PLOS digital health最新文献

{"title":"Recommendations for the analysis of leading indicators in epidemic surveillance.","authors":"Jonathon Mellor, Maria Tang, Robert S Paton, Thomas Ward","doi":"10.1371/journal.pdig.0001759","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001759","url":null,"abstract":"<p><p>Leading indicator analyses, a type of time series analysis, are frequently used to assess how epidemic surveillance signals relate to one another. Strong leading indicators can drive early, and better decisions in public health systems. We conducted a narrative review of leading indicator studies and evaluated methodological limitations in their reporting and analysis, which we used to generate recommendations in retrospective surveillance analyses. Achievable recommendations are provided based on the reporting and analysis components of real-time epidemic time series analysis. We provide contextual examples from the literature of previous studies demonstrating good practice and highlighting areas for improvement. We present a checklist and workflow that emphases real-time constraints. These recommendations include causal mechanism reporting, sample coverage and bias, reporting delays and data revisions, multiple event measurement, spatio-temporal granularly, time varying relationships, smoothing, transformations, uncertainty, and predictive utility. By following these good practices, analysts can improve research on leading indicators to make analyses more directly actionable for public health decision makers. This work builds on the existing methodology literature by giving a broader framework for overall good practices.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001759"},"PeriodicalIF":7.7,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637922/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119774","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":"Toward predictive prosthetic socket modeling: Preliminary linear regression models of transradial limb-socket geometry.","authors":"Vishal Pendse, Nader Allam, Calvin C Ngan, Elaine Lorette, Isabelle Morin-Girard, Jan Andrysek","doi":"10.1371/journal.pdig.0001767","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001767","url":null,"abstract":"<p><p>Socket fit is essential for successful upper-limb prosthetic devices, yet current design workflows remain labor-intensive and dependent on clinician experience. Several digital and algorithmic approaches have been proposed to partially automate socket design, many of which rely on characterizing conventional design practice. In upper-limb prosthetics, prior research has quantified transradial socket rectification practices, but the direct geometric relationship between the residual limb and final socket remains unclear despite its importance to digital socket design workflows. This study examined whether simple linear regression models could provide a preliminary, interpretable description of limb-socket geometric relationships in transradial socket design. Fourteen participants with transradial limb absence were included, whose digitized limb-socket pairs were aligned using a novel spline-based method. Relationships were quantified using global descriptors (volume, surface area, and proximal-distal length) and cross-sectional descriptors at 25%, 50%, and 75% of limb length (mediolateral length, anterior-posterior length, circumference, and cross-sectional area). For each descriptor, simple linear regressions were fit to predict socket geometry from limb geometry, and model performance was evaluated using leave-one-out cross-validation. Global descriptors demonstrated strong linear relationships, with R² values ranging from 0.94 to 0.97 and predicted R² values from 0.92 to 0.97, indicating that overall socket size is largely predictable from limb size. Cross-sectional descriptors showed more variable performance, with the strongest results at mid-length and weaker relationships toward the proximal and distal ends. Mean absolute percentage error ranged from 2.5% to 13.6% across descriptors, while retention values were generally high, indicating limited overfitting. These findings suggest that simple linear models can capture broad scaling relationships between transradial limbs and sockets, but are less able to explain localized geometry in regions where trimline design, suspension strategy, and distal-end clearance play a greater role.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001767"},"PeriodicalIF":7.7,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637916/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119834","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":"Implementation of electronic signposting to interventions that prevent cancer: A realist review.","authors":"Tracey J Brown, Natalie An Qi Tham, Felix Naughton, Henry Goodfellow, Louise Hull, Helena Jopling, Helen M Parretti, Alex T Ramsey, Adam P Wagner, Zarnie Khadjesari","doi":"10.1371/journal.pdig.0001770","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001770","url":null,"abstract":"<p><p>Uptake of evidence-based interventions that prevent cancer is very low. Electronic signposting using digital messages sent via electronic healthcare systems is increasingly utilised to improve service reach and uptake. However, theory for optimising the implementation of electronic signposting to cancer prevention interventions is lacking. We sought to generate a novel programme theory to illuminate what type of electronic signposting works, for whom and in what circumstances. A realist review, informed by Realist And Meta-narrative Evidence Syntheses: Evolving Standards (RAMESES I), was conducted. Medline, EMBASE, CINAHL, Scopus, PsycINFO, ERIC and AMED databases, and grey literature were searched. Studies that contributed information on context and mechanisms of action for electronic signposting to cancer prevention interventions for adults in any healthcare setting were included. Studies were assessed for quality based on relevance, richness and rigour. Realist synthesis and input from stakeholders, including patients, was used to aid development of our novel programme theory. Thirty studies were included, 26 of which were conducted in the United States. 57 individual context-mechanism-outcome configurations were identified. For patients, memorable messages using wording tailored to patient characteristics, and use of a popular communication channel (e.g., SMS text) improved 'buy-in' and usability. For providers, a good fit with organisational priorities, workflow, and establishing compatibility with existing technical systems was important. Increasing optimism of technology and ensuring electronic signposting did not risk existing patient-provider relationships were also key to success. To reduce cancer and cancer disparities, policymakers and providers need to implement electronic signposting in ways that promote 'buy-in', ensure perceived usability, and nurture positive attitudes towards technology. The field would benefit from further qualitative insight, health economic analysis, exploration of equity and long-term outcomes, and research in non-USA contexts. Protocol registration: PROSPERO [CRD42024586907].</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001770"},"PeriodicalIF":7.7,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637878/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119752","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":"Multi-task deep learning integrating pretreatment MRI and whole slide images predicts induction chemotherapy response and survival in locally advanced nasopharyngeal carcinoma.","authors":"Jing Hou, Xiaochun Yi, Congrui Li, Junjian Li, Hui Cao, Qiang Lu, Xiaoping Yu","doi":"10.1371/journal.pdig.0001378","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001378","url":null,"abstract":"<p><p>Predicting response to induction chemotherapy (IC) and overall survival (OS) is critical for optimizing treatment in patients with locally advanced nasopharyngeal carcinoma (LANPC). This study aimed to develop and validate a multi-task deep learning model integrating pretreatment MRI and whole slide images (WSIs) to predict IC response and OS in LANPC. Pretreatment MRI and WSIs from 404 patients with LANPC were retrospectively collected to construct a multi-task model (MoEMIL) for the simultaneous prediction of early IC response and OS. In our cohort, no progressive disease cases were observed; therefore, the poor responder group consisted exclusively of patients with stable disease. MoEMIL employed multi-instance learning to process WSIs, PyRadiomics and a convolutional neural network (ResNet50) to extract MRI features, and fused multimodal features through a multi-gate mixture-of-experts architecture. Clustering-constrained attention multiple instance learning and gradient-weighted class activation mapping were applied for visualization and interpretation. MoEMIL effectively stratified patients into good and poor IC response groups, achieving areas under the curve of 0.917, 0.869, and 0.801 in the train, validation, and test sets, respectively. In the test set, MoEMIL significantly outperformed the deep learning radiomics model and TNM staging for both endpoints. Compared to the Pathomics model, MoEMIL achieved significant improvement for OS (P = 0.0049) and borderline improvement for IC response (P = 0.064). The model could stratify patients into high- and low-risk OS groups (P < 0.05). MoEMIL might be an adjunctive tool for early induction chemotherapy response prediction and prognostic stratification in LANPC.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001378"},"PeriodicalIF":7.7,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637888/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119810","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":"Artificial intelligence for evaluation of magnetic resonance imaging-detected extramural vascular invasion in rectal cancer.","authors":"Haitao Huang, Lili Feng, Min-Er Zhong, Huifen Ye, Zhenhui Li, Su Yao, Yunrui Ye, Yulin Liu, Minning Zhao, Weixiong Xu, Lifen Yan, ChuanMiao Xie, Changhong Liang, Zaiyi Liu, Tong Tong, Yanfen Cui, Xin-Juan Fan, Ke Zhao","doi":"10.1371/journal.pdig.0001763","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001763","url":null,"abstract":"<p><p>MRI-detected extramural vascular invasion (mrEMVI) is an important prognostic biomarker in rectal cancer, reflecting tumor invasiveness and metastatic potential. To address the subjectivity and inter-observer variability inherent in manual mrEMVI assessment, this study trained and validated an nnUNet-based segmentation model for automated voxel-level localization and visualization of mrEMVI. This multi-center retrospective study included a total of 2,501 rectal cancer patients, comprising 1,830 in the training cohort (with 5-fold cross-validation) and 671 in two independent external test cohorts. The Dice similarity coefficient was used to evaluate segmentation performance; the inter-reader agreement for mrEMVI identification was assessed using Cohen's kappa (κ). The prognostic value of mrEMVI status identified by the artificial intelligence (AI) model was evaluated using Kaplan-Meier survival analysis and multivariable Cox regression. In internal five-fold cross-validation, the model yielded Dice scores of 0.850, 0.442, and 0.335 for tumor, intravascular tumor signal, and dilated vessel segmentation, respectively. The model demonstrated strong classification performance, with accuracies of 81.5% (95% CI: 76.7%-85.8%) and 84.7% (95% CI: 80.7%-88.2%) in the two external test cohorts, and achieved substantial agreement with senior radiologists (κ = 0.713-0.736). Patients identified as AI-mrEMVI+ had significantly lower 3-year disease-free survival (DFS) and 5-year overall survival (OS) rates than AI-mrEMVI- patients (DFS: 62.3% vs. 84.9%, HR = 2.67, 95% CI: 1.95-3.66; OS: 68.7% vs. 87.1%, HR = 2.64, 95% CI: 1.75-3.97; both p < 0.001). This work establishes a scalable, objective framework for mrEMVI assessment based on voxel-level segmentation, inter-observer agreement analysis, and comprehensive prognostic validation, with direct implications for risk stratification and treatment individualization in rectal cancer.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001763"},"PeriodicalIF":7.7,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119730","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":"Value in app store metadata and user reviews: A dual perspective on quality of Parkinson's and dementia apps.","authors":"Isabel Schwaninger, Paria Ighanian, Liyousew Borga, Marijus Giraitis, Petra Hoogendoorn, Jochen Klucken","doi":"10.1371/journal.pdig.0001730","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001730","url":null,"abstract":"<p><p>App stores provide a range of health applications for people living with Alzheimer's disease (AD) and Parkinson's disease (PD). Users like patients can access information from both manufacturer-provided app descriptions and metadata, as well as from user reviews. However, navigating this information to identify value-generating apps of high quality remains challenging. From a health technology assessment (HTA) standpoint, quality is defined by evidence-based medicine, safety, and user-centeredness. To explore the potential value of app store information available to patients, we conducted a descriptive, mixed-methods analysis of unstructured app metadata and user feedback from the Apple App Store and Google Play Store (as of May 2024). We analyzed 1,237 AD/PD-related apps which included 50 duplicates (resulting in 1,187 apps), utilizing descriptive statistics, content analysis, large language model-supported exploratory classification, and a topic modeling approach. In total, only about 2% of the apps claimed to be certified medical devices. Moreover, 24% of Apple apps and 14% of Google apps were in the \"Medical\" app store genre, among which we found that 63% of Apple and 54% of Google apps were patient-facing. We manually categorized patient-facing apps predominantly under \"Care Support,\" followed by \"Health & Wellness\" and \"Patient Monitoring.\" Importantly, user feedback provided exploratory, potentially valuable patient-reported outcome and experience information but is derived from personal opinions on \"user experience,\" \"health improvement,\" and \"costs.\" As quality information on DHTs could be identified in unstructured app metadata, this information should be improved in trustworthiness and more accessible to users like patients, supporting the public to find high-quality health apps. Furthermore, as user opinions contained information with potential value for patients, these should be explored as complementary value-generating indicators of health apps in future work.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001730"},"PeriodicalIF":7.7,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630307/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119912","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":"The use of artificial intelligence in assessing fever in the returning traveller: A scoping review.","authors":"Bhavya Gandhi, Leo Morjaria, Imeth Illamperuma, Meha Bhatt, Andrew Kapoor","doi":"10.1371/journal.pdig.0001742","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001742","url":null,"abstract":"<p><p>Fever in the returning traveller is a challenging presentation that requires a wide array of clinical expertise and draws on complex medical decision-making. Recent advancements in artificial intelligence have shown it can be a helpful clinical support tool in this context. This scoping review, conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines and registered on the Open Science Framework (https://doi.org/10.17605/OSF.IO/BSPKX), aimed to identify the current state of artificial intelligence use in assessing fever in the returning traveller. Here we describe the three eligible studies evaluating three distinct AI approaches identified in the literature. These heterogenous studies reported promising performance on study-specific endpoints in controlled settings. Given the lack of external validation, narrow populations studied, and absence of real-world implementation or user acceptance testing, further research is needed to explore this technology in a real-world clinical setting. The limited available evidence suggests that AI may have future potential to support assessment of fever in the returning traveller; however, clinical utility, safety, and real-world effectiveness remain unestablished. Large language models represent an emerging area of interest but were not evaluated in the studies included in this review.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001742"},"PeriodicalIF":7.7,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630189/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119800","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":"STREAM: A data-driven framework for physiological state monitoring in ICU patients.","authors":"Ali Namvar, Sundaresh Ram, Wassim W Labaki, Stefanie Galban, Njira L Lugogo, Craig J Galban","doi":"10.1371/journal.pdig.0001753","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001753","url":null,"abstract":"<p><p>Intensive care unit (ICU) monitoring systems face a critical gap: translating continuous physiological data into interpretable patterns that support clinical assessment. Existing approaches rely on static thresholds or severity scores that fail to capture dynamic disease progression patterns and provide limited insight into why patients change over time. We developed STREAM (State Trajectory Representation and Evolution-Aware Monitoring), which models each patient as a point in a multidimensional physiological space and applies geometric analysis of routine ICU data to track physiological instability. STREAM analyzes 26 routinely collected clinical measurements using optimal transport theory to discover data-derived physiological states without predefined categories and maps each patient to their nearest state. We evaluated STREAM using the multicenter eICU Collaborative Research Database (N = 158,294) for development and MIMIC-IV (N = 84,517) for external validation. STREAM identified five reproducible data-derived physiological states with distinct clinical signatures. Patients who spent less than 10% of their ICU stay within their expected state (state outliers) had ICU mortality of 37.6%, 16-fold higher than those who remained within their assigned states (2.3%). Mortality prediction achieved an area under the receiver operating characteristic curve of 0.863 at 8 hours and 0.903 at 72 hours, with excellent calibration (expected calibration error of 0.002). External validation on MIMIC-IV maintained robust performance (0.798 and 0.857, respectively), with state outliers exhibiting 10-fold higher mortality (33.5% vs. 3.2%). Feature importance analysis identified which laboratory values and vital signs are associated with movement toward higher-risk states, providing interpretable clinical explanations. STREAM provides transparent monitoring across data-derived physiological states, linking state dynamics with outcome prediction. Strong discrimination, calibration, and reproducibility across multicenter datasets support the method's potential for prospective evaluation.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001753"},"PeriodicalIF":7.7,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630200/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119797","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":"Impacts of digital third-wave interventions for adults on wellbeing and mental health outcomes: A systematic review and meta-analysis of randomized controlled trials.","authors":"Tom C Gordon, Andrew H Kemp, Josh Hope-Bell, Darren J Edwards","doi":"10.1371/journal.pdig.0001764","DOIUrl":"https://doi.org/10.1371/journal.pdig.0001764","url":null,"abstract":"<p><p>To synthesise the efficacy of digital third-wave process-based interventions (e.g., ACT, Mindfulness, Compassion) for improving wellbeing and ameliorating mental health symptoms in adults. A prospectively registered systematic review (OSF: 10.17605/OSF.IO/5RMU2) and random-effects meta-analysis of randomised controlled trials (RCTs) was conducted across six databases through January 2026. Certainty of evidence was assessed using the GRADE framework. Interventions (k = 147; N = 26,391) yielded small-to-moderate immediate post-intervention improvements in wellbeing (k = 46, g = 0.36), depression (k = 110, g = 0.44), anxiety (k = 93, g = 0.40), stress (k = 66, g = 0.46), quality of life (k = 32, g = 0.30), and psychological flexibility (k = 51, g = 0.41). Heterogeneity was substantial across most outcomes (I2 > 75%). Benefits were observed across healthy (61 trials; n = 15,770), mental health (41 trials; n = 6,130), and medical samples (46 trials; n = 4,491), with population type not significantly moderating immediate post-intervention effects. Comparator type significantly moderated several analyses, with smaller effects against active than inactive controls. Guidance did not significantly moderate immediate post-intervention effects, although it predicted larger short-term depression effects (QM = 4.17, p = .048). At short-term follow-up, effects remained statistically supported across all outcomes, while only depression, anxiety, and stress remained statistically supported at medium-term follow-up. GRADE certainty was moderate for most immediate post-intervention outcomes and low for quality of life. Digital third-wave interventions produced small-to-moderate average benefits across symptom-focused, wellbeing-focused, and process outcomes. Effects were smaller against active comparators, indicating that pooled benefits should be interpreted in relation to comparator intensity. Future research should prioritise rigorous active controls, longer follow-up, and direct tests of whether changes in psychological flexibility mediate improvements in symptoms and wellbeing.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 10","pages":"e0001764"},"PeriodicalIF":7.7,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630215/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119772","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":"Artificial intelligence for dysphagia screening: A machine learning approach.","authors":"Rafaela Soares Rech, Carla Diniz Lopes Becker, Dieine Estela Bernieri Schiavon, Danielli Pires Vieira, Juliana Balbinot Hilgert, Fernando Neves Hugo","doi":"10.1371/journal.pdig.0001755","DOIUrl":"10.1371/journal.pdig.0001755","url":null,"abstract":"<p><p>Early and reliable screening for oropharyngeal dysphagia symptoms in at-risk populations is a crucial first stage in effective management. This study aims to propose a machine learning model that can predict whether individuals are at risk of having confirmed dysphagia based on diagnostic accuracy. This was an exploratory cross-sectional diagnostic accuracy study. Adults and older adults were screened and assessed, and a videofluoroscopy swallowing study was performed to confirm dysphagia in participants with complaints about swallowing and signs or symptoms identified in the clinical assessment by a speech therapist. Eight algorithms were tested based on a theoretical model to evaluate their diagnostic accuracy: Naive Bayes, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Multilayer Perceptron, and Convolutional Neural Networks. The Pandas library in Python was used for data visualization and manipulation. In total, 465 participants were included, of whom 153 had dysphagia. A screening with 15 items related to personal, health, and oral health characteristics is proposed. The final four best-performing models were Naive Bayes (accuracy 0.76, sensitivity 0.84), Logistic Regression (accuracy 0.79, sensitivity 0.82), Support Vector Machine (accuracy 0.78, sensitivity 0.79), and Convolutional Neural Network (accuracy 0.78, sensitivity 0.74). The use of artificial intelligence based on different machine-learning approaches is promising for dysphagia screening, demonstrating adequate diagnostic accuracy. Future studies should be conducted to externally validate the proposed screening models.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"5 9","pages":"e0001755"},"PeriodicalIF":7.7,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13623117/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082990","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}