PLOS digital health最新文献

{"title":"Integrating equity, diversity, and inclusion throughout the lifecycle of artificial intelligence for healthcare: a scoping review.","authors":"Ting Wang, Elham Emami, Dana Jafarpour, Raymond Tolentino, Genevieve Gore, Samira Abbasgholizadeh Rahimi","doi":"10.1371/journal.pdig.0000941","DOIUrl":"10.1371/journal.pdig.0000941","url":null,"abstract":"<p><p>The lack of Equity, Diversity, and Inclusion (EDI) principles in the lifecycle of Artificial Intelligence (AI) technologies in healthcare is a growing concern. Despite its importance, there is still a gap in understanding the initiatives undertaken to address this issue. This review aims to explore what and how EDI principles have been integrated into the design, development, and implementation of AI studies in healthcare. We followed the scoping review framework by Levac et al. and the Joanna Briggs Institute. A comprehensive search was conducted until April 29, 2022, across MEDLINE, Embase, PsycInfo, Scopus, and SCI-EXPANDED. Only research studies in which the integration of EDI in AI was the primary focus were included. Non-research articles were excluded. Two independent reviewers screened the abstracts and full texts, resolving disagreements by consensus or by consulting a third reviewer. To synthesize the findings, we conducted a thematic analysis and used a narrative description. We adhered to the PRISMA-ScR checklist for reporting scoping reviews. The search yielded 10,664 records, with 42 studies included. Most studies were conducted on the American population. Previous research has shown that AI models improve when socio-demographic factors such as gender and race are considered. Despite frameworks for EDI integration, no comprehensive approach systematically applies EDI principles in AI model development. Additionally, the integration of EDI into the AI implementation phase remains under-explored, and the representation of EDI within AI teams has been overlooked. This review reports on what and how EDI principles have been integrated into the design, development, and implementation of AI technologies in healthcare. We used a thorough search strategy and rigorous methodology, though we acknowledge limitations such as language and publication bias. A comprehensive framework is needed to ensure that EDI principles are considered throughout the AI lifecycle. Future research could focus on strategies to reduce algorithmic bias, assess the long-term impact of EDI integration, and explore policy implications to ensure that AI technologies are ethical, responsible, and beneficial for all.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000941"},"PeriodicalIF":0.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12258586/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144638873","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":"Raising awareness of potential biases in medical machine learning: Experience from a Datathon.","authors":"Harry Hochheiser, Jesse Klug, Thomas Mathie, Tom J Pollard, Jesse D Raffa, Stephanie L Ballard, Evamarie A Conrad, Smitha Edakalavan, Allan Joseph, Nader Alnomasy, Sarah Nutman, Veronika Hill, Sumit Kapoor, Eddie Pérez Claudio, Olga V Kravchenko, Ruoting Li, Mehdi Nourelahi, Jenny Diaz, W Michael Taylor, Sydney R Rooney, Maeve Woeltje, Leo Anthony Celi, Christopher M Horvat","doi":"10.1371/journal.pdig.0000932","DOIUrl":"10.1371/journal.pdig.0000932","url":null,"abstract":"<p><strong>Objective: </strong>To challenge clinicians and informaticians to learn about potential sources of bias in medical machine learning models through investigation of data and predictions from an open-source severity of illness score.</p><p><strong>Methods: </strong>Over a two-day period (total elapsed time approximately 28 hours), we conducted a datathon that challenged interdisciplinary teams to investigate potential sources of bias in the Global Open Source Severity of Illness Score. Teams were invited to develop hypotheses, to use tools of their choosing to identify potential sources of bias, and to provide a final report.</p><p><strong>Results: </strong>Five teams participated, three of which included both informaticians and clinicians. Most (4/5) used Python for analyses, the remaining team used R. Common analysis themes included relationship of the GOSSIS-1 prediction score with demographics and care related variables; relationships between demographics and outcomes; calibration and factors related to the context of care; and the impact of missingness. Representativeness of the population, differences in calibration and model performance among groups, and differences in performance across hospital settings were identified as possible sources of bias.</p><p><strong>Discussion: </strong>Datathons are a promising approach for challenging developers and users to explore questions relating to unrecognized biases in medical machine learning algorithms.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000932"},"PeriodicalIF":0.0,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12250157/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144612668","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":"Short-horizon neonatal seizure prediction using EEG-based deep learning.","authors":"Jonathan Kim, Edilberto Amorim, Vikram R Rao, Hannah C Glass, Danilo Bernardo","doi":"10.1371/journal.pdig.0000890","DOIUrl":"10.1371/journal.pdig.0000890","url":null,"abstract":"<p><p>Strategies to predict neonatal seizure risk have typically focused on long-term static predictions with prediction horizons spanning days during the acute postnatal period. Higher temporal resolution or short-horizon neonatal seizure prediction, on the time-frame of minutes, remains unexplored. Here, we investigated quantitative electroencephalography (QEEG) based deep learning (DL) for short-horizon seizure prediction. We used two publicly available EEG seizure datasets with a total of 132 neonates containing a total of 281 hours of EEG data. We benchmarked current state-of-the-art time-series DL methods for seizure prediction, identifying convolutional LSTM (ConvLSTM) as having the strongest performance at preictal state classification. We assessed ConvLSTM performance in a seizure alarm system over varying short-range (1-7 minutes) seizure prediction horizons (SPH) and seizure occurrence periods (SOP) and identified optimal performance at SPH 3 min and SOP 7 min, with AUROC 0.8. At 80% sensitivity, false detection rate was 0.68 events/hour with time-in-warning of 0.36. Model calibration was moderate, with an expected calibration error of 0.106. These findings establish the feasibility of short-horizon neonatal seizure prediction and warrant the need for further validation.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000890"},"PeriodicalIF":0.0,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12250315/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144612669","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":"Digital health technologies for accessing contraceptive services among young people in Sub-Saharan Africa: A scoping review protocol.","authors":"Agnes Kyamulabi, Eva Oberle, Lotenna Olisaeloka, Innocent Kamya, Ingrid Nyesigire, Wendy V Norman, Abdul-Fatawu Abdulai","doi":"10.1371/journal.pdig.0000748","DOIUrl":"10.1371/journal.pdig.0000748","url":null,"abstract":"<p><p>This scoping review aims to examine and synthesize existing literature on the use of digital health technologies, with a focus on the extent and types of technologies used to access contraceptive services among young people in Sub-Saharan Africa (SSA). Globally, digital health technologies have emerged as pivotal tools in addressing contraceptive needs among young people. In SSA, where traditional healthcare systems often face numerous challenges, these technologies offer innovative solutions to improve access to contraceptive services. Despite growing interest in digital health technologies, comprehensive reviews on contraceptive access among young people in SSA are still lacking. Most existing studies focus broadly on sexual and reproductive health (SRH) or adult populations, leaving a gap in understanding the unique needs and experiences of young people using digital technologies for contraception services. It is unclear how much research has been conducted to examine how these technologies can facilitate contraceptive use, which technologies are used and why, where this evidence is concentrated within SSA, and the prevailing gaps. Therefore, we propose to undertake a scoping review. This scoping review will include studies focusing on young people aged 10-24 years in SSA, addressing access challenges to contraceptive services within this age group. The review will consider client-facing digital health technologies. All methodological approaches and designs will be included. Reviews, protocols, conference papers, policy briefs and studies conducted outside SSA will be excluded. The review will apply the comprehensive search strategy recommended by Joanna Briggs Institute (JBI). The initial limited search of MEDLINE (Ovid) and CINAHL Complete (EBSCOhost) was conducted with guidance from the University Librarian. This informed the selection of keywords, along with index terms, to develop a full search strategy for MEDLINE (Ovid), CINAHL Complete (EBSCOhost), Scopus, Compendix Engineering Village, and IEEE Xplore. The scoping review shall also use supplementary resources such as google scholar, and African Journal online (AJOL). We will also review the reference lists of articles that meet the inclusion criteria to ascertain articles that were not returned by the search criteria. Data will be presented using tables and charts, accompanied by a narrative summary. This scoping review was registered in Open Science Framework: https://doi.org/10.17605/OSF.IO/5QJ6P.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000748"},"PeriodicalIF":0.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12244615/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144610551","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":"Barriers and facilitators of provision of telemedicine in Nigeria: A systematic review.","authors":"Osagie Kenneth Cole, Mustapha Muhammed Abubakar, Abdulmuminu Isah, Sule Hayatu Sule, Blessing Onyinye Ukoha-Kalu","doi":"10.1371/journal.pdig.0000934","DOIUrl":"10.1371/journal.pdig.0000934","url":null,"abstract":"<p><p>Healthcare access remains a challenge in developing countries and could be a drawback to the attainment of Objective 3 of the Sustainable Development Goals. Digital interventions such as telemedicine have been identified as an effective tool to improve healthcare access. However, evidence suggests that the impact of telemedicine is not uniform globally due to variances in barriers and facilitators. Thus, we conducted a systematic review to identify the barriers and facilitators of telemedicine in Nigeria. The systematic review was pre-registered on PROSPERO (Identification Number: CRD42024609405). Search was conducted on PubMed, Scopus, and the Cumulative Index of Nursing and Allied Health Literature databases. We included studies that reported on the estimates of barriers and facilitators of telemedicine in Nigeria as well as the factors associated with telemedicine implementation, provision, or operation in Nigeria. The outcome was the reportage of barriers and facilitators of telemedicine in Nigeria. A total of 384 studies were identified from the search. After the application of eligibility criteria and deletion of duplicates, 29 studies were included in the review. The most reported barriers were technical and institutional-related while the most reported facilitators were human-resource-related. Technical barriers frequently reported were power outages, poor internet connectivity, and paucity of health professionals with technical expertise while institutional barriers were lack of regulation and poor organizational policies. Formal telemedicine training and education were the most reported human resource facilitators while the use of low-tech educational networks and internet accessibility were the most reported technical facilitators. Findings from this review suggest that technical barriers are a challenge to adopting telemedicine in Nigeria. Evidence shows that education and training are critical in addressing these technical challenges. Thus, this review provides a background for interventions towards the effective implementation of telemedicine in Nigeria.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000934"},"PeriodicalIF":0.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12244542/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144610549","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":"Improving meningitis surveillance and diagnosis with machine learning: Insights from São Paulo.","authors":"Audêncio Victor, Diego Augusto Medeiros Santos, Eduardo Koerich Nery, Danilo Pereira Mori, Pamella Cristina de Carvalho Lucas, Denise Cammarota, Guillermo Leonardo Florez Montero, Fabiano Novaes Barcellos Filho, Ana Lúcia Frugis Yu, Telma Regina Marques Pinto Carvalhanas","doi":"10.1371/journal.pdig.0000925","DOIUrl":"10.1371/journal.pdig.0000925","url":null,"abstract":"<p><strong>Introduction: </strong>Meningitis, an inflammatory condition of the membranes surrounding the brain and spinal cord, can be caused by various agents. Bacterial meningitis is particularly severe due to its high morbidity and mortality rates. This study aims to develop machine learning (ML) models to classify the aetiology of bacterial meningitis using data from the Notifiable Diseases Information System (SINAN) in São Paulo State, Brazil.</p><p><strong>Methods: </strong>Data were collected from the SINAN database, including sociodemographic variables, clinical symptoms, and cerebrospinal fluid (CSF) analyses. Five ML models Random Forest, LightGBM, XGBoost, CatBoost, and AdaBoost were applied to classify meningitis cases into bacterial, fungal, viral, and other types. Models were evaluated using metrics such as AUC-ROC, accuracy, precision, recall, F1-score, and MCC.</p><p><strong>Results: </strong>The CatBoost model demonstrated superior performance, achieving an AUC-ROC of 0.95 for binary classification (bacterial vs. non-bacterial) and 0.85 for multiclass classification (Neisseria meningitidis, Streptococcus pneumoniae, and Haemophilus influenzae). XGBoost and LightGBM also showed promising results with AUC-ROC scores of 0.94 and 0.92, respectively, for binary classification. The CatBoost model exhibited high sensitivity and reasonable specificity, highlighting its applicability in the rapid and accurate diagnosis of meningitis. SHAP analysis identified variables such as leukocyte count and the presence of petechiae as influential predictors in the models.</p><p><strong>Conclusion: </strong>ML algorithms, particularly CatBoost, XGBoost, and LightGBM, proved highly effective in the differential diagnosis of meningitis, offering a valuable tool for the rapid identification of meningitis types and bacterial serogroups. These techniques can be integrated into public health protocols to improve meningitis outbreak responses and optimize patient treatment.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000925"},"PeriodicalIF":0.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12244477/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144610552","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":"Bridging the gaps in Universal Health Coverage using Digital Health Citizenship.","authors":"Rupal Jain, Rajarshi Dasgupta","doi":"10.1371/journal.pdig.0000913","DOIUrl":"10.1371/journal.pdig.0000913","url":null,"abstract":"","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000913"},"PeriodicalIF":0.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12244526/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144610550","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":"CombiANT reader: Deep learning-based automatic image processing tool to robustly quantify antibiotic interactions.","authors":"Erik Hallström, Nikos Fatsis-Kavalopoulos, Manos Bimpis, Carolina Wählby, Anders Hast, Dan I Andersson","doi":"10.1371/journal.pdig.0000669","DOIUrl":"10.1371/journal.pdig.0000669","url":null,"abstract":"<p><p>Antibiotic resistance is a severe danger to human health, and combination therapy with several antibiotics has emerged as a viable treatment option for multi-resistant strains. CombiANT is a recently developed agar plate-based assay where three reservoirs on the bottom of the plate create a diffusion landscape of three antibiotics that allows testing of the efficiency of antibiotic combinations. This test, however, requires manually assigning nine reference points to each plate, which can be prone to errors, especially when plates need to be graded in large batches and by different users. In this study, an automated deep learning-based image processing method is presented that can accurately segment bacterial growth and measure distances between key points on the CombiANT assay at sub-millimeter precision. The software was tested on 100 plates using photos captured by three different users with their mobile phone cameras, comparing the automated analysis with the human scoring. The result indicates significant agreement between the users and the software ([Formula: see text] mm mean absolute error) and remains consistent when applied to different photos of the same assay despite varying photo qualities and lighting conditions. The speed and robustness of the automated analysis could streamline clinical workflows and make it easier to tailor treatment to specific infections. It could also aid large-scale antibiotic research by quickly processing hundreds of experiments in batch, obtaining better data, and ultimately supporting the development of better treatment strategies. The software can easily be integrated into a potential smartphone application, making it accessible in resource-limited environments. Integrating deep learning-based smartphone image analysis with simple agar-based tests like CombiANT could unlock powerful tools for combating antibiotic resistance.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000669"},"PeriodicalIF":0.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12237020/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144593132","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":"Youth as digital citizens in health: Experiences, challenges, and the road ahead.","authors":"Aishwarya Rohatgi","doi":"10.1371/journal.pdig.0000923","DOIUrl":"10.1371/journal.pdig.0000923","url":null,"abstract":"","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000923"},"PeriodicalIF":0.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12237030/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144593133","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":"A comparative approach of machine learning models to predict attrition in a diabetes management program.","authors":"Samantha Kanny, Grisha Post, Patricia Carbajales-Dale, William Cummings, Janet Evatt, Windsor Westbrook Sherrill","doi":"10.1371/journal.pdig.0000930","DOIUrl":"10.1371/journal.pdig.0000930","url":null,"abstract":"<p><p>Approximately 11.6% of Americans have diabetes and South Carolina has one of the highest rates of adults with diabetes. Diabetes self-management programs have been observed to be effective in promoting weight loss and improving diabetes knowledge and self-care behaviors. The ability to keep vulnerable individuals in these programs is critical to helping the growing diabetic population. Utilizing machine learning is gaining popularity in healthcare settings. The objective of this study is to assess the effectiveness of several machine learning methods in predicting attrition from a diabetes self-management program, utilizing participant demographics and various evaluation measures. Data were collected from participants enrolled in Health Extension for Diabetes (HED). Descriptive statistics were used to examine HED participant demographics, while Mann-Whitney U tests and chi-square tests were used to examine relationships between demographics and pre-program evaluation measures. Through the various analyses, health-related measures - specifically the SF-12 quality of life scores, Distressed Communities Index (DCI) score, along with demographic factors (race, age, height, and educational attainment), and spatial variables (drive time to the nearest grocery store) emerged as influential predictors of attrition. However, the machine learning models showed poor overall performance, with AUC values ranging from 0.53 - 0.64 and F-1 scores between 0.19 - 0.36, indicating low predictive power. Among the models tested, XGBoost with downsampling yielded the highest AUC value (0.64) and a slightly higher F-1 score (0.36). To enhance model interpretability, SHAP (SHapley Additive exPlanations) was applied. While these models are not suitable for accurately predicting individual attrition risk in diabetes self-management programs, they identify potential factors influencing dropout rates. These findings underscore the difficulty for models to accurately predict health behavior outcomes, highlighting the need for future research to improve predictive modeling to better support patient engagement and retention.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 7","pages":"e0000930"},"PeriodicalIF":0.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12233248/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144585813","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}