PLOS digital health最新文献

{"title":"Performance of a smartphone-based malaria screener in detecting malaria in people living with Sickle cell disease.","authors":"Deborah Nimako Sarpong Obeng, Samuel Osei, Nii Kpakpo Brown, David Nana Adjei, Linda Eva Amoah, Ewurama Dedea Ampadu Owusu","doi":"10.1371/journal.pdig.0000884","DOIUrl":"10.1371/journal.pdig.0000884","url":null,"abstract":"<p><p>Novel automated digital malaria diagnostic tests are being developed with the advancement of diagnostic tools. Whilst these tools are being evaluated and implemented in the general population, there is the need to focus on special populations such as individuals with Sickle Cell Disease (SCD) who have altered red blood cell morphology and atypical immune responses, which can obscure parasite detection. This study aimed to evaluate the diagnostic performance of one of such tools, the National Library of Medicine (NLM) malaria screener app in people living with sickle cell disease in a malaria-endemic country, Ghana. A descriptive cross-sectional study was conducted among SCD patients attending the Sickle Cell Clinic at Korle Bu Teaching Hospital in Accra, Ghana. Following informed consent, whole blood samples were collected and analyzed using the NLM malaria screener app, conventional microscopy, RDT, and Polymerase Chain Reaction (PCR), with PCR as the reference standard. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of each diagnostic method were compared against PCR results. The NLM app identified the highest number of positive malaria cases, with 110 positive cases (36.2%), while both RDT and microscopy reported the highest number of negatives, with 287 negative cases (94.4%). Compared to PCR, the NLM app demonstrated a sensitivity of 89.5% and a specificity of 67.4%. RDT and microscopy displayed the same sensitivity as the NLM app, each achieving 89.5%. However, while RDT and microscopy had a specificity of 100%, the NLM app had a considerably lower specificity of 67.4%.The NLM malaria screener app shows promise as a preliminary screening tool for malaria in individuals with SCD. However, its lower specificity indicates a need for confirmatory testing to avoid potential overdiagnosis and mismanagement. Enhancements in the app's specificity could further support its utility in rapid and accessible malaria diagnosis for people with SCD, aiding in timely management and treatment.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000884"},"PeriodicalIF":0.0,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12148164/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144259522","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 illusion of safety: A report to the FDA on AI healthcare product approvals.","authors":"Rawan Abulibdeh, Leo Anthony Celi, Ervin Sejdić","doi":"10.1371/journal.pdig.0000866","DOIUrl":"10.1371/journal.pdig.0000866","url":null,"abstract":"<p><p>Artificial intelligence is rapidly transforming healthcare, offering promising advancements in diagnosis, treatment, and patient outcomes. However, concerns regarding the regulatory oversight of artificial intelligence driven medical technologies have emerged, particularly with the U.S. Food and Drug Administration's current approval processes. This paper critically examines the U.S. Food and Drug Administration's regulatory framework for artificial intelligence powered healthcare products, highlighting gaps in safety evaluations, post-market surveillance, and ethical considerations. Artificial intelligence's continuous learning capabilities introduce unique risks, as algorithms evolve beyond their initial validation, potentially leading to performance degradation and biased outcomes. Although the U.S. Food and Drug Administration has taken steps to address these challenges, such as artificial intelligence/machine learning-based software as a medical device action plan and proposed regulatory adjustments, significant weaknesses remain, particularly in real-time monitoring, transparency and bias mitigation. This paper argues for a more adaptive, community-engaged regulatory approach that mandates extensive post-market evaluations, requires artificial intelligence developers to disclose training data sources, and establishes enforceable standards for fairness, equity, and accountability. A patient-centered regulatory framework must also integrate diverse perspectives to ensure artificial intelligence technologies serve all populations equitably. By fostering an agile, transparent, and ethics-driven oversight system, the U.S. Food and Drug Administration can balance innovation with patient safety, ensuring that artificial intelligence-driven medical technologies enhance, rather than compromise, healthcare outcomes.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000866"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140231/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236162","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":"Pharmacist-led rapid uptitration clinic in heart failure patients with reduced ejection fraction: Our experience within a virtual ward.","authors":"Hussein Alhakem, Angela Murphy, Liuba Fusco, Grant McQueen, Sarah Pearse, Jodian Barrett, Deirdre Linnard, Sadia Khan","doi":"10.1371/journal.pdig.0000868","DOIUrl":"10.1371/journal.pdig.0000868","url":null,"abstract":"<p><p>Heart failure with reduced ejection fraction is a chronic, progressive medical condition affecting millions of individuals worldwide. It is associated with high morbidity and mortality. The use of \"foundational quadruple therapy\" titrated to the maximum tolerated doses improves survival, quality of life, and reduces heart failure-related hospitalisation. Despite this evidence, there is a consistent trend of suboptimal dose up-titration, prolonged optimisation periods, and early therapy discontinuation. Virtual wards offer a potential innovative solution in transforming heart failure management by combining rapid medication optimisation with remote monitoring to improve patient outcomes. This retrospective study employed a single-group pre-post design to evaluate the effectiveness of a prescribing pharmacist in the rapid uptitration of Guidelines Directed Medical Therapy (GDMT) in patients with heart failure with reduced ejection fraction within a virtual ward setting. The study assessed clinical outcomes of 86 patients at baseline, following discharge from the virtual ward (typically after 4 weeks), and at 3-6 months post-discharge. Improvements were seen in NYHA scores, cardiac systolic function, and Optimal Medical Therapy (OMT) scores. The median Left Ventricular Ejection Fraction increased from 29% at baseline to 39% post-optimisation, signifying improved myocardial performance and a reduction in the severity of left ventricular dysfunction. Post-optimisation, 37% of patients attained an optimal OMT score of 8, 52% attained an acceptable score (5-7), and only 5% remained in the suboptimal range (0-4). Additionally, 84% of patients were prescribed all four foundational therapies. There was no notable increase in adverse events such as hypotension, bradycardia, or hyperkalaemia. Remote up-titration of heart failure medications within a virtual ward environment is a promising approach, offering a fast, feasible, safe, and efficient treatment solution for patients who are otherwise undertreated.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000868"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140189/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236160","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":"Transforming social media text into predictive tools for depression through AI: A test-case study on the Beck Depression Inventory-II.","authors":"Federico Ravenda, Antonio Preti, Michele Poletti, Antonietta Mira, Fabio Crestani, Andrea Raballo","doi":"10.1371/journal.pdig.0000848","DOIUrl":"10.1371/journal.pdig.0000848","url":null,"abstract":"<p><p>The characterization of mental states through assessment tools is a fundamental aspect in psychiatric and psychological clinical practice. In this context, standardized questionnaires based on Likert scales are often used for the assessment of emotions, attitudes, and perceptions. These tools enable clinicians and researchers to quantify subjective experiences, providing valuable data that elucidate the intricate nature of human emotions and beliefs. Despite their utility, administering and completing these questionnaires presents significant challenges. The process requires substantial time and resources from both clinicians and participants, which can create barriers to efficient data collection and analysis. Consequently, we aim to streamline this process without compromising the quality and reliability of the gathered data. This study was designed to develop a tool (aka EnsemBERT) that leveraging the power of Pre-trained Language Models (PLMs) could reliably predict the scores associated with each item of the Beck Depression Inventory (BDI-II) on the basis of users' generated social media posts. The results confirm that such AI-based approach is feasible and that the specific tool, i.e. EnsemBERT, can accurately predict questionnaire scores at various levels of granularity, i.e. individual item scores as well as overall questionnaire scores.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000848"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140242/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236163","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":"Young people's data protection and privacy rights must not be neglected in the digital transformation of health: Insights, perspectives, and recommendations for the African context.","authors":"Victor Oluwafemi Femi-Lawal, Temilola Aderemi","doi":"10.1371/journal.pdig.0000872","DOIUrl":"10.1371/journal.pdig.0000872","url":null,"abstract":"","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000872"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140233/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236165","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 digital crossroads: Media literacy and the future of youth online.","authors":"Kate Barranco, Kendall Bryant","doi":"10.1371/journal.pdig.0000876","DOIUrl":"10.1371/journal.pdig.0000876","url":null,"abstract":"","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000876"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140186/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236161","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":"When evidence is not enough: A qualitative exploration of healthcare workers' perspectives on expansion of two-way texting (2wT) for post- circumcision follow-up in South Africa.","authors":"Isabella Fabens, Calsile Makhele, Nelson Igaba, Khumbulani Moyo, Felex Ndebele, Jacqueline Pienaar, Geoffrey Setswe, Caryl Feldacker","doi":"10.1371/journal.pdig.0000867","DOIUrl":"10.1371/journal.pdig.0000867","url":null,"abstract":"<p><p>As per South African national guidelines, in-person follow-up visits after voluntary medical male circumcision (VMMC) are required but may be unnecessary. Two-way texting (2wT), an mHealth platform, engages clients in post-operative care and triages those with complications to in-person review. 2wT was found to be safe, effective, and efficient. In South Africa, to understand provider perspectives on 2wT and potential for expansion, 20 key informant interviews were conducted with management, clinicians, data officials and support staff involved in 2wT scale-up. Interviews were analyzed using rapid qualitative methods and informed by two implementation science frameworks: the Reach, Effectiveness, Adoption, Implementation and Maintenance (RE-AIM) framework and the Pragmatic, Robust, Implementation and Sustainability Model (PRISM). Participants shared mixed and multi-faceted feedback, including that 2wT improves monitoring and evaluation of clients and clinical outcomes while also reducing follow-up visits. Challenges included duplicative routine and 2wT reporting systems and perceptions that 2wT increased workload. To improve the likelihood of successful 2wT scale-up in routine VMMC settings, participants suggested: further 2wT sensitization to ensure clinician and support staff buy-in; a dedicated clinician or nurse to manage telehealth clients; improved dashboards to better visualize 2wT client data; mobilizing 2wT champions at facilities to garner support for 2wT as routine care; and updating VMMC guidelines to support VMMC telehealth. As attendance at follow-up visits may not be as high as reported, implementing 2wT may require more effort but also brings added benefits of client verification and documented follow-up. The transition from research to routine practice is challenging, but use of RE-AIM and PRISM indicate that it is not impossible. As VMMC funding is decreasing, more effort to share the evidence base for 2wT as a safe, cost-effective, high-quality approach for VMMC follow-up is needed to encourage widespread uptake and adoption.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000867"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140269/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236164","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":"Formative evaluation of the acceptance of HIV prevention Artificial Intelligence chatbots by Black gay, bisexual, and other men who have sex with men in the Southern United States: Focus group study.","authors":"Jackson Jr Nforbewing Ndenkeh, Gloria A Aidoo-Frimpong, LaRon E Nelson, Mary L Peng, Vimala Balakrishnan, Victoria Barnhart, Bernard Davis, James Donté Prayer, Alvan Quamina, Zhao Ni","doi":"10.1371/journal.pdig.0000891","DOIUrl":"10.1371/journal.pdig.0000891","url":null,"abstract":"<p><p>Gay, bisexual, and other men who have sex with men (MSM) account for 60% of new HIV infections among Black Americans in the Southern United States (U.S.). Despite recommendations for frequent HIV testing and daily pre-exposure prophylaxis (PrEP) uptake, there remains a gap in PrEP uptake among these Black MSM in the Southern U.S. Artificial Intelligence (AI) chatbots have the potential to boost users' health awareness and medication adherence. This study aims to evaluate Black MSM' perspectives on the challenges to the uptake of PrEP and identify Black MSM-preferred chatbot functionalities and platforms for embedding AI chatbots. Five focus group discussions were conducted (February - March 2024) among 21 Black MSM in the Southern U.S. Interview transcripts were thematically analyzed according to challenges to PrEP uptake and the four domains of the Unified Theory of Acceptance and Use of Technology (UTAUT): performance expectancy, effort expectancy, facilitating conditions, and social influence. Black MSM identified lack of awareness or insufficient information, stigmatizations of sexuality, HIV, and PrEP, as well as concerns with side effects, and low self-perceived HIV vulnerability as the major challenges they faced in PrEP uptake. Moreover, chatbots were perceived as an acceptable option for delivering PrEP education (performance expectancy), especially with accessible, user-friendly interfaces (effort expectancy). Other desired features included simplifying access to PrEP information, incorporating culturally sensitive algorithms, upholding anonymity (social influence), and linking users to healthcare providers and resources (facilitating condition). The study highlights the multifaceted considerations for the adoption of AI chatbots as an HIV-prevention intervention among Black MSM in the Southern U.S.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 6","pages":"e0000891"},"PeriodicalIF":0.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12136318/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144227858","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":"Enhancing fairness in disease prediction by optimizing multiple domain adversarial networks.","authors":"Bin Li, Xiaoqian Jiang, Kai Zhang, Arif O Harmanci, Bradley Malin, Hongchang Gao, Xinghua Shi","doi":"10.1371/journal.pdig.0000830","DOIUrl":"10.1371/journal.pdig.0000830","url":null,"abstract":"<p><p>Predictive models in biomedicine need to ensure equitable and reliable outcomes for the populations they are applied to. However, biases in AI models for medical predictions can lead to unfair treatment and widening disparities, underscoring the need for effective techniques to address these issues. However, current approaches struggle to simultaneously mitigate biases induced by multiple sensitive features in biomedical data. To enhance fairness, we introduce a framework based on a Multiple Domain Adversarial Neural Network (MDANN), which incorporates multiple adversarial components. In an MDANN, an adversarial module is applied to learn a fair pattern by negative gradients back-propagating across multiple sensitive features (i.e., the characteristics of patients that should not lead to a prediction outcome that may intentionally or unintentionally lead to disparities in clinical decisions). The MDANN applies loss functions based on the Area Under the Receiver Operating Characteristic Curve (AUC) to address the class imbalance, promoting equitable classification performance for minority groups (e.g., a subset of the population that is underrepresented or disadvantaged.) Moreover, we utilize pre-trained convolutional autoencoders (CAEs) to extract deep representations of data, aiming to enhance prediction accuracy and fairness. Combining these mechanisms, we mitigate multiple biases and disparities to provide reliable and equitable disease prediction. We empirically demonstrate that the MDANN approach leads to better accuracy and fairness in predicting disease progression using brain imaging data and mitigating multiple demographic biases for Alzheimer's Disease and Autism populations than other adversarial networks.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 5","pages":"e0000830"},"PeriodicalIF":0.0,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12124548/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144188650","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":"Impact of digital wound care solution on healing time: A descriptive study in home health settings.","authors":"Heba Tallah Mohammed, Robert D J Fraser, Amy Cassata","doi":"10.1371/journal.pdig.0000855","DOIUrl":"10.1371/journal.pdig.0000855","url":null,"abstract":"<p><strong>Background: </strong>Chronic wounds pose significant challenges in home healthcare (HH) due to prolonged healing times and high costs. Digital wound care solutions (DWCS) have shown potential for improving healing efficiency. This study evaluated the impact of continuous DWCS use on healing times at HH organizations and explored area reduction in non-healed yet improved pressure injuries (PIs) and diabetic ulcers (DUs).</p><p><strong>Methods: </strong>This descriptive study analyzed 195,915 wound assessments from 59 HH organizations using DWCS in 2022 and 2023. Average healing time was calculated by wound type and compared across the two years, with subgroup analyses for wounds healing within three months versus longer. Improvements in non-healed DUs and PIs were further categorized by initial wound size (≤2 cm², >2 cm² for DUs; ≤4 cm², >4 cm² for PIs).</p><p><strong>Results: </strong>Average healing time for all wounds decreased significantly from 62.5 days in 2022 to 38.6 days in 2023, a 38.2% improvement (p < 0.001). DU and PIs showed reductions of 30.8 and 29.3 days, respectively. The proportion of wounds healing within three months rose by 8.9%, with decreased average healing times within this period. For wounds requiring over three months, the average time saved was 57.6 days (8.2 weeks; P = 0.014), representing a 27% improvement. Non-healed but improving PIs showed increase in area reduction from 5.2 cm² to 17.7 cm², with a 25.4% faster time to reduction. Larger PIs (>4 cm²) showed greater reductions, with time to improvement decreasing by 35.5 days (34.7%, p < 0.001). DUs also improved, with area reduction increasing from 4.8 cm² to 15.3 cm² and a 23.8% faster reduction time, while larger DUs (>2 cm²) saw a 32.6-day decrease in time to improvement.</p><p><strong>Conclusion: </strong>Continuous DWCS use significantly reduces healing times and improves wound area reduction, underscoring its effectiveness in enhancing wound care outcomes in HH settings.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 5","pages":"e0000855"},"PeriodicalIF":0.0,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12124507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144188651","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}