Frontiers in digital health最新文献

{"title":"Think FAST: a novel framework to evaluate fidelity, accuracy, safety, and tone in conversational AI health coach dialogues.","authors":"Martha Neary, Emily Fulton, Victoria Rogers, Julia Wilson, Zoe Griffiths, Ram Chuttani, Paul M Sacher","doi":"10.3389/fdgth.2025.1460236","DOIUrl":"10.3389/fdgth.2025.1460236","url":null,"abstract":"<p><p>Developments in Machine Learning based Conversational and Generative Artificial Intelligence (GenAI) have created opportunities for sophisticated Conversational Agents to augment elements of healthcare. While not a replacement for professional care, AI offers opportunities for scalability, cost effectiveness, and automation of many aspects of patient care. However, to realize these opportunities and deliver AI-enabled support safely, interactions between patients and AI must be continuously monitored and evaluated against an agreed upon set of performance criteria. This paper presents one such set of criteria which was developed to evaluate interactions with an AI Health Coach designed to support patients receiving obesity treatment and deployed with an active patient user base. The evaluation framework evolved through an iterative process of development, testing, refining, training, reviewing and supervision. The framework evaluates at both individual message and overall conversation level, rating interactions as Acceptable or Unacceptable in four domains: Fidelity, Accuracy, Safety, and Tone (FAST), with a series of questions to be considered with respect to each domain. Processes to ensure consistent evaluation quality were established and additional patient safety procedures were defined for escalations to healthcare providers based on clinical risk. The framework can be implemented by trained evaluators and offers a method by which healthcare settings deploying AI to support patients can review quality and safety, thus ensuring safe adoption.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1460236"},"PeriodicalIF":3.2,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12216977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144556078","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":"Privacy, ethics, transparency, and accountability in AI systems for wearable devices.","authors":"Petar Radanliev","doi":"10.3389/fdgth.2025.1431246","DOIUrl":"10.3389/fdgth.2025.1431246","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) and machine learning (ML) into wearable sensor technologies has substantially advanced health data science, enabling continuous monitoring, personalised interventions, and predictive analytics. However, the fast advancement of these technologies has raised critical ethical and regulatory concerns, particularly around data privacy, algorithmic bias, informed consent, and the opacity of automated decision-making. This study undertakes a systematic examination of these challenges, highlighting the risks posed by unregulated data aggregation, biased model training, and inadequate transparency in AI-powered health applications. Through an analysis of current privacy frameworks and empirical assessment of publicly available datasets, the study identifies significant disparities in model performance across demographic groups and exposes vulnerabilities in both technical design and ethical governance. To address these issues, this article introduces a data-driven methodological framework that embeds transparency, accountability, and regulatory alignment across all stages of AI development. The framework operationalises ethical principles through concrete mechanisms, including explainable AI, bias mitigation techniques, and consent-aware data processing pipelines, while aligning with legal standards such as the GDPR, the UK Data Protection Act, and the EU AI Act. By incorporating transparency as a structural and procedural requirement, the framework presented in this article offers a replicable model for the responsible development of AI systems in wearable healthcare. In doing so, the study advocates for a regulatory paradigm that balances technological innovation with the protection of individual rights, fostering fair, secure, and trustworthy AI-driven health monitoring.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1431246"},"PeriodicalIF":3.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12209263/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546369","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":"Therapist experiences with implementation of blended (iCBT and face-to-face) treatment of alcohol use disorder (Blend-A): mixed methods study.","authors":"Kristine Tarp, Regina Christiansen, Randi Bilberg, Caroline Dalsgaard, Simone Borkner, Marie Folker, Anette S Nielsen","doi":"10.3389/fdgth.2025.1429582","DOIUrl":"10.3389/fdgth.2025.1429582","url":null,"abstract":"<p><strong>Introduction: </strong>Though therapists' experiences of offering internet-based treatment for alcohol use disorder have been examined in previous studies, the process of implementing blended internet-based and face-to-face treatment has so far not been studied. This study aims to investigate therapist experiences during implementation of blended face-to-face and internet-based treatment for alcohol use disorder.</p><p><strong>Methods: </strong>The study employed a mixed methods design, more specifically a triangulation design with a convergence model. Quantitative data using NoMAD were collected in two waves, involving 48 therapists at the 1st wave and 18 at the 2nd wave. Qualitative interviews were conducted six months after the 2nd wave. Eleven therapists participated in focus group interviews for qualitative data collection, and an additional three semi-structured interviews were recorded, transcribed, and subsequently analyzed using the Normalization Process Theory.</p><p><strong>Results: </strong>We found that the therapists generally had a positive experience with implementing blended face-to-face and internet-based treatment for alcohol use disorder and that their motivation to implement increased. The therapists found it challenging to find coherence between digital and face-to-face treatment in the beginning of the implementation process; however, later in the process, they experienced sense-making. Furthermore, the therapists reflected on their own practice regarding the intervention, both in terms of the amount of time spent on the platform and how it was received by the patients. Moreover, the therapists perceived that if they had all been engaged in the intervention to begin with, it would have led to a shared understanding of the platform and collective ownership. Finally, through each of their individual experiences, the therapists had gained adequate knowledge of the digital intervention; thus, had come to each of their individual perceptions of the best way to incorporate the digital technology in their workday.</p><p><strong>Discussion: </strong>Familiarity and perceived normalcy of using Blend-A did not change significantly over time, but the cognitive attitude to Blend-A did. The therapists were optimistic about the possible use of a blended treatment format, and that this had a positive effect on the implementation process. Over time, the therapists developed confidence in benefits and disadvantages of a blended format.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1429582"},"PeriodicalIF":3.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12209270/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546371","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":"Leveraging AI in digital one health: an inter-university collaboration for emerging and re-emerging infectious disease control in Cameroon.","authors":"Elvis Asangbeng Tanue, Denis L Nkweteyim, Moise Ondua, Ginyu Innocentia Kwalar, Odette Dzemo Kibu, Madeleine L Nyamsi, Peter L Achankeng, Christian Tchapga, Justine Ayuk, Patrick Jolly Ngono Ema, Maurice Marcel Sandeu, Gregory Eddie Halle-Ekane, Jude Dzevela Kong, Dickson Shey Nsagha","doi":"10.3389/fdgth.2025.1507391","DOIUrl":"10.3389/fdgth.2025.1507391","url":null,"abstract":"<p><p>Emerging and re-emerging infectious diseases (ERID) pose ongoing threats to global public health, demanding advanced detection methods for effective outbreak mitigation. This article explores collaboration between research teams based in the faculties of Health Sciences and Science of the University of Buea and the School of Veterinary Medicine and Science of the University of Ngaoundere (DigiCare Cameroon) for integrating artificial intelligence (AI) for early detection and management of ERID through a Digital One Health (DOH) approach. DigiCare is part of an interdisciplinary network called Artificial Intelligence for Pandemic and Epidemic Preparedness and Response Network (AI4PEP) aimed at addressing pandemic and epidemic preparedness and response by strengthening more equitable and effective public health preparedness and response to infectious disease outbreaks in low- and middle-income countries. DigiCare is aimed at improving the health and well-being of the population through sustainable and effective solutions that protect lives and ensure a resilient future leveraging on the power of AI and DOH. DigiCare Cameroon was launched on November 23rd, 2023, at the University of Buea campus during an event graced by numerous high-ranking university and government officials from the public health, environmental, scientific research, and veterinary sectors, alongside representatives from civil society, researchers, students, and community leaders. Baseline data have been collected in communities to provide an evidence-based platform to develop applications that tailor AI towards health care delivery using integrated DOH approaches. This inter-university collaboration will ultimately contribute in strengthening the capacities of health systems to prepare, prevent and mitigate epidemics and pandemics.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1507391"},"PeriodicalIF":3.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12209309/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546368","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 implementation of digital biomarkers in the diagnosis, treatment and monitoring of mood disorders: a narrative review.","authors":"Andrea P Garzón-Partida, Citlali B Padilla-Gómez, Diana Emilia Martínez-Fernández, Joaquín García-Estrada, Sonia Luquin, David Fernández-Quezada","doi":"10.3389/fdgth.2025.1595243","DOIUrl":"10.3389/fdgth.2025.1595243","url":null,"abstract":"<p><p>Mood Disorders are a group of mental health conditions characterized by a disruption of the emotional state that affects the quality of life of the people living with them. Mental Disorders are difficult to diagnose and treat due to the complex processes involved and limitations of the healthcare system. Digital biomarkers have created accessible, long-term, non-invasive, and user-friendly alternatives for the diagnosis, treatment, and monitoring of these conditions. The use of everyday devices like smartphones and smartwatches and specialized tools like actigraphy, in conjunction with powerful statistical tools, artificial intelligence, and machine learning, represents a promising avenue for the implementation of personalized strategies to monitor and treat Mood Disorders, and potentially higher adherence to treatment. We conducted several studies that implement a variety of methodologies and tools to better understand Mood Disorders, using a patient-focused approach with the ultimate goal of identifying better strategies to improve their quality of life.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1595243"},"PeriodicalIF":3.2,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12209236/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546370","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":"Exploring user characteristics, motives, and expectations and the therapeutic alliance in the mental health conversational AI Clare®: a baseline study.","authors":"Lea Maria Schäfer, Tabea Krause, Stephan Köhler","doi":"10.3389/fdgth.2025.1576135","DOIUrl":"10.3389/fdgth.2025.1576135","url":null,"abstract":"<p><p>This study examined the characteristics, motives, expectations, and attitudes of users interested in artificial intelligence (AI) self-help provided by the bot Clare®, a conversational AI for mental health support, and explored the development of a working alliance. A cross-sectional survey of 527 English-speaking self-referred users revealed high levels of anxiety (69%), depression (59%), severe stress (32%), and loneliness (86%). The participants expressed positive attitudes toward digital mental health solutions, with key motives including avoiding embarrassment (36%) and concerns about appearance in face-to-face consultations (35%). Expectations focused on emotional support (35%) and expressing feelings (32%). A strong working alliance was established within 3-5 days (Working Alliance Inventory-Short Report, <i>M</i> = 3.76, SD = .72). These findings highlight the potential of conversational AI in providing accessible and stigma-free support, informing the design of human-centric AI in mental health. Future research should explore long-term user outcomes and clinical large language model integration with traditional mental health services.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1576135"},"PeriodicalIF":3.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12203671/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144531415","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":"Usability testing of EatsUp®: mobile application for monitoring balanced dietary practices and active lifestyle among adolescents-a study in Jakarta, Indonesia.","authors":"Erfi Prafiantini, Rina Agustina, Betty Purwandari, Dian Novita Chandra, Dini Rahma Bintari, Fellatinnisa Zafira Rajwadini, Jihan Farhanah, Aryono Hendarto","doi":"10.3389/fdgth.2025.1506952","DOIUrl":"10.3389/fdgth.2025.1506952","url":null,"abstract":"<p><strong>Background: </strong>Adolescence is a critical period for establishing lifelong health habits, yet many adopt unhealthy behaviors, leading to obesity and other non-communicable diseases. Mobile apps offer a promising platform for delivering health interventions through education. Usability testing is essential to ensure mobile app features align with adolescent preferences and promote sustained behavior change.</p><p><strong>Methods: </strong>We conducted an experimental usability study from June to August 2024 in Jakarta, Indonesia targeting adolescents aged 15-18 who used the EatsUp® mobile application. Participants engaged with the app for seven consecutive days, completing daily tasks and a user experience questionnaire. User experience was assessed across six domains-Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, and Novelty-using a 7-point Likert scale. Descriptive statistics were used to analyze the data, which were compared against established user experience benchmarks.</p><p><strong>Results: </strong>A total of 30 high school students participated (mean ± SD age 16 ± 0.70 years), of whom 23 (76.7%) were female. Most participants (90.0%) used the EatsUp® application for at least seven consecutive days. The app received positive and high user experience ratings across all six parameters, with mean scores exceeding 0.8. Compared to the benchmark data from previous UEQ studies, the app ranked in the \"Excellent\" category (top 10%) for five parameters, while Perspicuity was rated as \"Good\" (top 25%).</p><p><strong>Conclusion: </strong>The <i>EatsUp</i>® app demonstrated strong usability, with an overall positive user experience. It ranked as \"Excellent\" in five user experience parameters except perspicuity, making it well-suited for adolescents. However, perspicuity needs improvement to enhance ease of use. Study limitations include a predominantly female sample from Jakarta-based schools, limiting generalizability. Future studies should include a more diverse population and explore features like gamification to enhance long-term engagement.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1506952"},"PeriodicalIF":3.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12203668/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144531416","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":"An AI-based module for interstitial glucose forecasting enabling a \"Do-It-Yourself\" application for people with type 1 diabetes.","authors":"Antonio J Rodriguez-Almeida, Guillermo V Socorro-Marrero, Carmelo Betancort, Garlene Zamora-Zamorano, Alejandro Deniz-Garcia, María L Álvarez-Malé, Eirik Årsand, Cristina Soguero-Ruiz, Ana M Wägner, Conceição Granja, Gustavo M Callico, Himar Fabelo","doi":"10.3389/fdgth.2025.1534830","DOIUrl":"10.3389/fdgth.2025.1534830","url":null,"abstract":"<p><strong>Introduction: </strong>Diabetes mellitus (DM) is a chronic condition defined by increased blood glucose that affects more than 500 million adults. Type 1 diabetes (T1D) needs to be treated with insulin. Keeping glucose within the desired range is challenging. Despite the advances in the mHealth field, the appearance of the do-it-yourself (DIY) tools, and the progress in glucose level prediction based on deep learning (DL), these tools fail to engage the users in the long-term. This limits the benefits that they could have on the daily T1D self-management, specifically by providing an accurate prediction of their short-term glucose level.</p><p><strong>Methods: </strong>This work proposed a DL-based DIY framework for interstitial glucose prediction using continuous glucose monitoring (CGM) data to generate one personalized DL model per user, without using data from other people. The DIY module reads the CGM raw data (as it would be uploaded by the potential users of this tool), and automatically prepares them to train and validate a DL model to perform glucose predictions up to one hour ahead. For training and validation, 1 year of CGM data collected from 29 subjects with T1D were used.</p><p><strong>Results and discussion: </strong>Results showed prediction performance comparable to the state-of-the-art, using only CGM data. To the best of our knowledge, this work is the first one in providing a DL-based DIY approach for fully personalized glucose prediction. Moreover, this framework is open source and has been deployed in Docker, enabling its standalone use, its integration on a smartphone application, or the experimentation with novel DL architectures.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1534830"},"PeriodicalIF":3.2,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12202434/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144531414","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":"AI-generated draft replies to patient messages: exploring effects of implementation.","authors":"Charlotte M H H T Bootsma-Robroeks, Jessica D Workum, Stephanie C E Schuit, Anne Hoekman, Tarannom Mehri, Job N Doornberg, Tom P van der Laan, Rosanne C Schoonbeek","doi":"10.3389/fdgth.2025.1588143","DOIUrl":"10.3389/fdgth.2025.1588143","url":null,"abstract":"<p><strong>Introduction: </strong>The integration of Large Language Models (LLMs) in Electronic Health Records (EHRs) has the potential to reduce administrative burden. Validating these tools in real-world clinical settings is essential for responsible implementation. In this study, the effect of implementing LLM-generated draft responses to patient questions in our EHR is evaluated with regard to adoption, use and potential time savings.</p><p><strong>Material and methods: </strong>Physicians across 14 medical specialties in a non-English large academic hospital were invited to use LLM-generated draft replies during this prospective observational clinical cohort study of 16 weeks, choosing either the drafted or a blank reply. The adoption rate, the level of adjustments to the initial drafted responses compared to the final sent messages (using ROUGE-1 and BLEU-1 natural language processing scores), and the time spent on these adjustments were analyzed.</p><p><strong>Results: </strong>A total of 919 messages by 100 physicians were evaluated. Clinicians used the LLM draft in 58% of replies. Of these, 43% used a large part of the suggested text for the final answer (≥10% match drafted responses: ROUGE-1: 86% similarity, vs. blank replies: ROUGE-1: 16%). Total response time did not significantly different when using a blank reply compared to using a drafted reply with ≥10% match (157 vs. 153 s, <i>p</i> = 0.69).</p><p><strong>Discussion: </strong>General adoption of LLM-generated draft responses to patient messages was 58%, although the level of adjustments on the drafted message varied widely between medical specialties. This implicates safe use in a non-English, tertiary setting. The current implementation has not yet resulted in time savings, but a learning curve can be expected.</p><p><strong>Registration number: </strong>19035.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1588143"},"PeriodicalIF":3.2,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12198195/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144509837","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":"Horizontal federated learning and assessment of Cox models.","authors":"Frank Westers, Sam Leder, Lucia Tealdi","doi":"10.3389/fdgth.2025.1603630","DOIUrl":"10.3389/fdgth.2025.1603630","url":null,"abstract":"<p><p>The Cox Proportional Hazards model is a widely used method for survival analysis in medical research. However, training an accurate model requires access to a sufficiently large dataset, which is often challenging due to data fragmentation. A potential solution is to combine data from multiple medical institutions, but privacy constraints typically prevent direct data sharing. Federated learning offers a privacy-preserving alternative by allowing multiple parties to collaboratively train a model without exchanging raw data. In this work, we develop algorithms for training Cox models in a federated setting, leveraging survival stacking to facilitate distributed learning. In addition, we introduce a novel secure computation of Schoenfeld residuals, a key diagnostic tool for validating the Cox model. We provide an open-source implementation of our approach and present empirical results that demonstrate the accuracy and benefits of federated Cox regression.</p>","PeriodicalId":73078,"journal":{"name":"Frontiers in digital health","volume":"7 ","pages":"1603630"},"PeriodicalIF":3.2,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12198214/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144509838","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}