear. To fully capture its nature in the lab, researchers have increasingly relied on virtual reality (VR) as an emotion-elicitation method, which can resemble even complex phenomena in a limited space. In this work, a multidisciplinary team proposed a novel experimental protocol integrating VR, electroencephalography (EEG), and transcranial magnetic stimulation (TMS) to investigate the brain mechanisms of this emotion.</p><p><strong>Methods: </strong>A group of bioengineers, psychologists, psychiatrists, and philosophers designed the SUBRAIN study, a single-center, one-arm, non-randomized interventional study to explore the neural processes underlying awe experiences. The study is ongoing and is expected to enroll fifty adults between 20 and 40 years of age. Currently, more than 40 individuals have been enrolled. The experimental protocol includes different steps: (i) screening, (ii) enrollment, (iii) pre-experimental assessment, (iv) VR experimental assessment, and (v) post-experimental debriefing. The brain's electrical activity is recorded using the EEG while participants navigated three immersive awe-inducing VR environments and a neutral one. At the same time, the cortical excitability and connectivity is investigated by performing a TMS-EEG session right after each VR navigation. Along with cerebral signals, self-reported questionnaires were used to assess the VR-induced changes in the emotional state of the subjects. This data is then analyzed to delve into the cerebral mechanisms of awe.</p><p><strong>Discussion: </strong>This study protocol is the first one that tries to fully understand the neural bases of awe by eliciting and studying this phenomenon in VR. The pairing of awe-inducing VR experiences and questionnaires investigating participants' affect and emotions, with non-invasive neural techniques, can provide a novel and extensive knowledge on this complex phenomenon. The protocol can inform on the combination of different instruments showing a reproducible and reliable setting for the investigation of induced complex emotions.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0302762"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Lessons learned from operationalizing the integration of nutrition-specific and nutrition-sensitive interventions in rural Ethiopia.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0290524
Girmay Ayana Mersha, Eshetu Zerihun Tariku, Wanzahun Godana Boynito, Meseret Woldeyohaness, Tadese Kebebe, Birhanu Wodajo, Stefaan De Henauw, Souheila Abbeddou
{"title":"Lessons learned from operationalizing the integration of nutrition-specific and nutrition-sensitive interventions in rural Ethiopia.","authors":"Girmay Ayana Mersha, Eshetu Zerihun Tariku, Wanzahun Godana Boynito, Meseret Woldeyohaness, Tadese Kebebe, Birhanu Wodajo, Stefaan De Henauw, Souheila Abbeddou","doi":"10.1371/journal.pone.0290524","DOIUrl":"https://doi.org/10.1371/journal.pone.0290524","url":null,"abstract":"<p><strong>Background: </strong>Undernutrition reduction requires coordinated efforts across sectors to address its causes. A multisectoral approach is important in diagnosing the problem and identifying solutions that would be implemented across different sectors. The study aimed to explore the experience of health and agriculture extension workers in integrating nutrition-specific and nutrition-sensitive interventions provided to households with children under two years of age at community level.</p><p><strong>Methods: </strong>A qualitative study was conducted in agrarian areas of Ethiopia following the completion of a multi-sectoral program that integrated health and agriculture interventions, in 2021. The program's goal was to reduce stunting and improve the dietary diversity of young children. In total, 28 key informant interviews were conducted with health- and agriculture-extension workers and mothers. A framework analysis approach was applied to manage and analyze data using NVivo version 12 software.</p><p><strong>Results: </strong>The study showed that joint health and agriculture interventions improved community knowledge on childcare and agricultural practices. The practice of farm gardening and cooking demonstrations were improved after the implementation of the program. Because of service integration, extension workers perceived an improved father's role in supporting mothers in childcaring and feeding nutritious diets to children and decreased severe cases of undernutrition. Integration of health and agriculture sectors for nutrition intervention was challenged by the high workload on extension workers, poor supervision and leadership commitment, lack of appropriate agricultural inputs, and absence of clarity on sector-specific roles. In some areas nutrition services are not owned by the health and agriculture sectors, and it was overlooked.</p><p><strong>Conclusion: </strong>Integrating community-level platforms were key entry points to address undernutrition and promote key agriculture and health interventions. The joint implementation of health and agriculture services were effective in the reduction of wasting and improved the role of family members in supporting mothers. However, Integration of sectors were facing challenges in creating shared vision to improve nutrition status of children and women, distributing workload and equal commitment among sectors.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0290524"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
First unambiguous record of pneumaticity in the axial skeleton of alvarezsaurians (Theropoda: Coelurosauria).
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0320121
G J Windholz, J G Meso, M J Wedel, M Pittman
{"title":"First unambiguous record of pneumaticity in the axial skeleton of alvarezsaurians (Theropoda: Coelurosauria).","authors":"G J Windholz, J G Meso, M J Wedel, M Pittman","doi":"10.1371/journal.pone.0320121","DOIUrl":"https://doi.org/10.1371/journal.pone.0320121","url":null,"abstract":"<p><p>Bonapartenykus ultimus is an alvarezsaurid theropod from the Upper Cretaceous of Patagonia, Argentina. This species is represented by the holotype specimen and several referred specimens, many of which have pneumatic structures. Pneumaticity involves the invasion of the interior of the skeleton by means of air sac diverticula. Such invasion occurs from cortical openings (foramina) that communicate with internal air spaces. Despite previous studies on pneumatic structures in theropod specimens, there are no studies focusing on the family Alvarezsauridae. Here we address this gap by presenting the first contribution focusing on the pneumatic features of an alvarezsaurid theropod using both external skeletal anatomy as well as computed tomographic images showing internal details. The specimens studied show that the axial skeleton of B. ultimus was invaded by pneumatic structures, reaching the middle section of the tail. Our study suggests that pneumaticity among alvarezsaurids did not have a linear evolutionary trajectory, but instead shows a more random pattern of variability. This study is an important first step that paves the way for future studies to uncover the extent of pneumatic invasion among alvarezsaurids and its macroevolutionary implications.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0320121"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143772799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A new metoposaurid (Temnospondyli) bonebed from the lower Popo Agie Formation (Carnian, Triassic) and an assessment of skeletal sorting.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0317325
Aaron M Kufner, Max E Deckman, Hannah R Miller, Calvin So, Brandon R Price, David M Lovelace
{"title":"A new metoposaurid (Temnospondyli) bonebed from the lower Popo Agie Formation (Carnian, Triassic) and an assessment of skeletal sorting.","authors":"Aaron M Kufner, Max E Deckman, Hannah R Miller, Calvin So, Brandon R Price, David M Lovelace","doi":"10.1371/journal.pone.0317325","DOIUrl":"https://doi.org/10.1371/journal.pone.0317325","url":null,"abstract":"<p><p>Metoposaurid-dominated bonebeds are relatively commonplace in Upper Triassic continental deposits with at least ten monodominant, densely-packed bonebeds globally. The biostratinomy of several classic localities in India, North America, and Poland have been explored in detail; however, variability in methods and resultant conclusions point to the need for a more rigorous approach to understanding both the taphonomic and the ecological origins of metoposaurid-dominated bonebeds. Here we present the first monodominant metoposaurid mass mortality assemblage from the Late Triassic Popo Agie Formation and the stratigraphically lowest known record of several fauna from the Popo Agie Fm including the first occurrence of Buettnererpeton bakeri in Wyoming. We employ previously tested binning methods based on perceived hydrodynamic equivalence (\"Voorhies groups\") to assess pre-burial skeletal sorting. We suggest a simple counting and normalization method that avoids the inherent bias introduced by the interpretation of hydrodynamic equivalence of skeletal elements in taxa that lack actualistic experimental data. In contrast to other North American metoposaurid bonebeds, the sedimentology and skeletal sorting analyses of the Nobby Knob quarry support an autochthonous origin of this assemblage in a fluvio-lacustrine system with relatively little pre-burial sorting. Despite differences in underlying assumptions regarding the dispersal potential of specific skeletal elements, binning methods tend to follow similar trends regardless of framework used to assess different assemblages.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0317325"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143772984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Socio-economic gradients in hypertension and diabetes management amid the COVID-19 pandemic in India.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0315867
Toshiaki Aizawa
{"title":"Socio-economic gradients in hypertension and diabetes management amid the COVID-19 pandemic in India.","authors":"Toshiaki Aizawa","doi":"10.1371/journal.pone.0315867","DOIUrl":"https://doi.org/10.1371/journal.pone.0315867","url":null,"abstract":"<p><p>This study examines socio-economic inequalities in the prevalence and treatment of hypertension and diabetes among adults in India, utilising data from the National Family Health Survey (NFHS) collected before and during the COVID-19 pandemic. Disparities associated with individual demographic and socio-economic characteristics are measured, with the level of inequality quantified using the dissimilarity index and contributing factors analysed through decomposition analysis. The results reveal significant socio-economic gradients, with wealthier individuals more likely to have elevated blood pressure and blood glucose levels and to treat them. Socio-economic gradients in treatment are even steeper among middle-aged groups during the pandemic. These wealth- and education-related disparities become more pronounced with age. This study highlights the need for targeted interventions and policies to address socio-economic disparities in access to essential care for socio-economically disadvantaged populations.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0315867"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Emergence to dominance: Estimating time to dominance of SARS-CoV-2 variants using nonlinear statistical models.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0311459
Srishti Awasthi, Maryam Zolfaghari Dehkharghani, Miguel Fudolig
{"title":"Emergence to dominance: Estimating time to dominance of SARS-CoV-2 variants using nonlinear statistical models.","authors":"Srishti Awasthi, Maryam Zolfaghari Dehkharghani, Miguel Fudolig","doi":"10.1371/journal.pone.0311459","DOIUrl":"https://doi.org/10.1371/journal.pone.0311459","url":null,"abstract":"<p><strong>Background/objective: </strong>Relative proportion of cases in a multi-strain pandemic like the COVID-19 pandemic provides insight on how fast a newly emergent variant dominates the infected population. However, the behavior of relative proportion of emerging variants is an understudied field. We investigated the emerging behavior of dominant COVID-19 variants using nonlinear statistical methods and calculated the time to dominance of each variant.</p><p><strong>Method: </strong>We used a phenomenological approach to model national- and regional-level variant share data from the national genomic surveillance system provided by the Centers for Disease Control and Prevention to determine the best model to describe the emergence of two recent dominant variants of the SARS-CoV-2 virus: XBB.1.5 and JN.1. The proportions were modeled using logistic, Weibull, and generalized additive models. Model performance was evaluated using the Akaike Information Criteria (AIC) and the root mean square error (RMSE).</p><p><strong>Findings: </strong>The Weibull model performed the worst out of all three approaches. The generalized additive model approach slightly outperformed the logistic model based on fit statistics, but lacked in interpretability compared to the logistic model. These models were then used to estimate the time elapsed from emergence to dominance in the infected population, denoted by the time to dominance (TTD). All three models yielded similar TTD estimates. The XBB.1.5 variant was found to dominate the population faster compared to the JN.1 variant, especially in HHS Region 2 (New York) where the XBB.1.5 was believed to emerge. This research expounds on how emerging viral strains transition to dominance, informing public health interventions against future emergent COVID-19 variants and other infectious diseases.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0311459"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enlightened prognosis: Hepatitis prediction with an explainable machine learning approach.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0319078
Niloy Das, Md Bipul Hossain, Apurba Adhikary, Avi Deb Raha, Yu Qiao, Md Mehedi Hassan, Anupam Kumar Bairagi
{"title":"Enlightened prognosis: Hepatitis prediction with an explainable machine learning approach.","authors":"Niloy Das, Md Bipul Hossain, Apurba Adhikary, Avi Deb Raha, Yu Qiao, Md Mehedi Hassan, Anupam Kumar Bairagi","doi":"10.1371/journal.pone.0319078","DOIUrl":"https://doi.org/10.1371/journal.pone.0319078","url":null,"abstract":"<p><p>Hepatitis is a widespread inflammatory condition of the liver, presenting a formidable global health challenge. Accurate and timely detection of hepatitis is crucial for effective patient management, yet existing methods exhibit limitations that underscore the need for innovative approaches. Early-stage detection of hepatitis is now possible with the recent adoption of machine learning and deep learning approaches. With this in mind, the study investigates the use of traditional machine learning models, specifically classifiers such as logistic regression, support vector machines (SVM), decision trees, random forest, multilayer perceptron (MLP), and other models, to predict hepatitis infections. After extensive data preprocessing including outlier detection, dataset balancing, and feature engineering, we evaluated the performance of these models. We explored three modeling approaches: machine learning with default hyperparameters, hyperparameter-tuned models using GridSearchCV, and ensemble modeling techniques. The SVM model demonstrated outstanding performance, achieving 99.25% accuracy and a perfect AUC score of 1.00 with consistency in other metrics with 99.27% precision, and 99.24% for both recall and F1-measure. The MLP and Random Forest proved to be in pace with the superior performance of SVM exhibiting an accuracy of 99.00%. To ensure robustness, we employed a 5-fold cross-validation technique. For deeper insight into model interpretability and validation, we employed an explainability analysis of our best-performed models to identify the most effective feature for hepatitis detection. Our proposed model, particularly SVM, exhibits better prediction performance regarding different performance metrics compared to existing literature.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0319078"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Association of tobacco use with depressive symptoms in adults: Considerations of symptom severity, symptom clusters, and sex.
IF 2.9 3区 综合性期刊
PLoS ONE Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1371/journal.pone.0319070
Shakila Meshkat, Qiaowei Lin, Vanessa K Tassone, Reinhard Janssen-Aguilar, Hilary Pang, Wendy Lou, Venkat Bhat
{"title":"Association of tobacco use with depressive symptoms in adults: Considerations of symptom severity, symptom clusters, and sex.","authors":"Shakila Meshkat, Qiaowei Lin, Vanessa K Tassone, Reinhard Janssen-Aguilar, Hilary Pang, Wendy Lou, Venkat Bhat","doi":"10.1371/journal.pone.0319070","DOIUrl":"https://doi.org/10.1371/journal.pone.0319070","url":null,"abstract":"<p><strong>Objective: </strong>We aim to assess the association between depressive symptoms, depressive symptom severity and symptom clusters with tobacco use. We will also evaluate sex differences in these associations.</p><p><strong>Method: </strong>This cross-sectional study used data from the National Health and Nutrition Examination Survey (2005-2018). Depressive symptoms were assessed using the Patient Health Questionnaire-9. Tobacco use was categorized into four groups: cigarette use, smoked tobacco products (pipes and cigars), smokeless tobacco products (chewing tobacco and snuff), and non-tobacco use (reference group).</p><p><strong>Results: </strong>This study included 33,509 participants. Cigarette use was associated with a 0.83-unit increase in total PHQ-9 scores (95% CI =  [0.63, 1.04]), and 1.73 times higher odds of reporting depressive symptoms (95% CI =  [1.48, 2.02]) compared to non-tobacco use. However, the use of smoked and smokeless tobacco was not associated with depressive symptoms. In females, cigarette use showed a stronger association with total PHQ-9 scores (aCoef =  1.23, 95% CI =  [0.92, 1.55]) than in males (aCoef =  0.45, 95% CI =  [0.21, 0.69]). Additionally, female smoked tobacco users showed positive associations with both PHQ-9 scores and the presence of depressive symptoms, but this relationship was not observed in males. Furthermore, subgroup analysis revealed associations between cigarette use and cognitive-affective and somatic symptom clusters, as well as a relationship between the logarithm of total cigarette consumption and depressive symptoms.</p><p><strong>Conclusion: </strong>Cigarette use was associated with higher odds of depressive symptoms with females having a stronger association. Further studies are needed to replicate these findings and examine the underlying mechanisms.</p>","PeriodicalId":20189,"journal":{"name":"PLoS ONE","volume":"20 4","pages":"e0319070"},"PeriodicalIF":2.9,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143773087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信