Ka Hay Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ka Hay Fan has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Dimitri Aristotle Raptis
Organ Transplant Center of Excellence, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia
2 shared publications - Ka Siu Fan
CEDAR Centre, Royal Surrey County Hospital Guildford UK
2 shared publications - Lorenzo Lenti
St George's Vascular Institute, St George's University Hospitals NHS Foundation Trust, London, UK; and St George's University of London, London, UK
2 shared publications - Shahi Ghani
Royal Free London NHS Foundation Trust, London, United Kingdom
2 shared publications - Ka Siu Fan
Department of Nutritional Sciences, University of Surrey, Guildford GU2 7XH, UK
1 shared publication
Latest Publications
- Open Access
Dermatological Knowledge and Image Analysis Performance of Large Language Models Based on Specialty Certificate Examination in Dermatology
Large language models (LLMs) are trained using large datasets and may be applied to language-based tasks. Studies have demonstrated their ability to perform and pass postgraduate medical examinations, and with the increasingly sophisticated deep learning algorithms and incorporation of image-analysis capabilities, they may also be applied to the Specialty Certificate Examination (SCE) in Dermatology. The Dermatology SCE sample questions were used to assess the performance of five freely available and high-performance LLMs. The LLMs’ performances were recorded by comparing their output on multiple-choice questions against the sample answers. One hundred questions, four of which included photographs, were entered into the LLMs. The responses were recorded and analysed, with the pass mark set at 77%. The accuracies for Claude-3.5 Sonnet, Copilot, Gemini, ChatGPT-4o, and Perplexity were 87, 88, 75, 90, and 87, respectively (p = 0.023). The LLMs were generally capable of interpreting and providing reasoned responses to clinical scenarios and clinical data. This continues to demonstrate the potential of LLMs in both medical education and clinical settings.
Open AccessDermatological Knowledge and Image Analysis Performance of Large Language Models Based on Specialty Certificate Examination in Dermatology
Large language models (LLMs) are trained using large datasets and may be applied to language-based tasks. Studies have demonstrated their ability to perform and pass postgraduate medical examinations, and with the increasingly sophisticated deep learning algorithms and incorporation of image-analysis capabilities, they may also be applied to the Specialty Certificate Examination (SCE) in Dermatology. The Dermatology SCE sample questions were used to assess the performance of five freely available and high-performance LLMs. The LLMs’ performances were recorded by comparing their output on multiple-choice questions against the sample answers. One hundred questions, four of which included photographs, were entered into the LLMs. The responses were recorded and analysed, with the pass mark set at 77%. The accuracies for Claude-3.5 Sonnet, Copilot, Gemini, ChatGPT-4o, and Perplexity were 87, 88, 75, 90, and 87, respectively (p = 0.023). The LLMs were generally capable of interpreting and providing reasoned responses to clinical scenarios and clinical data. This continues to demonstrate the potential of LLMs in both medical education and clinical settings.
- Open Access
- 26 March 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (3) , e22618
Using the Ensuring Quality Information for Patients Tool to Assess Patient Information on Appendicitis Websites: Systematic Search and Evaluation
Background: Appendicitis is a common surgical problem among the young adult population, who are likely to use the internet to obtain medical information. This information may determine the health-seeking behavior of an individual and may delay medical attention. Little is known regarding the quality of patient information on appendicitis on the internet, as this has not been previously studied. Objective: The aim of our study was to identify the quality of information regarding appendicitis on websites intended for the public. Methods: We conducted a systematic review of information on appendicitis available online using the following 4 search terms in google: “appendicitis,” “appendix,” “appendectomy,” and “appendicectomy”. The top 100 websites of each search term were assessed using the validated Ensuring Quality Information for Patients (EQIP) tool (score 0-36). Results: A total of 119 websites met the eligibility criteria for evaluation. The overall median EQIP score for all websites was 20 (IQR 18-22). More than half the websites originated from the USA (65/119, 54.6%), and 45.4% (54/119) of all websites originated from hospitals, although 43% (23/54) of these did not mention qualitative risks from surgery. Incidence rates were only provided for complications and mortality in 12.6% (15/119) and 3.3% (4/119) of all websites, respectively. Conclusions: The assessment of the quality and readability of websites concerning appendicitis by the EQIP tool indicates that most sites online were of poor credibility, with minimal information regarding complication rates and mortality. To improve education and awareness of appendicitis, there is an immediate need for more informative and patient-centered websites that are more compatible with international quality standards.
- 26 March 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (3) , e22618
Open AccessUsing the Ensuring Quality Information for Patients Tool to Assess Patient Information on Appendicitis Websites: Systematic Search and Evaluation
Background: Appendicitis is a common surgical problem among the young adult population, who are likely to use the internet to obtain medical information. This information may determine the health-seeking behavior of an individual and may delay medical attention. Little is known regarding the quality of patient information on appendicitis on the internet, as this has not been previously studied. Objective: The aim of our study was to identify the quality of information regarding appendicitis on websites intended for the public. Methods: We conducted a systematic review of information on appendicitis available online using the following 4 search terms in google: “appendicitis,” “appendix,” “appendectomy,” and “appendicectomy”. The top 100 websites of each search term were assessed using the validated Ensuring Quality Information for Patients (EQIP) tool (score 0-36). Results: A total of 119 websites met the eligibility criteria for evaluation. The overall median EQIP score for all websites was 20 (IQR 18-22). More than half the websites originated from the USA (65/119, 54.6%), and 45.4% (54/119) of all websites originated from hospitals, although 43% (23/54) of these did not mention qualitative risks from surgery. Incidence rates were only provided for complications and mortality in 12.6% (15/119) and 3.3% (4/119) of all websites, respectively. Conclusions: The assessment of the quality and readability of websites concerning appendicitis by the EQIP tool indicates that most sites online were of poor credibility, with minimal information regarding complication rates and mortality. To improve education and awareness of appendicitis, there is an immediate need for more informative and patient-centered websites that are more compatible with international quality standards.
- Open Access
- 17 July 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Using the Ensuring Quality Information for Patients Tool to Assess Patient Information on Appendicitis Websites: Systematic Search and Evaluation (Preprint)
BACKGROUND Appendicitis is a common surgical problem among the young adult population, who are likely to use the internet to obtain medical information. This information may determine the health-seeking behavior of an individual and may delay medical attention. Little is known regarding the quality of patient information on appendicitis on the internet, as this has not been previously studied. OBJECTIVE The aim of our study was to identify the quality of information regarding appendicitis on websites intended for the public. METHODS We conducted a systematic review of information on appendicitis available online using the following 4 search terms in google: “appendicitis,” “appendix,” “appendectomy,” and “appendicectomy”. The top 100 websites of each search term were assessed using the validated Ensuring Quality Information for Patients (EQIP) tool (score 0-36). RESULTS A total of 119 websites met the eligibility criteria for evaluation. The overall median EQIP score for all websites was 20 (IQR 18-22). More than half the websites originated from the USA (65/119, 54.6%), and 45.4% (54/119) of all websites originated from hospitals, although 43% (23/54) of these did not mention qualitative risks from surgery. Incidence rates were only provided for complications and mortality in 12.6% (15/119) and 3.3% (4/119) of all websites, respectively. CONCLUSIONS The assessment of the quality and readability of websites concerning appendicitis by the EQIP tool indicates that most sites online were of poor credibility, with minimal information regarding complication rates and mortality. To improve education and awareness of appendicitis, there is an immediate need for more informative and patient-centered websites that are more compatible with international quality standards.
- 17 July 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUsing the Ensuring Quality Information for Patients Tool to Assess Patient Information on Appendicitis Websites: Systematic Search and Evaluation (Preprint)
BACKGROUND Appendicitis is a common surgical problem among the young adult population, who are likely to use the internet to obtain medical information. This information may determine the health-seeking behavior of an individual and may delay medical attention. Little is known regarding the quality of patient information on appendicitis on the internet, as this has not been previously studied. OBJECTIVE The aim of our study was to identify the quality of information regarding appendicitis on websites intended for the public. METHODS We conducted a systematic review of information on appendicitis available online using the following 4 search terms in google: “appendicitis,” “appendix,” “appendectomy,” and “appendicectomy”. The top 100 websites of each search term were assessed using the validated Ensuring Quality Information for Patients (EQIP) tool (score 0-36). RESULTS A total of 119 websites met the eligibility criteria for evaluation. The overall median EQIP score for all websites was 20 (IQR 18-22). More than half the websites originated from the USA (65/119, 54.6%), and 45.4% (54/119) of all websites originated from hospitals, although 43% (23/54) of these did not mention qualitative risks from surgery. Incidence rates were only provided for complications and mortality in 12.6% (15/119) and 3.3% (4/119) of all websites, respectively. CONCLUSIONS The assessment of the quality and readability of websites concerning appendicitis by the EQIP tool indicates that most sites online were of poor credibility, with minimal information regarding complication rates and mortality. To improve education and awareness of appendicitis, there is an immediate need for more informative and patient-centered websites that are more compatible with international quality standards.