Frontiers in digital health最新文献

{"title":"Effectiveness of mobile health in symptom management of prostate cancer patients: a systematic review and meta-analysis.","authors":"Hai Shan Chen, Hua He, Hai Hang Lin, Yuan Zhang, Nu Li, Ya Mei Li","doi":"10.3389/fdgth.2025.1584764","DOIUrl":"10.3389/fdgth.2025.1584764","url":null,"abstract":"<p><strong>Background: </strong>Mobile health (mHealth) is an accessible strategy to deliver health information and is becoming increasingly popular as a form of follow-up among medical staff. However, the effects of mobile health on the physical and mental health outcomes of patients with prostate cancer after discharge from the hospital remain unclear. This meta-analysis evaluated the current evidence regarding the effects of mHealth interventions on the outcomes of patients with prostate cancer.</p><p><strong>Methods: </strong>Four databases (PubMed, Cochrane Central electronic database, EMBASE, and Web of Science) were searched from inception to 8 November 2024 for randomized controlled trials (RCTs) comparing the effects of mobile health vs. usual care on the outcomes of patients with prostate cancer. Pooled outcome measures were determined using random effects models.</p><p><strong>Results: </strong>In total, 11 RCTs, including 1,368 patients, met the criteria for inclusion in this meta-analysis. The meta-analysis revealed a significant effect of mHealth interventions on long-term bowel function outcomes (standard mean difference = 0.19, 95% confidence interval = 0.01-0.37, <i>P</i> = 0.04, I² = 0.00%) compared with the usual standard care or no mHealth. However, no significant differences were observed in the following outcomes: short-term and long-term effects on anxiety, depression, self-efficacy, psychological distress, and urinary and hormonal function, and short-term effects on bowel function.</p><p><strong>Conclusions: </strong>mHealth interventions can significantly improve long-term bowel function outcomes. However, more research is needed to confirm other physical and mental health outcomes.</p><p><strong>Systematic review registration: </strong>https://www.crd.york.ac.uk/prospero/, PROSPERO (CRD420250651320).</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1584764"},"PeriodicalIF":3.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092381/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144121573","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":"Vocal biomarkers in heart failure-design, rationale and baseline characteristics of the AHF-Voice study.","authors":"Fabian Kerwagen, Maximilian Bauser, Magdalena Baur, Fabian Kraus, Caroline Morbach, Rüdiger Pryss, Kristen Rak, Stefan Frantz, Michael Weber, Julia Hoxha, Stefan Störk","doi":"10.3389/fdgth.2025.1548600","DOIUrl":"10.3389/fdgth.2025.1548600","url":null,"abstract":"<p><p>Acute heart failure (AHF) is a life-threatening condition and a common cause of hospitalization. The defining clinical feature of AHF is volume overload, leading to pulmonary and peripheral edema and consequently to weight gain. Vocal biomarkers have the potential to facilitate the early detection of worsening HF and the prevention of AHF episodes by offering a non-invasive, low-barrier monitoring tool. The AHF-Voice study is a prospective monocentric cohort study designed to investigate the trajectories of voice alterations during and after episodes of AHF, identify potential vocal biomarkers, and enhance the understanding of the pathophysiological mechanisms underlying these voice changes. It will examine the characteristics and determinants of vocal biomarkers, analyzing their correlations with patients' clinical status and comparing them to alternative clinical parameters in HF. Further, it aims to determine whether specific vocal biomarkers can accurately map different HF phenotypes and assess their association with patient trajectories<b>.</b> The study phenotypes patients hospitalized for AHF at admission and discharge, and follows them for a period of 6 months. During hospitalization, daily voice recordings are collected using a specially-designed smartphone app. Following discharge, patients are requested to continue daily voice recordings with their own smartphone for the subsequent six months the 6-month follow-up. Patient-reported outcome measures and body composition are assessed in the hospital and at follow-up visits. Sub-studies explore vocal fold oscillation through video-laryngostroboscopy and assess the feasibility of combining voice analysis with in-ear sensor technology for comprehensive digital phenotyping. A total of 131 patients were enrolled between April 2023 and November 2024: their mean age was 75 years (SD 10), 31% were women, 86% were in NYHA functional class III or IV, and 38% presented with <i>de novo</i> heart failure. Additionally, 59% of participants owned smartphones. The AHF-Voice study will provide insights into the potential of vocal biomarkers as reliable indicators of congestion, paving the way for innovative and accessible tools to support heart failure management.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1548600"},"PeriodicalIF":3.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12082658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095942","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 role of technology and screen media use in treatment outcomes of children participating in a digital mental health intervention: a retrospective analysis of Bend Health.","authors":"Kelsey McAlister, Darian Lawrence-Sidebottom, Donna McCutchen, Monika Roots, Jennifer Huberty","doi":"10.3389/fdgth.2025.1556468","DOIUrl":"10.3389/fdgth.2025.1556468","url":null,"abstract":"<p><strong>Introduction: </strong>Digital mental health interventions (DMHIs) show promise in improving children's mental health, but there is limited understanding of how technology and screen media influence treatment outcomes. The purpose of this study was to leverage retrospective data to explore the relationships of technology and screen media use with mental health symptoms among children participating in a pediatric DMHI.</p><p><strong>Methods: </strong>Children ages 6-12 years who participated in a DMHI, Bend Health Inc, in the United States were included. Caregivers reported their child's screen media use and mental health symptoms every 30 days. Associations of screen media use with mental health symptoms were examined at baseline and throughout DMHI participation.</p><p><strong>Results: </strong>Nearly all children (98.0%) used screen media, with 58.3% exhibiting problematic use and 23.2% showing elevated use at baseline. Elevated screen media use was associated with more severe depressive (z = 2.19, <i>P</i> = .022) and anxiety symptoms (z = 2.36, <i>P</i> = .019) at baseline, though associations differed by type. Video streaming, internet use, and gaming were linked to inattention, hyperactivity, and oppositional behavior (P's < 0.05). While screen media use decreased for most children during care (93.1%), those with elevated use showed marginally greater improvements in anxiety (z = -1.87, <i>P</i> = .062) and inattention symptoms (z = -1.90, <i>P</i> = .058).</p><p><strong>Discussion: </strong>Findings suggest a nuanced interaction between technology use and DMHIs. Future research should explore the specific contexts of screen media use to optimize DMHI effectiveness and address the potential adverse effects of certain screen media activities.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1556468"},"PeriodicalIF":3.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12081425/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095937","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":"Efficient patient care in the digital age: impact of online appointment scheduling in a medical practice and a university hospital on the \"no-show\"-rate.","authors":"Paola Kammrath Betancor, Daniel Boehringer, Jens Jordan, Charlotte Lüchtenberg, Marcus Lambeck, Manuel Christoph Ketterer, Thomas Reinhard, Michael Reich","doi":"10.3389/fdgth.2025.1567397","DOIUrl":"10.3389/fdgth.2025.1567397","url":null,"abstract":"<p><strong>Background: </strong>Online appointment scheduling (OAS) increases patient satisfaction and enables more efficient care.</p><p><strong>Method: </strong>A retrospective study in an ophthalmology practice and an ophthalmology university hospital. Over 20 months, all booked practice-appointments before and after OAS implementation were recorded. Rates of cancellations/rescheduling and unexcused absences (\"no-shows\") were compared. During the same period, OAS usage, no-show rates, and related factors were analyzed in the hospital.</p><p><strong>Results: </strong>During the observation period, 16,894 appointments were booked in the practice and 81,173 in the hospital. In both, the rate of appointments scheduled via OAS increased continuously, with an average rate of 22.8% in the practice and 7.2% in the hospital. The no-show rate in the practice was lower for appointments booked online compared to those booked offline (median (x¯) 1.8% vs. 5.9%, <i>p</i> < 0.0001), whereas it was higher in the hospital (x¯ 14.3% vs. 11.2%, <i>p</i> < 0.0001). Regular consultations and SMS reminders were most effective in reducing no-shows in the hospital (Odds Ratio (OR) 0.40 and OR 0.93). The implementation of OAS in the practice reduced the rates of unused appointments (x¯ 22.7% vs. 10.3%, <i>p</i> < 0.0001) and never booked appointments (x¯ 8.6% vs. 1.6%, <i>p</i> < 0.0001), thereby increasing the utilization of available appointments (<i>p</i> < 0.0001).</p><p><strong>Conclusion: </strong>OAS improves flexibility and resource use in the practice. In the hospital, SMS reminders mostly reduce no-shows, prompting development of a comprehensive reminder model.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1567397"},"PeriodicalIF":3.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12081397/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095932","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":"Application of artificial intelligence and machine learning in lung transplantation: a comprehensive review.","authors":"Xiting Liu, Wenqian Chen, Wenwen Du, Pengmei Li, Xiaoxing Wang","doi":"10.3389/fdgth.2025.1583490","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1583490","url":null,"abstract":"<p><p>Lung transplantation (LTx) is an effective method for treating end-stage lung disease. The management of lung transplant recipients is a complex, multi-stage process that involves preoperative, intraoperative, and postoperative phases, integrating multidimensional data such as demographics, clinical data, pathology, imaging, and omics. Artificial intelligence (AI) and machine learning (ML) excel in handling such complex data and contribute to preoperative assessment and postoperative management of LTx, including the optimization of organ allocation, assessment of donor suitability, prediction of patient and graft survival, evaluation of quality of life, and early identification of complications, thereby enhancing the personalization of clinical decision-making. However, these technologies face numerous challenges in real-world clinical applications, such as the quality and reliability of datasets, model interpretability, physicians' trust in the technology, and legal and ethical issues. These problems require further research and resolution so that AI and ML can more effectively enhance the success rate of LTx and improve patients' quality of life.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1583490"},"PeriodicalIF":3.2,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12078212/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144082558","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":"Weakly supervised text classification on free-text comments in patient-reported outcome measures.","authors":"Anna-Grace Linton, Vania Gatseva Dimitrova, Amy Downing, Richard Wagland, Adam W Glaser","doi":"10.3389/fdgth.2025.1345360","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1345360","url":null,"abstract":"<p><strong>Background: </strong>Free-text comments in patient-reported outcome measures (PROMs) data provide insights into health-related quality of life (HRQoL). However, these comments are typically analysed using manual methods, such as content analysis, which is labour-intensive and time-consuming. Machine learning analysis methods are largely unsupervised, necessitating post-analysis interpretation. Weakly supervised text classification (WSTC) can be a valuable analytical method of analysis for classifying domain-specific text data, especially when limited labelled data are available. In this paper, we applied five WSTC techniques to PROMs comment data to explore the extent to which they can be used to identify HRQoL themes reported by patients with prostate and colorectal cancer.</p><p><strong>Methods: </strong>The main HRQoL themes and associated keywords were identified from a scoping review. They were used to classify PROMs comments with these themes from two national PROMs datasets: colorectal cancer (<i>n</i> = 5,634) and prostate cancer (<i>n</i> = 59,768). Classification was done using five keyword-based WSTC methods (anchored CorEx, BERTopic, Guided LDA, WeSTClass, and X-Class). To evaluate these methods, we assessed the overall performance of the methods and by theme. Domain experts reviewed the interpretability of the methods using the keywords extracted from the methods during training.</p><p><strong>Results: </strong>Based on the 12 papers identified in the scoping review, we determined six main themes and corresponding keywords to label PROMs comments using WSTC methods. These themes were: Comorbidities, Daily Life, Health Pathways and Services, Physical Function, Psychological and Emotional Function, and Social Function. The performance of the methods varied across themes and between the datasets. While the best-performing model for both datasets, CorEx, attained weighted F1 scores of 0.57 (colorectal cancer) and 0.61 (prostate cancer), methods achieved an F1 score of up to 0.92 (Social Function) on individual themes. By evaluating the keywords extracted from the trained models, we saw that the methods that can utilise expert-driven seed terms and extrapolate based on limited data performed the best.</p><p><strong>Conclusions: </strong>Overall, evaluating these WSTC methods provided insight into their applicability for analysing PROMs comments. Evaluating the classification performance illustrated the potential and limitations of keyword-based WSTC in labelling PROMs comments when labelled data are limited.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1345360"},"PeriodicalIF":3.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12075198/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144082296","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":"Beyond the gender data gap: co-creating equitable digital patient twins.","authors":"Nora Weinberger, Daniela Hery, Dana Mahr, Stephan O Adler, Jean Stadlbauer, Theresa D Ahrens","doi":"10.3389/fdgth.2025.1584415","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1584415","url":null,"abstract":"<p><p>Digital patient twins constitute a transformative innovation in personalized medicine, integrating patient-specific data into predictive models that leverage artificial intelligence (AI) to optimize diagnostics and treatments. However, existing digital patient twins often fail to incorporate gender-sensitive and socio-economic factors, reinforcing biases and diminishing their clinical effectiveness. This (gender) data gap, long recognized as a fundamental problem in digital health, translates into significant disparities in healthcare outcomes. This mini-review explores the interdisciplinary connections of technical foundations, medical relevance, as well as social and ethical challenges of digital patient twins, emphasizing the necessity of gender-sensitive design and co-creation approaches. We argue that without intersectional and inclusive frameworks, digital patient twins risk perpetuating existing inequalities rather than mitigating them. By addressing the interplay between gender, AI-driven decision-making and health equity, this mini-review highlights strategies for designing more inclusive and ethically responsible digital patient twins to further interdisciplinary approaches.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1584415"},"PeriodicalIF":3.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12075337/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144082591","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 quest for blood pressure markers in photoplethysmography and its applications in digital health.","authors":"Josep Sola, Andreu Arderiu, Tiago P Almeida, Sibylle Fallet, Sasan Yazdani, Serj Haddad, David Perruchoud, Olivier Grossenbacher, Jay Shah","doi":"10.3389/fdgth.2025.1518322","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1518322","url":null,"abstract":"<p><strong>Introduction: </strong>Photoplethysmography (PPG) sensors, capturing optical signals from arterial pulses, are debated for their potential in blood pressure (BP) measurement. This study employed the largest dataset to date of paired PPG and cuff BP readings to explore PPG signals for BP estimation.</p><p><strong>Methods: </strong>32,152 European residents (age 55.9% ± 11.8, 24% female, BMI 27.7 ± 4.6) voluntarily acquired and used a cuffless BP monitor (Aktiia SA, Switzerland) between March/2,021-March/2023. Systolic and diastolic BP (SBP, DBP) from an upper arm oscillometric cuff were collected simultaneously with wrist PPG (668,080 paired measurements). Six different machine learning models were developed to predict BP using cuff BP readings as reference (75%|15%|15% training|validation|testing): four baseline models [heart rate (HR), Age, Demography (DEM: Age + Gender + BMI), DEM + HR], and two models relying on the analysis of the PPG waveforms (PPG, PPG + DEM). Performance of each model was evaluated on the 4,823 subjects from the testing set using as metrics the Pearson's correlation (r) when comparing the estimated and the reference BP values, and the area under the receiver operating characteristic (AUROC) curves, and true positive and true negative rates (TPR, TNR) for the detection of high BP (reference SBP ≥ 140 or DBP ≥ 90 mmHg, applying a ± 8 mmHg exclusion zone to account for cuff measurement uncertainty).</p><p><strong>Results: </strong>Baseline models showed low correlation with cuff data and poor high BP detection (<i>r</i> < 0.35; AUROC < 0.65, TPR < 0.65, TNR < 0.58). PPG-based models excelled in correlating with cuff BP (SBP: <i>r</i> = 0.53 for PPG, <i>r</i> = 0.63 for PPG + DEM; DBP: <i>r</i> = 0.58 for PPG, <i>r</i> = 0.67 for PPG + DEM) and high BP detection (SBP: AUROC = 0.84, TPR = TNR = 0.75; DBP: AUROC = 0.89, TPR = TNR = 0.81 for PPG; SBP: AUROC = 0.89, TPR = TNR = 0.80; DBP: AUROC = 0.93, TPR = TNR = 0.86 for PPG + DEM).</p><p><strong>Discussion: </strong>This study demonstrated that PPG signals contain reliable markers of BP, and that BP values can be estimated using only markers found within PPG's optical pulsatility signals, outperforming models based solely on demographic data. These findings hold the potential to radically transform hypertension screening and global healthcare delivery, paving the way for innovative approaches in patient diagnosis, monitoring and treatment methodologies.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1518322"},"PeriodicalIF":3.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12075524/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144081888","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":"Comparison of the diagnostic concordance of tele-EMS and EMS physicians in the emergency medical service-a subanalysis of the TEMS-trial.","authors":"Patrick P Hess, Michael Czaplik, Johanna Hess, Hanna Schröder, Stefan K Beckers, Andreas Follmann, Mark Pitsch, Marc Felzen","doi":"10.3389/fdgth.2025.1519619","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1519619","url":null,"abstract":"<p><strong>Introduction: </strong>The emergency medical services (EMS) in Germany are facing several challenges in the near future. Due to the increasing number of emergency missions, the availability of EMS physicians is becoming more limited, resulting in longer response times. To maintain the high quality of EMS, telemedical support systems have shown potential as a valuable complement to the existing system for specific diagnoses. Since 2014, a tele-EMS system has been implemented in Aachen as an integrated telemedical solution alongside standard EMS. Accurate prehospital diagnosis plays a crucial role in ensuring appropriate hospital admission and reducing the time to clinical treatment for time-sensitive conditions. The main TEMS study demonstrated the overall non-inferiority of tele-EMS physicians compared to on-site EMS physicians. This sub-analysis focuses on comparing the diagnostic accuracy between these two groups.</p><p><strong>Methods: </strong>Up to four prehospital diagnoses were selected, coded according to the ICD-10 system, and compared with all admission and discharge diagnoses.</p><p><strong>Results: </strong>The comparison between diagnoses made by tele-EMS physicians and on-site EMS physicians with admission diagnoses showed no significant difference (<i>p</i> = 0.877). Additionally, no significant differences were found for the diagnoses of stroke (<i>p</i> = 0.385) and epileptic seizure (<i>p</i> = 0.738). However, patients from missions where paramedics decided to consult a tele-EMS physician had significantly longer hospital stays compared to those from missions where an on-site EMS physician was initially dispatched (<i>p</i> < 0.001).</p><p><strong>Discussion: </strong>This randomized controlled analysis demonstrated that there is no difference in diagnostic accuracy between on-site EMS physicians and remote tele-EMS physicians. The significantly longer hospital stays for patients treated by tele-EMS physicians suggest that EMS physicians may be called too frequently for non-severe cases.</p><p><strong>Clinical trial registration: </strong>clinicaltrials.gov, identifier (NCT02617875).</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1519619"},"PeriodicalIF":3.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12075532/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144082592","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":"Stress can be detected during emotion-evoking smartphone use: a pilot study using machine learning.","authors":"Lydia Helene Rupp, Akash Kumar, Misha Sadeghi, Lena Schindler-Gmelch, Marie Keinert, Bjoern M Eskofier, Matthias Berking","doi":"10.3389/fdgth.2025.1578917","DOIUrl":"https://doi.org/10.3389/fdgth.2025.1578917","url":null,"abstract":"<p><strong>Introduction: </strong>The detrimental consequences of stress highlight the need for precise stress detection, as this offers a window for timely intervention. However, both objective and subjective measurements suffer from validity limitations. Contactless sensing technologies using machine learning methods present a potential alternative and could be used to estimate stress from externally visible physiological changes, such as emotional facial expressions. Although previous studies were able to classify stress from emotional expressions with accuracies of up to 88.32%, most works employed a classification approach and relied on data from contexts where stress was induced. Therefore, the primary aim of the present study was to clarify whether stress can be detected from facial expressions of six basic emotions (anxiety, anger, disgust, sadness, joy, love) and relaxation using a prediction approach.</p><p><strong>Method: </strong>To attain this goal, we analyzed video recordings of facial emotional expressions collected from n = 69 participants in a secondary analysis of a dataset from an interventional study. We aimed to explore associations with stress (assessed by the PSS-10 and a one-item stress measure).</p><p><strong>Results: </strong>Comparing two regression machine learning models [Random Forest (RF) and XGBoost], we found that facial emotional expressions were promising indicators of stress scores, with model fit being best when data from all six emotional facial expressions was used to train the model (one-item stress measure: MSE (XGB) = 2.31, MAE (XGB) = 1.32, MSE (RF) = 3.86, MAE (RF) = 1.69; PSS-10: MSE (XGB) = 25.65, MAE (XGB) = 4.16, MSE (RF) = 26.32, MAE (RF) = 4.14). XGBoost showed to be more reliable for prediction, with lower error for both training and test data.</p><p><strong>Discussion: </strong>The findings provide further evidence that non-invasive video recordings can complement standard objective and subjective markers of stress.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1578917"},"PeriodicalIF":3.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12075543/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144082593","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}