Lu He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lu He has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Bo Li
The Hong Kong University of Science and Technology
4 shared publications - Changyang He
School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen (HITSZ)
4 shared publications - Kai Zheng
Department of Informatics, University of California, Irvine, Irvine, CA, USA
3 shared publications - Zhicong Lu
Department of Computer Science, George Mason University, Fairfax, Virginia, USA
3 shared publications Tingjue Yin
Department of Informatics, Donald Bren School of Information and Computer Science, University of California, Irvine, Irvine, CA, United States
2 shared publications- AkkeNeel Talsma
School of Nursing, University of Wisconsin-Milwaukee, Milwaukee, WI, United States
1 shared publication
Latest Publications
- 13 June 2026
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 33 (9) , 1822-1833
Large language model biases in health care: a scoping review and call for an integrated assessment framework
Objectives: To conduct a scoping review of bias assessment in studies applying large language models (LLMs) to health data and to synthesize their prevailing conceptualization of bias. Materials and Methods: Following PRISMA guidelines, we queried PubMed and Scopus. Two annotators screened titles, abstracts, and full texts for eligibility, calibrating their assessments throughout the process. For included studies, we extracted and summarized data on LLMs (name and version, development domain, open- or closed-sourced status, and commercial or academic origin), natural language processing tasks (task formulation, gold-standard dataset, evaluation metrics, prompting or fine-tuning strategies), and biases (type, assessment, and bias summary). Results: Of the 1585 records retrieved, 76 papers met the eligibility criteria for full review. Among these, 59 reported identifying bias. Three major conceptualizations of bias emerged: behavioral output bias (nonstereotyping and stereotyping), predictive outcome bias, and representational bias. Studies generally adopted an observational approach (measuring bias using the existing dataset) or an experimental approach (altering prompts, eg, with different demographic information, and comparing outputs). Discussion and Conclusion: Behavioral output bias and predictive outcome bias, both of which emphasize parity, dominate existing studies. Whether evaluated against external accuracy or internal equality benchmarks, these approaches often assume that equal performance across groups is inherently desirable. Treating all disparities as bias risks conflating poor model behavior with real-world disparities, and researchers should remain aware of potential tradeoffs between parity and accuracy objectives. We introduce an integrated framework that combines parity and accuracy benchmarks and encourages transparent, context-aware interpretation of group differences.
- 13 June 2026
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 33 (9) , 1822-1833
Large language model biases in health care: a scoping review and call for an integrated assessment framework
Objectives: To conduct a scoping review of bias assessment in studies applying large language models (LLMs) to health data and to synthesize their prevailing conceptualization of bias. Materials and Methods: Following PRISMA guidelines, we queried PubMed and Scopus. Two annotators screened titles, abstracts, and full texts for eligibility, calibrating their assessments throughout the process. For included studies, we extracted and summarized data on LLMs (name and version, development domain, open- or closed-sourced status, and commercial or academic origin), natural language processing tasks (task formulation, gold-standard dataset, evaluation metrics, prompting or fine-tuning strategies), and biases (type, assessment, and bias summary). Results: Of the 1585 records retrieved, 76 papers met the eligibility criteria for full review. Among these, 59 reported identifying bias. Three major conceptualizations of bias emerged: behavioral output bias (nonstereotyping and stereotyping), predictive outcome bias, and representational bias. Studies generally adopted an observational approach (measuring bias using the existing dataset) or an experimental approach (altering prompts, eg, with different demographic information, and comparing outputs). Discussion and Conclusion: Behavioral output bias and predictive outcome bias, both of which emphasize parity, dominate existing studies. Whether evaluated against external accuracy or internal equality benchmarks, these approaches often assume that equal performance across groups is inherently desirable. Treating all disparities as bias risks conflating poor model behavior with real-world disparities, and researchers should remain aware of potential tradeoffs between parity and accuracy objectives. We introduce an integrated framework that combines parity and accuracy benchmarks and encourages transparent, context-aware interpretation of group differences.
- Open Access
- 16 October 2025
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 13, e63908
Clinical Information Extraction From Notes of Veterans With Lymphoid Malignancies: Natural Language Processing Study
Background: Clinical natural language processing (cNLP) techniques are commonly developed and used to extract information from clinical notes to facilitate clinical decision-making and research. However, they are less established for rare diseases such as lymphoid malignancies due to the lack of annotated data as well as the heterogeneity and complexity of how clinical information is documented. In addition, there is increasing evidence that cNLP techniques may be prone to biases embedded in clinical documentation or model development. These biases can result in disparities in performance when extracting clinical information or predicting patient outcomes. Objective: This study aims to report the development and validation of a cNLP pipeline that extracts clinical information such as performance status, staging, and diagnosis, as well as less common information such as substance use and military environmental exposures, from the clinical notes of veterans with lymphoid malignancies. Methods: We developed a rule-based cNLP pipeline that integrates domain expertise. We tested and compared the performance of the cNLP pipeline on notes from 2 veteran patient cohorts: one from non-Hispanic White veterans and the other from non-Hispanic Black veterans. Results: Overall, our pipeline achieved promising performance on our study data, especially for extracting entities that have standard clinical documentation, such as performance status. We also found that while the pipeline has robust performance across the two patient groups, the false-positive and false-negative rates were significantly associated with race for detecting the primary diagnosis (P=.001 for both); the false-negative rate was significantly associated with race for identifying substance use (P=.02). Conclusions: The system exhibits satisfying and comparable performance for most clinical entities of interest except for (1) the primary diagnosis and (2) substance use. Future work will address the challenges encountered in developing and deploying the cNLP pipeline on the Department of Veterans Affairs data for rare cancers and enhance the performance of cNLP systems to avoid biases.
- 16 October 2025
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 13, e63908
Open AccessClinical Information Extraction From Notes of Veterans With Lymphoid Malignancies: Natural Language Processing Study
Background: Clinical natural language processing (cNLP) techniques are commonly developed and used to extract information from clinical notes to facilitate clinical decision-making and research. However, they are less established for rare diseases such as lymphoid malignancies due to the lack of annotated data as well as the heterogeneity and complexity of how clinical information is documented. In addition, there is increasing evidence that cNLP techniques may be prone to biases embedded in clinical documentation or model development. These biases can result in disparities in performance when extracting clinical information or predicting patient outcomes. Objective: This study aims to report the development and validation of a cNLP pipeline that extracts clinical information such as performance status, staging, and diagnosis, as well as less common information such as substance use and military environmental exposures, from the clinical notes of veterans with lymphoid malignancies. Methods: We developed a rule-based cNLP pipeline that integrates domain expertise. We tested and compared the performance of the cNLP pipeline on notes from 2 veteran patient cohorts: one from non-Hispanic White veterans and the other from non-Hispanic Black veterans. Results: Overall, our pipeline achieved promising performance on our study data, especially for extracting entities that have standard clinical documentation, such as performance status. We also found that while the pipeline has robust performance across the two patient groups, the false-positive and false-negative rates were significantly associated with race for detecting the primary diagnosis (P=.001 for both); the false-negative rate was significantly associated with race for identifying substance use (P=.02). Conclusions: The system exhibits satisfying and comparable performance for most clinical entities of interest except for (1) the primary diagnosis and (2) substance use. Future work will address the challenges encountered in developing and deploying the cNLP pipeline on the Department of Veterans Affairs data for rare cancers and enhance the performance of cNLP systems to avoid biases.
- Open Access
- 4 July 2025
- Published by JMIR Publications Inc. in JMIR Nursing
- Vol. 8 (1) , e73672
Using Large Language Models to Assess Burnout Among Health Care Workers in the Context of COVID-19 Vaccine Decisions and Health Beliefs: Retrospective Cohort Study
Background: Burnout among health care workers affects their well-being and decision-making, influencing patient and public health outcomes. Health care workers’ health beliefs and COVID-19 vaccine decisions may affect the risks of burnout. Therefore, understanding the interplay between these crucial factors is essential for identifying at-risk staff, providing targeted support, and addressing workplace challenges to prevent further escalation of burnout-related issues. Objective: This study examines how burnout is impacted by health beliefs and COVID-19 vaccine decisions among health care workers. Building on our previously developed Health Belief Model (HBM) classifier based on the HBM framework, which explains how individual perceptions of health risks and benefits influence behavior, we focused on key HBM constructs, including the perceived severity of COVID-19, perceived barriers to vaccination, and their relationship to burnout. We aim to leverage natural language processing techniques to automatically identify theoretically grounded burnout symptoms from comments authored by nurses in a large-scale, national survey and assess their associations with vaccine hesitancy and health beliefs. Methods: We analyzed 1944 open-ended comments written by 1501 vaccine-hesitant nurses, using data from the Nurses’ Health Study surveys. We fine-tuned LLaMA 3, an open-source large language model with few-shot prompts and enhanced performance with structured annotation guidance and reasoning-aware inference. Comments were classified into burnout dimensions—Emotional Exhaustion, Depersonalization, and Inefficacy—based on the Maslach Burnout Inventory framework. Results: The model achieved a high weighted accuracy of 92% and an F1-score of 91% for Depersonalization. Emotional Exhaustion was identified in 52% (1003/1944) of comments, correlating strongly with perceived severity (189/323, 59%) and barriers to vaccination (281/650, 43%). Demographic analyses revealed significant variations in burnout prevalence, with older age groups reporting greater burnout. Conclusions: This study highlights the relationship between burnout and vaccine decision-making among health care workers, uncovering areas for further exploration. By exploring the complex interplay between psychological strain and vaccine hesitancy, this study sets the stage for developing transformative interventions and policies that could redefine workforce resilience and public health strategies.
- 4 July 2025
- Published by JMIR Publications Inc. in JMIR Nursing
- Vol. 8 (1) , e73672
Open AccessUsing Large Language Models to Assess Burnout Among Health Care Workers in the Context of COVID-19 Vaccine Decisions and Health Beliefs: Retrospective Cohort Study
Background: Burnout among health care workers affects their well-being and decision-making, influencing patient and public health outcomes. Health care workers’ health beliefs and COVID-19 vaccine decisions may affect the risks of burnout. Therefore, understanding the interplay between these crucial factors is essential for identifying at-risk staff, providing targeted support, and addressing workplace challenges to prevent further escalation of burnout-related issues. Objective: This study examines how burnout is impacted by health beliefs and COVID-19 vaccine decisions among health care workers. Building on our previously developed Health Belief Model (HBM) classifier based on the HBM framework, which explains how individual perceptions of health risks and benefits influence behavior, we focused on key HBM constructs, including the perceived severity of COVID-19, perceived barriers to vaccination, and their relationship to burnout. We aim to leverage natural language processing techniques to automatically identify theoretically grounded burnout symptoms from comments authored by nurses in a large-scale, national survey and assess their associations with vaccine hesitancy and health beliefs. Methods: We analyzed 1944 open-ended comments written by 1501 vaccine-hesitant nurses, using data from the Nurses’ Health Study surveys. We fine-tuned LLaMA 3, an open-source large language model with few-shot prompts and enhanced performance with structured annotation guidance and reasoning-aware inference. Comments were classified into burnout dimensions—Emotional Exhaustion, Depersonalization, and Inefficacy—based on the Maslach Burnout Inventory framework. Results: The model achieved a high weighted accuracy of 92% and an F1-score of 91% for Depersonalization. Emotional Exhaustion was identified in 52% (1003/1944) of comments, correlating strongly with perceived severity (189/323, 59%) and barriers to vaccination (281/650, 43%). Demographic analyses revealed significant variations in burnout prevalence, with older age groups reporting greater burnout. Conclusions: This study highlights the relationship between burnout and vaccine decision-making among health care workers, uncovering areas for further exploration. By exploring the complex interplay between psychological strain and vaccine hesitancy, this study sets the stage for developing transformative interventions and policies that could redefine workforce resilience and public health strategies.
- Open Access
- 17 April 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW1) , 1-32
Images Connect Us Together: Navigating a COVID-19 Local Outbreak in China Through Social Media Images
Social media images, curated or casual, have become a crucial component of communicating situational information and emotions during health crises. Despite its prevalence and significance in informational dissemination and emotional connection, there lacks a comprehensive understanding of visual crisis communication in the aftermath of a pandemic which is characterized by uncertain local situations and emotional fatigue. To fill this gap, this work collected 345,423 crisis-related posts and 65,376 original images during the Xi'an COVID-19 local outbreak in China, and adopted a mixed-methods approach to understanding themes, goals, and strategies of crisis imagery. Image clustering captured the diversity of visual themes during the outbreak, such as text images embedding authoritative guidelines and "visual diaries" recording and sharing the quarantine life. Through text classification of the post that visuals were situated in, we found that different visual themes highly correlated with the informational and emotional goals of the post text, such as adopting text images to convey the latest policies and sharing food images to express anxiety. We further unpacked nuanced strategies of crisis image use through inductive coding, such as signifying authority and triggering empathy. We discuss the opportunities and challenges of crisis imagery and provide design implications to facilitate effective visual crisis communication.
- 17 April 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW1) , 1-32
Open AccessImages Connect Us Together: Navigating a COVID-19 Local Outbreak in China Through Social Media Images
Social media images, curated or casual, have become a crucial component of communicating situational information and emotions during health crises. Despite its prevalence and significance in informational dissemination and emotional connection, there lacks a comprehensive understanding of visual crisis communication in the aftermath of a pandemic which is characterized by uncertain local situations and emotional fatigue. To fill this gap, this work collected 345,423 crisis-related posts and 65,376 original images during the Xi'an COVID-19 local outbreak in China, and adopted a mixed-methods approach to understanding themes, goals, and strategies of crisis imagery. Image clustering captured the diversity of visual themes during the outbreak, such as text images embedding authoritative guidelines and "visual diaries" recording and sharing the quarantine life. Through text classification of the post that visuals were situated in, we found that different visual themes highly correlated with the informational and emotional goals of the post text, such as adopting text images to convey the latest policies and sharing food images to express anxiety. We further unpacked nuanced strategies of crisis image use through inductive coding, such as signifying authority and triggering empathy. We discuss the opportunities and challenges of crisis imagery and provide design implications to facilitate effective visual crisis communication.
- Open Access
- 17 April 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW1) , 1-31
Engage Wider Audience or Facilitate Quality Answers? a Mixed-methods Analysis of Questioning Strategies for Research Sensemaking on a Community Q&A Site
Discussing research-sensemaking questions on Community Question and Answering (CQA) platforms has been an increasingly common practice for the public to participate in science communication. Nonetheless, how users strategically craft research-sensemaking questions to engage public participation and facilitate knowledge construction is a significant yet less understood problem. To fill this gap, we collected 837 science-related questions and 157,684 answers from Zhihu, and conducted a mixed-methods study to explore user-developed strategies in proposing research-sensemaking questions, and their potential effects on public engagement and knowledge construction. Through open coding, we captured a comprehensive taxonomy of question-crafting strategies, such as eyecatching narratives with counter-intuitive claims and rigorous descriptions with data use. Regression analysis indicated that these strategies correlated with user engagement and answer construction in different ways (e.g., emotional questions attracted more views and answers), yet there existed a general divergence between wide participation and quality knowledge establishment, when most questioning strategies could not ensure both. Based on log analysis, we further found that collaborative editing afforded unique values in refining research-sensemaking questions regarding accuracy, rigor, comprehensiveness and attractiveness. We propose design implications to facilitate accessible, accurate and engaging science communication on CQA platforms.
- 17 April 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW1) , 1-31
Open AccessEngage Wider Audience or Facilitate Quality Answers? a Mixed-methods Analysis of Questioning Strategies for Research Sensemaking on a Community Q&A Site
Discussing research-sensemaking questions on Community Question and Answering (CQA) platforms has been an increasingly common practice for the public to participate in science communication. Nonetheless, how users strategically craft research-sensemaking questions to engage public participation and facilitate knowledge construction is a significant yet less understood problem. To fill this gap, we collected 837 science-related questions and 157,684 answers from Zhihu, and conducted a mixed-methods study to explore user-developed strategies in proposing research-sensemaking questions, and their potential effects on public engagement and knowledge construction. Through open coding, we captured a comprehensive taxonomy of question-crafting strategies, such as eyecatching narratives with counter-intuitive claims and rigorous descriptions with data use. Regression analysis indicated that these strategies correlated with user engagement and answer construction in different ways (e.g., emotional questions attracted more views and answers), yet there existed a general divergence between wide participation and quality knowledge establishment, when most questioning strategies could not ensure both. Based on log analysis, we further found that collaborative editing afforded unique values in refining research-sensemaking questions regarding accuracy, rigor, comprehensiveness and attractiveness. We propose design implications to facilitate accessible, accurate and engaging science communication on CQA platforms.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Seeking Love and Companionship through Streaming: Unpacking Livestreamer-moderated Senior Matchmaking in China
Livestreamer-moderated matchmaking has gained wide popularity among the elderly population in China. Compared to algorithm-mediated online dating, it is characterized by (1) the mediation of matchmakers in a synchronous virtual environment and (2) the natural development of livestreaming-based matchmaking communities. Nonetheless, how these new features influence single seniors’ match-seeking remains unknown. To fill this research gap, we conduct a qualitative study consisting of observations and semi-structured interviews with 6 livestreaming matchmakers and 12 senior match-seekers (age: 50-70). We uncover matchmakers’ mediation roles during and beyond livestreaming to facilitate seniors’ match-seeking, and their additional duties to enhance seniors’ safety in this process. Livestreaming-based matchmaking communities afford multiple important values for single seniors to acquire companionship and help in seeking late-life love. We unpack the perceived benefits and challenges of livestreamer-moderated matchmaking, and discuss how to support single seniors’ match-seeking in an accessible, safe, and convenient manner.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessSeeking Love and Companionship through Streaming: Unpacking Livestreamer-moderated Senior Matchmaking in China
Livestreamer-moderated matchmaking has gained wide popularity among the elderly population in China. Compared to algorithm-mediated online dating, it is characterized by (1) the mediation of matchmakers in a synchronous virtual environment and (2) the natural development of livestreaming-based matchmaking communities. Nonetheless, how these new features influence single seniors’ match-seeking remains unknown. To fill this research gap, we conduct a qualitative study consisting of observations and semi-structured interviews with 6 livestreaming matchmakers and 12 senior match-seekers (age: 50-70). We uncover matchmakers’ mediation roles during and beyond livestreaming to facilitate seniors’ match-seeking, and their additional duties to enhance seniors’ safety in this process. Livestreaming-based matchmaking communities afford multiple important values for single seniors to acquire companionship and help in seeking late-life love. We unpack the perceived benefits and challenges of livestreamer-moderated matchmaking, and discuss how to support single seniors’ match-seeking in an accessible, safe, and convenient manner.
- Open Access
- 14 April 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW1) , 1-28
"I Have to Use My Son's QR Code to Run the Business": Unpacking Senior Street Vendors' Challenges in Mobile Money Collection in China
Mobile payment systems have become an infrastructural component in citizens' socio-economic life in China. The rapid shift to a cashless society demands vendors of all ages to quickly adapt themselves to the ubiquitous mobile payment era. However, how this trend may impact senior vendors, a group that typically uses less technology, remains unknown despite its significance in inclusive mobile payment design. This work aims to address this gap by investigating the challenges and strategies of senior vendors in mobile payment adoption. Particularly, we focus on a traditional low-resource setting with a large volume of senior vendors: street vending. We conduct a qualitative study incorporating field observations on 33 senior street vendors and semi-structured interviews with 15 of them (aged 53-78), and take Moneywork as an analytical lens to unpack their challenges in physical and social interactions. We find that senior street vendors are a group passively adopting mobile payments due to business requirements instead of recognizing their advantages. Vendors with relatively low digital literacy have to take an alternative method - using family members' QR codes - to run the business as family-dependent money receivers. With limited considerations for senior vendors' situational vulnerabilities, unexpected difficulties of payment confirmation emerge during transactions, such as reduced confirmation efficacy under noisy surroundings and degraded hearing. Transaction security issues also appear when mobile payment-based frauds target both confirmation interfaces (e.g., fake sounds of successful payment) and trust systems (e.g., showing half-done proof to flee without paying) in street vending. Finally, we raise a less visible yet critical concern of family-dependent vendors on the lost money freedom when their income flows into their families' wallets. We propose design implications for mobile payment systems to support more secure, efficient and accessible money collection services to underrepresented groups.
- 14 April 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW1) , 1-28
Open Access"I Have to Use My Son's QR Code to Run the Business": Unpacking Senior Street Vendors' Challenges in Mobile Money Collection in China
Mobile payment systems have become an infrastructural component in citizens' socio-economic life in China. The rapid shift to a cashless society demands vendors of all ages to quickly adapt themselves to the ubiquitous mobile payment era. However, how this trend may impact senior vendors, a group that typically uses less technology, remains unknown despite its significance in inclusive mobile payment design. This work aims to address this gap by investigating the challenges and strategies of senior vendors in mobile payment adoption. Particularly, we focus on a traditional low-resource setting with a large volume of senior vendors: street vending. We conduct a qualitative study incorporating field observations on 33 senior street vendors and semi-structured interviews with 15 of them (aged 53-78), and take Moneywork as an analytical lens to unpack their challenges in physical and social interactions. We find that senior street vendors are a group passively adopting mobile payments due to business requirements instead of recognizing their advantages. Vendors with relatively low digital literacy have to take an alternative method - using family members' QR codes - to run the business as family-dependent money receivers. With limited considerations for senior vendors' situational vulnerabilities, unexpected difficulties of payment confirmation emerge during transactions, such as reduced confirmation efficacy under noisy surroundings and degraded hearing. Transaction security issues also appear when mobile payment-based frauds target both confirmation interfaces (e.g., fake sounds of successful payment) and trust systems (e.g., showing half-done proof to flee without paying) in street vending. Finally, we raise a less visible yet critical concern of family-dependent vendors on the lost money freedom when their income flows into their families' wallets. We propose design implications for mobile payment systems to support more secure, efficient and accessible money collection services to underrepresented groups.
- Open Access
- 28 October 2022
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 13, 1003514
Clinical application of multicolor imaging in Leber hereditary optic neuropathy
Purpose: To characterize features of retinal never fiber in Leber Hereditary Optic Neuropathy (LHON) using multicolor (MC) imaging and color fundus photography (CFP).Methods: Ninety-two eyes of patients with LHON underwent MC imaging, optic disc spectral domain optical coherence tomography (SD-OCT), and CFP. Two independent observers graded RNFL visibility scores and two other experts determined never fiber bundle defects from four-quadrant readings. CFP, standard MC, infrared reflectance (IR), green reflectance (GR), blue reflectance (BR), and green-blue-enhanced (BG) imaging were compared.Results: Agreement on never fiber bundle defects was substantial for CFP, standard MC, GR, BR, and BG images relative to IR. It was shown that BR (2.71 ± 0.55) had the best mean RNFL visibility score, BG (2.69 ± 0.52), GR (2.69 ± 0.56), standard MC (2.04 ± 0.79), CFP (1.80 ± 0.82), and IR (0.45 ± 0.59) followed. Agreement on temporal area defects was relatively improved. Youden's indices for CFP (78.21%), standard MC (84.48%), GR (90.92%), BR (89.64%), and BG (90.99%) indicated good detection of defects in the papillomacular bundle (PMB)/ high suspicion of patients with LHON, particularly for BG and GR. According to the proportion of never fiber bundle defects, standard MC, GR, BR, and BG can roughly determine the LHON clinical stage, especially in subacute and chronic stages, and standard MC is superior for patients with LHON of all stages. The stage judged by MC was consistent with the course inferred by pRNFL thickness.Conclusion: As an adjunct to SD-OCT, the MC image, particularly the GR and BG can delineate RNFL more effectively than CFP. The MC image may be a useful adjunct to OCT for detecting or monitoring never fiber bundle defects, providing inexpensive and rapid methods that can quickly identify patients with high suspicion of LHON.
- 28 October 2022
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 13, 1003514
Open AccessClinical application of multicolor imaging in Leber hereditary optic neuropathy
Purpose: To characterize features of retinal never fiber in Leber Hereditary Optic Neuropathy (LHON) using multicolor (MC) imaging and color fundus photography (CFP).Methods: Ninety-two eyes of patients with LHON underwent MC imaging, optic disc spectral domain optical coherence tomography (SD-OCT), and CFP. Two independent observers graded RNFL visibility scores and two other experts determined never fiber bundle defects from four-quadrant readings. CFP, standard MC, infrared reflectance (IR), green reflectance (GR), blue reflectance (BR), and green-blue-enhanced (BG) imaging were compared.Results: Agreement on never fiber bundle defects was substantial for CFP, standard MC, GR, BR, and BG images relative to IR. It was shown that BR (2.71 ± 0.55) had the best mean RNFL visibility score, BG (2.69 ± 0.52), GR (2.69 ± 0.56), standard MC (2.04 ± 0.79), CFP (1.80 ± 0.82), and IR (0.45 ± 0.59) followed. Agreement on temporal area defects was relatively improved. Youden's indices for CFP (78.21%), standard MC (84.48%), GR (90.92%), BR (89.64%), and BG (90.99%) indicated good detection of defects in the papillomacular bundle (PMB)/ high suspicion of patients with LHON, particularly for BG and GR. According to the proportion of never fiber bundle defects, standard MC, GR, BR, and BG can roughly determine the LHON clinical stage, especially in subacute and chronic stages, and standard MC is superior for patients with LHON of all stages. The stage judged by MC was consistent with the course inferred by pRNFL thickness.Conclusion: As an adjunct to SD-OCT, the MC image, particularly the GR and BG can delineate RNFL more effectively than CFP. The MC image may be a useful adjunct to OCT for detecting or monitoring never fiber bundle defects, providing inexpensive and rapid methods that can quickly identify patients with high suspicion of LHON.
- Open Access
- 12 October 2022
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 5 (4) , ooac077
Clinical, technical, and implementation characteristics of real-world health applications using FHIR
The Fast Healthcare Interoperability Resources (FHIR) standard is increasingly being adopted for healthcare data exchange in the United States and globally, but an overall picture of the applications (apps) that implement the standard is not well known. This study aimed to provide a preliminary assessment of real-world FHIR apps’ clinical, technical, and implementation characteristics. To achieve this aim, we (1) searched digital repositories and libraries containing FHIR apps, (2) extracted the app name, source, and developer contact information, and (3) collected information about the apps via an electronic survey of FHIR app developers and implementers. Respondents reported a variety of health domains, terminologies, FHIR specifications, and types of developing organizations for the 112 apps about which we received information. Apps were increasingly introduced from 2012 to 2022, and most focused on clinical care (n = 74) or research (n = 45). The majority were stand-alone web-based (n = 67) or embedded within an electronic health record (n = 51). Of the many health domains covered, cardiovascular care was the most common (n = 28). Half (n = 56) were implemented across multiple health settings, highlighting FHIR’s substitutable nature. Overall, this study demonstrates the momentum around FHIR, the diversity of FHIR apps, and the need for a robust global FHIR app repository.
- 12 October 2022
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 5 (4) , ooac077
Open AccessClinical, technical, and implementation characteristics of real-world health applications using FHIR
The Fast Healthcare Interoperability Resources (FHIR) standard is increasingly being adopted for healthcare data exchange in the United States and globally, but an overall picture of the applications (apps) that implement the standard is not well known. This study aimed to provide a preliminary assessment of real-world FHIR apps’ clinical, technical, and implementation characteristics. To achieve this aim, we (1) searched digital repositories and libraries containing FHIR apps, (2) extracted the app name, source, and developer contact information, and (3) collected information about the apps via an electronic survey of FHIR app developers and implementers. Respondents reported a variety of health domains, terminologies, FHIR specifications, and types of developing organizations for the 112 apps about which we received information. Apps were increasingly introduced from 2012 to 2022, and most focused on clinical care (n = 74) or research (n = 45). The majority were stand-alone web-based (n = 67) or embedded within an electronic health record (n = 51). Of the many health domains covered, cardiovascular care was the most common (n = 28). Half (n = 56) were implemented across multiple health settings, highlighting FHIR’s substitutable nature. Overall, this study demonstrates the momentum around FHIR, the diversity of FHIR apps, and the need for a robust global FHIR app repository.
- 11 July 2022
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 132, 104142
They May Not Work! An evaluation of eleven sentiment analysis tools on seven social media datasets
- 11 July 2022
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 132, 104142
They May Not Work! An evaluation of eleven sentiment analysis tools on seven social media datasets