Informatics in Medicine Unlocked最新文献

{"title":"Dynamic time warping for enhanced fNIRS-based motor assessment during lower limb kinematics","authors":"Murad Althobaiti,&nbsp;Nouf Jubran AlQahtani,&nbsp;Mahbubunnabi Tamal","doi":"10.1016/j.imu.2025.101684","DOIUrl":"10.1016/j.imu.2025.101684","url":null,"abstract":"<div><div>Understanding cortical activation during lower limb movement is crucial for advancing neurorehabilitation, motor control research, and brain-computer interface (BCI) applications. Functional near-infrared spectroscopy (fNIRS) offers a non-invasive approach to monitoring hemodynamic changes associated with movement-related brain activity. This study investigates fNIRS channel activation patterns during lower limb kinematics to identify key motor regions involved in movement execution, utilizing both Pearson Correlation (PC) and Dynamic Time Warping (DTW) for signal analysis. Nine participants performed six controlled leg movements in a single session, and then repeated the same movements in a subsequent session after a short break, while fNIRS data were recorded from the motor cortex. Signal processing involved motion artifact correction, normalization, and statistical analysis to assess activation consistency. PC and DTW were employed to compare reference and observed signal variations. While DTW exhibited lower average reproducibility than PC, it was chosen for final analysis due to its sensitivity to temporal dynamics and non-linear relationships in the fNIRS signals. The results highlight that fNIRS channels 33, 34, and 37 consistently exhibit reproducible activation patterns associated with lower limb movement. These findings support the effectiveness of fNIRS in capturing neural dynamics related to lower limb kinematics, and demonstrate the utility of DTW for identifying subtle but significant task-related activations. Future research should include larger sample sizes and more varied movement tasks to further validate the reliability of fNIRS-based motor assessments and explore the potential of DTW in real-time motor control applications.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"58 ","pages":"Article 101684"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144907899","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":"Spatiotemporal chest wall movement analysis using depth sensor imaging for detecting respiratory asynchrony","authors":"Masaru Mitsuya ,&nbsp;Hiroki Nishine ,&nbsp;Hiroshi Handa ,&nbsp;Masamichi Mineshita ,&nbsp;Masaki Kurosawa ,&nbsp;Tetsuo Kirimoto ,&nbsp;Shohei Sato ,&nbsp;Takemi Matsui ,&nbsp;Guanghao Sun","doi":"10.1016/j.imu.2025.101619","DOIUrl":"10.1016/j.imu.2025.101619","url":null,"abstract":"<div><h3>Background and objective</h3><div>This study aimed to enhance point-of-care pulmonary function tests by developing a novel method for the spatiotemporal analysis of chest wall movements using a sequence of depth sensor images.</div></div><div><h3>Methods</h3><div>The proposed method employs singular value decomposition (SVD) to extract features from respiratory waveforms, which are then used to cluster pixels while preserving high resolution. The initial validation using simulated thoracic movement data confirmed the validity of the method. Further validation with clinical data capturing the chest wall movements of a patient undergoing interventional bronchology for a right bronchial tumor demonstrated the ability of this method to detect respiratory asynchrony.</div></div><div><h3>Results</h3><div>A phase lag of 867 ms was observed between the left and right sides of the rib cage preoperatively along with notable amplitude differences. These asynchronies resolved postoperatively. These results were consistent with the pulmonary pathophysiology, underscoring the clinical relevance of this method. The proposed system, integrated into an iOS app for an iPhone, is user-friendly and noninvasive and has the potential to become a valuable tool for the real-time assessment of interventional outcomes.</div></div><div><h3>Conclusions</h3><div>The novel method can be applied to various pulmonary diseases to detect the regional ventilation distribution. The method establishes a new generic framework for clinical studies of chest wall motion and pathophysiology.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"53 ","pages":"Article 101619"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143103203","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":"Machine learning approach to study drug effects and identification of signals from symptomatic and asymptomatic mutation carries using iPSC-derived cardiomyocytes","authors":"Martti Juhola ,&nbsp;Henry Joutsijoki ,&nbsp;Kirsi Penttinen ,&nbsp;Katriina Aalto-Setälä","doi":"10.1016/j.imu.2025.101631","DOIUrl":"10.1016/j.imu.2025.101631","url":null,"abstract":"<div><div>Earlier it has been found that peak data of calcium transient signals originating from human induced pluripotent stem cell-derived cardiomyocytes are possible to be used to study how machine learning methods can be applied to separate which cells respond to a drug. Beating behavior of induced pluripotent stem cell derived cardiomyocytes (iPSC-CMs) from a symptomatic individual and an asymptomatic individual carrying a mutation for Brugada syndrome was analyzed with Ca²⁺ imaging method. Using machine learning methods, it is studied whether it is possible to classify the current peak data successfully and whether differences in the two mutant cell lines could be observed. We applied more machine learning methods than before. Baseline signals were first recorded and they were then exposed to adrenaline and these to an antiarrhythmic drug flecainide which should provoke the disease phenotype. Calcium transient signals derived from induced pluripotent stem cell-derived cardiomyocytes were used for all computational analyses executed. Good classification results were generated with effective machine learning methods. Various test situations were applied to study how different parts of data can be separated to ensure their differences. Good results were gained that support the target so that it is possible to analyze whether the drug impacted on iPSC-CMs. It is also possible to separate which cells were affected by the drug and which were not affected. An important finding was that there were significant differences between calcium transient signals data originated from control subjects and patients and also between responses of the cells from symptomatic and asymptomatic individuals.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"54 ","pages":"Article 101631"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579488","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":"Explainable AI for early malaria detection using stacked-LSTM and attention mechanisms","authors":"Adil Gaouar ,&nbsp;Souaad Hamza Cherif ,&nbsp;Abdellatif Rahmoun ,&nbsp;Mostafa El Habib Daho","doi":"10.1016/j.imu.2025.101667","DOIUrl":"10.1016/j.imu.2025.101667","url":null,"abstract":"<div><div>Malaria remains a global public health challenge, affecting more than 247 million people and causing 619,000 deaths worldwide in 2024 (according to WHO). Rapid diagnosis is essential for effective treatment and to improve patients’ chances of survival. In this study, we propose an interpretable deep learning framework for accurate malaria diagnosis using blood smear images. Also, We evaluate and compare several baseline deep learning (DL) models (fundamentals), customized VGG-16 and VGG-19, as well as newer DL models such as Vision Transformer (ViT) and MobileNet, and, for the first time, a stacked long-short-term memory network (stacked-LSTM) with an attention mechanism for automatic detection of malaria from blood smear images. These models were trained and validated on a publicly available dataset of over 27.000 labeled blood smear images. The comparative and statistical study conducted in this research showed us that the proposed Stacked-LSTM model with attention mechanism outperformed all other approaches, achieving a classification accuracy (0.9912), sensitivity, specificity, precision, F1 score (0.9911), and area under the curve (AUC) superior to all other models. Despite their solid performance, these models are often considered ”black boxes” due to their lack of transparency in the decision-making process, which poses significant challenges in medical applications and fields where human life is at stake. To address this, we have integrated explainable AI (XAI) techniques, namely Grad-CAM and LIME, to improve the model’s interpretability. Our results demonstrate the complementary value of combining high-performance deep learning models with XAI methods to enhance trust and certainty in AI-assisted medical diagnosis, suggesting that our model can support early and interpretable malaria detection in clinical environments.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"57 ","pages":"Article 101667"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632161","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":"Machine learning-based classification of medication adherence among patients with noncommunicable diseases","authors":"Wellington Kanyongo ,&nbsp;Absalom E. Ezugwu ,&nbsp;Tsitsi Moyo ,&nbsp;Jean Vincent Fonou Dombeu","doi":"10.1016/j.imu.2024.101611","DOIUrl":"10.1016/j.imu.2024.101611","url":null,"abstract":"<div><div>Non-adherence to medication among individuals with non-communicable diseases (NCDs) leads to increased morbidity, mortality, and healthcare costs. The integration of electronic drug prescription and dispensation systems enables comprehensive analysis of medication adherence (MA). Patient-level and medical claims data for 8141 diabetic and hypertensive patients in Harare, Zimbabwe, were analysed. Non-adherence was defined as medication refills falling below 75 % of the intended 12 monthly claims, while adherence required at least 75 % of the refills. Classification employed multiple machine learning algorithms, including SVM, KNN, DT, Naïve Bayes, DNN, LR, and RF in Python 3.11.3. Significant variables for MA were identified through the Random Forest (RF) feature importance mechanism and the information gain technique. These included the annual quantity of medical supplies, annual claim amount, patient age, wellness program subscription, medical aid cover, contribution towards medical aid cover, comorbidity, diagnosis, hospital cover type, complications development, gender, and medical aid scheme. The total units of medical supplies dispensed annually emerged as the most significant predictor of MA. Considering the 8-feature subset, which consistently produced the most robust machine learning models, the classification accuracy of the ML classifiers ranged from 84.9 % to 88.2 %, while the AUC values varied between 0.857 and 0.934. RF, an ensemble learning technique, was the most robust classifier, achieving 88.2 % accuracy, an AUC of 0.935, and superior precision, recall, and F1-score. This model shows promise as a prognostic tool for enhancing MA, aiding in identifying adherence levels among patients. These findings contribute to addressing disparities in medication refilling and adherence rates among patients with NCDs. The ML model holds potential for the development of intelligent MA and intervention applications to improve patient adherence to medication in the chronic disease domain.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"52 ","pages":"Article 101611"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143178787","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":"An interpretable XGBoost model for risk prediction of progression from sepsis-associated acute kidney injury to chronic kidney disease","authors":"Yingying Lin ,&nbsp;Jingqi Gao ,&nbsp;Linfang Chen ,&nbsp;Yixiao Hong ,&nbsp;Min Li ,&nbsp;Peiling Chen ,&nbsp;Xiuling Shang","doi":"10.1016/j.imu.2025.101685","DOIUrl":"10.1016/j.imu.2025.101685","url":null,"abstract":"<div><h3>Objective</h3><div>To develop an interpretable machine learning (ML) model for predicting the risk of progression from sepsis-associated acute kidney injury (SA-AKI) to chronic kidney disease (CKD) guiding early stratified interventions.</div></div><div><h3>Methods</h3><div>Using data from 1315 SA-AKI patients [Medical Information Mart for Intensive Care IV (MIMIC-IV) database], we constructed an extreme gradient boosting (XGBoost) model with SHapley Additive exPlanations (SHAP) interpretability. Performance was evaluated by discrimination, calibration, and clinical utility [decision curve analysis (DCA)].</div></div><div><h3>Results</h3><div>CKD incidence was 36.7 % (median onset: 7.6 months). The XGBoost model achieved: superior discrimination [training area under the curve (AUC) 0.920; validation AUC 0.951 versus Sequential Organ Failure Assessment (SOFA) renal 0.616 and logistic regression (LR) 0.822], robust calibration, and clinical applicability. SHAP identified actionable thresholds (age &gt;65, maximum serum creatinine &gt;0.9 mg/dl) for early intervention. Feature stability analysis revealed a stage-dependent coefficient drift for serum creatinine (Δβ = +0.84), reflecting dynamic pathophysiology. Crucially, the model provides clinically interpretable outputs without requiring SHAP expertise, enabling seamless integration into workflows.</div></div><div><h3>Conclusion</h3><div>Our model delivers personalized, interpretable CKD risk alerts for SA-AKI patients, empowering clinicians to stratify follow-up care. External validation is warranted to confirm generalizability.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"58 ","pages":"Article 101685"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144931604","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":"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":"Social media for professional outreach: A study of Saudi dental societies' instagram usage","authors":"Khalifa S. Al-Khalifa ,&nbsp;Taif A. Alsuroor ,&nbsp;Shog A. Alafaleq ,&nbsp;Aminah M. Alsayoud ,&nbsp;Mohammed S. Alqattan ,&nbsp;Mahmoud H. Al-Johani ,&nbsp;Hassan S. Halawany","doi":"10.1016/j.imu.2025.101680","DOIUrl":"10.1016/j.imu.2025.101680","url":null,"abstract":"<div><h3>Aim</h3><div>This study aimed to analyze the Instagram posting patterns of Saudi dental societies to understand engagement trends, content focus, and audience interaction.</div></div><div><h3>Methods</h3><div>A cross-sectional, observational study was conducted from February 2023 to February 2024 using publicly available data from the Instagram accounts of officially licensed Saudi dental societies. Collected data included posting frequency, thematic content, language, and engagement metrics (likes, comments, mentions, and hashtags). Posts were categorized into themes like continuing education, research, and community outreach.</div></div><div><h3>Results</h3><div>A cyclical engagement pattern was observed, with increased activity around conferences, particularly in January and October. “Announcements” was the most frequent thematic classification (59.6 %). While “continuing education” was the most frequent content theme (77.6 %). English was predominantly used by top performing dental societies, suggesting a focus on international outreach. In contrast, other societies primarily used Arabic. Notably, reels achieved higher engagement than other post types, highlighting the importance of dynamic content.</div></div><div><h3>Conclusion</h3><div>The study highlights the strategic use of Instagram by Saudi dental societies and identifies opportunities to expand content related to research and oral health. Future strategies could improve engagement through diversified content, cross-platform promotion, and targeted hashtag use, fostering a more informed and engaged digital community.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"58 ","pages":"Article 101680"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780451","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":"Towards an explainable machine learning model to reduce readmission risks for diabetes patients","authors":"Changfeng Guo ,&nbsp;Haoran Zhou ,&nbsp;Ivan Miguel Pires ,&nbsp;Paulo Jorge Coelho ,&nbsp;Runzhe Tong ,&nbsp;Farnaz Farid","doi":"10.1016/j.imu.2025.101686","DOIUrl":"10.1016/j.imu.2025.101686","url":null,"abstract":"<div><h3>Objective:</h3><div>Hospital readmission of Diabetes patients is a persistent burden on the healthcare industry. Artificial Intelligence (AI) based Machine Learning (ML) techniques offer the potential to predict readmission rates and related risk features for diabetic patients. However, complex machine learning-based solutions are often not explainable and hard to understand for the relevant parties. To this end, this study designs and implements an explainable model to predict readmission rates and identify the risk factors associated with readmission in patients with diabetes.</div></div><div><h3>Methods:</h3><div>The model employs various explainable visualization techniques, including the permutation importance plot, partial dependence plot (PDP), SHapley Additive exPlanations (SHAP), and interpretable classifiers on a publicly available dataset from US hospitals.</div></div><div><h3>Results:</h3><div>The bagging random forest model yields the best results, achieving 89% accuracy and 67% precision.</div></div><div><h3>Conclusion:</h3><div>The explainability visualization techniques reveal that the number of inpatient admissions and emergency visits in a year is the two most critical risk factors for the readmission rate of diabetic patients.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"58 ","pages":"Article 101686"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099555","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":"Benchmarking vision-language models for brain cancer diagnosis using multisequence MRI","authors":"Ahmed T. Elboardy ,&nbsp;Ghada Khoriba ,&nbsp;Mohammad al-Shatouri ,&nbsp;Mohammed Mousa ,&nbsp;Essam A. Rashed","doi":"10.1016/j.imu.2025.101692","DOIUrl":"10.1016/j.imu.2025.101692","url":null,"abstract":"<div><div>The rapid adoption of Large Language Models (LLMs) in various fields has prompted growing interest in their application within the healthcare ecosystem. In particular, Vision Language Models (VLMs) offer potential for generating radiology reports. This study aims to perform a comprehensive evaluation of state-of-the-art VLMs with varying sizes and domain specializations to determine their effectiveness in generating radiology reports for MRI scans of brain cancer patients. We conducted a comparative analysis of several open-source VLMs, including Qwen2-VL, Meta-Vision 3.2, PaliGemma 2, DeepSeek-VL2, Nvidia open-source models, and medical-specific VLMs. Each model family was assessed across small, medium, and large variants. A benchmark dataset comprising multisequence brain MRI scans of cancer patients was curated with expert annotation and guidance from board-certified radiologists. The models were evaluated on their ability to generate complete radiology reports, using objective metrics, reasoning models (R1 and o1 models that judged the AI generations based on completeness, conciseness, and correctness), and human experts. Model performance varied significantly across size and type. Among large-scale models, Meta-Vision 3.2 90B achieved the highest scores with o1 of 70.19% and R1 of 68.09%. In the medium category, Meta-Vision 11B and DeepSeek-VL-2-27B outperformed others, achieving o1 scores of 57.56% and 53.44%, and R1 scores of 51.06% and 52.75%, respectively. For smaller models, Qwen2-VL-2B demonstrated the best performance (o1: 23.88%, R1: 23.25%). To our knowledge, this is the first study evaluating VLMs for generating comprehensive radiology reports for brain cancer diagnosis using multisequence MRI. Our findings reveal substantial performance differences based on model size and specialization, offering important guidance for future development and optimization of medical VLMs to support diagnostic radiology workflows.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"58 ","pages":"Article 101692"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099558","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}