DIGITAL HEALTH最新文献

{"title":"Synergistic evaluation system of \"technology and service\" in smart elderly care institutions in China.","authors":"Xiaoyun Liu, Ka-Yin Chau, Xiaoxiao Liu, Yan Wan","doi":"10.1177/20552076251326681","DOIUrl":"https://doi.org/10.1177/20552076251326681","url":null,"abstract":"<p><strong>Background: </strong>Smart elderly care faces numerous challenges while aligning with the national strategy of promoting the silver economy. Chief among these challenges is the inconsistent quality of services offered by smart elderly care institutions, which significantly impedes the industry's further development. Therefore, the objective of this paper is to develop a theoretical framework for assessing the quality of smart elderly care services, refine the evaluation index system for these services, and explore strategies to enhance their quality.</p><p><strong>Methods: </strong>Based on the Structure-Process-Outcome model, this paper has developed an integrated theoretical framework and employed a combination of modified-Delphi method and Decision-Making Trial and Evaluation Laboratory - Analytic Network Process to establish and assign weights to the service quality evaluation system for smart elderly care institutions in China.</p><p><strong>Results: </strong>This study develops a \"Technology + Service\" synergistic theoretical framework and an index system comprising four first-tier indicators, 12 second-tier indicators, and 54 third-tier indicators. The most significant indicators identified are service resources, smart elderly care infrastructure, staffing, service empathy, the rate of health file creation, 3S device coverage rate, and average living space per bed.</p><p><strong>Conclusion: </strong>The results reveal that service resources, especially the information technology infrastructure and smart equipment are the most crucial aspects of smart elderly care institutions. Additionally, institutions should focus on improving the expertise of their staff and providing psychological care for elderly adults.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251326681"},"PeriodicalIF":2.9,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12033596/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144050123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Providing digital mental health support and guidance across Colombia: An observational study.","authors":"Haley M LaMonica, Paula Natalia Bettancourt Niño, Carlos Gómez-Restrepo, Jose Miguel Uribe-Restrepo, Tatiana Colón-Llamas, Andrea Escobar Altare, Ibeth Alexandra Naranjo-Bedoya, Laura Tatiana Morales-Zuluaga, Jaime A Pavlich-Mariscal, Alexandra Pomares-Quimbaya, Angelica María Puentes Mojica, Alvaro Andrés Navarro Mancilla, Esperanza Peña Torres, Frank Iorfino, Carla Gorban, Ian B Hickie, Laura Ospina-Pinillos","doi":"10.1177/20552076251330766","DOIUrl":"https://doi.org/10.1177/20552076251330766","url":null,"abstract":"<p><strong>Objective: </strong>Colombia's mental health system is plagued by significant shortages in services and health professionals. Digital health technologies enable access to information and care, overcoming barriers related to systemic limitations, geographic location, cost and stigma. This paper aims to characterise the sample of Colombians who sought telecounselling and support through Mentes Colectivas, a web-based mental health counselling platform.</p><p><strong>Methods: </strong>Participants provided basic demographics and completed the Kessler 6 to track psychological distress. Counsellors collected information about participants' level of functional impairment, presenting problems, mental health warning signs and session attendance. Descriptive statistics were used to characterise the sample. A range of inferential statistics were used to analyse group differences based on age and session, explore associations within clinical presentations, examine predictors of session attendance and analyse clinical differences between episodes of care.</p><p><strong>Results: </strong>A total of 6442 participants (mean age = 33.6 years; 78.5% female) attended an initial session, with 35.7% returning for at least one follow-up session. Participants on average reported moderate levels of psychological distress, with young people reporting significantly higher distress relative to adults and older adults. Symptoms of anxiety and depression and sleep disturbances were most common.</p><p><strong>Conclusions: </strong>This research confirms the feasibility of Mentes Colectivas to promote help-seeking and support self-management of mental health across the lifespan in Colombia. Digital health technologies have the potential to play a vital role in increasing equity of access to care for the Colombian population, improving mental health and functioning as well as potentially strengthening the health of families and communities.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251330766"},"PeriodicalIF":2.9,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12033600/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144008219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sociodemographic and health predictors of adherence to self-administered computerized cognitive assessment.","authors":"Marisa Magno, Ana Isabel Martins, Joana Pais, Vítor Tedim Cruz, Anabela G Silva, Nelson Pacheco Rocha","doi":"10.1177/20552076251332774","DOIUrl":"https://doi.org/10.1177/20552076251332774","url":null,"abstract":"<p><strong>Introduction: </strong>Cognitive assessment is essential to detect early cognitive decline and guide interventions. Self-administered computerized assessment is a promising option for periodic cognitive screening in the general population. One of the most critical challenges to implementing cognitive screening in at risk populations is participants' adherence. However, there is insufficient evidence to determine which factors are essential for adherence to long-term digital cognitive screening.</p><p><strong>Aims: </strong>This study aims to investigate potential sociodemographic and health predictors of adherence to a self-administered web-based cognitive monitoring, the Brain on Track (BoT), in the general population.</p><p><strong>Methods: </strong>Participants (<i>n</i> = 347) were recruited from the general community. The participants were asked to perform one BoT test every 3 months for cognitive screening and were followed at two time points, namely, 1-year and 3- to 6-year follow-up. Regression models were used to investigate sociodemographic and health predictors of adherence to BoT use at 1 year and up to 6 years.</p><p><strong>Results: </strong>Being older positively affects adherence to periodic cognitive screening for both follow-up periods. Being a female, having more years of formal education, presenting more BoT baseline correct answers and fewer BoT baseline incorrect answers, and reporting memory complaints positively affect adherence to periodic screening at 3 to 6 years of follow-up but not at 1-year follow-up.</p><p><strong>Discussion: </strong>The identified determinants of adherence can be considered when planning long-term cognitive screening protocols to increase adherence. Specific strategies could be helpful to improve the adherence of participants who adhere less.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251332774"},"PeriodicalIF":2.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12032462/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of a virtual simulative diabetes care program on learning ability and clinical thinking skills in nursing interns.","authors":"Tianhui Xu, Qin Wang, Fang Liu, Li Yang, Rong Wang, Huiting Weng","doi":"10.1177/20552076251332834","DOIUrl":"https://doi.org/10.1177/20552076251332834","url":null,"abstract":"<p><strong>Introduction: </strong>Diabetes is a major global health issue, requiring nursing interns to develop essential diabetes management skills. Traditional teaching methods are limited by clinical settings, hindering the development of comprehensive theoretical and clinical competencies. This study developed a Virtual Simulative Diabetes Care Program to address these limitations.</p><p><strong>Methods: </strong>A quasi-experimental design was employed. Nursing interns were assigned to an intervention group (virtual simulation) or a control group (traditional face-to-face training). Self-directed learning ability and clinical thinking skills were assessed using the validated Independent Learning Ability Scale and Clinical Thinking Skills Scale. Pre- and post-intervention measurements were conducted, and data were analyzed using independent <i>t</i>-tests and Mann-Whitney <i>U</i> tests, with significance set at <i>P</i> < .05.</p><p><strong>Results: </strong>The intervention group showed significantly higher self-directed learning ability (104.53 ± 7.75 vs. 99.00 ± 13.77, <i>P</i> < .05) and clinical thinking skills (99.71 ± 12.15 vs. 91.69 ± 17.44, <i>P</i> < .05) compared to the control group. Within the intervention group, both abilities significantly improved from pre- to post-internship (<i>P</i> < .05). Practical skills, including blood glucose monitoring and insulin injection, also improved, with higher scores in the intervention group. The virtual simulation program was rated as effective, with an overall score of 8.37 ± 1.20 and \"Excellent\" ratings for learning functionality.</p><p><strong>Conclusions: </strong>The virtual simulation-based diabetes care program significantly improved nursing interns' learning and clinical skills.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251332834"},"PeriodicalIF":2.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12032435/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144038859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Translation and psychometric evaluation of the Chinese version of the Digital Competence Questionnaire for clinical nurses.","authors":"Zhengang Wei, Hongli Liu, Jicheng Zhang, Yan Chen, Lixia Chang, Huiyu Cheng, Xue Bai, Xiaohua Wang, Su Li","doi":"10.1177/20552076251332987","DOIUrl":"https://doi.org/10.1177/20552076251332987","url":null,"abstract":"<p><strong>Background: </strong>Adequate digital competence is crucial for clinical nurses to effectively adapt to the evolving digital technologies in their practice. Currently, there is a lack of a brief assessment tool in China that comprehensively measures the digital competence of nurses in clinical practice across the dimensions of knowledge, skills, and attitudes. Therefore, this study aims to translate the Digital Competence Questionnaire (DCQ) into Chinese and evaluate its psychometric properties.</p><p><strong>Methods: </strong>Following Brislin's translation model, the DCQ was translated and back-translated, and cultural adaptation and revisions of the Chinese version were conducted through expert consultations and a pilot survey. A cross-sectional study was carried out from July to October 2024 to conduct a methodological investigation on the translation and validation of the DCQ.</p><p><strong>Results: </strong>The Chinese version of the DCQ includes two dimensions-attitude and knowledge & skills-with a total of 12 items. The overall Cronbach's <i>α</i> value for the questionnaire is 0.970, while Cronbach's <i>α</i> for the individual dimensions ranges from 0.921 to 0.945. The split-half reliability of the entire scale is 0.912, and the test-retest reliability is 0.846. Confirmatory factor analysis supported the hypothesized first-order two-factor model, with all fit indices demonstrating satisfactory values and remaining within acceptable levels.</p><p><strong>Conclusion: </strong>The Chinese version of the DCQ has been successfully introduced in China, demonstrating strong psychometric properties. It can be used in healthcare settings as a tool to assess the digital competence of nurses, providing a basis for developing subsequent digital technology training programs and targeted interventions.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251332987"},"PeriodicalIF":2.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12032463/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144062691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning-based prediction of in-hospital mortality in patients with chronic respiratory disease exacerbations.","authors":"Seung Yeob Ryu, Seon Min Lee, Young Jae Kim, Kwang Gi Kim","doi":"10.1177/20552076251326703","DOIUrl":"10.1177/20552076251326703","url":null,"abstract":"<p><strong>Objective: </strong>Exacerbation of chronic respiratory diseases leads to poor prognosis and a significant socioeconomic burden. To address this issue, an artificial intelligence model must assess patient prognosis early and classify patients into high- and low-risk groups. This study aimed to develop a model to predict in-hospital mortality in patients with chronic respiratory disease using demographic, clinical, and environmental factors, specifically air pollution exposure levels.</p><p><strong>Methods: </strong>This study included 6272 patients diagnosed with chronic respiratory diseases comprising 39 risk factors. Air pollution indicators such as particulate matter (PM10), fine particulate matter (PM2.5), CO, NO₂, O₃, and SO₂ were used based on long-term and short-term exposure levels. Logistic regression, support vector machine, random forest, and extreme gradient boost were used to develop prediction models.</p><p><strong>Results: </strong>The AUCs for the four models were 0.932, 0.935, 0.933, and 0.944. The key risk factors that significantly influenced predictions included blood urea nitrogen, red blood cell distribution width, respiratory rate, and age, which were positively correlated with mortality prediction. In contrast, albumin, lymphocyte count, diastolic blood pressure, and SpO2 were negatively correlated with mortality prediction.</p><p><strong>Conclusion: </strong>This study developed a prediction model for in-hospital mortality in patients with chronic respiratory disease and demonstrated a relatively high predictive performance. By incorporating environmental factors, such as air pollution exposure levels, the model with the best performance suggested that 365 days of exposure to air pollution was a key risk factor in mortality prediction.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251326703"},"PeriodicalIF":2.9,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11970076/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risk factors and a predictive model for mixed urinary incontinence among parous women: Insights from a large-scale multicenter epidemiological investigation.","authors":"Qi Wang, Stefano Manodoro, Huifang Lin, Xiaofang Li, Chaoqin Lin, Xiaoxiang Jiang","doi":"10.1177/20552076251333661","DOIUrl":"10.1177/20552076251333661","url":null,"abstract":"<p><strong>Purpose: </strong>This study aims to identify independent risk factors for mixed urinary incontinence (MUI) in parous women using a multicenter epidemiological study and to establish and validate a predictive nomogram.</p><p><strong>Methods: </strong>A large-scale survey was conducted from June 2022 to September 2023, including parous women aged over 20 selected through stratified random sampling. Data encompassed sociodemographic and obstetric histories, comorbidities, and standardized questionnaires. The primary goal was to identify high-risk factors for MUI, while the secondary was to develop a nomogram. Risk factors were determined using univariable and multivariable analyses. The nomogram's performance was assessed via concordance index (C-index) and calibration plots through internal and external validation.</p><p><strong>Results: </strong>A total of 7709 women participated, with an MUI prevalence of 6.8%. Independent risk factors included higher body mass index, urban residence, postmenopausal status, multiple vaginal deliveries, history of pelvic surgery and macrosomia, family history of pelvic floor dysfunction, hypertension, and constipation. The area under the curve for the nomogram model was 0.717 in the training set, 0.714 for internal validation, and 0.725 for external validation. The calibration plots showed a good agreement between the predicted and observed outcomes.</p><p><strong>Conclusion: </strong>This study identifies key risk factors for MUI in parous women and introduces a validated nomogram with high but not perfect predictive accuracy. The model enables early identification and management of MUI, though further refinement could enhance accuracy.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251333661"},"PeriodicalIF":2.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11970075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The relationship between age and physical activity as objectively measured by accelerometers in older adults with and without dementia.","authors":"Karl Brown, Andrew Shutes-David, Sarah Payne, Adrienne Jankowski, Katie Wilson, Edmund Seto, Debby W Tsuang","doi":"10.1177/20552076251330808","DOIUrl":"10.1177/20552076251330808","url":null,"abstract":"<p><strong>Objective: </strong>This study sought to investigate differences in physical activity and activity fragmentation between older adults with and without dementia and between older adults with dementia with Lewy bodies (DLB) and older adults with Alzheimer's disease (AD). The study also sought to investigate how these differences vary in magnitude at different ages.</p><p><strong>Methods: </strong>Accelerometry data were analyzed from individuals with dementia (<i>n</i> = 94) and individuals without dementia (<i>n</i> = 613) who participated in the National Health and Aging Trends Study (NHATS), as well as from individuals with DLB (<i>n</i> = 12) and AD (<i>n</i> = 10) who participated in a pilot study.</p><p><strong>Results: </strong>In the NHATS cohort, individuals without dementia had more activity counts (0.325 million [95% CI 0.162 million, 0.487 million]) and a longer active bout length (0.631 minutes [95% CI 0.311, 0.952]) at the mean age of 79 than individuals with dementia at the same age. There was also suggestive evidence that individuals without dementia had a shorter resting bout length (-2.196 minutes [95% CI -4.996, 0.605]) than individuals with dementia. Differences in data collection and processing prevented direct comparisons between the cohorts, and the parallel analyses in the smaller cohort were underpowered to detect statistically significant differences between DLB and AD.</p><p><strong>Conclusion: </strong>This work shows that objectively measured accelerometry data differ between individuals with and without dementia; future studies with larger samples should investigate whether accelerometry data can be used to aid in the early identification of dementia and differentiation of dementia subtypes.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251330808"},"PeriodicalIF":2.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11970097/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond the STI clinic: Use of administrative claims data and machine learning to develop and validate patient-level prediction models for gonorrhea.","authors":"Lorenzo Argante, Germain Lonnet, Emmanuel Aris, Jane Whelan","doi":"10.1177/20552076251331895","DOIUrl":"10.1177/20552076251331895","url":null,"abstract":"<p><strong>Background: </strong>Gonorrhea is a sexually transmitted infection (STI) that, untreated, can result in debilitating complications such as pelvic inflammatory disease, pain, and infertility. A minority of cases are diagnosed in STI clinics in the United States. Gonorrhea is often asymptomatic and presumed to be substantially underdiagnosed and/or undertreated.</p><p><strong>Objectives: </strong>To generate and compare predictive machine learning (ML) models using administrative claims data to characterize young women in the general United States population who would be most likely to contract gonorrhea.</p><p><strong>Methods: </strong>Data were extracted from the Merative™ MarketScan^® Commercial and Medicaid databases containing routinely collected administrative claims data. Women aged 16-35 years with two years of continuous observation between 1 January 2017 and 31 December 2018 were included. ML classification models were constructed based on logistic regression and tree-based algorithms.</p><p><strong>Results: </strong>Models constructed using tree-based algorithms such as XGBoost provided the best discriminatory results, but simpler ridge regressions models with splines also achieved reasonable discrimination, allowing for the identification of population subsets at increased risk of gonorrhea infection. A subset of 0.1% of the population identified by the XGBoost model had a 70-fold higher risk of gonorrhea than the general population. External validation applying the different models on a Medicaid dataset that was not included in developing the original models was checked and deemed acceptable.</p><p><strong>Conclusions: </strong>The models and methods presented here could facilitate the identification of women at high risk of contracting gonorrhea for whom targeted preventive measures may be most beneficial.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251331895"},"PeriodicalIF":2.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11970062/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting 30-day readmissions in pneumonia patients using machine learning and residential greenness.","authors":"Seohyun Choi, Young Jae Kim, Seon Min Lee, Kwang Gi Kim","doi":"10.1177/20552076251325990","DOIUrl":"10.1177/20552076251325990","url":null,"abstract":"<p><strong>Introduction: </strong>Identifying factors that increase the risk of hospital readmission will help determine high-risk patients and decrease the socioeconomic burden. Pneumonia is associated with high readmission rates. Although residential greenness has been reported to have beneficial health effects, no studies have investigated its importance in predicting readmission in patients with pneumonia. This study aimed to build prediction models for 30-day readmission in patients with pneumonia and to analyze the importance of risk factors for readmission, mainly residential greenness.</p><p><strong>Methods: </strong>Data on 47 risk factors were collected from 22,600 patients diagnosed with pneumonia. Residential greenness was quantified as the mean of normalized difference vegetation index of the district in which the patient resides. Prediction models were built using logistic regression, support vector machine, random forest, and extreme gradient boosting.</p><p><strong>Results: </strong>Residential greenness was selected from the top 21 risk factors after feature selection. The area under the curves of the four models were 0.6919, 0.6931, 0.7117, and 0.7044. Age, red blood cell distribution width, and history of cancer were the top three risk factors affecting readmission prediction. Residential greenness was the 15th important factor.</p><p><strong>Discussion: </strong>We constructed prediction models for 30-day readmission of patients with pneumonia by incorporating residential greenness as a risk factor. The models demonstrated sufficient performance, and residential greenness was significant in predicting readmission. Incorporating residential greenness into the identification of groups at high risk for readmission can complement the possible loss of information when using data from electronic health records.</p>","PeriodicalId":51333,"journal":{"name":"DIGITAL HEALTH","volume":"11 ","pages":"20552076251325990"},"PeriodicalIF":2.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11970095/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143797010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}