Jonas Ho

Dr. Jonas Ho


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2025 in BMJ Open Gastroenterology
Verified
Journal Article
Open access
PDF file
DLDaniel Yan Zheng Lim
Daniel Yan Zheng Lim
YTYu Bin Tan
Yu Bin Tan
JHJonas Ho
Jonas Ho
SCSushmitha Carkarine
Sushmitha Carkarine
TCTian Wei Valerie Chew
Tian Wei Valerie Chew
DTDamien Tan
Damien Tan
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.

20 December 2024 in JGH Open
Verified
Journal Article
Open access
JHJonas Ho
Jonas Ho
RRR Rajesh
R Rajesh
WWWei Keat Wan
Wei Keat Wan
MCMark Cheah
Mark Cheah
YTYi Yuan Tan
Yi Yuan Tan
Background: Linitis plastica is a challenging diagnosis in the setting of a patient with previous breast cancer.Case presentation: We present a case of a 74‐year‐old Chinese Female with a history of breast cancer who presented with epigastric pain, nausea, early satiety, and weight loss of 5 kg in 3 months. Endoscopic diagnosis of linitis plastica was made, but subsequent management plans were dependent on accurate histological assessment in view of her oncological history.Discussion and conclusion: Our case highlights the clinical conundrum confronting the endoscopist in evaluating suspected linitis plastica where the imaging, endoscopic, and macroscopic histological findings between primary gastric adenocarcinoma and metastatic breast cancer can be indistinguishable. Optimal deep tissue acquisition is required to differentiate the true diagnosis in such cases.