DIGITAL HEALTH最新文献

{"title":"Healthcare professionals' readiness and perceived barriers to drone-assisted emergency healthcare in Palestine.","authors":"Nawaf Amro, Mohammad Qtait, Regina Allande Cussó, Waed Ayoub, Eleen Arar, Rula Sayed Ahmad, Aya Salameh, Mohammad Joma, Rebhi Bsharat, Juan Gómez Salgado","doi":"10.1177/20552076261484721","DOIUrl":"10.1177/20552076261484721","url":null,"abstract":"<p><strong>Introduction: </strong>Drone technology has emerged as a promising tool for improving emergency medical response systems, particularly in regions experiencing logistical and political constraints, such as Palestine. This study aimed to assess healthcare professionals' readiness for and perceived barriers to drone-assisted emergency healthcare in Palestine and to identify key barriers to the integration of drone-assisted healthcare services.</p><p><strong>Methods: </strong>A descriptive cross-sectional study was conducted between February 1 and April 30, 2025, using an online questionnaire. A total of 409 healthcare professionals, including nurses, physicians, paramedics, and anesthesia technicians, participated in the study. Readiness was assessed using mean scores, with readiness levels classified using an equal-width interval method as low (1.00-2.33), moderate (2.34-3.67), or high (3.68-5.00). Perceived structural and implementation barriers were also evaluated. Data were analyzed using the Statistical Package for the Social Sciences (SPSS), version 27, with descriptive and inferential statistics.</p><p><strong>Results: </strong>The overall mean readiness score was 3.53 ± 0.69, indicating a moderate level of readiness for drone-assisted emergency healthcare. At the individual level, 48.4% of participants were classified as having high readiness and 44.8% as having moderate readiness. Significant differences in readiness were observed according to marital status (<i>p</i> = .036), educational level (<i>p</i> = .014), and work setting (<i>p</i> = .001), with higher readiness observed among participants working in non-governmental institutions. The most frequently reported barriers were logistical and environmental challenges (95.7%), human resource and training gaps (95.2%), and the absence of clear national drone policies (81.0%).</p><p><strong>Conclusion: </strong>Healthcare professionals in Palestine demonstrated an overall moderate level of readiness toward drone-assisted emergency healthcare; however, substantial structural, workforce, and regulatory barriers remain. Addressing these challenges through policy development, targeted training, and infrastructure enhancement is essential to facilitate effective implementation.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261484721"},"PeriodicalIF":3.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13535075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI radiomics-based machine learning model for complete response classification after chemoradiotherapy in advanced rectal cancer.","authors":"Jin Young Min, Jun Young Park, Young Jae Kim, Youngbae Jeon, Kwang Gi Kim, Jeong-Heum Baek","doi":"10.1177/20552076261484806","DOIUrl":"10.1177/20552076261484806","url":null,"abstract":"<p><strong>Objective: </strong>Accurate identification of complete response (CR) after neoadjuvant chemoradiotherapy (NCRT) is essential for selecting candidates for watch-and-wait treatment in advanced rectal cancer. This study aimed to develop and evaluate a magnetic resonance imaging (MRI) radiomics-based machine learning model to classify CR and Non-CR in post-NCRT rectal MRI images.</p><p><strong>Methods: </strong>Using region-of-interest masks, 107 radiomic features were extracted and normalized to a 0-1 range using min-max scaling. Four feature selection methods (ANOVA, RFE, SBS, and LASSO) were paired with four classifiers (LR, SVM, RF, and XGB), and all combinations were evaluated through 5-fold cross-validation in the training set using mean ROC AUC as the comparison metric.</p><p><strong>Results: </strong>Among 16 combinations, RFE + SVM achieved the highest cross-validation AUC of 0.89. On an independent test set, the model achieved a sensitivity of 0.84, specificity of 0.80, accuracy of 0.82, and F1-score of 0.82. The most informative features were intensity and local texture features, including TotalEnergy, 10Percentile, Coarseness, Strength, Correlation, ZoneEntropy, and Idmn.</p><p><strong>Conclusions: </strong>MRI radiomics combined with machine learning shows preliminary promise as an exploratory approach for classifying CR and Non-CR after NCRT in rectal cancer. Given the retrospective, single-center design and the absence of external validation, these findings should be interpreted as preliminary, and prospective multicenter validation is required before clinical implementation. A multicenter external validation integrating endoscopy and digital rectal examination findings is planned to enhance generalizability and clinical utility.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261484806"},"PeriodicalIF":3.9,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530500/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"\"Coach in your pocket\": Men's digital self-management of type 2 diabetes.","authors":"Ledric D Sherman, Kaileigh Carter","doi":"10.1177/20552076261487026","DOIUrl":"10.1177/20552076261487026","url":null,"abstract":"<p><strong>Objective: </strong>To explore how adult men use digital technologies to support type 2 diabetes self-management and examine the perceived benefits, challenges, and meanings associated with technology use in everyday life.</p><p><strong>Methods: </strong>A qualitative study was conducted with 41 adult men with type 2 diabetes recruited between September 2025 and May 2026 through Prolific, community-based outreach, social media, and participant referrals. Semi-structured interviews were conducted virtually via Zoom, lasted approximately 25-75 minutes, and were professionally transcribed. Both authors analyzed transcripts using an inductive thematic approach in MAXQDA. Data saturation was observed at approximately interviews 36-38, with the remaining scheduled interviews supporting the adequacy of the dataset.</p><p><strong>Results: </strong>Six interrelated themes characterized participants' experiences: real-time monitoring and awareness; technology as a reminder and organizational tool; learning and self-education; communication with healthcare providers; motivation and accountability; and barriers and frustrations with technology use. Across themes, participants described digital tools as helping them act independently on health information, maintain routines, make diabetes visible and actionable, and approach clinical encounters with organized personal data. Cost, usability, and trust in device accuracy remained important constraints.</p><p><strong>Conclusions: </strong>Digital technologies were embedded in participants' everyday diabetes self-management and often supported autonomy, practical problem-solving, accountability, and communication. Digital interventions for men with type 2 diabetes may be most useful when they provide actionable feedback, support self-directed management, integrate with clinical care, and minimize cost and usability burdens.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261487026"},"PeriodicalIF":3.9,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From sequential prediction to clinical utility: Reframing admission-time length-of-stay modeling for ICU care.","authors":"Kaijian Yang","doi":"10.1177/20552076261462690","DOIUrl":"10.1177/20552076261462690","url":null,"abstract":"","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261462690"},"PeriodicalIF":3.9,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530461/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bias in administrative coding for mitral valve prolapse: Implications for electronic health record research.","authors":"Anand Shah, Faisal F Syed, Shaaf Ahmad, Jeffrey L Klein","doi":"10.1177/20552076261486963","DOIUrl":"10.1177/20552076261486963","url":null,"abstract":"<p><strong>Objectives: </strong>Electronic health records and administrative claims are increasingly utilized for conducting observational studies, pragmatic clinical trials, and training machine learning models. For accurate and reliable conclusions, input data requires validation. We sought to evaluate International Classification of Diseases, Tenth Revision (ICD-10) diagnosis coding for Mitral valve prolapse (MVP).</p><p><strong>Methods: </strong>We compared ICD-10 diagnosis coding for MVP with echocardiographic evidence of MVP in a large academic center over the years 2018 - 2024.</p><p><strong>Results: </strong>Among 5,520 patients with an MVP ICD-10 code (I34.1), 1,883 had echocardiographic confirmation (positive predictive value 34.1%, 95% CI 32.9% - 35.4%). Among 5,667 patients with echocardiographic confirmed MVP, 3,784 lacked the corresponding ICD-10 code (sensitivity was 33.2%, 95% CI 32.0 % - 34.5%). In sub-analysis with granular covariates (N = 1,183), false-positive coding was associated with higher prevalence of atrial fibrillation, heart failure, and coronary artery disease than patients with confirmed MVP in univariate analysis. In multivariable analysis, heart failure was associated with increased odds of false-positive ICD coding (aOR 1.77, 95% CI 1.08 - 2.89; p = 0.02).</p><p><strong>Conclusions: </strong>These findings suggest that administrative MVP codes do not accurately identify patients with the disease and appear to introduce non-random phenotype bias with implications for EHR research and machine learning.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261486963"},"PeriodicalIF":3.9,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530510/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SA-FGPN: Stability-aware feature-gated progressive learning for pediatric brain tumor classification from high dimensional gene expression data.","authors":"Qiuhong Ma, Qifang Cai, Yuqing Liu, Lifeng Li, Ke Jin","doi":"10.1177/20552076261484299","DOIUrl":"10.1177/20552076261484299","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objectives: &lt;/strong&gt;Accurate pediatric brain tumor classification from gene expression data remains challenging due to the extremely high-dimensional nature of transcriptomic datasets, where tens of thousands of features are available from only a limited number of samples. This imbalance increases the risk of overfitting, unstable feature selection, and unreliable performance estimation. Moreover, molecular heterogeneity among pediatric brain tumor subtypes makes robust prediction and biological interpretation difficult. This study aims to develop a stable and interpretable deep learning framework for pediatric brain tumor classification from transcriptomic profiles.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We propose a Stability-Aware Feature-Gated Progressive Network (SA-FGPN) that integrates leakage-controlled preprocessing, low-rank transcriptomic compression, progressive nonlinear dimensionality reduction, residual projection bottleneck learning, feature-interaction modeling, and stability-aware feature gating. The low-rank compressor reduces model complexity under the &lt;math&gt;&lt;mrow&gt;&lt;mi&gt;D&lt;/mi&gt; &lt;mo&gt;≫&lt;/mo&gt; &lt;mi&gt;N&lt;/mi&gt;&lt;/mrow&gt; &lt;/math&gt; setting, while progressive representation learning and residual projections improve optimization stability. A sparsity- and consistency-regularized feature-gating mechanism is introduced to reduce dependence on unstable latent representations. For biological interpretation, fold-averaged Integrated Gradients are employed to identify important transcriptomic probes, followed by gene-stability analysis and functional enrichment analysis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Experiments were conducted on a pediatric brain tumor gene expression dataset containing 130 samples and 54,676 probe-level features. Under repeated stratified 5-fold cross-validation with 10 repetitions, SA-FGPN achieved an accuracy of &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.9847&lt;/mn&gt; &lt;mo&gt;±&lt;/mo&gt; &lt;mn&gt;0.0142&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , macro-F1 of &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.9728&lt;/mn&gt; &lt;mo&gt;±&lt;/mo&gt; &lt;mn&gt;0.0201&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; , and macro-AUC of &lt;math&gt;&lt;mrow&gt;&lt;mn&gt;0.9916&lt;/mn&gt; &lt;mo&gt;±&lt;/mo&gt; &lt;mn&gt;0.0078&lt;/mn&gt;&lt;/mrow&gt; &lt;/math&gt; . Across 30 repeated random stratified splits, the maximum observed accuracy was 0.9897. SA-FGPN consistently outperformed classical machine learning methods and recent deep learning baselines, including autoencoder-, CNN-, CNN-BiLSTM-, and transformer-based approaches. Statistical significance testing, calibration analysis, permutation testing, ablation experiments, computational evaluation, and gene-stability analysis further demonstrated the robustness and reliability of the proposed framework.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;SA-FGPN provides an effective, robust, and biologically interpretable solution for pediatric brain tumor classification from high-dimensional transcriptomic data. By integrating stability-aware feature selection with progressive representation learning, the proposed framework improves predictive performance while enabling the identification of biological","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261484299"},"PeriodicalIF":3.9,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530492/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Working under pressure: How virtual reality and psychoeducation shape stress and moral distress responses in nurses.","authors":"Karisa Parkington, Marianne Rouleau-Tang, Amit Bhat, Josh Martin, Alice Rueda, Bazen Gashaw Teferra, Yuqing Liu, Martin Ivanov, Benjamin C Darnell, Lindsay Beavers, Douglas M Campbell, Andrei Torres, Wendy Lou, Anthony Nazarov, Andrea R Ashbaugh, Brett Litz, Rakesh Jetly, Gillian Strudwick, Adam Dubrowski, Bill Kapralos, Sridhar Krishnan, Venkat Bhat","doi":"10.1177/20552076261484009","DOIUrl":"10.1177/20552076261484009","url":null,"abstract":"<p><strong>Introduction: </strong>Nurses face high levels of stress, particularly in high-pressure environments, such as hospitals. Digital interventions, including virtual reality (VR), offer promising avenues for educating frontline workers, monitoring momentary distress, and delivering evidence-based stress-reduction programs.</p><p><strong>Objectives: </strong>This study examined: (1) the tolerability, realism, and utility of a VR simulation for eliciting and monitoring stress among nurses; (2) within- (repeated measures) and between- (demographics) participant differences in stress and moral distress responses throughout the VR simulation and across runs; (3) knowledge retention of psychoeducation content; and (4) perceived success and helpfulness of stress-reduction strategies.</p><p><strong>Methods: </strong>Nursing professionals (<i>N</i> = 99) completed two runs of a hospital-based VR simulation interspersed with an 8-minute psychoeducation video regarding moral distress and stress-reduction techniques. Stress and moral distress were assessed in real-time during the simulation, alongside post-VR questionnaires assessing presence and cybersickness, and two interviews (debriefing and exit), analyzed using a qualitative coding schema. The STROBE checklist guided results reporting.</p><p><strong>Results: </strong>The VR simulation elicited distinct non-linear trajectories of acute stress and moral distress across simulation checkpoints and runs. The intervention was well-tolerated with low cybersickness (VRSQ: <i>M</i> = 13.29), high general presence (IPQ: <i>Mdn</i> = 5.00), and moderate spatial presence and realism (IPQ: <i>Mdn</i> = 3.00). Most participants recalled at least two of the three stress-reduction techniques with high ratings of perceived understanding and helpfulness. However, objective assessments revealed overestimations of conceptual understanding, highlighting gaps in knowledge retention and indicating that tailored, multi-modal psychoeducation may be necessary to ensure consistent uptake and effectiveness across the nursing workforce.</p><p><strong>Conclusion: </strong>Our hospital-based immersive VR simulation is a feasible and ethically sound method for inducing and monitoring stress and moral distress in nurses. Findings underscore the importance of triangulating self-report and objective measures to assess intervention effectiveness and inform future digital health education strategies.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261484009"},"PeriodicalIF":3.9,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13530541/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-driven health misinformation in Somalia's digital era: A neglected crisis demanding global action.","authors":"Samar Yusuf Omar, Maryama Ahmed Ali, Abdirahman Mohamed Adan, Ilyas Abdullahi Khalif","doi":"10.1177/20552076261481589","DOIUrl":"10.1177/20552076261481589","url":null,"abstract":"<p><p>The rapid expansion of artificial intelligence (AI) and generative technologies is transforming global health communication, but it is also accelerating the spread of health misinformation, particularly in fragile and low-resource settings. Somalia, characterized by limited digital health literacy, weak regulatory frameworks, and increasing reliance on social media for health information, represents a highly vulnerable context for AI-driven infodemics. This Letter to the Editor examines the emerging threat of AI-generated health misinformation in Somalia's digital landscape, highlighting its potential to undermine public trust, distort health behaviours, and weaken epidemic preparedness. It also explores the dual role of AI as both a risk amplifier and a potential solution, particularly through automated misinformation detection, digital health education, and multilingual information dissemination. Evidence suggests that generative AI tools can produce highly persuasive false health content at scale, making it difficult for users to distinguish between credible and misleading information. In Somalia, where institutional fact-checking mechanisms and digital governance structures remain underdeveloped, these risks are further intensified. The letter argues for urgent multisectoral action involving policymakers, healthcare institutions, academic bodies, and technology platforms to strengthen digital health literacy, establish AI governance frameworks, and enhance real-time misinformation surveillance. Addressing these challenges is essential to safeguarding public health, strengthening health system resilience, and ensuring equitable access to accurate health information in the digital era.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261481589"},"PeriodicalIF":3.9,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527336/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148867949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A targeted behavioral economics-based mobile health intervention to improve medication adherence in patients with hypertension: A three-arm randomized controlled trial.","authors":"Jan Strebel, Anjali Raja Beharelle, Michael Mayr, Valeriya Nemtsova, Joachim Zahnd, Gregoire Wuerzner, Georg Ehret, Michael Stiefel, Emrush Rexhaj, Théo Meister, Annina S Vischer, Thilo Burkard","doi":"10.1177/20552076261481025","DOIUrl":"10.1177/20552076261481025","url":null,"abstract":"<p><strong>Background: </strong>Non-adherence to antihypertensive therapy remains a major barrier to optimal blood pressure (BP) control. This study evaluated whether a multi-faceted medication adherence mobile application (mApp), with or without financial incentives (FI), improves adherence and BP compared with standard care.</p><p><strong>Methods: </strong>In this multicenter, randomized, open-label trial, outpatients with hypertension taking ≥4 pills/day were randomized to (A) mApp with FI, (B) mApp without FI, or (C) standard-of-care. Adherence was measured by Medication Event Monitoring System (MEMS) dispensers. Primary endpoint was median adherence at 90 days comparing A with C; the co-primary endpoint compared adherence during month 3 versus month 1. Secondary outcomes included self-reported adherence, office and ambulatory BP over 90 and 180 days.</p><p><strong>Results: </strong>Of 219 randomized participants, 176 (80.4%) completed the 90-day visit (median age 63 years; 23% women). Median adherence at 90 days was 95.6% in A and C (p=0.551). Median change in adherence from month 1 to month 3 was 0% in A and 1.6% in C (p=0.691). No significant differences were observed for BP. Self-reported adherence did not differ between groups, although within-group analyses showed improvement over time in A (p=0.001).</p><p><strong>Conclusions: </strong>In outpatients with hypertension and unexpectedly high observed adherence and no substantial BP elevation at baseline, neither the mApp nor FI improved MEMS-measured adherence or BP. Future interventions should focus on identifying and engaging patients with low medication adherence and sufficient room for BP improvement, for whom digital strategies may have greater impact.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261481025"},"PeriodicalIF":3.9,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527327/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148867837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maternal health data reliability: Findings from Sidama region, Ethiopia.","authors":"Belayneh Bekele Kare, Andargachew Kassa Biratu, Mark Spigt","doi":"10.1177/20552076261484695","DOIUrl":"10.1177/20552076261484695","url":null,"abstract":"<p><strong>Background: </strong>High-quality routine health information is critical for monitoring maternal health indicators and guiding effective health interventions. However, data quality remains a persistent challenge in low-resource settings like Ethiopia, particularly at sub-national levels. This study assessed the reliability of maternal health service data and its determinants in public health facilities in Sidama Region, Ethiopia.</p><p><strong>Methods: </strong>Institution-based cross-sectional study was conducted from January 5 to 30, 2025 on 517 maternal health service units selected by a multistage sampling method. Data collection tool was adapted from the Performance of Routine Information System Management framework. Data were collected from each unit by using structured interviews with health professionals and reviews of registration books, individual medical records, and monthly reports. Data quality was measured by accuracy, internal consistency, completeness, and timeliness. Multilevel logistic regression was used to identify factors associated with good data quality.</p><p><strong>Results: </strong>Overall, 63.1% of service delivery units demonstrated good data quality. Register content completeness (66.5%), report timeliness (65.0%), and report accuracy (59.2%) showed relatively high performance, while internal consistency (34.0%) and report content completeness (37.9%) remained low. Factors significantly associated with good data quality included the availability of standardized indicators (AOR = 2.30), user-friendly reporting formats (AOR = 2.94), trained staff (AOR = 2.33), and supervisory feedback (AOR = 2.49). Health posts were significantly less likely to achieve good data quality compared to hospitals (AOR = 0.19).</p><p><strong>Conclusion: </strong>Maternal health data quality, particularly internal consistency and report completeness, in Sidama Region was below the national standards. Improving data quality should prioritize strengthening technical capacity, enhancing supervision and feedback, promoting staff motivation, and investing in under-resourced health posts.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"12 ","pages":"20552076261484695"},"PeriodicalIF":3.9,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13527323/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148868021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}