Abdel-Badih Ariss
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
Research Subjects
Research Interests
Abdel-Badih Ariss has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Ahmad Hassan
Department of Emergency Medicine, Massachusetts General Hospital, Boston, USA
1 shared publication - Akshay Swaminathan
Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA, USA
1 shared publication - Alex J. Goodell
Clinical Scholar and Postdoctoral Fellow, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA
1 shared publication - Andrew A. Lee
Department of Anesthesiology, Perioperative, and Pain Medicine, Stanford University School of Medicine, Stanford, CA, USA
1 shared publication - Ben Deverett
Stanford University School of Medicine
1 shared publication - Boyu Peng
Department of Technology, MGH Institute of Health Professions, USA
1 shared publication
Latest Publications
- Top Cited Papers
- 1 January 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (1)
Verifying Facts in Patient Care Documents Generated by Large Language Models Using Electronic Health Records
- 1 January 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (1)
Top Cited PapersVerifying Facts in Patient Care Documents Generated by Large Language Models Using Electronic Health Records
- Open Access
- 16 December 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 9, e70130
Representation of Medical Concepts in Emoji: Cross-Sectional Analysis Using MeSH to Identify Gaps and Opportunities (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Emoji are a universal visual language widely used in digital communication, yet their representation of medical concepts remains limited. The introduction of medical emoji like the anatomical heart and lungs highlights their potential for healthcare communication, but significant gaps persist. Objective: To systematically analyze the representation of medical concepts in emoji by mapping Medical Subject Headings (MeSH) to Unicode emoji, identifying gaps in medical emoji representation, and proposing areas for future emoji development Methods: A cross-sectional study was conducted using the sentence transformer model. Digital resources, including the MeSH thesaurus and Unicode emoji set version 15.0, were utilized. Embeddings for 2,077 MeSH terms and 3,055 emojis were generated, and cosine similarity scores were calculated to evaluate the semantic alignment between MeSH terms and emoji descriptions. A threshold of 0.7 was set to indicate a strong semantic match. Results: The analysis revealed significant variations in emoji representation across medical categories. "Geographicals" had the highest match rate (33.33%), whereas "Anatomy" showed only 7.94% matches, with 13 of 163 terms exceeding the similarity threshold. Categories such as "Disciplines and Occupations," "Information Science," and "Psychiatry and Psychology" had no matches (0%), highlighting notable gaps. The findings underscore substantial disparities in medical emoji representation, particularly for internal organs, mental health, and specialized disciplines. Limited availability of representative emoji may hinder effective healthcare communication, especially in digital health contexts. This study emphasizes the potential of artificial intelligence to design emojis that address these gaps and improve inclusivity. Conclusions: Significant gaps in medical emoji representation across various domains were identified. Future efforts should prioritize underrepresented medical categories and leverage AI-driven approaches for emoji development to enhance healthcare communication and accessibility.
- 16 December 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 9, e70130
Open AccessRepresentation of Medical Concepts in Emoji: Cross-Sectional Analysis Using MeSH to Identify Gaps and Opportunities (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Emoji are a universal visual language widely used in digital communication, yet their representation of medical concepts remains limited. The introduction of medical emoji like the anatomical heart and lungs highlights their potential for healthcare communication, but significant gaps persist. Objective: To systematically analyze the representation of medical concepts in emoji by mapping Medical Subject Headings (MeSH) to Unicode emoji, identifying gaps in medical emoji representation, and proposing areas for future emoji development Methods: A cross-sectional study was conducted using the sentence transformer model. Digital resources, including the MeSH thesaurus and Unicode emoji set version 15.0, were utilized. Embeddings for 2,077 MeSH terms and 3,055 emojis were generated, and cosine similarity scores were calculated to evaluate the semantic alignment between MeSH terms and emoji descriptions. A threshold of 0.7 was set to indicate a strong semantic match. Results: The analysis revealed significant variations in emoji representation across medical categories. "Geographicals" had the highest match rate (33.33%), whereas "Anatomy" showed only 7.94% matches, with 13 of 163 terms exceeding the similarity threshold. Categories such as "Disciplines and Occupations," "Information Science," and "Psychiatry and Psychology" had no matches (0%), highlighting notable gaps. The findings underscore substantial disparities in medical emoji representation, particularly for internal organs, mental health, and specialized disciplines. Limited availability of representative emoji may hinder effective healthcare communication, especially in digital health contexts. This study emphasizes the potential of artificial intelligence to design emojis that address these gaps and improve inclusivity. Conclusions: Significant gaps in medical emoji representation across various domains were identified. Future efforts should prioritize underrepresented medical categories and leverage AI-driven approaches for emoji development to enhance healthcare communication and accessibility.
- Open Access
Paediatric injury in Beirut: a multicentre retrospective chart review study
Objective This study aims to assess the epidemiology of paediatric injury in Beirut, giving insights into their characteristics, contributing risk factors and outcomes. Design and setting A retrospective study was conducted to review medical charts for children aged 0–15 years presented to five hospital emergency departments (ED) located in Beirut over a 1-year period (June 2017–May 2018). Participants A total of 1142 trauma-related visits for children under 15 years of age were included. A descriptive analysis and a bivariate analysis were performed to investigate admitted and treated/discharged patients. Primary outcome A logistic regression was conducted to identify factors associated with hospital admission among injured children. Results A total of 1142 cases of paediatric injury ED cases were sampled, mean age was 7.7±4.35 years. Children aged 0–5 years accounted for more than one-third of the total cases, 40.0% (206/516) of the fall injuries and 60.1% (220/366) of home injuries. The leading cause of paediatric injury was fall (45.2%), nearly 4.1% of the cases were admitted to hospitals. Factors associated with admission included injury to abdomen (OR=8.25 (CI 1.11 to 61.24)), to upper extremity (OR=5.79 (CI 2.04 to 16.49)), to lower extremity (OR=5.55 (95% CI 2.02 to 15.20) and other insurance type (OR=8.33 (CI 2.19 to 31.67)). The three types of injuries mostly associated with hospital admission were fracture (OR=13.55 (CI 4.77 to 38.44)), concussion (OR=13.60 (CI 2.83 to 65.41)) and organ system injury (OR=31.63 (CI 3.45 to 290.11)). Conclusions Injury remains a major health problem among the paediatric population in Lebanon. Parental child safety educational programmes and age-targeted injury prevention strategies should be initiated and implemented to mitigate the burden of child injuries and improve child safety and well-being.
Open AccessPaediatric injury in Beirut: a multicentre retrospective chart review study
Objective This study aims to assess the epidemiology of paediatric injury in Beirut, giving insights into their characteristics, contributing risk factors and outcomes. Design and setting A retrospective study was conducted to review medical charts for children aged 0–15 years presented to five hospital emergency departments (ED) located in Beirut over a 1-year period (June 2017–May 2018). Participants A total of 1142 trauma-related visits for children under 15 years of age were included. A descriptive analysis and a bivariate analysis were performed to investigate admitted and treated/discharged patients. Primary outcome A logistic regression was conducted to identify factors associated with hospital admission among injured children. Results A total of 1142 cases of paediatric injury ED cases were sampled, mean age was 7.7±4.35 years. Children aged 0–5 years accounted for more than one-third of the total cases, 40.0% (206/516) of the fall injuries and 60.1% (220/366) of home injuries. The leading cause of paediatric injury was fall (45.2%), nearly 4.1% of the cases were admitted to hospitals. Factors associated with admission included injury to abdomen (OR=8.25 (CI 1.11 to 61.24)), to upper extremity (OR=5.79 (CI 2.04 to 16.49)), to lower extremity (OR=5.55 (95% CI 2.02 to 15.20) and other insurance type (OR=8.33 (CI 2.19 to 31.67)). The three types of injuries mostly associated with hospital admission were fracture (OR=13.55 (CI 4.77 to 38.44)), concussion (OR=13.60 (CI 2.83 to 65.41)) and organ system injury (OR=31.63 (CI 3.45 to 290.11)). Conclusions Injury remains a major health problem among the paediatric population in Lebanon. Parental child safety educational programmes and age-targeted injury prevention strategies should be initiated and implemented to mitigate the burden of child injuries and improve child safety and well-being.