Healthcare Technology Letters最新文献

{"title":"Gamified Digital Solutions for Tinnitus Health Literacy: The Erasmus+ Project TinWise","authors":"Evangelos Paraskevopoulos,&nbsp;Marios Avraamides,&nbsp;Panagiotis Bamidis,&nbsp;Christian Dobel,&nbsp;Christos I. Ioannou,&nbsp;Cosima Lukas,&nbsp;Birgit Mazurek,&nbsp;Andria Shimi,&nbsp;Efstathios Sidiropoulos,&nbsp;Kurt Steinmetzger,&nbsp;Eleftheria Vellidou","doi":"10.1049/htl2.70072","DOIUrl":"10.1049/htl2.70072","url":null,"abstract":"<p>Tinnitus is a common auditory symptom – sound perceived without an external source. Chronic tinnitus affects about 65 million adults in the EU, often impairing quality of life through distress, sleep problems, anxiety, and depression. Yet, management remains inconsistent across Europe due to patient heterogeneity and lack of standardised care. Health literacy is increasingly recognised as key to empowering patients in self-management and reducing burden. The Erasmus+ project <i>TinWise</i> addresses this by creating a gamified health literacy platform for tinnitus patients and educating healthcare professionals on digital self-help strategies. Building on <i>Tin-TRAC</i>, which developed an open-access e-learning platform, <i>TinWise</i> integrates gamification to enhance motivation, engagement, and knowledge retention. The project applies the OPHELIA framework to optimise literacy strategies and follows the ASPIRE learning construct for co-creating content. <i>TinWise</i> will deliver interactive, co-created digital games to promote self-help literacy, an AI-powered chatbot for real-time guidance, and a patient-linking service to enhance community support. It also aims to train healthcare professionals using reusable learning objects, supporting the integration of digital tools into tinnitus care. Through modern technology and inclusive design, <i>TinWise</i> supports European priorities in digital education, patient empowerment, and healthcare innovation, ultimately improving tinnitus care and outcomes across Europe.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13266412/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148266217","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":"Effect of Technology-Supported Measures Used for Care Transition Decisions for Chronic Disease Patients: A Systematic Review and Meta-Analysis","authors":"Despoina Petsani,&nbsp;Dorra-Rakia Allegue,&nbsp;Christina Plomariti,&nbsp;Eva Kehayia,&nbsp;Sara Ahmed,&nbsp;Michael Doumas,&nbsp;Panagiotis Bamidis,&nbsp;Evdokimos Konstantinidis","doi":"10.1049/htl2.70089","DOIUrl":"10.1049/htl2.70089","url":null,"abstract":"<p>To evaluate the impact of digital interventions used to support care transitions on health outcomes and hospital costs compared with usual clinical care for patients with chronic diseases, we conducted a systematic review and meta-analysis. A systematic search of Cochrane, ACM, Embase, MEDLINE, and PsycINFO was performed from database inception until 6 October 2023. Meta-analysis was conducted for hospitalisation outcomes, mortality rates, and cost-effectiveness, while quality of life, mobility and qualitative outcomes were summarised narratively. Following full-text screening, 34 studies were eligible for review. After excluding eight studies due to a high risk of bias, the final analysis included 25 studies comprising a total of 29,724 patients. The meta-analysis revealed a marginal but statistically significant reduction in hospitalisation rates (SMD = −0.07, 95% CI −0.13 to −0.01, <i>p =</i> 0.02) and a statistically significant reduction in mortality (OR = 0.71, 95% CI 0.58 to 0.85, <i>p =</i> 0.0003), favouring digital interventions. Digitally supported transitional care interventions suggest a potential trend toward supporting quality of life, although evidence was not conclusive. Future research should focus on digitalising established care transition models and evaluating technology's added value for effectiveness and user satisfaction.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13238818/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148200381","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":"Interpretable Model for Clinical Use in Left Atrial Appendage Segmentation via an Optimised Deformable-Attention U-Net With Spatial–Channel Fusion","authors":"Ali Pakizeh Moghadam,&nbsp;Javad Haddadnia","doi":"10.1049/htl2.70088","DOIUrl":"10.1049/htl2.70088","url":null,"abstract":"<p>Accurate segmentation of the left atrial appendage (LAA) is essential for device occlusion planning in atrial fibrillation patients who cannot receive anticoagulation. Yet 3D echocardiography suffers from low signal-to-noise ratio, anisotropy and marked morphological variability, increasing overfitting risk and reliance on operator-dependent post-processing. Existing U-Net variants capture local detail but often miss long-range dependencies, while transformers improve context at the cost of boundary precision; semi-automated pipelines still require experts. We present a fully automated, AERO-optimised DAT-DAD U-Net with SE-augmented skip fusion. Deformable attention transformers (DAT) provide content-adaptive global context, while a dual attention with deformable convolution (DAD) block refines rims and addresses shape irregularities; spatial-channel squeeze-and-excitation improves multi-scale fusion. Hyperparameters are selected by AERO, a surrogate- and multi-fidelity-driven optimiser balancing exploration and exploitation under limited data in practice. Validation used a 22-patient 3D echocardiography cohort from King's College Hospital. Volumes were reformatted into axial 2D slices, trained with on-the-fly anatomy-preserving augmentation and evaluated using strict patient-wise splits. The model achieved Dice 0.8925 ± 0.0144, IoU 0.8026 ± 0.0156 and HD95 9.14 ± 1.96 mm. Ablations confirmed additive gains from DAT, DAD and SE, with faster convergence and a lower error floor, supporting operator-light, time-sensitive LAA workflows.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13319416/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148370173","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":"Bibliometric Trends in the Integration of Computer Vision With Healthcare","authors":"Rakhi Issrani,&nbsp;Hafiz Muhammad Zeeshan,&nbsp;Abid Iqbal,&nbsp;Shahzad Ahmad,&nbsp;Shazia Iqbal,&nbsp;Namdeo Prabhu,&nbsp;Muhammad Nadeem Baig","doi":"10.1049/htl2.70085","DOIUrl":"10.1049/htl2.70085","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <p>Computer vision, enabled by machine learning and image processing techniques, plays a crucial role in healthcare by facilitating the analysis of medical images such as magnetic resonance imaging, computed tomography and X-rays. It supports disease diagnosis, treatment planning, telemedicine and remote patient monitoring. Despite rapid growth, research in this field remains fragmented, making it difficult to comprehensively understand its evolution and research patterns. This study aimed to systematically analyse global research trends in computer vision applications in healthcare using bibliometric methods. A bibliometric analysis was conducted on 1023 publications retrieved from the Web of Science (Wos) database published between 2000 and 2022. Scientific output, citation patterns, leading journals, authors, institutions, countries, funding agencies and research themes were analysed using VOSviewer, Biblioshiny and ScientoPy. The annual scientific output showed a consistent upward trend, with a peak in 2021. IEEE Access emerged as the most productive journal (90 publications), while IEEE transactions on medical imaging was the most cited source. China led in publication output and international collaboration, followed by the United States. Keyword analysis revealed dominant themes such as deep learning, image segmentation, classification and medical imaging. This bibliometric analysis provides a comprehensive overview of the intellectual structure, research hotspots and collaborative patterns in computer vision–based healthcare research. The findings offer valuable insights for researchers, clinicians and policymakers and identify potential directions for future investigations.</p>\u0000 </section>\u0000 </div>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13174573/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147964543","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-Based Depression Recognition With Preserved Efficacy From Compressed EEG Signals Using Wavelet Transform and Adaptive Filtering","authors":"Marjan Rezakhani Taleghani,&nbsp;Hadi Grailu","doi":"10.1049/htl2.70084","DOIUrl":"10.1049/htl2.70084","url":null,"abstract":"<p>Electroencephalogram (EEG) signals are critical for diagnosing neurological disorders like depression but require substantial storage, posing challenges for telemedicine. This paper proposes a novel lossy compression method integrating two-dimensional zigzag and spiral rearrangement, wavelet transform (bior4.4), and adaptive filtering to minimise storage while preserving depression recognition accuracy. Using the Hospital University Sains Malaysia (HUSM) dataset (34 depressed, 30 healthy subjects), EEG signals were converted into 2D matrices, compressed with four wavelet encoders (SPIHT, STW, EZW, LVL-MMC), and reconstructed. A feedforward artificial neural network (ANN) with 80 features (relative wavelet energy and entropy) classified depressed and healthy individuals. The combination of zigzag and STW methods achieved a compression ratio (CR) of 89.30, a percentage root-mean-square distortion (PRD) of 0.23, and a peak signal-to-noise ratio (PSNR) of 58.80 dB, with depression recognition accuracy of 90.2%. Classification was performed on both original and reconstructed signals to evaluate the effect of compression on diagnostic performance. Notably, compressed signals occasionally outperformed original signals, likely due to noise reduction. This method offers a robust solution for efficient EEG storage and accurate depression diagnosis in resource-constrained settings.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13158272/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147933789","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":"Parameter-Efficient Deep Learning Models for Vital Sign Estimation From PPG","authors":"Taha Samavati,&nbsp;Mahdi Farvardin,&nbsp;Aboozar Ghaffari","doi":"10.1049/htl2.70083","DOIUrl":"10.1049/htl2.70083","url":null,"abstract":"<p>Photoplethysmography (PPG) enables non-invasive estimation of vital signs across a range of sensors, from wrist wearables and clinical monitors to smartphone cameras. We present parameter-efficient, end-to-end deep models for heart rate (HR), blood oxygen saturation (<span></span><math>\u0000 <semantics>\u0000 <msub>\u0000 <mi>SpO</mi>\u0000 <mn>2</mn>\u0000 </msub>\u0000 <annotation>${rm SpO}_{2}$</annotation>\u0000 </semantics></math>) and respiratory rate (RR) estimation. These models operate directly on PPG signals and integrate preprocessing as a layer. Our family of fully convolutional architectures includes a baseline FCN, a residual FCN, a ConvNeXt-inspired FCN and a compact DCT-based variant. These models achieve strong cross-dataset performance while using only 3.3K–53K parameters. On PPG-DaLiA, the best performing model achieves 6.07 <span></span><math>\u0000 <semantics>\u0000 <mo>±</mo>\u0000 <annotation>$pm$</annotation>\u0000 </semantics></math> 2.70 bpm MAE for HR. In HR, <span></span><math>\u0000 <semantics>\u0000 <msub>\u0000 <mi>SpO</mi>\u0000 <mn>2</mn>\u0000 </msub>\u0000 <annotation>${rm SpO}_{2}$</annotation>\u0000 </semantics></math> and RR tasks on the BIDMC dataset, the best-performing method achieves error rates of 2.2 bpm, 3.14% and 1.49 breaths per minute, respectively. We also release MTHS, a smartphone-based vital-sign dataset comprising 62 fingertip-PPG recordings (35 men and 27 women) with 1-Hz HR and <span></span><math>\u0000 <semantics>\u0000 <msub>\u0000 <mi>SpO</mi>\u0000 <mn>2</mn>\u0000 </msub>\u0000 <annotation>${rm SpO}_{2}$</annotation>\u0000 </semantics></math> annotations. Additionally, we demonstrate practical feasibility via on-device deployment using TFLite on smartphones. These results show that compact, fully convolutional and DCT-based designs provide accurate, generalizable, and deployment-ready PPG vital-sign estimators across sensors and datasets.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13158377/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147934088","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":"Correction to ‘In-Vivo Hand Mass Determination and an Anthropometric Investigation on Segment Length and Radius for Prosthetic Segment Design’","authors":"","doi":"10.1049/htl2.70086","DOIUrl":"10.1049/htl2.70086","url":null,"abstract":"<p>P. Tsakonas, N. D. Evans, J. Hardwicke, S. Homer-Vanniasinkam, and M. J. Chappell, “In-Vivo Hand Mass Determination and an Anthropometric Investigation on Segment Length and Radius for Prosthetic Segment Design,” <i>Healthcare Technology Letters</i> 13, no. 1 (2026): e70078, https://doi.org/10.1049/htl2.70078</p><p>Figure 1 was depicting an anatomically incorrect human hand skeleton, and the arrows indicating the landmarks for measuring segment diameters were not shown in the published version. The revised Figure 1 can be seen below, which has been adapted from [1].</p><p>[1] S. W., Wolfe, W. C., Pederson, S. H., Kozin, M. S. Cohen, <i>Green's Operative Hand Surgery</i>, 7th ed. (Elsevier Health Sciences, 2016).</p><p>We apologize for this error.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13154910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147869768","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":"A Secure and Efficient Framework for ECG Signal Digitization and Encryption for Internet of Medical Things Applications","authors":"Nader Mahmoud,&nbsp;Shymaa S. Shaban","doi":"10.1049/htl2.70082","DOIUrl":"10.1049/htl2.70082","url":null,"abstract":"<p>The Internet of Medical Things (IoMT) is transforming healthcare through smart devices, real-time monitoring, and cloud-based data exchange. Electrocardiogram (ECG) signals are crucial in diagnosing cardiovascular conditions; however, their sensitivity is still a major challenge for secure transmission and storage. This paper presents a novel content-based encryption framework tailored for ECG data. Unlike conventional approaches that process either raw signals or images separately, the proposed method first extracts accurately ECG waveforms from 2D images while handling noisy or overlapping traces through a dedicated preprocessing and segmentation pipeline. A two-layer chaotic scheme is then employed to encrypt the extracted 1D signals: the Arnold Cat map (ACM) for spatial scrambling and Double Random Phase Encoding for frequency-domain transformation. These cryptographic modules can also operate directly on native digital ECG signals and integrate seamlessly with paper-based ECG datasets, ensuring broad applicability across acquisition formats. Experimental results on a 12-lead ECG dataset demonstrate high digitization accuracy (Structural Similarity Index = 0.94), fast execution (0.0036 s), strong encryption (entropy = 7.3, correlation = 0.0006), and perfect signal recovery (PSNR = ∞). Overall, the framework provides a secure and efficient solution for IoMT-driven healthcare systems, outperforming existing ECG encryption methods across standard evaluation metrics.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13135227/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147821740","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":"Systematic Review of Explainable Artificial Intelligence for Epileptic Seizure Onset Early Warning: Towards Responsible Artificial Intelligence","authors":"Daraje Kaba Gurmessa,&nbsp;Kula Kekeba Tune,&nbsp;Worku Jimma","doi":"10.1049/htl2.70081","DOIUrl":"10.1049/htl2.70081","url":null,"abstract":"<p>A substantial amount of literature has been published on epileptic seizures. However, adequate evidence is still lacking to demonstrate that utilising explainable artificial intelligence for epileptic seizures can ensure an individual's safety. Furthermore, there is a need to define the fundamental challenges and opportunities present in the current state-of-the-art solutions and guide efforts towards responsible artificial intelligence. To identify fundamental challenges and opportunities in the existing state-of-the-art solutions available for explainable artificial intelligence-based epileptic seizure onset early warning: towards responsible artificial intelligence. The PRISMA checklist was utilised to develop this report. Papers were extracted from original articles and prior conference studies published in reputable databases such as PubMed, IEEE Xplore, ScienceDirect, Scopus and Google Scholar from January 2019 to 17 November 2024. Rayyan's online platform was used to identify duplicates, inclusions and exclusions of papers. This systematic review protocol was registered with the PROSPERO database. The included papers were assessed based on Microsoft's Responsible Artificial Intelligence template. The Responsible AI Impact Assessment Template, Principle 3 (transparency and explainability), determined a high-risk rating. A total of 26 studies are included based on the established inclusion and exclusion criteria. This study investigated 14.29% of responsible artificial intelligence principles applied in at least one paper with a high-risk rate. The results indicate that to transform researched solutions into practical applications, epileptic monitoring applications should be tested within the eight principles set by Microsoft. The black box explanation lacks insight into the deep internal features and operational methods, suggesting that further investigation is necessary. Systematic Review Registration ID: CRD42024544.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13135226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147821783","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":"Federated Learning for Thoracic Disease Classification Using Convolutional Neural Networks and Differential Privacy","authors":"Muhammad Zulqarnain,&nbsp;Syed Jawad Hussain,&nbsp;Muhammad Zeeshan Aslam,&nbsp;Ahsan Fiaz,&nbsp;Muhammad Islam","doi":"10.1049/htl2.70080","DOIUrl":"10.1049/htl2.70080","url":null,"abstract":"<p>Early diagnosis of thoracic diseases using chest x-ray imaging remains a critical challenge, particularly in resource-constrained healthcare environments where data sharing is restricted due to privacy concerns. Federated learning (FL) offers a decentralized solution by enabling collaborative model training without sharing sensitive patient data. However, integrating privacy-preserving mechanisms such as differential privacy (DP) introduces additional challenges related to performance degradation and computational overhead. In this study, we present a unified FL framework for multi-label thoracic disease classification using multiple convolutional neural network (CNN) architectures, including ResNet50, DenseNet169, EfficientNet variants and MobileNetV3. Unlike prior studies focusing on single-model evaluation, this work provides a controlled comparative analysis under identical FL settings and investigates the impact of client scalability (5–10 clients) on model performance. Furthermore, we conduct a comprehensive empirical analysis of the privacy utility trade-off by integrating DP with varying privacy budgets (<i>ε</i> = 1, 15 and 30). Experimental results on the CheXpert and NIH Chest x-ray14 datasets demonstrate that the proposed EfficientNet-B3-based federated model achieves a mean AUC of 0.8027, while maintaining robustness across decentralized settings. The integration of DP leads to a predictable reduction in performance, with mean AUC ranging from 0.60 to 0.64, highlighting the inherent trade-off between privacy and diagnostic accuracy. The findings emphasize the practical viability of FL for privacy-sensitive medical imaging applications and provide insights into model selection, scalability and privacy configuration for real-world deployment. The source code for this study is publicly accessible at https://github.com/Zulqarnain8-8/FEDERATED_LEARNING_FOR_THORACIC_DISEASE_CLASSIFICATION.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"13 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13135224/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147821806","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}