Informatics in Medicine Unlocked最新文献

{"title":"Comparative performance analysis of ensemble learning methods for fetal health classification","authors":"Tasnim Bill Zannah ,&nbsp;Sadia Islam Tonni ,&nbsp;Md. Alif Sheakh ,&nbsp;Mst. Sazia Tahosin ,&nbsp;Afjal Hossan Sarower ,&nbsp;Mahbuba Begum","doi":"10.1016/j.imu.2025.101656","DOIUrl":"10.1016/j.imu.2025.101656","url":null,"abstract":"<div><div>Fetal health monitoring is vital for early diagnosis and intervention during pregnancy, with cardiotocography (CTG) being a standard tool for assessing fetal well-being. However, CTG interpretation often suffers from subjectivity and inconsistency, motivating the need for automated, accurate, and interpretable diagnostic models. To address these challenges, we propose a robust machine learning framework that combines effective feature selection and ensemble learning with explainability. Specifically, Recursive Feature Elimination is used to reduce redundancy and identify the ten most discriminative features. An ensemble classifier, integrating Decision Tree, Random Forest, and Gradient Boosting, is developed to enhance classification accuracy. The model is trained and evaluated on a publicly available CTG dataset, achieving 99.56 % accuracy, 99.54 % precision, 99.59 % recall, and a 99.56 % F1 score. To ensure generalization, we conducted K-fold cross-validation and confusion matrix analysis. For interpretability, the framework incorporates Local Interpretable Model-agnostic Explanation, revealing influential features in each prediction. Compared to existing approaches, our model demonstrates superior performance and transparency, offering a practical and reliable decision-support system for fetal health assessment in clinical settings.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"56 ","pages":"Article 101656"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105114","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}

{"title":"Improving resectable gastric cancer prognosis prediction: A machine learning analysis combining clinical features and body composition radiomics","authors":"Gianni S.S. Liveraro ,&nbsp;Maria E.S. Takahashi ,&nbsp;Fabiana Lascala ,&nbsp;Luiz R. Lopes ,&nbsp;Nelson A. Andreollo ,&nbsp;Maria C.S. Mendes ,&nbsp;Jun Takahashi ,&nbsp;José B.C. Carvalheira","doi":"10.1016/j.imu.2024.101608","DOIUrl":"10.1016/j.imu.2024.101608","url":null,"abstract":"<div><div>We evaluate the significance of body composition radiomics in predicting outcomes for resectable gastric cancer (GC) patients, as these parameters can enhance optimal surveillance strategies and risk-stratification models. Automated segmentation using deep learning algorithms was employed on CT images to analyze body composition in 276 GC patients, retrospectively recruited from the Clinical Hospital of the University of Campinas. Radiomics features of skeletal muscle (SM), visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT) were calculated. Body composition radiomics were integrated with clinicopathological factors using machine learning (ML) algorithms trained for patient outcome prediction. We compared results using Random Forest, Logistic Regression and Boosted Decision Tree algorithms. To identify the relevant features for the prognosis, recursive feature inclusion (RFI) was performed using SHAP Importance ranking. Our study uncovered novel body composition radiomic features that enhance patient prognosis, particularly the 90th percentile radiodensity value (HU) for SM and VAT. The ML model output also refined pathological staging: Stage II patients with a higher predicted mortality risk by the model had overall survival (OS) similar to Stage III patients, while Stage III patients with lower predicted risk showed OS comparable to Stage II. This approach demonstrates that the integration of clinical and radiomic features enhances the accuracy of pathological staging and offers more detailed information to refine treatment strategies for gastric cancer patients. Skeletal muscle and visceral adipose tissue radiodensity percentiles emerged as crucial determinants of patient outcomes.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"52 ","pages":"Article 101608"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143178785","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}

{"title":"Mapping the key players in Kawasaki disease; role of inflammatory genes and protein-protein interactions","authors":"Wael Hafez ,&nbsp;Feras Al-Obeidat ,&nbsp;Asrar Rashid ,&nbsp;Afsheen Raza ,&nbsp;Nouran Hamza ,&nbsp;Nesma Ahmed ,&nbsp;Marwa M. Abdeljawad ,&nbsp;Raziya Kadwa ,&nbsp;Abdelhameed Elmesery ,&nbsp;Muneir Gador ,&nbsp;Dina Khair ,&nbsp;Gihan Zina ,&nbsp;fatema Abdulaal ,&nbsp;Mina Wassef Girgiss ,&nbsp;Maha Abdelhadi ,&nbsp;Ahmed Abdelrahman ,&nbsp;Mahmad Anwar Ibrahim ,&nbsp;Mohamed El Sherbiny","doi":"10.1016/j.imu.2025.101645","DOIUrl":"10.1016/j.imu.2025.101645","url":null,"abstract":"<div><h3>Background</h3><div>Kawasaki disease <strong>(KD)</strong> is a complex acquired condition characterized by systemic blood vessel inflammation that primarily affects children under five years of age. It is clinically diagnosed as a syndrome, making it susceptible to misdiagnoses. Severe complications such as myocardial damage and coronary artery abnormalities can be fatal; thus, early diagnosis is critical for preventing disease progression. Currently, no specific diagnostic test can distinguish KD from viral or bacterial infections. Additionally, the molecular mechanisms underlying the disease remain unclear, hindering the development of targeted therapies.</div></div><div><h3>Objective</h3><div>This study aimed to identify the genetic patterns and molecular mechanisms associated with KD using a comprehensive gene expression analysis.</div></div><div><h3>Methods</h3><div>RNA sequencing and microarray genomic datasets were retrieved from the NCBI Gene Expression Omnibus (GEO). Four datasets (GSE68004, GSE63881, GSE73461, and GSE73463) were used for the final analysis. These datasets compared patients with KD to healthy controls, and patients with acute KD to convalescent patients. Differentially expressed genes (DEGs) were identified in the datasets. Enrichment analysis was conducted, followed by protein-protein interaction (PPI) network analysis to identify hub genes. Heatmaps were generated to visualize gene expression patterns.</div></div><div><h3>Results</h3><div>Eighteen hub genes were identified in the KD versus control comparison, whereas 20 hub genes were identified in the acute versus convalescent analysis. These genes play key roles in inflammation, cytokine storm, innate immune modulation, and endothelial damage.</div></div><div><h3>Conclusion</h3><div>This study provides valuable insights into the molecular mechanisms underlying KD, and identifies potential diagnostic biomarkers and therapeutic targets.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"56 ","pages":"Article 101645"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937873","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}

{"title":"EMG-based body–machine interface for targeted trunk muscle activation","authors":"Carolina Correia ,&nbsp;Andrea Bandini ,&nbsp;Silvestro Micera ,&nbsp;Sara Moccia","doi":"10.1016/j.imu.2025.101641","DOIUrl":"10.1016/j.imu.2025.101641","url":null,"abstract":"<div><div>Deficits in trunk control, commonly observed in individuals with neurological conditions, can significantly impair balance, posture, and functional movements. Body–machine interfaces (BoMIs) are promising tools for trunk rehabilitation, as they can provide real-time feedback on user movements and muscle activity, allowing for continuous monitoring and guidance during motor control training. However, research on BoMIs for trunk rehabilitation is limited, and current methods often lack precision in addressing trunk muscle deficits. This work introduces a BoMI that combines trunk electromyography (EMG) and motion data to selectively modulate trunk muscle activity during motor control tasks. The system utilizes machine learning to generate personalized trunk motion trajectories based on predefined EMG profiles. Each trajectory is displayed on a screen as a moving target, which users must follow by controlling the BoMI with their trunk movements. We hypothesize that by visually guiding users to track these generated trajectories, the BoMI could evoke the EMG patterns implicitly encoded within them. Tested with neurotypical individuals, the BoMI effectively elicited the desired trunk EMG profiles, achieving a mean similarity index of 0.82 ± 0.13, a correlation coefficient of 0.95 ± 0.03, and minimal timing mismatches. These results support the feasibility of using an EMG-based BoMI for precise trunk muscle training, which could potentially assist therapists in more efficiently monitoring and adjusting patients’ muscle engagement during interventions. Future work will focus on developing a control framework to dynamically adapt task difficulty to users’ needs, expanding the approach to include additional trunk muscles, and evaluating its translation to individuals with trunk muscle impairments.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"56 ","pages":"Article 101641"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922413","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}

{"title":"Fully automatic fossa ovalis segmentation from computed tomography images using deep neural network with atlas-based localization","authors":"Gakuto Aoyama ,&nbsp;Toru Tanaka ,&nbsp;Yukiteru Masuda ,&nbsp;Naoki Matsuki ,&nbsp;Ryo Ishikawa ,&nbsp;Masahiko Asami ,&nbsp;Kiyohide Satoh ,&nbsp;Takuya Sakaguchi","doi":"10.1016/j.imu.2025.101613","DOIUrl":"10.1016/j.imu.2025.101613","url":null,"abstract":"<div><h3>Background and objective</h3><div>Information on the location of the fossa ovalis (FO) is necessary for planning interventional procedures that require an inter-atrial septal (IAS) puncture. At present, this information is obtained manually from pre-procedural medical images, which is time consuming with limited reproducibility. In this paper, we propose a method to automatically segment the FO region from computed tomography (CT) images.</div></div><div><h3>Methods</h3><div>Our proposed method roughly crops CT images based on atlas information of the FO and heart chambers, and inputs the cropped CT images to a U-Net-based deep neural network (DNN) to segment the FO region. This method was evaluated by five-fold cross validation using 215 CT images with manually annotated FO regions, and its segmentation accuracy was compared to two previously reported methods based on thinness of the IAS wall and on simple DNN.</div></div><div><h3>Results</h3><div>The segmentation process was successful in all cases for the IAS-based method, but failed in 4 cases for the proposed method and in 30 cases for the DNN method due to irregular heart structure. For the segmentation accuracies of our proposed method, the IAS wall thinness-based method and DNN based-method, mean chamfer distances were 2.16 ± 1.43, 3.30 ± 1.37 and 2.66 ± 1.32 respectively, with the difference being statistically significant.</div></div><div><h3>Conclusions</h3><div>These results suggest that our proposed method can automatically segment the FO region more accurately with fewer failures.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"52 ","pages":"Article 101613"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143178834","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}

{"title":"Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI","authors":"Md Ismail Hossain Siddiqui ,&nbsp;Shakil Khan ,&nbsp;Zishad Hossain Limon ,&nbsp;Hamdadur Rahman ,&nbsp;Mahbub Alam Khan ,&nbsp;Abdullah Al Sakib ,&nbsp;S M Masfequier Rahman Swapno ,&nbsp;Rezaul Haque ,&nbsp;Ahmed Wasif Reza ,&nbsp;Abhishek Appaji","doi":"10.1016/j.imu.2025.101657","DOIUrl":"10.1016/j.imu.2025.101657","url":null,"abstract":"<div><div>Cervical cancer is a preventable yet life-threatening disease that claims hundreds of thousands of lives each year, particularly in low-resource settings where timely screening is scarce. Current Deep Learning (DL) approaches for automated cervical cytology classification encounter challenges such as class imbalance, computational inefficiency, and inadequate generalizability. This study proposes a novel CerviXEnsemble model that integrates multiple pre-trained DL architectures (Inception-ResNetV2, EfficientNet-B6, ResNet152, Inception-ResNetV2, EfficientNet-B6, DenseNet201, and NASNetMobile) as base learners, along with a dense-layer meta-learner that refines and consolidates predictions for improved robustness. Unlike traditional single-CNN models, our stacking ensemble approach utilizes diverse feature representations to enhance classification stability and generalization across multiple cytology datasets. To validate the model, we experimented with the Herlev and SIPaKMeD benchmark datasets in this study. Techniques like contrast enhancement and data augmentation were employed to optimize feature extraction. The model achieved state-of-the-art performance, attaining an accuracy of 99.38 % and an F1-score of 98.49 % on the Herlev dataset and an accuracy of 98.71 % and an F1-score of 97.53 % on SIPaKMeD. These performances are superior to previous studies in controlling class imbalance and providing stable predictions over different samples. Additionally, Explainable AI (XAI) techniques were incorporated to ensure transparent and interpretable predictions, aiding clinicians in their decision-making processes. An interpratable web application was developed for real-time Pap smear analysis to reduce the diagnostic workload for pathologists by identifying high-risk samples. This solution shows great promise for use in various healthcare settings, maintaining high diagnostic accuracy while requiring minimal computational resources, making it suitable for both urban hospitals and rural clinics.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"56 ","pages":"Article 101657"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138953","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}

{"title":"DeepPatchNet: A deep learning model for enhanced screening and diagnosis of oral cancer","authors":"Idriss Tafala ,&nbsp;Fatima-Ezzahraa Ben-Bouazza ,&nbsp;Aymane Edder ,&nbsp;Oumaima Manchadi ,&nbsp;Bassma Jioudi","doi":"10.1016/j.imu.2025.101658","DOIUrl":"10.1016/j.imu.2025.101658","url":null,"abstract":"<div><div>Oral cancer remains a serious global health challenge, significantly affecting patient survival and quality of life. While convolutional neural networks (CNNs) have historically dominated image classification tasks, recent advances suggest that transformer-based models may offer superior performance—albeit with high data and computational demands. In this study, we present <strong>DeepPatchNet</strong>, a novel deep learning architecture that integrates DeepLabV3+ and ConvMixer to address these limitations. Designed for histopathological image classification, DeepPatchNet provides a lightweight, interpretable, and high-performing solution. We evaluated the model on the NDB-UFES dataset (3763 images) and an independent H&amp;E-stained OSCC dataset (1020 images), benchmarking its performance against state-of-the-art models including Vision Transformers (ViTs)<span><span>[1]</span></span>, <span><span>[2]</span></span>, InceptionResNetV2, VGG19, and ConvNeXt. DeepPatchNet achieved superior performance with 86.71% accuracy, 86.80% precision, 86.71% recall, and an F1 score of 86.75%, outperforming all comparison models. Furthermore, the integration of Gradient-weighted Class Activation Mapping (Grad-CAM) enhances interpretability by visually highlighting diagnostically relevant features, addressing a key barrier to clinical adoption. While our results are promising, further validation in real-world clinical settings is needed. DeepPatchNet shows strong potential as a reliable decision support tool for early oral cancer detection and diagnosis.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"57 ","pages":"Article 101658"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306776","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}

{"title":"An explainable machine learning model for COVID-19 severity prognosis at hospital admission","authors":"Antonios T. Tsanakas ,&nbsp;Yvonne M. Mueller ,&nbsp;Harmen JG. van de Werken ,&nbsp;Ricardo Pujol Borrell ,&nbsp;Christos A. Ouzounis ,&nbsp;Peter D. Katsikis","doi":"10.1016/j.imu.2024.101602","DOIUrl":"10.1016/j.imu.2024.101602","url":null,"abstract":"<div><div>The coronavirus disease −2019 (COVID-19) pandemic has resulted in serious healthcare challenges. Due to its high transmissibility and hospitalization rates, COVID-19 has led to many deaths and imposed a considerable burden on healthcare systems worldwide. The development of prognostic approaches supporting clinical decisions for hospitalized patients can contribute to better management of the pandemic. We deploy several Artificial Intelligence (AI) techniques to derive COVID-19 severity classification prognosis models for unvaccinated patients hospitalized with mild symptoms using immunological biomarkers. The risk levels are precisely defined, targeting patients with uncertain prognostic trajectories. Forty molecular biomarkers were evaluated for their ability to predict the course of the illness. Seven biomarkers, including IL-6, IL-10, CCL2, LDH, IFNα, ferritin, and anti-SARS-CoV-2 N protein IgA antibody, emerge as the most significant early predictors for the prospective development of severe disease. After applying feature selection, we settled for two complete sets of five and three biomarkers to generate appropriate classification models. A Random Forest model with five biomarkers appears to be the most effective, with an accuracy of 0.92 for the external set. Yet, a Decision Tree model with just three biomarkers, and an accuracy of 0.84 for the external set, provides marginally lower yet robust performance and an explainable structure that broadly reflects our current understanding of disease severity. These findings suggest that the severity is influenced by a few key pathological processes. Therefore, a three-biomarker model that utilizes IL-6, IFNα, and anti-SARS-CoV-2 N protein IgA antibody levels may enhance clinical decision-making and patient triage at hospitalization, contributing to the successful management of the disease.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"52 ","pages":"Article 101602"},"PeriodicalIF":0.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142759656","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}

{"title":"Detecting ChatGPT in published documents: Chatbot catchphrases and buzzwords","authors":"Edward J. Ciaccio","doi":"10.1016/j.imu.2024.101516","DOIUrl":"https://doi.org/10.1016/j.imu.2024.101516","url":null,"abstract":"","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"16 30","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141055460","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}

{"title":"EEG-based functional connectivity analysis of brain abnormalities: A review study","authors":"Nastaran Khaleghi ,&nbsp;Shaghayegh Hashemi ,&nbsp;Mohammad Peivandi ,&nbsp;Sevda Zafarmandi Ardabili ,&nbsp;Mohammadreza Behjati ,&nbsp;Sobhan Sheykhivand ,&nbsp;Sebelan Danishvar","doi":"10.1016/j.imu.2024.101476","DOIUrl":"https://doi.org/10.1016/j.imu.2024.101476","url":null,"abstract":"<div><p>Several imaging modalities and many signal recording techniques have been used to study the brain activities. Significant advancements in medical device technologies like electroencephalographs have provided conditions for recording neural information with high temporal resolution. These recordings can be used to calculate the connections between different brain areas. It has been proved that brain abnormalities affect the brain activity in different brain regions and the connectivity patterns between them would change as the result. This paper studies the electroencephalogram (EEG) functional connectivity methods and investigates the impacts of brain abnormalities on the brain functional connectivities. The effects of different brain abnormalities including stroke, depression, emotional disorders, epilepsy, attention deficit hyperactivity disorder (ADHD), autism, and Alzheimer's disease on functional connectivity of the EEG recordings have been explored in this study. The EEG-based metrics and network properties of different brain abnormalities have been discussed to have a comparison of the connectivities affected by each abnormality. Also, the effects of therapy and medical intake on the EEG functional connectivity network of each abnormality have been reviewed.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"47 ","pages":"Article 101476"},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824000327/pdfft?md5=f4cca409c15776d628c46f1cedf6de45&pid=1-s2.0-S2352914824000327-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140351321","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}