BMC digital health最新文献

{"title":"A novel telehealth tool using a snack activity to identify autism spectrum disorder","authors":"Zenghui Ma, Yan Jin, Ruoying He, Qinyi Liu, Xing Su, Jialu Chen, Disha Xu, Jianhong Cheng, Tiantian Zheng, Yanqing Guo, Xue Li, Jing Liu","doi":"10.1186/s44247-023-00047-8","DOIUrl":"https://doi.org/10.1186/s44247-023-00047-8","url":null,"abstract":"Abstract Background The COVID-19 pandemic has caused an unprecedented need for accessible health care services and significantly accelerated the development processes of telehealth tools for autism spectrum disorder (ASD) early screening and diagnosis. This study aimed to examine the feasibility and utility of a time-efficient telehealth tool combining a structured snack time assessment activity and a novel behaviour coding scheme for identifying ASD. Methods A total of 134 1–6-year-old individuals with ASD (age in months: mean = 51.3, SD = 13.1) and 134 age- and sex-matched typically developing individuals (TD) (age in months: mean = 54, SD = 9.44) completed a 1-min snack time interaction assessment with examiners. The recorded videos were then coded by trained coders for 17 ASD-related behaviours; the beginning and end points and the form and function of each behaviour were recorded, which took 10–15 min. Coded details were transformed into 62 indicators representing the count, duration, rate, and proportion of those behaviours. Results Twenty indicators with good reliability were selected for group difference, univariate and multivariate analyses. Fifteen behaviour indicators differed significantly between the ASD and TD groups and remained significant after Bonferroni correction, including the children’s response to the examiner’s initiation, eye gaze, pointing, facial expressions, vocalization and verbalization, and giving behaviours. Five indicators were included in the final prediction model: total counts of eye gaze, counts of standard pointing divided by the total counts of pointing, counts of appropriate facial expressions, counts of socially oriented vocalizations and verbalizations divided by the total counts of vocalizations and verbalizations, and counts of children using giving behaviours to respond to the examiner's initiations divided by the total counts of the examiner's initiation of snack requisitions. The ROC curve revealed a good prediction performance with an area under the curve (AUC) of 0.955, a sensitivity of 92.5% and a specificity of 84.3%. Conclusion Our results suggest that the snack activity-based ASD telehealth approach shows promise in primary health care settings for early ASD screening.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"49 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135432491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"21st century medicine and emerging biotechnological syndromes: a cross-disciplinary systematic review of novel patient presentations in the age of technology","authors":"Isabel Straw, Geraint Rees, Parashkev Nachev","doi":"10.1186/s44247-023-00044-x","DOIUrl":"https://doi.org/10.1186/s44247-023-00044-x","url":null,"abstract":"Abstract Background Biotechnological syndromes refer to the illnesses that arise at the intersection of human physiology and digital technology. Now that we experience health and illness through so much technology (e.g. wearables, telemedicine, implanted devices), the medium is redefining our expression of symptoms, the observable signs of pathology and the range of diseases that may occur. Here, we systematically review all case reports describing illnesses related to digital technology in the past ten years, in order to identify novel biotechnological syndromes, map out new causal pathways of disease, and identify gaps in care that have disadvantaged a community of patients suffering from these digital complaints. Methods PubMed, MEDLINE, Scopus, Cochrane Library and Web of Science were searched for case reports and case series that described patient cases involving biotechnological syndromes from 01/01/2012 to 01/02/2022. For inclusion the technology had to play a causative role in the disease process and had to be digital (as opposed to simple electronic). Results Our search returned 7742 articles, 1373 duplicates were removed, 671 met the criteria for full review and 372 were included in the results. Results were categorised by specialty, demonstrating that syndromes were most common in Cardiology ( n = 162), Microbiology and Infectious Diseases ( n = 36), and Emergency and Trauma ( n = 26). Discussion The 372 unique patient cases demonstrated a range of severity from mild (e.g., injuries related to Pokemon Go) to moderate (e.g. pacemaker-generated rib fractures) and severe (e.g. ventilator software bugs causing cardiac arrest). Syndromes resulted from both consumer technology (e.g. gaming addictions) and medical technologies (e.g. errors in spinal stimulators). Cases occurred at both the individual level (e.g. faulty insulin pumps) and at the population level (e.g. harm from healthcare cyberattacks). Limitations This was a retrospective systematic review of heterogeneous reports, written in English, which may only reflect a small proportion of true prevalence rates in the population.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135944200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of a digital and conventional prevention program on work ability, physical health, and mental health among employees with initial impairments","authors":"Detlef Schmidt, Julian Fritsch, Katharina Feil, Susanne Weyland, Darko Jekauc","doi":"10.1186/s44247-023-00043-y","DOIUrl":"https://doi.org/10.1186/s44247-023-00043-y","url":null,"abstract":"Abstract Background This quasi-experimental study aimed to compare the effectiveness of a digital prevention intervention on work ability, physical health, and mental health with a conventional prevention program for employees with initial impairments. The study recruited 245 participants, of whom 173 completed the study, 98 (65 female, 66.3%) in the intervention group and 75 (55 female, 73.3%) in the control group. Both groups received prevention programs, with the intervention group using the Caspar digital platform and the control group using the conventional BETSI/RV Fit program. There were three measurement points in the study: T0 before the intervention, T1 in the middle of the intervention, and T2 at the end of the intervention. Participants’ health was assessed using the SF-12 health status questionnaire, while their work ability was measured using the short version of the Work Ability Index. Results Repeated-measures analyses of variance indicated that both prevention programs were effective in improving work ability and mental health, while physical health did not show any significant improvement. Additionally, the results of the study suggest that younger individuals benefited more from the digital prevention intervention, while older individuals benefited more from the conventional prevention program. Conclusion The study emphasizes the need for further research and improvements in both research and practice. Future studies should include larger sample sizes, randomized controlled trials, and follow-up assessments to enhance understanding of the effectiveness and the durability of effects of prevention programs.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effectiveness and user experience of a biofeedback intervention program for stress management supported by virtual reality and mobile technology: a randomized controlled study","authors":"Jasmine I. Kerr, Raphael P. Weibel, Mara Naegelin, Andrea Ferrario, Victor R. Schinazi, Roberto La Marca, Christoph Hoelscher, Urs M. Nater, Florian von Wangenheim","doi":"10.1186/s44247-023-00042-z","DOIUrl":"https://doi.org/10.1186/s44247-023-00042-z","url":null,"abstract":"Abstract Background Heart rate variability biofeedback (HRV-BF) can be used for stress management. Recent feasibility studies suggest that delivering HRV-BF in virtual reality (VR) is associated with better user experience (UX) and might yield more beneficial changes in HRV than two-dimensional screens. The effectiveness of a VR-supported HRV-BF intervention program has, however, not been investigated yet. Methods In this study, 87 healthy women and men were assigned to a VR-supported HRV-BF intervention (INT; $$n=44$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mrow> <mml:mi>n</mml:mi> <mml:mo>=</mml:mo> <mml:mn>44</mml:mn> </mml:mrow> </mml:math> ) or a wait-list control (WLC; $$n=43$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mrow> <mml:mi>n</mml:mi> <mml:mo>=</mml:mo> <mml:mn>43</mml:mn> </mml:mrow> </mml:math> ) group. The INT came to the lab for four weekly HRV-BF sessions in VR using a head-mounted display. Between lab sessions, participants were asked to perform breathing exercises without biofeedback supported by a mobile application. Stress-related psychological and psychophysiological outcomes were assessed pre- and post-intervention and at a follow-up four weeks after the intervention in both groups. A psychosocial stress test was conducted post-intervention to investigate changes in stress reactivity. UX was assessed after each HRV-BF session in the INT. Results Analysis revealed that LF increased significantly from pre- to post-, whereas pNN50 increased and chronic stress decreased significantly from pre-intervention to follow-up in the INT compared to the WLC. Anxiety and mental fatigue decreased significantly, while mindfulness and health-related quality of life increased significantly from pre- to post- and from pre-intervention to follow-up in the INT compared to the WLC (all small effects). The two groups did not differ in their stress reactivity post-intervention. As for UX in the INT, the degree of feeling autonomous concerning technology adoption significantly decreased over time. Competence, involvement, and immersion, however, increased significantly from the first to the last HRV-BF session, while hedonic motivation significantly peaked in the second session and then gradually returned to first-session levels. Conclusions This HRV-BF intervention program, supported by VR and mobile technology, was able to significantly improve stress indicators and stress-related symptoms and achieved good to very good UX. Future studies should control for potential placebo effects and emphasize higher degrees of personalization and adaptability to increase autonomy and, thereby, long-term health and well-being. These findings may serve as a first step towards future HRV-BF applications of cutting-edge, increasingly accessible technologies, such as wearables, VR, and smartphones, in the service of mental health and healthcare. Trial registration The study was registered retrospectively as a clinical","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135806046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a 12-week app-guided exercise intervention in patients with knee osteoarthritis (re.flex): a study protocol for a randomized controlled trial","authors":"Valerie Dieter, Peter Martus, Pia Janssen, Inga Krauss","doi":"10.1186/s44247-023-00040-1","DOIUrl":"https://doi.org/10.1186/s44247-023-00040-1","url":null,"abstract":"Abstract Background Current health care demonstrates an insufficient provision and utilization of physical exercises despite their recommendation as a first-line treatment in clinical guidelines for patients with knee osteoarthritis (OA). Mobile health (m-health) technologies offer new opportunities to guide and monitor home-based exercise programs by using mobile devices and inertial sensors in combination with a digital application (app). This study will evaluate patient benefits resulting from the use of the specific digital health application re.flex for patients with knee OA. Methods This monocentric, two-arm, randomized controlled parallel-group trial will evaluate the effectiveness of the app- and sensor-guided exercise program re.flex for patients with moderate-to-severe knee OA. We aim to recruit 200 participants via newspapers, newsletters and information events. Participants will be randomly allocated to the intervention group and the control group in a 1:1 ratio. Participants in the control group will not receive any study intervention or instruction for any change to their previous health care utilization. Despite this, they are allowed to make use of usual care provided by their treating physician. The intervention group comprises a 12-week home training program with three sessions per week in addition to usual care. Exercises will be guided and monitored by use of the training app (re.flex) and two accelerometers that are attached proximally and distally to the affected knee joint. Pre- and postmeasurements will take place at baseline (t0) and after 12 weeks (t1). Primary outcomes will be osteoarthritis-specific pain and physical function measured with the Knee Osteoarthritis Outcome Score (KOOS) subscales Pain and Function in daily living (ADL). Second, further self-reported health outcomes, a performance measurement, app logfiles and safety will be assessed. Intervention effects will be calculated by baseline-adjusted analysis of covariance (ANCOVA) using an intention-to-treat approach. Multiple imputation will be applied. Discussion Re.flex can bridge part of the gap between recommendations for strengthening exercises in patients with knee OA and the insufficient actual care situation. This randomized controlled trial is designed to provide conclusions on the effectiveness of the health application re.flex for the population under study and will provide further insight into adherence rates and the safety of its use. Trial registration The trial was registered on 20/01/2023 at www.drks.de (ID: DRKS00030932).","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134947206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation of the six-minute walking distance measured by FeetMe® insoles","authors":"Andrey Mostovov, Damien Jacobs, Leila Farid, Paul Dhellin, Guillaume Baille","doi":"10.1186/s44247-023-00038-9","DOIUrl":"https://doi.org/10.1186/s44247-023-00038-9","url":null,"abstract":"Abstract Background The six-minute walk test (6MWT) is widely used to assess functional capacity in patients with various diseases. Use of wearable devices can make this test more accurate and easier to administer, and may even enhance it by providing additional information. The purpose of this study was to evaluate the validity of FeetMe® insoles for assessing the total six-minute walking distance (6MWD) by comparing the FeetMe® estimates and those obtained by a rater to the ground truth measured with a surveyor’s wheel. Results Data were analyzed from healthy volunteers who performed the 6MWT on 10-m and 30-m tracks while wearing FeetMe® insoles ( n = 32), and being simultaneously assessed by a rater ( n = 33) and followed by an investigator with a surveyor’s wheel. The mean average error (MAE) of the estimates was below 13 m on both tracks for FeetMe®, whereas it ranged from 16.24 m to 38.88 m on the 30-m and 10-m tracks for the rater. Conclusion The FeetMe® insoles provided a more accurate estimate and showed greater agreement with the ground truth than the rater, and the accuracy of the FeetMe® estimates did not vary according to the track length. We conclude that the FeetMe insoles are a valid solution for measuring the 6MWD.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135738747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Description of patient characteristics and medication adherence among medication access mobile application users and nonusers: a single-center questionnaire-based cross-sectional study","authors":"Ghadah Assiri, Dalal Alabdulkarim, Asrar Alanazi, Sarah Altamimi, Nadin Lafi Alanazi, Wael Khawagi","doi":"10.1186/s44247-023-00039-8","DOIUrl":"https://doi.org/10.1186/s44247-023-00039-8","url":null,"abstract":"Abstract Background In this study, we aimed to describe patient characteristics and medication adherence among medication access mobile application users and nonusers. Methods This was a cross-sectional study of a randomly selected sample of patients who refilled their medications either through the mobile application ‘MNG-HA Care’ or by phone call to a government-funded multispecialty hospital in Riyadh, Saudi Arabia. Data were collected through an online survey and filed either via WhatsApp or by phone call. Medication adherence was assessed using the five-item Medication Adherence Report Scale (MARS-5). Results A total of 280 respondents were recruited, and their mean age was 48.8 years (standard deviation (SD): 17.8). More than 75% of application users and nonusers were younger (18–64 years) and lived in urban areas, 58% were male, 37.5% held a bachelor’s degree, and 40% were unemployed. The number of respondents who accessed the mobile application (mobile application users) was 212, and 64.2% of them were adherent to their medications. Sixty-eight of the respondents used a phone call for refills (mobile application nonusers), and 77.9% of them were adherent to their medications. The most common self-reported reasons for using the application were to book an appointment and to request a medication refill. The most common self-reported reasons for not using the application were respondents’ lack of knowledge about the availability of the application and preference for speaking directly to the health care provider. Adjusted multivariate logistic regression analysis revealed that medication adherence was not associated with application use (Odds Ratio (OR): 0.65; 95% CI: 0.33–1.29). However, male patients had significantly higher adherence than females (OR 2.68, 95% CI 1.31 to 5.51), and employed patients had significantly lower adherence than unemployed patients (OR 0.37, 95% CI 0.17 to 0.81). Conclusions Providing patients with access to their medication list through a mobile application alone did not significantly impact medication adherence. Further research is needed to explore the potential benefits of incorporating additional features, such as medication instructions and reminders within mobile applications, to improve medication adherence.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135791439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tuuned in: use of an online contraceptive decision aid for women increases reproductive self-efficacy and knowledge; results of an experimental clinical trial","authors":"Summer Mengelkoch, Matthew Espinosa, Stephen A. Butler, Laura Joigneau Prieto, Emma Russell, Chris Ramshaw, Shardi Nahavandi, Sarah E. Hill","doi":"10.1186/s44247-023-00034-z","DOIUrl":"https://doi.org/10.1186/s44247-023-00034-z","url":null,"abstract":"Abstract Background Digital decision aids are becoming increasingly common in many areas of healthcare. These aids are designed to involve patients in medical decision making, with the aim of improving patient outcomes while decreasing healthcare burden. Previously developed contraceptive-based decision aids have been found to be effective at increasing women’s knowledge about reproductive health and contraception. Here, we sought to evaluate the effectiveness of a novel contraceptive-based decision aid at increasing women’s self-efficacy and knowledge about their reproductive health and contraceptive options, as well as their perceptions of their learning. This study was registered as a clinic trial at ClinicalTrials.gov (Contraception Decision Aid Use and Patient Outcomes, ID# NCT05177783) on 05/01/2022. Methods The Tuune® contraceptive decision aid’s effectiveness was evaluated by conducting an experiment in which 324 women were assigned to use the Tuune® decision aid or a control decision aid. Primary outcomes included reproductive health self-efficacy, reproductive health and contraceptive knowledge, and perceptions of learning. Secondary analyses examined whether prior experience using hormonal contraceptives moderated the relationship between decision aid and each outcome measure. Results Women assigned to use the Tuune® decision aid exhibited greater reproductive health self-efficacy, greater knowledge about reproductive health and contraception, and perceived having learned more than women assigned to use the control decision aid ( p s ≤ .029). This pattern was also observed in women with previous contraceptive use experience, where women using Tuune® reported better outcomes than women using the control aid, regardless of their history of hormonal contraceptive use experience, although this interaction was not significant ( p = .089). Conclusions Use of the Tuune® contraceptive-based decision aid improved each of the predicted outcomes relative to a control decision aid. This suggests that use of the Tuune® contraceptive-based decision aid is well poised to increase women’s confidence and knowledge about contraceptive use and may also reduce burden on healthcare systems.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135110872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Machine learning-based prediction of COVID-19 mortality using immunological and metabolic biomarkers","authors":"Thomas Wetere Tulu, Tsz Kin Wan, Ching Long Chan, Chun Hei Wu, Peter Yat Ming Woo, Cee Zhung Steven Tseng, Asmir Vodencarevic, Cristina Menni, Kei Hang Katie Chan","doi":"10.1186/s44247-023-00045-w","DOIUrl":"https://doi.org/10.1186/s44247-023-00045-w","url":null,"abstract":"","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135878150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discovering social determinants of health from case reports using natural language processing: algorithmic development and validation","authors":"Shaina Raza, Elham Dolatabadi, Nancy Ondrusek, Laura Rosella, Brian Schwartz","doi":"10.1186/s44247-023-00035-y","DOIUrl":"https://doi.org/10.1186/s44247-023-00035-y","url":null,"abstract":"Abstract Background Social determinants of health are non-medical factors that influence health outcomes (SDOH). There is a wealth of SDOH information available in electronic health records, clinical reports, and social media data, usually in free text format. Extracting key information from free text poses a significant challenge and necessitates the use of natural language processing (NLP) techniques to extract key information. Objective The objective of this research is to advance the automatic extraction of SDOH from clinical texts. Setting and data The case reports of COVID-19 patients from the published literature are curated to create a corpus. A portion of the data is annotated by experts to create ground truth labels, and semi-supervised learning method is used for corpus re-annotation. Methods An NLP framework is developed and tested to extract SDOH from the free texts. A two-way evaluation method is used to assess the quantity and quality of the methods. Results The proposed NER implementation achieves an accuracy (F1-score) of 92.98% on our test set and generalizes well on benchmark data. A careful analysis of case examples demonstrates the superiority of the proposed approach in correctly classifying the named entities. Conclusions NLP can be used to extract key information, such as SDOH factors from free texts. A more accurate understanding of SDOH is needed to further improve healthcare outcomes.","PeriodicalId":72426,"journal":{"name":"BMC digital health","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135938654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}