PLOS digital health最新文献

{"title":"Explore barriers to using the internet for health information access in African countries: A systematic review.","authors":"Alex Ayenew Chereka, Adamu Ambachew Shibabaw, Fikadu Wake Butta, Mathias Nega Tadesse, Mekashaw Tareke Abebe, Fekadu Ayelgn Atanie, Gemeda Wakgari Kitil","doi":"10.1371/journal.pdig.0000719","DOIUrl":"10.1371/journal.pdig.0000719","url":null,"abstract":"<p><strong>Background: </strong>The Internet is a crucial source of health information, providing access to vast volumes of high-quality, up-to-date, and relevant healthcare information. Its impact extends beyond information access, influencing medical practice through the widespread adoption of telemedicine and evidence-based medicine. Despite the significant global increase in internet usage, Africa lags in internet penetration, particularly in utilizing the internet for health information. This study aims to systematically review the literature to explore barriers to accessing health information on the Internet in African countries.</p><p><strong>Methods: </strong>The study was conducted from January 1 to February 28, 2023. It followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guideline to systematically review published studies investigating the utilization of the Internet for health information in African countries. A comprehensive search was conducted across various databases, including Google Scholar, PubMed, Cochrane Library, Hinari, CINAHL, and Global Health. The inclusion criteria were applied, resulting in the selection of six studies that formed the basis for our analysis.</p><p><strong>Result: </strong>This systematic review identifies eleven barriers to accessing health information on the internet. These include a lack of ownership of smart electronic devices, infrequent internet use, limited internet access, low E-health and computer literacy, slow internet connection, high cost of internet access, insufficient information search skills, residing in rural areas, dealing with diverse fields, and having low perceptions.</p><p><strong>Conclusion: </strong>Improving our understanding of barriers to accessing health information online is essential for policymakers, governments, academics, and healthcare professionals. To enhance the use of the Internet for health information and strengthen the overall health system, policymakers should prioritize increasing Internet accessibility, reducing costs, improving connections, offering basic computer skills training, and ensuring the availability of electronic devices in all institutions.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000719"},"PeriodicalIF":0.0,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11771857/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143054505","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":"Quality of life disparities among Mexican people with systemic lupus erythematosus.","authors":"Ana Laura Hernández-Ledesma, Domingo Martínez, Elizabeth Fajardo-Brigido, Talía V Román-López, Karen J Nuñez-Reza, Andrea Y Tapia-Atilano, Sandra V Vera Del Valle, Donají Domínguez-Zúñiga, Lizbet Tinajero-Nieto, Angélica Peña-Ayala, Estefania Torres-Valdez, Gabriel Frontana-Vázquez, María Gutiérrez-Arcelus, Florencia Rosetti, Sarael Alcauter, Miguel E Rentería, Alejandra E Ruiz-Contreras, Deshiré Alpízar-Rodríguez, Alejandra Medina-Rivera","doi":"10.1371/journal.pdig.0000706","DOIUrl":"10.1371/journal.pdig.0000706","url":null,"abstract":"<p><p>Higher prevalence and worst outcome have been reported among people with systemic lupus erythematosus with non-European ancestries, with both genetic and socioeconomic variables as contributing factors. In Mexico, studies assessing the inequities related to quality of life for Systemic Lupus Erythematosus patients remain sparse. This study aims to assess the inequities related to quality of life in a cohort of Mexican people with SLE. This study included 942 individuals with SLE from the Mexican Lupus Registry (LupusRGMX) and two healthy control groups. Self-answered surveys were collected via the Research Electronic Data Capture platform between May 2021 and January 2023. Data was analyzed as a cross-sectional study. A random forest model was implemented to assess potential predictive variables. Permutation tests were performed to analyze the effect health providers had on diagnosis lag and quality of life's differences among socioeconomic levels. Partial correlation analysis between the number of patients and rheumatologists registered was also performed. Systemic Lupus Erythematosus participants had significantly lower quality of life than healthy people (p-values < 0.0001). Socioeconomic status, delay in diagnosis, and corticosteroid consumption were the factors that influenced QoL the most (RMSE = 9.53 with the importance variable validated); lower quality of life was associated with lower socioeconomic status (p-value < 0.0001). Disparities in health services were reflected in longer diagnosis time among people with public health providers (p-value = 0.0419). A significant association between diagnosed patients and available rheumatologists by geographical state was observed (ρ = 0.4, p-value = 0.0259), which can be translated into restricted access to specialists. Since most of our cohort exhibited low socioeconomic status, it is important to consider them as a vulnerable population; this study settles the necessity to deepen the effects of the socioeconomic disparities, allowing to design public policies and strategies aimed to reduce Systemic Lupus Erythematosus disparities, therefore improving quality of life of Mexican people with Systemic Lupus Erythematosus.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000706"},"PeriodicalIF":0.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11756751/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030420","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 comparison of CXR-CAD software to radiologists in identifying COVID-19 in individuals evaluated for Sars CoV-2 infection in Malawi and Zambia.","authors":"Sam Linsen, Aurélie Kamoun, Andrews Gunda, Tamara Mwenifumbo, Chancy Chavula, Lindiwe Nchimunya, Yucheng Tsai, Namwaka Mulenga, Godfrey Kadewele, Eunice Nahache Kajombo, Veronica Sunkutu, Jane Shawa, Rigveda Kadam, Matthew Arentz","doi":"10.1371/journal.pdig.0000535","DOIUrl":"10.1371/journal.pdig.0000535","url":null,"abstract":"<p><p>AI based software, including computer aided detection software for chest radiographs (CXR-CAD), was developed during the pandemic to improve COVID-19 case finding and triage. In high burden TB countries, the use of highly portable CXR and computer aided detection software has been adopted more broadly to improve the screening and triage of individuals for TB, but there is little evidence in these settings regarding COVID-19 CAD performance. We performed a multicenter, retrospective cross-over study evaluating CXRs from individuals at risk for COVID-19. We evaluated performance of CAD software and radiologists in comparison to COVID-19 laboratory results in 671 individuals evaluated for COVID-19 at sites in Zambia and Malawi between January 2021 and June 2022. All CXRs were interpreted by an expert radiologist and two commercially available COVID-19 CXR-CAD software. Radiologists interpreted CXRs for COVID-19 with a sensitivity of 73% (95% CI: 69%- 76%) and specificity of 49% (95% CI: 40%-58%). One CAD software (CAD2) showed performance in diagnosing COVID-19 that was comparable to that of radiologists, (AUC-ROC of 0.70 (95% CI: 0.65-0.75)), while a second (CAD1) showed inferior performance (AUC-ROC of 0.57 (95% CI: 0.52-0.63)). Agreement between CAD software and radiologists was moderate for diagnosing COVID-19, and agreement was very good in differentiating normal and abnormal CXRs in this high prevalent population. The study highlights the potential of CXR-CAD as a tool to support effective triage of individuals in Malawi and Zambia during the pandemic, particularly for distinguishing normal from abnormal CXRs. These findings suggest that while current AI-based diagnostics like CXR-CAD show promise, their effectiveness varies significantly. In order to better prepare for future pandemics, there is a need for representative training data to optimize performance in key populations, and ongoing data collection to maintain diagnostic accuracy, especially as new disease strains emerge.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000535"},"PeriodicalIF":0.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11756753/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030416","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":"Synthetic data as external control arms in scarce single-arm clinical trials.","authors":"Severin Elvatun, Daan Knoors, Simon Brant, Christian Jonasson, Jan F Nygård","doi":"10.1371/journal.pdig.0000581","DOIUrl":"10.1371/journal.pdig.0000581","url":null,"abstract":"<p><p>An external control arm based on health registry data can serve as an alternative comparator in single-arm drug development studies that lack a benchmark for comparison to the experimental treatment. However, accessing such observational healthcare data involves a lengthy and intricate application process, delaying drug approval studies and access to novel treatments. Clinical trials typically comprise only a few hundred patients usually with high-cardinality features, which makes individual data instances more exposed to re-identification attacks. We examine whether synthetic data can serve as a proxy for the empirical control arm data by providing the same research outcomes while reducing the risk of information disclosure. We propose a reversible data generalization procedure to address these particular data characteristics that can be used in conjunction with any generator algorithm. It reduces the input data cardinality pre-synthesis and reverses it post-synthesis to regain the original data structure. Finally, we test a selection of state-of-the-art generators against a suite of utility and privacy metrics. The external control arm benchmark was generated using data from Norwegian health registries. In this retrospective study, we compare various synthetic data generation algorithms in numerical experiments, focusing on the utility of the synthetic data to support the conclusions drawn from the empirical data, and analysing the risk of sensitive information disclosure. Our results indicate that data generalization is advantageous to enhance both data utility and privacy in smaller datasets with high cardinality. Moreover, the generator algorithms demonstrate the ability to generate synthetic data of high utility without compromising the confidentiality of the empirical data. Our finding suggests that synthetic external control arms could serve as a viable alternative to observational data in drug development studies, while reducing the risk of revealing sensitive patient information.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000581"},"PeriodicalIF":0.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11756779/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143030422","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":"Predicting the onset of chronic kidney disease (CKD) for diabetic patients with aggregated longitudinal EMR data.","authors":"Neda Aminnejad, Michelle Greiver, Huaxiong Huang","doi":"10.1371/journal.pdig.0000700","DOIUrl":"10.1371/journal.pdig.0000700","url":null,"abstract":"<p><p>Chronic kidney disease (CKD) affects over 13% of the population, totaling more than 800 million individuals worldwide. Timely identification and intervention are crucial to delay CKD progression and improve patient outcomes. This research focuses on developing a predictive model to classify diabetic patients showing signs of kidney function impairment based on their CKD development risk. Our model utilizes electronic medical record (EMR) data, specifically by incorporating patient demographics, laboratory results, chronic conditions, risk factors, and medication codes to predict the onset of CKD in diabetic patients six months in advance, achieving an average Area Under the Curve (AUC) of 0.88. We leverage aggregated EMR data to effectively capture relevant information within the observation year instead of using temporal EMR data. Furthermore, we identify the most significant features for predicting CKD onset, including mean, minimum, and first quartile of estimated glomerular filtration rate (eGFR) during the observation year, along with variables such as diagnosis age and duration of hypertension, osteoarthritis, and diabetes, as well as levels of hemoglobin and fasting blood glucose (FBG). We also explored a refined model utilizing only these most significant features, which yields a slightly lower AUC of 0.86. These variables are typically available in primary data, empowering physicians for real-time risk assessment. The proposed model's ability to identify higher-risk patients is essential for timely intervention, personalized care, risk stratification, patient education, and potential cost savings. This research contributes valuable insights for healthcare practitioners seeking efficient tools for early CKD detection in diabetic populations.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000700"},"PeriodicalIF":0.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11753645/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143025870","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":"Study protocol for a multi-center stepped-wedge cluster randomized trial to explore the usability and outcomes among young people living with HIV in Kiambu and Kirinyaga counties of Kenya, using an online health portal.","authors":"Eric Nturibi, Jared Mecha, Elizabeth Kubo, Albert Orwa, Florence Kaara, Faith Musau, Christine Wamuyu, Justus Kilonzi, Randeep Gill, Sanne Roels","doi":"10.1371/journal.pdig.0000380","DOIUrl":"https://doi.org/10.1371/journal.pdig.0000380","url":null,"abstract":"<p><p>While the incidence of Human Immunodeficiency Virus (HIV) infection is decreasing in most age groups worldwide, it is rising among adolescents and young adults, who also face a higher rate of HIV-related deaths. This tech-savvy demographic may benefit from an online patient portal designed to enhance patient activation-empowering them to manage their health independently. However, the effectiveness of such digital health interventions on young HIV patients in Kenya remains uncertain. We will conduct a 12-month stepped wedge cluster randomized trial involving 15-24-year-old HIV patients with smartphone access. The primary outcome will be patient activation, with secondary outcomes including self-reported adherence, social engagement and viral suppression. We will also evaluate the portal's functionality, usability, fidelity, and costs. Participants will be recruited from 47 antiretroviral treatment (ART) sites with electronic medical records (EMR), forming 16 clusters of 30 participants each. Clusters will be randomized into three sequences for intervention every three months. Baseline measurements (patient activation, adherence, social engagement and viral suppression) will be collected over two weeks, followed by checks at 3, 6, and 12 months. Data will be analyzed using generalized linear mixed models and adjusted for cluster effects and potential confounders. Results will be disseminated through stakeholder forums, scientific conferences, peer-reviewed publications, and the media.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000380"},"PeriodicalIF":0.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11741603/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143017883","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":"Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale.","authors":"Richard T Lester, Matthew Manson, Muhammed Semakula, Hyeju Jang, Hassan Mugabo, Ali Magzari, Junhong Ma Blackmer, Fanan Fattah, Simon Pierre Niyonsenga, Edson Rwagasore, Charles Ruranga, Eric Remera, Jean Claude S Ngabonziza, Giuseppe Carenini, Sabin Nsanzimana","doi":"10.1371/journal.pdig.0000625","DOIUrl":"https://doi.org/10.1371/journal.pdig.0000625","url":null,"abstract":"<p><p>Community isolation of patients with communicable infectious diseases limits spread of pathogens but our understanding of isolated patients' needs and challenges is incomplete. Rwanda deployed a digital health service nationally to assist public health clinicians to remotely monitor and support SARS-CoV-2 cases via their mobile phones using daily interactive short message service (SMS) check-ins. We aimed to assess the texting patterns and communicated topics to better understand patient experiences. We extracted data on all COVID-19 cases and exposed contacts who were enrolled in the WelTel text messaging program between March 18, 2020, and March 31, 2022, and linked demographic and clinical data from the national COVID-19 registry. A sample of the text conversation corpus was English-translated and labeled with topics of interest defined by medical experts. Multiple natural language processing (NLP) topic classification models were trained and compared using F1 scores. Best performing models were applied to classify unlabeled conversations. Total 33,081 isolated patients (mean age 33·9, range 0-100), 44% female, including 30,398 cases and 2,683 contacts) were registered in WelTel. Registered patients generated 12,119 interactive text conversations in Kinyarwanda (n = 8,183, 67%), English (n = 3,069, 25%) and other languages. Sufficiently trained large language models (LLMs) were unavailable for Kinyarwanda. Traditional machine learning (ML) models outperformed fine-tuned transformer architecture language models on the native untranslated language corpus, however, the reverse was observed of models trained on English-only data. The most frequently identified topics discussed included symptoms (69%), diagnostics (38%), social issues (19%), prevention (18%), healthcare logistics (16%), and treatment (8·5%). Education, advice, and triage on these topics were provided to patients. Interactive text messaging can be used to remotely support isolated patients in pandemics at scale. NLP can help evaluate the medical and social factors that affect isolated patients which could ultimately inform precision public health responses to future pandemics.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000625"},"PeriodicalIF":0.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11734906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143017882","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":"Use of assistive technology to assess distal motor function in subjects with neuromuscular disease.","authors":"Dominique Vincent-Genod, Sylvain Roche, Aurélie Barrière, Capucine de Lattre, Marie Tinat, Eelke Venema, Emmeline Lagrange, Adriana Gomes Lisboa de Souza, Guillaume Thomann, Justine Coton, Vincent Gautheron, Léonard Féasson, Pascal Rippert, Carole Vuillerot","doi":"10.1371/journal.pdig.0000534","DOIUrl":"10.1371/journal.pdig.0000534","url":null,"abstract":"<p><p>Among the 32 items of the Motor Function Measure scale, 3 concern the assessment of hand function on a paper-based support. Their characteristics make it possible to envisage the use of a tablet instead of the original paper-based support for their completion. This would then make it possible to automate the score to reduce intra- and inter-individual variability. The main objective of the present study was to validate the digital completion of items 18, 19, and 22 by measuring the agreement of the scores obtained using a digital tablet with those obtained using the original paper-based support in children and adults with various neuromuscular diseases (NMD). The secondary objective is to calibrate an algorithm for the automatic items scoring.</p><p><strong>Design: </strong>Prospective, multicentre, non-interventional study.</p><p><strong>Methods: </strong>Ninety-eight subjects aged 5 to 60 years with a confirmed NMD completed MFM items 18, 19, and 22 both on a paper support and a digital tablet.</p><p><strong>Results: </strong>The median age of included subjects was 16.2 years. Agreement between scores as assessed using the weighted Kappa coefficient was almost perfect for the scores of items 18 and 22 (K = 0.93, and 0.95, respectively) and substantial for item 19 (K = 0.70). In all cases of disagreement, the difference was of 1 point. The most frequent disagreement concerned item 19; mainly in the direction of a scoring of 1 point less on the tablet. An automatic analysis algorithm was tested on 82 recordings to suggest improvements.</p><p><strong>Conclusion: </strong>The switch from original paper-based support to the tablet results in minimal and acceptable differences, and maintains a valid and reproducible measure of the 3 items. The developed algorithm for automatic scoring appears feasible with the perspective to include them in a digital application that will make it easier to monitor patients.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000534"},"PeriodicalIF":0.0,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11729976/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980867","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":"Epidemiological methods in transition: Minimizing biases in classical and digital approaches.","authors":"Sara Mesquita, Lília Perfeito, Daniela Paolotti, Joana Gonçalves-Sá","doi":"10.1371/journal.pdig.0000670","DOIUrl":"10.1371/journal.pdig.0000670","url":null,"abstract":"<p><p>Epidemiology and Public Health have increasingly relied on structured and unstructured data, collected inside and outside of typical health systems, to study, identify, and mitigate diseases at the population level. Focusing on infectious diseases, we review the state of Digital Epidemiology at the beginning of 2020 and how it changed after the COVID-19 pandemic, in both nature and breadth. We argue that Epidemiology's progressive use of data generated outside of clinical and public health systems creates several technical challenges, particularly in carrying specific biases that are almost impossible to correct for a priori. Using a statistical perspective, we discuss how a definition of Digital Epidemiology that emphasizes \"data-type\" instead of \"data-source,\" may be more operationally useful, by clarifying key methodological differences and gaps. Therefore, we briefly describe some of the possible biases arising from varied collection methods and sources, and offer some recommendations to better explore the potential of Digital Epidemiology, particularly on how to help reduce inequity.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000670"},"PeriodicalIF":0.0,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980853","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":"Performance evaluation and comparative analysis of different machine learning algorithms in predicting postnatal care utilization: Evidence from the ethiopian demographic and health survey 2016.","authors":"Daniel Niguse Mamo, Agmasie Damtew Walle, Eden Ketema Woldekidan, Jibril Bashir Adem, Yosef Haile Gebremariam, Meron Asmamaw Alemayehu, Ermias Bekele Enyew, Shimels Derso Kebede","doi":"10.1371/journal.pdig.0000707","DOIUrl":"10.1371/journal.pdig.0000707","url":null,"abstract":"<p><p>Postnatal care refers to the support provided to mothers and their newborns immediately after childbirth and during the first six weeks of life, a period when most maternal and neonatal deaths occur. In the 30 countries studied, nearly 40 percent of women did not receive a postpartum care check-up. This research aims to evaluate and compare the effectiveness of machine learning algorithms in predicting postnatal care utilization in Ethiopia and to identify the key factors involved. The study employs machine learning techniques to analyse secondary data from the 2016 Ethiopian Demographic and Health Survey. It aims to predict postnatal care utilization and identify key predictors via Python software, applying fifteen machine-learning algorithms to a sample of 7,193 women. Feature importance techniques were used to select the top predictors. The models' effectiveness was evaluated using sensitivity, specificity, F1 score, precision, accuracy, and area under the curve. Among the four experiments, tenfold cross-validation with balancing using Synthetic Minority Over-sampling Technique was outperformed. From fifteen models, the MLP Classifier (f1 score = 0.9548, AUC = 0.99), Random Forest Classifier (f1 score = 0.9543, AUC = 0.98), and Bagging Classifier (f1 score = 0.9498, AUC = 0.98) performed excellently, with a strong ability to differentiate between classes. The Region, residence, maternal education, religion, wealth index, health insurance status, and place of delivery are identified as contributing factors that predict postnatal care utilization. This study assessed machine learning models for forecasting postnatal care usage. Ten-fold cross-validation with Synthetic Minority Oversampling Technique produced the best results, emphasizing the significance of addressing class imbalance in healthcare datasets. This approach enhances the accuracy and dependability of predictive models. Key findings reveal regional and socioeconomic factors influencing PNC utilization, which can guide targeted initiatives to improve postnatal care utilization and ultimately enhance maternal and child health.</p>","PeriodicalId":74465,"journal":{"name":"PLOS digital health","volume":"4 1","pages":"e0000707"},"PeriodicalIF":0.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11717314/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142960064","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}