PLOS digital health最新文献

{"title":"Evaluating knowledge fusion models on detecting adverse drug events in text.","authors":"Philipp Wegner, Holger Fröhlich, Sumit Madan","doi":"10.1371/journal.pdig.0000468","DOIUrl":"10.1371/journal.pdig.0000468","url":null,"abstract":"<p><p>Detecting adverse drug events (ADE) of drugs that are already available on the market is an essential part of the pharmacovigilance work conducted by both medical regulatory bodies and the pharmaceutical industry. Concerns regarding drug safety and economic interests serve as motivating factors for the efforts to identify ADEs. Hereby, social media platforms play an important role as a valuable source of reports on ADEs, particularly through collecting posts discussing adverse events associated with specific drugs. We aim with our study to assess the effectiveness of knowledge fusion approaches in combination with transformer-based NLP models to extract ADE mentions from diverse datasets, for instance, texts from Twitter, websites like askapatient.com, and drug labels. The extraction task is formulated as a named entity recognition (NER) problem. The proposed methodology involves applying fusion learning methods to enhance the performance of transformer-based language models with additional contextual knowledge from ontologies or knowledge graphs. Additionally, the study introduces a multi-modal architecture that combines transformer-based language models with graph attention networks (GAT) to identify ADE spans in textual data. A multi-modality model consisting of the ERNIE model with knowledge on drugs reached an F1-score of 71.84% on CADEC corpus. Additionally, a combination of a graph attention network with BERT resulted in an F1-score of 65.16% on SMM4H corpus. Impressively, the same model achieved an F1-score of 72.50% on the PsyTAR corpus, 79.54% on the ADE corpus, and 94.15% on the TAC corpus. Except for the CADEC corpus, the knowledge fusion models consistently outperformed the baseline model, BERT. Our study demonstrates the significance of context knowledge in improving the performance of knowledge fusion models for detecting ADEs from various types of textual data.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000468"},"PeriodicalIF":0.0,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11918363/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659939","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":"What makes clinical machine learning fair? A practical ethics framework.","authors":"Marine Hoche, Olga Mineeva, Gunnar Rätsch, Effy Vayena, Alessandro Blasimme","doi":"10.1371/journal.pdig.0000728","DOIUrl":"10.1371/journal.pdig.0000728","url":null,"abstract":"<p><p>Machine learning (ML) can offer a tremendous contribution to medicine by streamlining decision-making, reducing mistakes, improving clinical accuracy and ensuring better patient outcomes. The prospects of a widespread and rapid integration of machine learning in clinical workflow have attracted considerable attention including due to complex ethical implications-algorithmic bias being among the most frequently discussed ML models. Here we introduce and discuss a practical ethics framework inductively-generated via normative analysis of the practical challenges in developing an actual clinical ML model (see case study). The framework is usable to identify, measure and address bias in clinical machine learning models, thus improving fairness as to both model performance and health outcomes. We detail a proportionate approach to ML bias by defining the demands of fair ML in light of what is ethically justifiable and, at the same time, technically feasible in light of inevitable trade-offs. Our framework enables ethically robust and transparent decision-making both in the design and the context-dependent aspects of ML bias mitigation, thus improving accountability for both developers and clinical users.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000728"},"PeriodicalIF":0.0,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11918422/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659941","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":"Maternal information-seeking on pregnancy-induced hypertension and associated factors among pregnant women, in low resource country, A cross-sectional study design.","authors":"Ayana Alebachew Muluneh, Fekade Demeke Bayou, Kegnie Shitu, Ayenew Sisay Gebeyew, Sefefe Birhanu Tizie, Mulugeta Desalegn Kasaye, Adamu Ambachew Shibabaw, Agmasie Damtew Walle","doi":"10.1371/journal.pdig.0000740","DOIUrl":"10.1371/journal.pdig.0000740","url":null,"abstract":"<p><p>Pregnancy-induced hypertension is the most prevalent medical problem associated with pregnancy. It has been reported to affect 6-10% of all pregnant women worldwide. Mothers' failure to seek information related to PIH increases the risk of death from the complication of pregnancy-induced hypertension. This study aimed to assess PIH information-seeking behaviour and its associated factors among pregnant women in rural Sekela Woreda. A community-based cross-sectional study was conducted from May 15 to June 15, 2022. An interviewer-administered structured questionnaire was used to collect the data. The sample size was 635. A cluster sampling technique was used to select the sampled kebeles. The study population included rural pregnant women. This study included pregnant women who were permanent residents of the study area, whereas this study excluded pregnant women who were admitted only for delivery services and temporary residents who visited the study area. The mean age of the participants was 31.8 ± 6.09 years, with minimum and maximum ages of 20 and 45 years, respectively. We conducted descriptive analysis, bivariable analysis, and multivariable analysis to identify determinants of PIH information seeking. The proportion of pregnancy-induced hypertension (PIH) information seeking among pregnant women was 214 (35.4%) out of 604. Pregnant mothers aged 35 years and above (AOR =0.67, 95% CI =0.46, 0.97), family resistance (AOR = 0.45, 95% CI =0.29, 0.69), health care satisfaction (AOR =1.7, 95% CI =1.1, 2.5), and perceived severity of pregnancy-induced hypertension (PIH) (AOR =1.6, 95% CI =1.1, 2.4) were significantly associated with pregnancy-induced hypertension information seeking. According to our findings Information seeking related to pregnancy-induced hypertension is low. Aged mothers, family resistance, mothers' satisfaction with health care services, and perceived severity of PIH were found to be associated with pregnancy-induced hypertension information seeking. Expanding health education programs for pregnant women and providing awareness and training about PIH to participants and their husbands is the most effective way to reduce the prevalence of PIH complications.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000740"},"PeriodicalIF":0.0,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11957557/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659940","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 NASSS (Non-Adoption, Abandonment, Scale-Up, Spread and Sustainability) framework use over time: A scoping review.","authors":"Hwayeon Danielle Shin, Emily Hamovitch, Evgenia Gatov, Madison MacKinnon, Luma Samawi, Rhonda Boateng, Kevin E Thorpe, Melanie Barwick","doi":"10.1371/journal.pdig.0000418","DOIUrl":"10.1371/journal.pdig.0000418","url":null,"abstract":"&lt;p&gt;&lt;p&gt;The Non-adoption, Abandonment, Scale-up, Spread, Sustainability (NASSS) framework (2017) was established as an evidence-based, theory-informed tool to predict and evaluate the success of implementing health and care technologies. While the NASSS is gaining popularity, its use has not been systematically described. Literature reviews on the applications of popular implementation frameworks, such as the RE-AIM and the CFIR, have enabled their advancement in implementation science. Similarly, we sought to advance the science of implementation and application of theories, models, and frameworks (TMFs) in research by exploring the application of the NASSS in the five years since its inception. We aim to understand the characteristics of studies that used the NASSS, how it was used, and the lessons learned from its application. We conducted a scoping review following the JBI methodology. On December 20, 2022, we searched the following databases: Ovid MEDLINE, EMBASE, PsychINFO, CINAHL, Scopus, Web of Science, and LISTA. We used typologies and frameworks to characterize evidence to address our aim. This review included 57 studies that were qualitative (n=28), mixed/multi-methods (n=13), case studies (n=6), observational (n=3), experimental (n=3), and other designs (e.g., quality improvement) (n=4). The four most common types of digital applications being implemented were telemedicine/virtual care (n=24), personal health devices (n=10), digital interventions such as internet Cognitive Behavioural Therapies (n=10), and knowledge generation applications (n=9). Studies used the NASSS to inform study design (n=9), data collection (n=35), analysis (n=41), data presentation (n=33), and interpretation (n=39). Most studies applied the NASSS retrospectively to implementation (n=33). The remainder applied the NASSS prospectively (n=15) or concurrently (n=8) with implementation. We also collated reported barriers and enablers to implementation. We found the most reported barriers fell within the Organization and Adopter System domains, and the most frequently reported enablers fell within the Value Proposition domain. Eighteen studies highlighted the NASSS as a valuable and practical resource, particularly for unravelling complexities, comprehending implementation context, understanding contextual relevance in implementing health technology, and recognizing its adaptable nature to cater to researchers' requirements. Most studies used the NASSS retrospectively, which may be attributed to the framework's novelty. However, this finding highlights the need for prospective and concurrent application of the NASSS within the implementation process. In addition, almost all included studies reported multiple domains as barriers and enablers to implementation, indicating that implementation is a highly complex process that requires careful preparation to ensure implementation success. Finally, we identified a need for better reporting when using the NASSS in implementa","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000418"},"PeriodicalIF":0.0,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11913280/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143652342","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":"Systemic transphobia and ongoing barriers to healthcare for transgender and nonbinary people: A historical analysis of #TransHealthFail.","authors":"Allison J McLaughlin, Saren Nonoyama, Lauren Glupe, Jordon D Bosse","doi":"10.1371/journal.pdig.0000718","DOIUrl":"10.1371/journal.pdig.0000718","url":null,"abstract":"<p><p>Transgender (T+) people report negative healthcare experiences such as being misgendered, pathologizing gender, and gatekeeping care, as well as treatment refusal. Less is known about T+ patients' perceptions of interrelated factors associated with, and consequences of, negative experiences. The purpose of this analysis was to explore T+ patients' negative healthcare experiences through Twitter posts using the hashtag #transhealthfail. Publicly available Tweets published between July 2015 and November 2021 from US-based Twitter accounts were collected via Mozdeh. Tweets were deductively analyzed for content using a list of a-priori codes developed from existing literature. Additional codes were developed as new ideas emerged from the data. When possible, type of care location, providers interacted with, and initial reason for seeking care were extracted. Each Tweet was coded by at least two team members using NVivo12. A total of 1,340 tweets from 652 unique Twitter users were analyzed. Negative experiences were reported across healthcare settings and professional types, with physicians, nurses, and counselors/therapists being named most frequently. Primary antecedents of negative healthcare experiences and barriers to accessing care were related to health insurance issues and providers' lack of knowledge, discomfort, and binary gender beliefs. Negative healthcare interactions led T+ patients to perceive receiving a different standard of care and having unmet needs, which could lead to delaying/avoiding care in the future. As such, these results highlight the potential for direct and indirect harm related to providers' specific actions. Patient strategies to prevent and/or manage negative encounters and care facilitators were also identified. A multi-pronged approach addressing healthcare policy, improving knowledge and attitudes of healthcare providers and ancillary staff, and creating clinical settings that are physically and psychologically safe for T+ patients is critical to improving the healthcare experiences, and ultimately health, of T+ people.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000718"},"PeriodicalIF":0.0,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11902059/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143617894","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 Smart Triage combined with a quality improvement program for children presenting to facilities in Kenya and Uganda: An interrupted time series analysis.","authors":"J Mark Ansermino, Yashodani Pillay, Abner Tagoola, Cherri Zhang, Dustin Dunsmuir, Stephen Kamau, Joyce Kigo, Collins Agaba, Ivan Aine Aye, Bella Hwang, Stefanie K Novakowski, Charly Huxford, Matthew O Wiens, David Kimutai, Mary Ouma, Ismail Ahmed, Paul Mwaniki, Florence Oyella, Emmanuel Tenywa, Harriet Nambuya, Bernard Opar Toliva, Nathan Kenya-Mugisha, Niranjan Kissoon, Samuel Akech","doi":"10.1371/journal.pdig.0000466","DOIUrl":"10.1371/journal.pdig.0000466","url":null,"abstract":"<p><p>Sepsis occurs predominantly in low-middle-income countries. Sub-optimal triage contributes to poor early case recognition and outcomes from sepsis. Improved recognition and quality of care can lead to improved outcomes. We evaluated the impact of Smart Triage using improved time to intravenous antimicrobial administration in a multisite interventional study. Smart Triage, a digital platform with a risk score and clinical dashboard, was implemented (with control sites) in Kenya (February 2021-December 2022) and Uganda (April 2020-April 2022). Children presenting to the outpatient departments with an acute illness were enrolled. A controlled interrupted time series was used to assess the effect on time from arrival at the facility to intravenous antimicrobial administration. Secondary analyses included antimicrobial use, admission rates and mortality (NCT04304235). During the baseline period, the time to antimicrobials decreased significantly in Kenya (132 and 58 minutes) at control and intervention sites. In Uganda, the time to antimicrobials marginally decreased (3 minutes) at the intervention site. Then, during the implementation period in Kenya, the time to antimicrobials at the intervention site decreased by 98 min (57%, 95% CI 81-114) but increased by 49 min (21%, 95% CI: 23-76) at the control site. In Uganda, the time to antimicrobials initially decreased but was not sustained and there was no significant difference between intervention and control sites. At both intervention sites, there was a significant reduction in antimicrobial utilization of 47% (Kenya) and 33% (Uganda) compared to baseline. There was a reduction in admission rates of 47% (Kenya) and 33% (Uganda) compared to baseline. Mortality reduced by 25% (Kenya) and 75% (Uganda) compared to the baseline period. We showed significant improvements in time to intravenous antibiotics in Kenya but not Uganda, likely due to COVID-19, a short study period and resource constraints. The reduced antimicrobial use and admission and mortality rates are remarkable and welcome benefits. The admission and mortality rates should be interpreted cautiously as these were secondary outcomes. This study underlines the difficulty of implementing technologies and sustaining quality improvement in health systems.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000466"},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11892856/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598457","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":"Clinical validation of a novel hand dexterity measurement device.","authors":"Conor D Hayden, Bruce P Murphy, Deirdre Gilsenan, Bahman Nasseroleslami, Orla Hardiman, Deirdre Murray","doi":"10.1371/journal.pdig.0000744","DOIUrl":"10.1371/journal.pdig.0000744","url":null,"abstract":"<p><p>The lack of sensitive objective outcome measures for hand dexterity is a barrier for clinical assessment of neurological conditions and has negatively affected clinical trials. Here, we clinically validate a new method for measuring hand dexterity, a novel hand worn sensor that digitises the Finger Tapping Test. The device was assessed in a cohort of 180 healthy controls and 51 people with Amyotrophic Lateral Sclerosis (ALS) and compared against rating scales and traditional measures (Nine Hole Peg test and grip dynamometry). 14 features were extracted from the device and using a logistic regression algorithm, a 0-100 dexterity performance score was generated for each participant, which accounted for age/sex differences. The device returned objective ratings of a participant's hand dexterity (dominant, non-dominant and overall score). The average overall dexterity performance score in all healthy participants was 88 ± 17 (mean ± standard deviation). The overall dexterity score was statistically significantly worse in participants with ALS (age/sex matched healthy subset: 80 ± 20, ALS: 45 ± 32, p-value < 0.0001). The device also had a higher completion rate, (94% dominant hand) compared to the traditional measures (82% dominant hand). This test and scoring system have been validated and the regression model was developed using a framework that is potentially applicable to any relevant condition. This device could act as an objective outcome measure in clinical trials and may be useful in improving patient care.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000744"},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893126/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598456","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":"Introducing the Team Card: Enhancing governance for medical Artificial Intelligence (AI) systems in the age of complexity.","authors":"Lesedi Mamodise Modise, Mahsa Alborzi Avanaki, Saleem Ameen, Leo A Celi, Victor Xin Yuan Chen, Ashley Cordes, Matthew Elmore, Amelia Fiske, Jack Gallifant, Megan Hayes, Alvin Marcelo, Joao Matos, Luis Nakayama, Ezinwanne Ozoani, Benjamin C Silverman, Donnella S Comeau","doi":"10.1371/journal.pdig.0000495","DOIUrl":"10.1371/journal.pdig.0000495","url":null,"abstract":"<p><p>This paper introduces the Team Card (TC) as a protocol to address harmful biases in the development of clinical artificial intelligence (AI) systems by emphasizing the often-overlooked role of researchers' positionality. While harmful bias in medical AI, particularly in Clinical Decision Support (CDS) tools, is frequently attributed to issues of data quality, this limited framing neglects how researchers' worldviews-shaped by their training, backgrounds, and experiences-can influence AI design and deployment. These unexamined subjectivities can create epistemic limitations, amplifying biases and increasing the risk of inequitable applications in clinical settings. The TC emphasizes reflexivity-critical self-reflection-as an ethical strategy to identify and address biases stemming from the subjectivity of research teams. By systematically documenting team composition, positionality, and the steps taken to monitor and address unconscious bias, TCs establish a framework for assessing how diversity within teams impacts AI development. Studies across business, science, and organizational contexts demonstrate that diversity improves outcomes, including innovation, decision-making quality, and overall performance. However, epistemic diversity-diverse ways of thinking and problem-solving-must be actively cultivated through intentional, collaborative processes to mitigate bias effectively. By embedding epistemic diversity into research practices, TCs may enhance model performance, improve fairness and offer an empirical basis for evaluating how diversity influences bias mitigation efforts over time. This represents a critical step toward developing inclusive, ethical, and effective AI systems in clinical care. A publicly available prototype presenting our TC is accessible at https://www.teamcard.io/team/demo.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000495"},"PeriodicalIF":0.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11878906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Infusing behavior science into large language models for activity coaching.","authors":"Madhurima Vardhan, Narayan Hegde, Deepak Nathani, Emily Rosenzweig, Cathy Speed, Alan Karthikesalingam, Martin Seneviratne","doi":"10.1371/journal.pdig.0000786","DOIUrl":"https://doi.org/10.1371/journal.pdig.0000786","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1371/journal.pdig.0000431.].</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 3","pages":"e0000786"},"PeriodicalIF":0.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11875281/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560158","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":"Validation and user experience testing of DataCryptChain: An open-source standard combining blockchain technology with asymmetric encryption for private, secure, shareable, and tamper-proof research data.","authors":"Jeffrey Michael Franc","doi":"10.1371/journal.pdig.0000741","DOIUrl":"10.1371/journal.pdig.0000741","url":null,"abstract":"<p><p>DataCryptChain is an open-source standard combining blockchain with advanced encryption ensuring research data remains private, secure, shareable, and tamper-proof. Ability to detect intentional tampering of data was measured, and user experience was evaluated. In this study, simulated datasets were randomized to be tampered with or not tampered with, and detection of tampering was measured. Volunteer's ability to complete assigned tasks using the software was evaluated. Among 10000 simulated datasets (4436 randomized to tampering) there was 100% sensitivity and specificity for detection. All volunteers successfully installed DataCryptChain and 5/6 completed their tasks. All participants were able to transmit data without ever exposing unencrypted data and with no need to share passwords. Several deficiencies in the user experience were noted. Importantly, the test users felt that although they would be willing to use DataCryptChain in practice, it would need a more user-friendly interface. This study demonstrates a novel algorithm using blockchain and asymmetric encryption that, although previously documented theoretically, has never been published as a working software package. While DataCryptChain has 100% sensitivity and specificity for detecting data tampering, further development is needed to improve the user experience.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 2","pages":"e0000741"},"PeriodicalIF":0.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11849895/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493977","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}