Yu Bin Tan
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
Yu Bin Tan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Yan Zheng Lim
Department of Gastroenterology and Hepatology, Singapore General Hospital, Singapore, Singapore
3 shared publications - Chee-Kiat Tan
Department of Gastroenterology and Hepatology Singapore General Hospital Singapore Singapore
2 shared publications Gerald Gui Ren Sng
Data Science and Artificial Intelligence Lab, Singapore General Hospital, Singapore
2 shared publicationsJoshua Yi Min Tung
Data Science and Artificial Intelligence Lab, Singapore General Hospital, Singapore
2 shared publications- Andrew Boon Eu Kwek
Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore
1 shared publication Damien Meng Yew Tan
Department of Gastroenterology and Hepatology Singapore General Hospital Singapore
1 shared publication
Latest Publications
- 12 September 2025
- Published by Wiley in Journal of Gastroenterology and Hepatology
- Vol. 40 (10) , 2355-2358
Screening Smarter, Not Just Harder: FIT, Colonoscopy, and the Future of CRC Prevention in the Asia Pacific Region
- 12 September 2025
- Published by Wiley in Journal of Gastroenterology and Hepatology
- Vol. 40 (10) , 2355-2358
Screening Smarter, Not Just Harder: FIT, Colonoscopy, and the Future of CRC Prevention in the Asia Pacific Region
- Open Access
- 4 March 2025
- Published by BMJ in BMJ Open Gastroenterology
- Vol. 12 (1) , e001496
Vision-language large learning model, GPT4V, accurately classifies the Boston Bowel Preparation Scale score
Introduction: Large learning models (LLMs) such as GPT are advanced artificial intelligence (AI) models. Originally developed for natural language processing, they have been adapted for multi-modal tasks with vision-language input. One clinically relevant task is scoring the Boston Bowel Preparation Scale (BBPS). While traditional AI techniques use large amounts of data for training, we hypothesise that vision-language LLM can perform this task with fewer examples. Methods: We used the GPT4V vision-language LLM developed by OpenAI, via the OpenAI application programming interface. A standardised prompt instructed the model to grade BBPS with contextual references extracted from the original paper describing the BBPS by Lai et al (GIE 2009). Performance was tested on the HyperKvasir dataset, an open dataset for automated BBPS grading. Results: Of 1794 images, GPT4V returned valid results for 1772 (98%). It had an accuracy of 0.84 for two-class classification (BBPS 0–1 vs 2–3) and 0.74 for four-class classification (BBPS 0, 1, 2, 3). Macro-averaged F1 scores were 0.81 and 0.63, respectively. Qualitatively, most errors arose from misclassification of BBPS 1 as 2. These results compare favourably with current methods using large amounts of training data, which achieve an accuracy in the range of 0.8–0.9. Conclusion: This study provides proof-of-concept that a vision-language LLM is able to perform BBPS classification accurately, without large training datasets. This represents a paradigm shift in AI classification methods in medicine, where many diseases lack sufficient data to train traditional AI models. An LLM with appropriate examples may be used in such cases.
- 4 March 2025
- Published by BMJ in BMJ Open Gastroenterology
- Vol. 12 (1) , e001496
Open AccessVision-language large learning model, GPT4V, accurately classifies the Boston Bowel Preparation Scale score
Introduction: Large learning models (LLMs) such as GPT are advanced artificial intelligence (AI) models. Originally developed for natural language processing, they have been adapted for multi-modal tasks with vision-language input. One clinically relevant task is scoring the Boston Bowel Preparation Scale (BBPS). While traditional AI techniques use large amounts of data for training, we hypothesise that vision-language LLM can perform this task with fewer examples. Methods: We used the GPT4V vision-language LLM developed by OpenAI, via the OpenAI application programming interface. A standardised prompt instructed the model to grade BBPS with contextual references extracted from the original paper describing the BBPS by Lai et al (GIE 2009). Performance was tested on the HyperKvasir dataset, an open dataset for automated BBPS grading. Results: Of 1794 images, GPT4V returned valid results for 1772 (98%). It had an accuracy of 0.84 for two-class classification (BBPS 0–1 vs 2–3) and 0.74 for four-class classification (BBPS 0, 1, 2, 3). Macro-averaged F1 scores were 0.81 and 0.63, respectively. Qualitatively, most errors arose from misclassification of BBPS 1 as 2. These results compare favourably with current methods using large amounts of training data, which achieve an accuracy in the range of 0.8–0.9. Conclusion: This study provides proof-of-concept that a vision-language LLM is able to perform BBPS classification accurately, without large training datasets. This represents a paradigm shift in AI classification methods in medicine, where many diseases lack sufficient data to train traditional AI models. An LLM with appropriate examples may be used in such cases.
- 19 October 2023
- Published by Wiley in Journal of Gastroenterology and Hepatology
- Vol. 39 (1) , 81-106
ChatGPT on guidelines: Providing contextual knowledge to GPT allows it to provide advice on appropriate colonoscopy intervals
Background and Aim: Colonoscopy is commonly used in screening and surveillance for colorectal cancer. Multiple different guidelines provide recommendations on the interval between colonoscopies. This can be challenging for non‐specialist healthcare providers to navigate. Large language models like ChatGPT are a potential tool for parsing patient histories and providing advice. However, the standard GPT model is not designed for medical use and can hallucinate. One way to overcome these challenges is to provide contextual information with medical guidelines to help the model respond accurately to queries.Our study compares the standard GPT4 against a contextualized model provided with relevant screening guidelines. We evaluated whether the models could provide correct advice for screening and surveillance intervals for colonoscopy.Methods: Relevant guidelines pertaining to colorectal cancer screening and surveillance were formulated into a knowledge base for GPT. We tested 62 example case scenarios (three times each) on standard GPT4 and on a contextualized model with the knowledge base.Results: The contextualized GPT4 model outperformed the standard GPT4 in all domains. No high‐risk features were missed, and only two cases had hallucination of additional high‐risk features. A correct interval to colonoscopy was provided in the majority of cases. Guidelines were appropriately cited in almost all cases.Conclusions: A contextualized GPT4 model could identify high‐risk features and quote appropriate guidelines without significant hallucination. It gave a correct interval to the next colonoscopy in the majority of cases. This provides proof of concept that ChatGPT with appropriate refinement can serve as an accurate physician assistant.
- 19 October 2023
- Published by Wiley in Journal of Gastroenterology and Hepatology
- Vol. 39 (1) , 81-106
ChatGPT on guidelines: Providing contextual knowledge to GPT allows it to provide advice on appropriate colonoscopy intervals
Background and Aim: Colonoscopy is commonly used in screening and surveillance for colorectal cancer. Multiple different guidelines provide recommendations on the interval between colonoscopies. This can be challenging for non‐specialist healthcare providers to navigate. Large language models like ChatGPT are a potential tool for parsing patient histories and providing advice. However, the standard GPT model is not designed for medical use and can hallucinate. One way to overcome these challenges is to provide contextual information with medical guidelines to help the model respond accurately to queries.Our study compares the standard GPT4 against a contextualized model provided with relevant screening guidelines. We evaluated whether the models could provide correct advice for screening and surveillance intervals for colonoscopy.Methods: Relevant guidelines pertaining to colorectal cancer screening and surveillance were formulated into a knowledge base for GPT. We tested 62 example case scenarios (three times each) on standard GPT4 and on a contextualized model with the knowledge base.Results: The contextualized GPT4 model outperformed the standard GPT4 in all domains. No high‐risk features were missed, and only two cases had hallucination of additional high‐risk features. A correct interval to colonoscopy was provided in the majority of cases. Guidelines were appropriately cited in almost all cases.Conclusions: A contextualized GPT4 model could identify high‐risk features and quote appropriate guidelines without significant hallucination. It gave a correct interval to the next colonoscopy in the majority of cases. This provides proof of concept that ChatGPT with appropriate refinement can serve as an accurate physician assistant.
- Open Access
Unusual cause of a polypoid lesion in the extrahepatic bile duct
Adenomyomas are benign lesions that are most frequently found in the gallbladder but can also be rarely found in the biliary tract. Although benign, they present close similarity to malignant lesions and thus deserve important clinical consideration. We present a case of a 74-year-old Chinese man who presented acutely with fever and painless obstructive jaundice. CT imaging showed a large calculus within a dilated common bile duct (CBD) and, despite undergoing an endoscopic retrograde cholangiopancreatography (ERCP) with stone clearance, there was a persistent filling defect that was adherent to the wall of the proximal common bile duct. His CA 19-9 was also significantly raised. Intraductal ultrasonography (IDUS) showed a polypoid mass with papillary-like projections, and ERCP forcep biopsies were unable to exclude a lesion with neoplastic potential. The patient subsequently underwent cholecystectomy with open CBD excision and Roux-en-Y hepaticojejunostomy, and histology showed features consistent with a biliary adenomyoma.
Open AccessUnusual cause of a polypoid lesion in the extrahepatic bile duct
Adenomyomas are benign lesions that are most frequently found in the gallbladder but can also be rarely found in the biliary tract. Although benign, they present close similarity to malignant lesions and thus deserve important clinical consideration. We present a case of a 74-year-old Chinese man who presented acutely with fever and painless obstructive jaundice. CT imaging showed a large calculus within a dilated common bile duct (CBD) and, despite undergoing an endoscopic retrograde cholangiopancreatography (ERCP) with stone clearance, there was a persistent filling defect that was adherent to the wall of the proximal common bile duct. His CA 19-9 was also significantly raised. Intraductal ultrasonography (IDUS) showed a polypoid mass with papillary-like projections, and ERCP forcep biopsies were unable to exclude a lesion with neoplastic potential. The patient subsequently underwent cholecystectomy with open CBD excision and Roux-en-Y hepaticojejunostomy, and histology showed features consistent with a biliary adenomyoma.