Daniel Shu Wei Ting

Kabilan Elangovan, Jasmine Chiat Ling Ong, Liyuan Jin et al.

Large Language Models (LLMs) have emerged as a potential solution to assist digital health development with patient education, commonly medication-related enquires. We trained and validated Med-Pal, a medication domain-specific LLM-chatbot fine-tuned with a fine-grained and expert curated dataset from a selection of five light-weighted open-source LLMs of smaller parameter size (7 billion or less) regarding computational constraints and prioritizing operational efficiency. A multi-disciplinary team performed a clinical evaluation of LLMs responses using the SCORE criteria, focusing on safety, accuracy, bias, reproducibility, and ease of understanding. Best performing light-weighted LLM was chosen as Med-Pal for further engineering with guard-railing using adversarial prompting. Med-Pal and existing light-weighted LLMs, including pretrained Biomistral and finetuned Meerkat, were validated on an independent dataset on a broad range of medication-related questions (231 in total), 12 different question types across 14 different medication classes. Mistral-7b emerged as the top performer among selected lightweight LLMs, achieving the highest median score of 14 and 71.9% high-quality responses in accuracy and safety domains, hence chosen as the backbone LLM for Med-Pal. When compared against Biomistral, Med-pal outperformed in generating responses appropriate for patient communication, with significant reductions bias and errors typical of general LLMs. Comparable performance was observed when comparing Med-Pal with Meerkat. Med-Pal showcases the feasibility of developing and employing fine-tuned light-weighted LLMs to enhance digital health communications.

Siqi Li, Pinyan Liu, Gustavo G. Nascimento et al.

Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations and discusses potential innovations. We searched five databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from three primary perspectives, including data quality, modeling strategies, and FL frameworks. Out of the 1160 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis. The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

Mingxuan Liu, Yilin Ning, Salinelat Teixayavong et al.

Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the issue of fairness remains a concern in high-stakes fields such as healthcare. Despite extensive discussion and efforts in algorithm development, AI fairness and clinical concerns have not been adequately addressed. In this paper, we discuss the misalignment between technical and clinical perspectives of AI fairness, highlight the barriers to AI fairness' translation to healthcare, advocate multidisciplinary collaboration to bridge the knowledge gap, and provide possible solutions to address the clinical concerns pertaining to AI fairness.

Yilin Ning, Salinelat Teixayavong, Yuqing Shang et al.

The widespread use of ChatGPT and other emerging technology powered by generative artificial intelligence (GenAI) has drawn much attention to potential ethical issues, especially in high-stakes applications such as healthcare, but ethical discussions are yet to translate into operationalisable solutions. Furthermore, ongoing ethical discussions often neglect other types of GenAI that have been used to synthesise data (e.g., images) for research and practical purposes, which resolved some ethical issues and exposed others. We conduct a scoping review of ethical discussions on GenAI in healthcare to comprehensively analyse gaps in the current research, and further propose to reduce the gaps by developing a checklist for comprehensive assessment and transparent documentation of ethical discussions in GenAI research. The checklist can be readily integrated into the current peer review and publication system to enhance GenAI research, and may be used for ethics-related disclosures for GenAI-powered products, healthcare applications of such products and beyond.

Rui Yang, Huitao Li, Weihao Xuan et al.

Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40% relative to baseline models, with a more than threefold increase in performance on low-resource languages. Together, these resources provide an important foundation for advancing the equitable development and application of LLMs globally, enabling broader language communities to benefit from technological advances.

Mingxuan Liu, Yuhe Ke, Wentao Zhu et al.

The integration of large language models (LLMs) into healthcare holds promise to enhance clinical decision-making, yet their susceptibility to biases remains a critical concern. Gender has long influenced physician behaviors and patient outcomes, raising concerns that LLMs assuming human-like roles, such as clinicians or medical educators, may replicate or amplify gender-related biases. Using case studies from the New England Journal of Medicine Challenge (NEJM), we assigned genders (female, male, or unspecified) to multiple open-source and proprietary LLMs. We evaluated their response consistency across LLM-gender assignments regarding both LLM-based diagnosis and models' judgments on the clinical relevance or necessity of patient gender. In our findings, diagnoses were relatively consistent across LLM genders for most models. However, for patient gender's relevance and necessity in LLM-based diagnosis, all models demonstrated substantial inconsistency across LLM genders, particularly for relevance judgements. Some models even displayed a systematic female-male disparity in their interpretation of patient gender. These findings present an underexplored bias that could undermine the reliability of LLMs in clinical practice, underscoring the need for routine checks of identity-assignment consistency when interacting with LLMs to ensure reliable and equitable AI-supported clinical care.

YuHe Ke, Liyuan Jin, Kabilan Elangovan et al.

Purpose: Large Language Models (LLMs) hold significant promise for medical applications. Retrieval Augmented Generation (RAG) emerges as a promising approach for customizing domain knowledge in LLMs. This case study presents the development and evaluation of an LLM-RAG pipeline tailored for healthcare, focusing specifically on preoperative medicine. Methods: We developed an LLM-RAG model using 35 preoperative guidelines and tested it against human-generated responses, with a total of 1260 responses evaluated. The RAG process involved converting clinical documents into text using Python-based frameworks like LangChain and Llamaindex, and processing these texts into chunks for embedding and retrieval. Vector storage techniques and selected embedding models to optimize data retrieval, using Pinecone for vector storage with a dimensionality of 1536 and cosine similarity for loss metrics. Human-generated answers, provided by junior doctors, were used as a comparison. Results: The LLM-RAG model generated answers within an average of 15-20 seconds, significantly faster than the 10 minutes typically required by humans. Among the basic LLMs, GPT4.0 exhibited the best accuracy of 80.1%. This accuracy was further increased to 91.4% when the model was enhanced with RAG. Compared to the human-generated instructions, which had an accuracy of 86.3%, the performance of the GPT4.0 RAG model demonstrated non-inferiority (p=0.610). Conclusions: In this case study, we demonstrated a LLM-RAG model for healthcare implementation. The pipeline shows the advantages of grounded knowledge, upgradability, and scalability as important aspects of healthcare LLM deployment.

Jasmine Chiat Ling Ong, Liyuan Jin, Kabilan Elangovan et al.

Importance: We introduce a novel Retrieval Augmented Generation (RAG)-Large Language Model (LLM) framework as a Clinical Decision Support Systems (CDSS) to support safe medication prescription. Objective: To evaluate the efficacy of LLM-based CDSS in correctly identifying medication errors in different patient case vignettes from diverse medical and surgical sub-disciplines, against a human expert panel derived ground truth. We compared performance for under 2 different CDSS practical healthcare integration modalities: LLM-based CDSS alone (fully autonomous mode) vs junior pharmacist + LLM-based CDSS (co-pilot, assistive mode). Design, Setting, and Participants: Utilizing a RAG model with state-of-the-art medically-related LLMs (GPT-4, Gemini Pro 1.0 and Med-PaLM 2), this study used 61 prescribing error scenarios embedded into 23 complex clinical vignettes across 12 different medical and surgical specialties. A multidisciplinary expert panel assessed these cases for Drug-Related Problems (DRPs) using the PCNE classification and graded severity / potential for harm using revised NCC MERP medication error index. We compared. Results RAG-LLM performed better compared to LLM alone. When employed in a co-pilot mode, accuracy, recall, and F1 scores were optimized, indicating effectiveness in identifying moderate to severe DRPs. The accuracy of DRP detection with RAG-LLM improved in several categories but at the expense of lower precision. Conclusions This study established that a RAG-LLM based CDSS significantly boosts the accuracy of medication error identification when used alongside junior pharmacists (co-pilot), with notable improvements in detecting severe DRPs. This study also illuminates the comparative performance of current state-of-the-art LLMs in RAG-based CDSS systems.

Ting Fang Tan, Kabilan Elangovan, Liyuan Jin et al.

Purpose: To assess the alignment of GPT-4-based evaluation to human clinician experts, for the evaluation of responses to ophthalmology-related patient queries generated by fine-tuned LLM chatbots. Methods: 400 ophthalmology questions and paired answers were created by ophthalmologists to represent commonly asked patient questions, divided into fine-tuning (368; 92%), and testing (40; 8%). We find-tuned 5 different LLMs, including LLAMA2-7b, LLAMA2-7b-Chat, LLAMA2-13b, and LLAMA2-13b-Chat. For the testing dataset, additional 8 glaucoma QnA pairs were included. 200 responses to the testing dataset were generated by 5 fine-tuned LLMs for evaluation. A customized clinical evaluation rubric was used to guide GPT-4 evaluation, grounded on clinical accuracy, relevance, patient safety, and ease of understanding. GPT-4 evaluation was then compared against ranking by 5 clinicians for clinical alignment. Results: Among all fine-tuned LLMs, GPT-3.5 scored the highest (87.1%), followed by LLAMA2-13b (80.9%), LLAMA2-13b-chat (75.5%), LLAMA2-7b-Chat (70%) and LLAMA2-7b (68.8%) based on the GPT-4 evaluation. GPT-4 evaluation demonstrated significant agreement with human clinician rankings, with Spearman and Kendall Tau correlation coefficients of 0.90 and 0.80 respectively; while correlation based on Cohen Kappa was more modest at 0.50. Notably, qualitative analysis and the glaucoma sub-analysis revealed clinical inaccuracies in the LLM-generated responses, which were appropriately identified by the GPT-4 evaluation. Conclusion: The notable clinical alignment of GPT-4 evaluation highlighted its potential to streamline the clinical evaluation of LLM chatbot responses to healthcare-related queries. By complementing the existing clinician-dependent manual grading, this efficient and automated evaluation could assist the validation of future developments in LLM applications for healthcare.

Yu He Ke, Liyuan Jin, Kabilan Elangovan et al.

Large Language Models (LLMs) show potential for medical applications but often lack specialized clinical knowledge. Retrieval Augmented Generation (RAG) allows customization with domain-specific information, making it suitable for healthcare. This study evaluates the accuracy, consistency, and safety of RAG models in determining fitness for surgery and providing preoperative instructions. We developed LLM-RAG models using 35 local and 23 international preoperative guidelines and tested them against human-generated responses. A total of 3,682 responses were evaluated. Clinical documents were processed using Llamaindex, and 10 LLMs, including GPT3.5, GPT4, and Claude-3, were assessed. Fourteen clinical scenarios were analyzed, focusing on seven aspects of preoperative instructions. Established guidelines and expert judgment were used to determine correct responses, with human-generated answers serving as comparisons. The LLM-RAG models generated responses within 20 seconds, significantly faster than clinicians (10 minutes). The GPT4 LLM-RAG model achieved the highest accuracy (96.4% vs. 86.6%, p=0.016), with no hallucinations and producing correct instructions comparable to clinicians. Results were consistent across both local and international guidelines. This study demonstrates the potential of LLM-RAG models for preoperative healthcare tasks, highlighting their efficiency, scalability, and reliability.

Yang Bai, Haoran Cheng, Yang Zhou et al.

Despite the promise of foundation models in medical AI, current systems remain limited - they are modality-specific and lack transparent reasoning processes, hindering clinical adoption. To address this gap, we present EVLF-FM, a multimodal vision-language foundation model (VLM) designed to unify broad diagnostic capability with fine-grain explainability. The development and testing of EVLF-FM encompassed over 1.3 million total samples from 23 global datasets across eleven imaging modalities related to six clinical specialties: dermatology, hepatology, ophthalmology, pathology, pulmonology, and radiology. External validation employed 8,884 independent test samples from 10 additional datasets across five imaging modalities. Technically, EVLF-FM is developed to assist with multiple disease diagnosis and visual question answering with pixel-level visual grounding and reasoning capabilities. In internal validation for disease diagnostics, EVLF-FM achieved the highest average accuracy (0.858) and F1-score (0.797), outperforming leading generalist and specialist models. In medical visual grounding, EVLF-FM also achieved stellar performance across nine modalities with average mIOU of 0.743 and Acc@0.5 of 0.837. External validations further confirmed strong zero-shot and few-shot performance, with competitive F1-scores despite a smaller model size. Through a hybrid training strategy combining supervised and visual reinforcement fine-tuning, EVLF-FM not only achieves state-of-the-art accuracy but also exhibits step-by-step reasoning, aligning outputs with visual evidence. EVLF-FM is an early multi-disease VLM model with explainability and reasoning capabilities that could advance adoption of and trust in foundation models for real-world clinical deployment.

Yang Zhou, Chrystie Wan Ning Quek, Jun Zhou et al.

Current artificial intelligence models for medical imaging are predominantly single modality and single disease. Attempts to create multimodal and multi-disease models have resulted in inconsistent clinical accuracy. Furthermore, training these models typically requires large, labour-intensive, well-labelled datasets. We developed MerMED-FM, a state-of-the-art multimodal, multi-specialty foundation model trained using self-supervised learning and a memory module. MerMED-FM was trained on 3.3 million medical images from over ten specialties and seven modalities, including computed tomography (CT), chest X-rays (CXR), ultrasound (US), pathology patches, color fundus photography (CFP), optical coherence tomography (OCT) and dermatology images. MerMED-FM was evaluated across multiple diseases and compared against existing foundational models. Strong performance was achieved across all modalities, with AUROCs of 0.988 (OCT); 0.982 (pathology); 0.951 (US); 0.943 (CT); 0.931 (skin); 0.894 (CFP); 0.858 (CXR). MerMED-FM has the potential to be a highly adaptable, versatile, cross-specialty foundation model that enables robust medical imaging interpretation across diverse medical disciplines.

Rui Yang, Huitao Li, Matthew Yu Heng Wong et al.

Natural language processing (NLP) has been traditionally applied to medicine, and generative large language models (LLMs) have become prominent recently. However, the differences between them across different medical tasks remain underexplored. We analyzed 19,123 studies, finding that generative LLMs demonstrate advantages in open-ended tasks, while traditional NLP dominates in information extraction and analysis tasks. As these technologies advance, ethical use of them is essential to ensure their potential in medical applications.

Yu He Ke, Liyuan Jin, Kabilan Elangovan et al.

Large Language Models (LLMs) are emerging as powerful tools in healthcare, particularly for complex, domain-specific tasks. This study describes the development and evaluation of the PErioperative AI CHatbot (PEACH), a secure LLM-based system integrated with local perioperative guidelines to support preoperative clinical decision-making. PEACH was embedded with 35 institutional perioperative protocols in the secure Claude 3.5 Sonet LLM framework within Pair Chat (developed by Singapore Government) and tested in a silent deployment with real-world data. Accuracy, safety, and usability were assessed. Deviations and hallucinations were categorized based on potential harm, and user feedback was evaluated using the Technology Acceptance Model (TAM). Updates were made after the initial silent deployment to amend one protocol. In 240 real-world clinical iterations, PEACH achieved a first-generation accuracy of 97.5% (78/80) and an overall accuracy of 96.7% (232/240) across three iterations. The updated PEACH demonstrated improved accuracy of 97.9% (235/240), with a statistically significant difference from the null hypothesis of 95% accuracy (p = 0.018, 95% CI: 0.952-0.991). Minimal hallucinations and deviations were observed (both 1/240 and 2/240, respectively). Clinicians reported that PEACH expedited decisions in 95% of cases, and inter-rater reliability ranged from kappa 0.772-0.893 within PEACH and 0.610-0.784 among attendings. PEACH is an accurate, adaptable tool that enhances consistency and efficiency in perioperative decision-making. Future research should explore its scalability across specialties and its impact on clinical outcomes.

Rui Yang, Yilin Ning, Emilia Keppo et al.

Generative artificial intelligence (AI) has brought revolutionary innovations in various fields, including medicine. However, it also exhibits limitations. In response, retrieval-augmented generation (RAG) provides a potential solution, enabling models to generate more accurate contents by leveraging the retrieval of external knowledge. With the rapid advancement of generative AI, RAG can pave the way for connecting this transformative technology with medical applications and is expected to bring innovations in equity, reliability, and personalization to health care.

Yu He Ke, Rui Yang, Sui An Lie et al.

Background: Cognitive biases in clinical decision-making significantly contribute to errors in diagnosis and suboptimal patient outcomes. Addressing these biases presents a formidable challenge in the medical field. Objective: This study explores the role of large language models (LLMs) in mitigating these biases through the utilization of a multi-agent framework. We simulate the clinical decision-making processes through multi-agent conversation and evaluate its efficacy in improving diagnostic accuracy. Methods: A total of 16 published and unpublished case reports where cognitive biases have resulted in misdiagnoses were identified from the literature. In the multi-agent framework, we leveraged GPT-4 to facilitate interactions among four simulated agents to replicate clinical team dynamics. Each agent has a distinct role: 1) To make the final diagnosis after considering the discussions, 2) The devil's advocate and correct confirmation and anchoring bias, 3) The tutor and facilitator of the discussion to reduce premature closure bias, and 4) To record and summarize the findings. A total of 80 simulations were evaluated for the accuracy of initial diagnosis, top differential diagnosis and final two differential diagnoses. Results: In a total of 80 responses evaluating both initial and final diagnoses, the initial diagnosis had an accuracy of 0% (0/80), but following multi-agent discussions, the accuracy for the top differential diagnosis increased to 71.3% (57/80), and for the final two differential diagnoses, to 80.0% (64/80). Conclusions: The framework demonstrated an ability to re-evaluate and correct misconceptions, even in scenarios with misleading initial investigations. The LLM-driven multi-agent conversation framework shows promise in enhancing diagnostic accuracy in diagnostically challenging medical scenarios.

Yilin Ning, Siqi Li, Marcus Eng Hock Ong et al.

Risk scores are widely used for clinical decision making and commonly generated from logistic regression models. Machine-learning-based methods may work well for identifying important predictors, but such 'black box' variable selection limits interpretability, and variable importance evaluated from a single model can be biased. We propose a robust and interpretable variable selection approach using the recently developed Shapley variable importance cloud (ShapleyVIC) that accounts for variability across models. Our approach evaluates and visualizes overall variable contributions for in-depth inference and transparent variable selection, and filters out non-significant contributors to simplify model building steps. We derive an ensemble variable ranking from variable contributions, which is easily integrated with an automated and modularized risk score generator, AutoScore, for convenient implementation. In a study of early death or unplanned readmission, ShapleyVIC selected 6 of 41 candidate variables to create a well-performing model, which had similar performance to a 16-variable model from machine-learning-based ranking.

Yilin Ning, Marcus Eng Hock Ong, Bibhas Chakraborty et al.

Interpretable machine learning has been focusing on explaining final models that optimize performance. The current state-of-the-art is the Shapley additive explanations (SHAP) that locally explains variable impact on individual predictions, and it is recently extended for a global assessment across the dataset. Recently, Dong and Rudin proposed to extend the investigation to models from the same class as the final model that are "good enough", and identified a previous overclaim of variable importance based on a single model. However, this method does not directly integrate with existing Shapley-based interpretations. We close this gap by proposing a Shapley variable importance cloud that pools information across good models to avoid biased assessments in SHAP analyses of final models, and communicate the findings via novel visualizations. We demonstrate the additional insights gain compared to conventional explanations and Dong and Rudin's method using criminal justice and electronic medical records data.

Shaohua Li, Yong Liu, Xiuchao Sui et al.

Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x,y (and also z in 3D images) dimensions. However often only labels of the whole images are annotated, and localized ROIs are unavailable; and 3) ROIs in medical images often appear in varying sizes (scales). We approach these three challenges with a Multi-Instance Multi-Scale (MIMS) CNN: 1) We propose a multi-scale convolutional layer, which extracts patterns of different receptive fields with a shared set of convolutional kernels, so that scale-invariant patterns are captured by this compact set of kernels. As this layer contains only a small number of parameters, training on small datasets becomes feasible; 2) We propose a "top-k pooling" to aggregate the feature maps in varying scales from multiple spatial dimensions, allowing the model to be trained using weak annotations within the multiple instance learning (MIL) framework. Our method is shown to perform well on three classification tasks involving two 3D and two 2D medical image datasets.