BioMedical Engineering OnLine最新文献

{"title":"System-level design trade-offs in magnetic hyperthermia RF instrumentation: a power electronics and electromagnetic design review.","authors":"Serhat Ilgaz Yöner, Alpay Özcan","doi":"10.1186/s12938-026-01633-3","DOIUrl":"10.1186/s12938-026-01633-3","url":null,"abstract":"<p><strong>Purpose: </strong>Magnetic hyperthermia (MH) is a promising localized cancer therapy based on magnetic nanoparticle (MNP)-mediated heating. Although research has extensively focused on MNP development, therapeutic efficacy and safety also depend critically on the engineering of the induction system. This review aims to provide an engineering-focused analysis of contemporary MH instrumentation and its design trade-offs.</p><p><strong>Methods: </strong>The instrumentation architecture is examined through a dual-domain evaluation of the power electronic and electromagnetic design chain. RF generator architectures are analyzed across the DC supply, oscillator, amplifier, and impedance matching stages. RF coil designs are evaluated according to geometry, inductance, and cooling strategies. An ordinal scoring framework is used to compare representative implementations and assess the influence of architectural choices on energy delivery and thermal stability, providing a structured basis for relative comparison rather than a definitive performance ranking.</p><p><strong>Results: </strong>The analysis demonstrates that MNP performance is fundamentally constrained by the magnetic field generated by the complete instrumentation chain. Power-stage stability, impedance matching, coil characteristics, cooling, and spatial field homogeneity collectively determine the achievable operating conditions.</p><p><strong>Conclusion: </strong>Reliable MH requires system-level optimization rather than isolated MNP development. By clarifying key hardware trade-offs and their effects on field generation, this review supports the design of more standardized and reproducible MH induction systems.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"25 1","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13644266/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149126678","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":"Biomimetic electrospun nanofibrous composites for bone tissue engineering: a review of materials, fabrication, and applications.","authors":"N Valarmathi, S Sumathi, Helen P Kavitha, M Swaminathan, Manikandan Krishnamurthy, Manikandan Ayyar, Abdullatif Hakami, Abinet Gosaye Ayanie","doi":"10.1186/s12938-026-01596-5","DOIUrl":"https://doi.org/10.1186/s12938-026-01596-5","url":null,"abstract":"<p><p>A flexible and promising method for creating polymeric nanofibrous composites for BTE (bone tissue engineering) is electrospinning. The optimal composites should resemble bone's natural ECM (extracellular matrix), possess suitable surface chemistry, exhibit strong mechanical strength, and demonstrate bioactivity and biocompatibility. Selecting the appropriate material for composite fabrication is a critical initial step in developing a BTE (tissue engineered) product. BTE is a multidisciplinary area that applies engineering concepts to bone-related biological processes. Key considerations in this field include composites, cells, growth factors, and their interfaces in the microenvironment. This review article examines the recent developments in BTE using biomimetic electrospun polymeric biomaterials. It provides an overview of Natural polymer, synthetic polymer, bone structure, biocomposite discusses the ideal characteristics of bone scaffolds, and offers a basic introduction to BTE. The fabrication of bone composites is explored in detail, including various materials and techniques used. Additionally covered the characteristics, benefits, and uses of electrospinning in BTE. The application of electrospun nanofibrous composites composed of natural and synthetic polymers for BTE is thoroughly reviewed and discussed, as well as the biomineralization processes involved. Finally, the study concludes with insights into biomimetic composites for BTE based on electrospun nanofibers.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"25 1","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149222961","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":"Efficacy of TACE combined with targeted immunotherapy in the treatment of advanced liver cancer.","authors":"Peng Xie, Fuqiang Jiang","doi":"10.1186/s12938-026-01604-8","DOIUrl":"10.1186/s12938-026-01604-8","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To investigate the efficacy of transcatheter arterial chemoembolization (TACE) combined with targeted immunotherapy in the treatment of advanced liver cancer.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Method: &lt;/strong&gt;A total of 115 patients with intermediate-advanced liver cancer treated in our hospital from June 2021 to June 2024 were retrospectively selected and divided into two groups according to the actual treatment regimen received. The grouping was a non-randomized retrospective design. The conventional group (n = 57) received TACE alone, while the combination group (n = 58) received TACE combined with targeted immunotherapy. Clinical efficacy, tumor markers [alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen 125 (CA125), carbohydrate antigen 199 (CA199), protein induced by vitamin K absence-II (PIVKA-II)], immune function [immunoglobulin A (IgA), immunoglobulin G (IgG), immunoglobulin M (IgM)], and liver function indicators [serum albumin (ALB), glutamic-pyruvic transaminase (GPT), total bilirubin (TBIL)] were compared between the two groups. Kaplan-Meier survival analysis and the Cox proportional hazards regression model were used to evaluate survival rate, the incidence of adverse events was also compared. To control for potential confounding factors, 1:1 propensity score matching (PSM) was performed as a sensitivity analysis, subgroup analyses of efficacy and safety for different targeted drugs within the combination group were also carried out. Immunohistochemistry was used to detect the expression of Ki-67, CD8 ⁺ T, and PD-L1 in two groups before treatment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Result: &lt;/strong&gt;Compared with the conventional group, the proportion of objective response rate (ORR), disease control rate (DCR) patients in the combined group was significantly higher (P &lt; 0.05). After treatment, the levels of tumor markers in both groups were significantly reduced, which were lower in the combined group than the conventional group (P &lt; 0.001). After treatment, the immune function in both groups were improved, with the combined group showing superior efficacy compared to the conventional group (P &lt; 0.001). After treatment, the liver function in both groups were improved. The ALB level in the combined group was significantly higher than that in the conventional group, while the GPT and TBIL levels were significantly lower than those in the conventional group (P &lt; 0.001). The one-year cumulative survival rate of patients in the combined group was higher than that of the conventional group (P &lt; 0.05). The overall incidence of grade ≥ 3 adverse events did not differ significantly between the two groups (P &gt; 0.05). After PSM, the DCR and 1-year cumulative survival rate in the combination group remained significantly superior to those in the conventional group (both P &lt; 0.05). Combination therapy was an independent protective factor for survival (HR = 0.520, 95% CI 0.310-0.874, P = 0.012), while CNLC stage IIIa was an inde","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660114/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468265","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":"Rehabilitation assessment approaches and technologies to measure gaze behaviour during walking in older adults and central neurological populations: a scoping review protocol.","authors":"Nicole Cesca, Damian M Manzone, Kristin E Musselman, José Zariffa, Emilia Main, Thomas P Walden","doi":"10.1186/s12938-026-01597-4","DOIUrl":"10.1186/s12938-026-01597-4","url":null,"abstract":"<p><strong>Introduction: </strong>Falls are a frequent event among older adults and individuals with central neurological conditions. Gaze behaviour (i.e. how individuals use visual input to guide movement) plays a critical role in motor control while walking and likely contributes to fall prevention. However, existing research in this area remains fragmented. This scoping review will aim to identify how gaze behaviour is measured and utilized during gait rehabilitation among older adults and individuals with central neurological conditions. Findings will inform standardized assessment approaches and the development of interventions targeting gaze behaviour to improve walking and reduce fall risk.</p><p><strong>Methods and analysis: </strong>This review will follow the Joanna Briggs Institute scoping review guidelines and is registered with the Open Science Framework. Studies will be included if they involve older adults (≥ 65 years) or individuals with central neurological conditions and measure gaze behaviour during walking. A comprehensive search strategy was developed in collaboration with a University Health Network Librarian and refined iteratively by the research team. Eight databases (Medline, Embase, CENTRAL, CDSR, Emcare Nursing, APA PsycINFO, Web of Science Core Collection, and CINAHL) were searched from inception to August 2025. Title and abstract screening will be followed by a full-text review to identify articles that meet the inclusion criteria. Data related to study/participant characteristics, methods for eye tracking, intervention, equipment, outcome measures, and key findings will be extracted. Methodological quality of studies will be assessed using the appropriate tool based on study design. Results will be reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews checklist.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656576/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468279","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":"Computational mechanobiological model combining epiphyseal, apophyseal, and appositional growth and inner bone remodeling of the juvenile femur.","authors":"Andreas Lipphaus, Ralf-Bodo Tröbs, Matthias Klimek, Sascha Selkmann, Ulrich Witzel","doi":"10.1186/s12938-026-01598-3","DOIUrl":"10.1186/s12938-026-01598-3","url":null,"abstract":"<p><p>In silico models for simulating bone growth based on mechanical or non-mechanical epigenetic factors are widely used. In this study, a well-known mechanobiological model, which states that octahedral shear stress accelerates longitudinal bone growth and hydrostatic stress retards it, is applied to a finite element model of the femur of an 8-year-old boy. Proximal and distal epiphyseal plates as well as the growth plate of the greater trochanter, cartilaginous growth at the femoral isthmus, and appositional bone growth are included in the model. Furthermore, changes in the density of the cancellous bone in the metaphyses are modeled based on Wolff's law using compressive stresses as the mechanical stimulus. Muscle forces during a dynamic gait cycle were determined for nine discrete loading cases by optimizing to minimize bending stress. The highest stresses in the femoral shaft were determined as medial compressive stresses with a maximum of -33.2 MPa. Highest internal axial load in the shaft was 985 N during loading response. The simulated bone growth resulted in an increase in femur length of 23.7 mm and a decrease in femoral neck angle by -1.4°, anteversion angle by -2.4°, and lateral distal femur angle by -1.6° per year. Growth of the apophysis of the greater trochanter resulted in an unchanged articulo-trochanteric distance. The bone remodeling led to an increase in bone density, particularly in the medial proximal metaphysis. The consideration of different growth mechanisms allowed a comprehensive simulation of femoral growth with high agreement with anthropometric data. Possible applications are the simulation of the correction of deformities.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":"25 1","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13374303/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454339","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":"Prediction model for recurrent laryngeal nerve injury in microwave ablation of thyroid nodules.","authors":"Zhixiang Wang, Yawen Wang, Yiran Wang, Mingyang Hu, Sunfan Pu, Yanjia Gou, Dong Liu","doi":"10.1186/s12938-026-01573-y","DOIUrl":"10.1186/s12938-026-01573-y","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to develop an explainable machine learning (ML) framework integrating clinical, imaging, and procedural features for predicting recurrent laryngeal nerve (RLN) injury risk during microwave ablation (MWA) of thyroid nodules.</p><p><strong>Methods: </strong>A retrospective study is conducted using data from 254 patients who underwent thyroid nodule MWA. Recursive feature elimination (RFE) with 5 × fivefold cross-validation selected 12 optimal features across four ML models: logistic regression (LR), decision tree (DT), random forest (RF), and support vector machine (SVM). Model performance is evaluated via AUC, accuracy, sensitivity, specificity, Brier score, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) provides interpretability by quantifying feature contributions.</p><p><strong>Results: </strong>The RandomForest model achieved the highest discriminative performance (AUC = 0.9755 ± 0.0242, accuracy = 0.9729 ± 0.0155) and calibration (Brier score = 0.038). Key predictors included nodule volume, ablation time, and proximity to the tracheoesophageal groove. SHAP analysis revealed model-specific interactions: nodule orientation (SVM) and post-ablation dimensions (RF) significantly influenced risk. DCA confirmed clinical utility, with RF providing the highest net benefit across thresholds (0.2-0.6). Laboratory markers and echogenicity demonstrated cross-model consistency, underscoring their biological relevance.</p><p><strong>Conclusion: </strong>This study establishes the first interpretable ML framework for RLN injury prediction in thyroid nodule MWA, highlighting the superiority of ensemble learning and clinical-imaging integration. Future validation in diverse cohorts and real-time integration into ablation systems may enhance procedural safety.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637350/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148418250","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":"Biomechanics of the retina: experimental and clinical perspectives.","authors":"Brianna E Samson, Mohamed H Nashnoush, Corey A Smith","doi":"10.1186/s12938-026-01599-2","DOIUrl":"10.1186/s12938-026-01599-2","url":null,"abstract":"<p><p>The retina is an essential component of the visual system, a delicate neural tissue that converts light signals into electrical impulses and links the visual environment to the brain. Its structure and functional performance depend on multiple layers of interconnected cells and extracellular matrix components that together provide mechanical support. The retina's biomechanical properties, including elasticity, stiffness, and tensile strength, govern how it deforms and recovers under physiological load and mechanical stress. Quantifying these properties is essential for understanding how the retina resists tractional and compressive forces that can lead to injury or disease. Techniques including tensile testing, atomic force microscopy, optical coherence elastography, Brillouin microscopy, and computational modeling have advanced our understanding of retinal stiffness and revealed altered tissue mechanics in ocular disease. This review describes current knowledge of retinal structure and material behavior, experimental and computational approaches used to assess mechanical properties, and how biomechanical changes contribute to the development and progression of retinal disorders.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13625495/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148403331","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":"Kinematic tracking of the small bones of the wrist in sequential 3DCT and dynamic 4DCT volume images using open-source Hierarchical 3D Registration, a module within SlicerAutoscoper^M.","authors":"Joseph J Crisco, Amy M Morton, Cesar Lopez, Andrew Thoreson, Kristin D Zhao, John D Holtgrewe, Jean-Christophe Fillion-Robin, Beatriz Paniagua","doi":"10.1186/s12938-026-01601-x","DOIUrl":"10.1186/s12938-026-01601-x","url":null,"abstract":"<p><p>Quantitative kinematic tracking of in vivo skeletal structures efficiently and with high temporal resolution is important to a wide range of questions in biomechanical research. As such, software tools are needed for efficient, semi-automated registration of bones imaged with either 3DCT or 4DCT. This study presents Hierarchical 3D Registration (3DH), an open-source approach to skeletal tracking of three-dimensional image volume sets. The 3DH approach and software are presented using sequential 3DCT datasets of participants performing various thumb tasks and dynamic 4DCT datasets of simulated flexion-extension in cadaveric wrists collected in previous studies. The agreement in computed arthrokinematics with previously calculated values using independent approaches for 3DCT and 4DCT data was assessed with Bland-Altman analyses. Using 3DH, all target bones were successfully tracked for both the 3DCT and 4DCT sets. For 3DCT data of the radius, first metacarpal and trapezium, the mean bias for the helical angle was -0.06 degrees with 95% limits of agreement ranging between -1.87 degrees and 1.74 degrees. The mean bias for translation was 0.12 mm with 95% limits of agreement ranging between -2.23 mm and 2.00 mm. For 4DCT data of the scaphoid and lunate, mean biases of the Euler angle rotations were less than 0.77 degrees about any direction and widest 95% limits of agreement ranging between - 7.11 degrees and 8.65 degrees. Mean biases of translations were less than 0.5 mm in any direction with widest 95% limits of agreement ranging between - 2.36 mm and 1.43 mm. The ability to track bones from both 3DCT and 4DCT data sources with agreement to prior methodologies demonstrates the 3DH approach is a capable tool, which could promote collaboration and consistency of results using open-source software that is a module in the 3DSlicer computing environment.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13602495/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148381422","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":"Technical and clinical feasibility of single-use gastroscopy with real-time AI-based quality monitoring and single-use colonoscopy: a prospective two-center study.","authors":"Yang Lv, Long Xu, Wei Gong, Ying Zhu, Wen Xu, Guili Xia, Zhili Zhang, Fachao Zhi","doi":"10.1186/s12938-026-01595-6","DOIUrl":"10.1186/s12938-026-01595-6","url":null,"abstract":"<p><strong>Background: </strong>Single-use gastrointestinal endoscopes eliminate the need for post-procedure reprocessing and have become an area of interest in endoscopic device development and quality management. However, clinical data on their use in routine gastrointestinal endoscopy remain limited. This prospective, two-center, single-arm study evaluated the feasibility and short-term safety of single-use gastroscopy performed with ENDOANGEL, an artificial intelligence (AI)-based real-time quality monitoring system, and single-use colonoscopy in routine gastrointestinal endoscopy. Formal AI-based quality scoring was applied to gastroscopy, whereas ENDOANGEL-related colonoscopy indicators were recorded descriptively.</p><p><strong>Results: </strong>A total of 120 participants were enrolled, including 60 who underwent gastroscopy and 60 who underwent colonoscopy. Imaging of predefined anatomical sites was successful in all participants in both groups (60/60 in each group; 95% CI 94.0-100.0%). All procedures were completed without conversion to reusable endoscopes. The overall image quality scores were 39.2 ± 0.8/40 for gastroscopy and 31.3 ± 0.8/32 for colonoscopy. Mean total procedure times were 9.3 ± 2.7 min and 12.6 ± 3.1 min, respectively. No device malfunction, device defect, or procedure-related adverse event was observed during the procedure or within 24 h after endoscopy. In gastroscopy, all ENDOANGEL-assisted examinations achieved the maximum procedural score, and ENDOANGEL-based assessment agreed with manual assessment of imaging success and procedure completion. In colonoscopy, ENDOANGEL-related cecal intubation reminders agreed with manual assessment in all procedures, and withdrawal-speed alerts were recorded in 4 of 60 procedures.</p><p><strong>Conclusion: </strong>Single-use gastroscopy with real-time AI-based quality monitoring and single-use colonoscopy were feasible in routine gastrointestinal endoscopy and showed a favorable short-term safety profile within 24 h. AI-related findings should be interpreted as feasibility and agreement data for gastroscopy and as descriptive process-monitoring observations for colonoscopy. Further controlled studies are needed to compare single-use and reusable systems and to clarify the clinical role of AI-based process monitoring in single-use endoscopy.</p><p><strong>Trial registration: </strong>Chinese Clinical Trial Registry, ChiCTR2100045101. Retrospectively registered on April 6, 2021.</p>","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13595721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148374290","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":"Non-invasive classification of stable HFpEF using a deep learning model trained on acoustic features of sustained vowels.","authors":"Yi Lyu, Quan-Cheng Jiang, Hai-Mei Wu, Chun-Feng Chen, Jing Hong, Yi-Qin Wang, Yu-Jing Shi, Hai-Xia Yan, Jin Xu","doi":"10.1186/s12938-026-01600-y","DOIUrl":"10.1186/s12938-026-01600-y","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Conventional identification of stable HFpEF still depends on resource-intensive clinical assessment, whereas non-invasive acoustic analysis of sustained vowels may provide a complementary and accessible classification signal.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The objective of this study was to develop and validate a classification model for stable heart failure with preserved ejection fraction (HFpEF) versus healthy controls using acoustic features extracted from the sustained vowel /ɑː/. In this retrospective case-control study, voice recordings were obtained from a primary cohort of 341 participants and an independent external validation cohort of 172 participants. The present study extracted 384 features using the Interspeech 2009 feature set and compared five deep learning models. The top-performing deep learning architecture, the multilayer perceptron (MLP), was further assessed through tenfold cross-validation, independent external validation, and feature analysis using SHapley Additive exPlanations and Local Interpretable Model-Agnostic Explanations. Additional analyses benchmarked the MLP against classical machine-learning models and examined uncertainty, calibration, prevalence sensitivity, and demographic confounding.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;For the binary classification of stable HFpEF versus healthy controls, the MLP classifier demonstrated the strongest performance in the five-model deep learning comparison, achieving a mean tenfold cross-validation accuracy of 0.8593 and an area under the curve (AUC) of 0.9130. On the independent external validation cohort, the primary MLP achieved an AUC of 0.836. In a broader benchmark, acoustic-feature models clearly outperformed age/sex-only models, and MLP remained competitive against strong classical tabular baselines. A regularized MLP sensitivity model achieved an external AUC of 0.8638 (95% bootstrap CI 0.8074-0.9188), whereas the best untuned SVM achieved an external AUC of 0.8628. Interpretability analyses highlighted MFCC-related spectral-envelope descriptors as influential feature families, although fold-wise stability supported family-level rather than single-feature conclusions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;While the performance gap between cross-validation and external validation indicates room for further refinement, this study demonstrates that sustained-vowel IS09 acoustic features contain discriminative signal for stable HFpEF versus healthy controls under controlled conditions. The MLP was the strongest model among the tested deep learning architectures, but the broader benchmark showed that it was competitive rather than clearly superior to classical tabular models. These findings support acoustic-feature analysis as a preliminary research-stage adjunctive classification signal, while broader prospective validation in clinically heterogeneous populations is required before any clinical screening, triage, or monitoring role can be esta","PeriodicalId":8927,"journal":{"name":"BioMedical Engineering OnLine","volume":" ","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13591906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148366732","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}