Physiological measurement最新文献

{"title":"Diagnosing anaemia via smartphone colorimetry of the eye in a population of pregnant women.","authors":"Thomas Alan Wemyss, Anubhuti Rana, Sara L Hillman, Miranda Nixon-Hill, Kapil Yadav, Vatsla Dadhwal, Terence S Leung","doi":"10.1088/1361-6579/adab4d","DOIUrl":"10.1088/1361-6579/adab4d","url":null,"abstract":"<p><p><i>Objective.</i>Screening for disease using a smartphone camera is an emerging tool for conditions such as jaundice and anaemia, which are associated with a colour change (yellowing in jaundice; pallor in anaemia) of the external tissues. Based on this, we aimed to test a technique to non-invasively screen for anaemia in a population highly affected by anaemia: pregnant women in India. In this group, anaemia can have severe health consequences for both the mother and child.<i>Approach.</i>Over 3 years of data collection, in 486 pregnant women in India, we attempted to replicate a previously successful smartphone imaging technique to screen for anaemia. Using smartphone images of the eye and eyelid, we compared two techniques (white balancing and ambient subtraction) to control for variation in ambient lighting, and then extracted 'redness' features from images, which we used as features to predict anaemia via statistical modelling.<i>Main results.</i>We found that we were not able to predict anaemia with enough accuracy to be clinically useful, at 89.6% sensitivity and 26.1% specificity. We consider the hypothesis that this may be due to pigmentation on the sclera and palpebral conjunctiva. Visual judgement showed that pigmentation on the sclera, which may affect the measured colour, is more prevalent in pregnant women in India than in preschool aged children in Ghana (a population previously studied in this context). When participants with subjectively judged visible scleral pigmentation are removed, ability to screen for anaemia using the smartphone images slightly improves (93.1% sensitivity, 28.6% specificity).<i>Significance.</i>These findings provide evidence to reinforce that applying smartphone imaging techniques to understudied populations in the real world requires caution-a promising result in one group may not necessarily transfer to another demographic.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143009918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The acute effect of bitemporal electroconvulsive therapy on synchronous changes in heart rate variability and heart rate in patients with depression.","authors":"Xiang Chen, Changjiang He, Hui Zhang, Han Yang, Jin Li","doi":"10.1088/1361-6579/adaad6","DOIUrl":"10.1088/1361-6579/adaad6","url":null,"abstract":"<p><p><i>Objective.</i>The transient autonomic nervous system responses induced by electroconvulsive therapy (ECT) may serve as critical indicators of treatment efficacy and potential side effects; however, their precise characteristics remains unclear. Considering that the intense stimulation of ECT may disrupt the typical antagonistic relationship between the sympathetic and parasympathetic branches, this study aims to conduct a meticulous analysis of the rapid changes in heart rate variability (HRV) and HR during ECT, with a particular focus on their synchronized interplay.<i>Methods.</i>Pulse interval sequences were collected from 50 sessions of bitemporal ECT administered to 27 patients diagnosed with major depressive disorder. The average HR and ultra-short term HRV indices RMSSD and SDNN, as well as the Poincaré indices SD1, SD2 and SD2/SD1, were calculated using a 10 s sliding window with a step size of 1 s. In particular, the synchronous changes between SD1, SD2, SD2/SD1 and HR were analyzed.<i>Results.</i>The synchronous changes of the indices showed different characteristics over time. In particular, SD1, SD2 and HR increased significantly by 41.50 ± 11.45 ms, 33.97 ± 10.98 ms and 9.68 ± 2.00 bpm respectively between 8 and 20 s, whereas they decreased significantly by 19.89 ± 9.07 ms, 17.54 ± 8.54 ms and 3.80 ± 1.33 bpm respectively between 45 and 53 s after ECT stimulus onset. SD1 and SD2 both had highly significant positive correlations with HR in the above phases.<i>Conclusion.</i>The results suggest that bitemporal ECT induces the sympathetic and parasympathetic co-activation during the early ictal period and brief co-inhibition approximately 45 s after stimulus. Our findings may provide new insights comprehending the mechanisms of ECT and its associated cardiovascular risks.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143009922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-critical strategy adjustment based artificial intelligence method in generating diagnostic reports of respiratory diseases.","authors":"Binyue Chen, Guohua Liu, Quan Zhang","doi":"10.1088/1361-6579/ada869","DOIUrl":"10.1088/1361-6579/ada869","url":null,"abstract":"<p><p><i>Objective</i>. Humanity faces many health challenges, among which respiratory diseases are one of the leading causes of human death. Existing AI-driven pre-diagnosis approaches can enhance the efficiency of diagnosis but still face challenges. For example, single-modal data suffer from information redundancy or loss, difficulty in learning relationships between features, and revealing the obscure characteristics of complex diseases. Therefore, it is critical to explore a method that can assist clinicians in detecting lesions early and in pre-diagnosing corresponding diseases.<i>Approach.</i>This paper introduces a novel network structure, strong constraint self-critical strategy network (SCSCS-Net), which can effectively extract image features from chest x-ray images and generate medical image descriptions, assist clinicians in analyzing patients' medical imaging information, deeply explore potential disease characteristics, and assist in making pre-diagnostic decisions. The SCSCS-Net consists of a reinforced cross-modal feature representation model and a self-critical cross-modal alignment model, which are responsible for learning the features interdependence between images and reports by using a multi-subspace self-attention structure and guiding the model in learning report generation strategies to improve the professionalism and consistency of medical terms in generated reports, respectively.<i>Main results.</i>We further compare our model with some advanced models on the same dataset, and the results demonstrate that our method achieves better performance. Finally, the CE and NLG metrics further confirm that the proposed method acquires the ability to generate high-quality medical reports with higher clinical consistency in generating medical reports.<i>Significance.</i>Our novel method has the potential to improve the early detection and pre-diagnosis of respiratory diseases. The model proposed in this paper allows to narrow the gap between artificial intelligence technology and clinical medical diagnosis and provides the possibility for in-depth integration.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142953092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ventilation-perfusion matching in early-stage of prone position ventilation: a prospective cohort study between COVID-19 ARDS and ARDS from other etiologies.","authors":"Yingying Yang, Hantian Li, Yi Chi, Inéz Frerichs, Zhanqi Zhao, Yuan Li, Chunyang Zhang, Huiwen Chu, Huaiwu He, Yun Long","doi":"10.1088/1361-6579/ada8f1","DOIUrl":"10.1088/1361-6579/ada8f1","url":null,"abstract":"&lt;p&gt;&lt;p&gt;&lt;i&gt;Objective.&lt;/i&gt;Prone positioning has been established as a therapeutic strategy for severe acute respiratory distress syndrome (ARDS). In COVID-19-associated ARDS (CARDS), the application of prone position has shown varying responses, influenced by factors such as lung recruitability and SARS-CoV-2-induced pulmonary endothelial dysfunction. This study aimed to compare the early impact of pronation on lung ventilation-perfusion matching (VQmatch) in CARDS and non-COVID-19 ARDS patients (non-CARDS).&lt;i&gt;Approach.&lt;/i&gt;This was a two-center, prospective study comparing between CARDS and non-CARDS. Electrical impedance tomography (EIT) was used to compare the VQmatch between supine and early-stage prone positions (∼2 h). The study identified the areas of Deadspace, shunt, and VQmatch. Within the defined VQmatch region, the global inhomogeneity index (VQmatch-GI) was computed to evaluate the degree of heterogeneity. Paired Wilcoxon signed-rank test and Chi-square test were used in statistical analysis.&lt;i&gt;Main results.&lt;/i&gt;15 CARDS patients and 14 non-CARDS patients undergoing mechanical ventilation were included. In comparison to the non-CARDS group, the CARDS group exhibited a higher prevalence of diffuse lung disease (15 [100%] vs. 4 [28.6%], CARDS vs. Non-CARDS,&lt;i&gt;p&lt;/i&gt;&lt; 0.001), along with elevated SOFA score, PCO&lt;sub&gt;2&lt;/sub&gt;, PEEP, and Ppeak. Among non-CARDS patients, 11/14 demonstrated improved oxygenation, whereas only 5/15 CARDS patients exhibited oxygenation improvement in prone ventilation. In 13/29 patients with oxygenation improvement (defined as above 20% increase in SpO&lt;sub&gt;2&lt;/sub&gt;/FiO&lt;sub&gt;2&lt;/sub&gt;), there was a significant decreased deadspace (21.3 [11.5, 33.1] vs. 9.7 [7.3, 16.9],&lt;i&gt;p&lt;/i&gt;= 0.039), and VQmatch showed an upward trend. When comparing prone ventilation to supine ventilation, non-CARDS patients showed a significant improvement in overall VQmatch (Supine 65.7 [49.7, 68.5] vs. Prone 67.4 [60.8, 72.6],&lt;i&gt;p&lt;/i&gt;= 0.019). CARDS patients had a notable decrease in ventral VQmatch (VQmatch_Ventral: Supine 35.0 [26.9, 42.0] vs. Prone 22.7 [12.4, 32.9],&lt;i&gt;p&lt;/i&gt;= 0.003), and an improvement in dorsal VQmatch (VQmatch_Dorsal: Supine 33.4 [20.4, 39.4] vs. Prone 46.4 [37.4, 48.4],&lt;i&gt;p&lt;/i&gt;= 0.031), leading to no significant improvement in overall VQmatch. Ten CARDS patients with no improvement in VQmatch had increased shunting and VQmatch-GI.&lt;i&gt;Significance.&lt;/i&gt;In non-CARDS patients, the improvement in oxygenation and VQmatch following prone positioning exhibits a consistent pattern. Conversely, in CARDS patients, the impact of prone positioning reveals considerable individual variability. This study indicates that the response to short-time prone ventilation can vary in ARDS patients with different etiologies.&lt;b&gt;Trial registration:&lt;/b&gt;NCT05816928, 04/17/2023, retrospectively registered. Ventilation-Perfusion Matching in Early-stage Prone Position Ventilation, NCT05816928. Registered 17 April 2023 - Retrospectively registered,https://clini","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142966402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accuracy of flow volume estimation in the dilated aorta using 4D flow MRI: a pulsatile phantom study.","authors":"Eduardo E Rodríguez, Alejandro Valda, Mariano E Casciaro, Sebastian Graf, Edmundo Cabrera Fischer, Damian Craiem","doi":"10.1088/1361-6579/adab4e","DOIUrl":"10.1088/1361-6579/adab4e","url":null,"abstract":"<p><p><i>Objectives.</i>Aortic dilatation is a severe pathology that increases the risk of rupture and its hemodynamics could be accurately assessed by using the 4D flow cardiovascular magnetic resonance (CMR) technique but flow assessment under complex flow patterns require validation. The aim of this work was to develop an<i>in vitro</i>system compatible with CMR to assess the accuracy of volume flow measurements in dilated aortas.<i>Approach.</i>Two latex models, one with ascending and the other with abdominal aortic aneurysms were manufactured to ensure a constant and controlled net flow volume along the aortic length. A pneumatic piston driven by a stepper motor and controlled by an embedded system located in the control room modulated a pulsatile fluid flow using a pump with an elastic membrane placed in the magnet near the elastic models. All the visualization and measurement algorithms were integrated into a custom computer platform. 4D flow imaging was used to estimate the flow rate and volume through multiple aortic planes and compared to the reference assessed by weight method and to 2D flow measurements.<i>Main results.</i>The errors of flow volume assessment using 4D flow remained within reasonable limits along the length of the aortic models. Mean differences in net flow volume from the reference were less than 2 ml (range -4 to 6 ml), corresponding to mean relative differences of less than 4% (range -8% to 11%). Averaged net, forward and backward flow volume estimations along the aortic length were similar using 2D and 4D flow measurements (<i>p</i>> 0.05). Peak forward and backward flow rates increased in the dilated regions and were comparable to those observed in patients.<i>Significance.</i>The accuracy of flow volume estimates in complex flow patterns, such as those observed in patients with aneurysms, was validated<i>in vitro</i>using 4D flow.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143009916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ST-CIRL: a reinforcement learning-based feature selection approach for enhanced anxiety classification.","authors":"Shikha Shikha, Divyashikha Sethia, S Indu","doi":"10.1088/1361-6579/adb006","DOIUrl":"https://doi.org/10.1088/1361-6579/adb006","url":null,"abstract":"<p><p>A physiological signal-based Human-Computer Interaction (HCI) system provides a communication link between human emotional states and external devices. Accurately classifying these signals is vital for effective interaction, which requires extracting and selecting the most discriminative features to differentiate between various emotional states. This paper introduces the SMOTETomek-Correlated Interactive Reinforcement Learning (ST-CIRL) framework for anxiety classification, which leverages meta-descriptive statistics to enhance the state representation in the reinforcement learning process. Firstly, it addresses class imbalance using SMOTETomek and further reduces dimensionality by pruning redundant features. Secondly, the ST-CIRL framework enhances classification accuracy through the collaboration of multiple agents to select the most informative features using Interactive Reinforcement Learning (IRL).&#xD;Further, the paper utilizes classifiers, including Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and Light Gradient Boosting (LGBM) for anxiety classification. Thirdly, the hyperparameters of these machine learning algorithms are tuned using the Optuna approach to enhance model performance. The proposed ST-CIRL framework achieves a maximum accuracy of 95.35% and an F1-score of 95.49% using the LightGBM classifier. Furthermore, the results demonstrate that the proposed approach outperforms current state-of-the-art methods. These findings validate the efficacy of the SMOTETomek method and the innovative feature optimization approach, highlighting the potential of reinforcement learning in enhancing HCI systems and expanding its applicability in intelligent system design.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143067238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From motion to emotion: exploring challenging behaviors in autism spectrum disorder through analysis of wearable physiology and movement.","authors":"Ali Bahrami Rad, Tania Villavicencio, Yashar Kiarashi, Conor Anderson, Jenny Foster, Hyeokhyen Kwon, Theresa Hamlin, Johanna Lantz, Gari D Clifford","doi":"10.1088/1361-6579/ada51b","DOIUrl":"10.1088/1361-6579/ada51b","url":null,"abstract":"<p><p><i>Objective.</i>This study aims to evaluate the efficacy of wearable physiology and movement sensors in identifying a spectrum of challenging behaviors, including self-injurious behavior, in children and teenagers with autism spectrum disorder (ASD) in real-world settings.<i>Approach.</i>We utilized a long-short-term memory network with features derived using the wavelet scatter transform to analyze physiological biosignals, including electrodermal activity and skin temperature, alongside three-dimensional movement data captured via accelerometers. The study was conducted in naturalistic environments, focusing on participants' daily activities.<i>Main results.</i>Our findings indicate that the best performance in detecting challenging behaviors was achieved using movement data. The results showed a sensitivity of 0.62, specificity of 0.71, F1-score of 0.36, and an area under the ROC curve of 0.71. These results are particularly significant given the study's focus on real-world scenarios and the limited existing research in this area.<i>Significance.</i>This study demonstrates that using wearable technology to record physiological and movement signals can detect challenging behaviors in children with ASD in real-world settings. This methodology has the potential to greatly improve the management of these behaviors, thereby enhancing the quality of life for children with ASD and their caregivers. This approach marks a significant step forward in applying the outcome of ASD research in practical, everyday environments.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11775438/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142922589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"tinyHLS: a novel open source high level synthesis tool targeting hardware accelerators for artificial neural network inference.","authors":"Ingo Hoyer, Alexander Utz, Christoph Hoog Antink, Karsten Seidl","doi":"10.1088/1361-6579/ada8f0","DOIUrl":"10.1088/1361-6579/ada8f0","url":null,"abstract":"<p><p><i>Objective.</i>In recent years, wearable devices such as smartwatches and smart patches have revolutionized biosignal acquisition and analysis, particularly for monitoring electrocardiography (ECG). However, the limited power supply of these devices often precludes real-time data analysis on the patch itself.<i>Approach.</i>This paper introduces a novel Python package, tinyHLS (High Level Synthesis), designed to address these challenges by converting Python-based AI models into platform-independent hardware description language code accelerators. Specifically designed for convolutional neural networks, tinyHLS seamlessly integrates into the AI developer's workflow in Python TensorFlow Keras. Our methodology leverages a template-based hardware compiler that ensures flexibility, efficiency, and ease of use. In this work, tinyHLS is first-published featuring templates for several layers of neural networks, such as dense, convolution, max and global average pooling. In the first version, rectified linear unit is supported as activation. It targets one-dimensional data, with a particular focus on time series data.<i>Main results.</i>The generated accelerators are validated in detecting atrial fibrillation on ECG data, demonstrating significant improvements in processing speed (62-fold) and energy efficiency (4.5-fold). Quality of code and synthesizability are ensured by validating the outputs with commercial ASIC design tools.<i>Significance.</i>Importantly, tinyHLS is open-source and does not rely on commercial tools, making it a versatile solution for both academic and commercial applications. The paper also discusses the integration with an open-source RISC-V and potential for future enhancements of tinyHLS, including its application in edge servers and cloud computing. The source code is available on GitHub:https://github.com/Fraunhofer-IMS/tinyHLS.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142966300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review of automated prediction of sudden cardiac death using ECG signals.","authors":"Preeti P Ghasad, Jagath V S Vegivada, Vipin M Kamble, Ankit A Bhurane, Nikhil Santosh, Manish Sharma, Ru-San Tan, U Rajendra Acharya","doi":"10.1088/1361-6579/ad9ce5","DOIUrl":"10.1088/1361-6579/ad9ce5","url":null,"abstract":"&lt;p&gt;&lt;p&gt;&lt;i&gt;Background&lt;/i&gt;. Sudden cardiac death (SCD) stands as a life-threatening cardiac event capable of swiftly claiming lives. It ranks prominently among the leading causes of global mortality, contributing to approximately 10% of deaths worldwide. The timely anticipation of SCD holds the promise of immediate life-saving interventions, such as cardiopulmonary resuscitation. However, recent strides in the realms of deep learning (DL), machine learning (ML), and artificial intelligence have ushered in fresh opportunities for the automation of SCD prediction using physiological signals. Researchers have devised numerous models to automatically predict SCD using a combination of diverse feature extraction techniques and classifiers. Methods: We conducted a thorough review of research publications ranging from 2011 to 2023, with a specific focus on the automated prediction of SCD. Traditionally, specialists utilize molecular biomarkers, symptoms, and 12-lead ECG recordings for SCD prediction. However, continuous patient monitoring by experts is impractical, and only a fraction of patients seeks help after experiencing symptoms. However, over the past two decades, ML techniques have emerged and evolved for this purpose. Importantly, since 2021, the studies we have scrutinized delve into a diverse array of ML and DL algorithms, encompassing K-nearest neighbors, support vector machines, decision trees, random forest, Naive Bayes, and convolutional neural networks as classifiers.&lt;i&gt;Results&lt;/i&gt;. This literature review presents a comprehensive analysis of ML and DL models employed in predicting SCD. The analysis provided valuable information on the fundamental structure of cardiac fatalities, extracting relevant characteristics from electrocardiogram (ECG) and heart rate variability (HRV) signals, using databases, and evaluating classifier performance. The review offers a succinct yet thorough examination of automated SCD prediction methodologies, emphasizing current constraints and underscoring the necessity for further advancements. It serves as a valuable resource, providing valuable insights and outlining potential research directions for aspiring scholars in the domain of SCD prediction.&lt;i&gt;Conclusions&lt;/i&gt;. In recent years, researchers have made substantial strides in the prediction of SCD by leveraging openly accessible databases such as the MIT-BIH SCD Holter and Normal Sinus Rhythm, which contains extensive 24 h recordings of SCD patients. These sophisticated methodologies have previously demonstrated the potential to achieve remarkable accuracy, reaching levels as high as 97%, and can forecast SCD events with a lead time of 30-70 min. Despite these promising outcomes, the quest for even greater accuracy and reliability persists. ML and DL methodologies have shown great promise, their performance is intrinsically linked to the volume of training data available. Most predictive models rely on small-scale databases, raising concerns about their appl","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142807683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning generalization for diabetic retinopathy staging from fundus images.","authors":"Yevgeniy Men, Jonathan Fhima, Leo Anthony Celi, Lucas Zago Ribeiro, Luis Filipe Nakayama, Joachim A Behar","doi":"10.1088/1361-6579/ada86a","DOIUrl":"10.1088/1361-6579/ada86a","url":null,"abstract":"<p><p><i>Objective</i>. Diabetic retinopathy (DR) is a serious diabetes complication that can lead to vision loss, making timely identification crucial. Existing data-driven algorithms for DR staging from digital fundus images (DFIs) often struggle with generalization due to distribution shifts between training and target domains.<i>Approach</i>. To address this, DRStageNet, a deep learning model, was developed using six public and independent datasets with 91 984 DFIs from diverse demographics. Five pretrained self-supervised vision transformers (ViTs) were benchmarked, with the best further trained using a multi-source domain (MSD) fine-tuning strategy.<i>Main results</i>. DINOv2 showed a 27.4% improvement in L-Kappa versus other pretrained ViT. MSD fine-tuning improved performance in four of five target domains. The error analysis revealing 60% of errors due to incorrect labels, 77.5% of which were correctly classified by DRStageNet.<i>Significance</i>. We developed DRStageNet, a DL model for DR, designed to accurately stage the condition while addressing the challenge of generalizing performance across target domains. The model and explainability heatmaps are available atwww.aimlab-technion.com/lirot-ai.</p>","PeriodicalId":20047,"journal":{"name":"Physiological measurement","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142953090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}