Girish N. Nadkarni

Seyed Amir Ahmad Safavi-Naini, Shuhaib Ali, Omer Shahab et al.

Background and Aims: This study evaluates the medical reasoning performance of large language models (LLMs) and vision language models (VLMs) in gastroenterology. Methods: We used 300 gastroenterology board exam-style multiple-choice questions, 138 of which contain images to systematically assess the impact of model configurations and parameters and prompt engineering strategies utilizing GPT-3.5. Next, we assessed the performance of proprietary and open-source LLMs (versions), including GPT (3.5, 4, 4o, 4omini), Claude (3, 3.5), Gemini (1.0), Mistral, Llama (2, 3, 3.1), Mixtral, and Phi (3), across different interfaces (web and API), computing environments (cloud and local), and model precisions (with and without quantization). Finally, we assessed accuracy using a semiautomated pipeline. Results: Among the proprietary models, GPT-4o (73.7%) and Claude3.5-Sonnet (74.0%) achieved the highest accuracy, outperforming the top open-source models: Llama3.1-405b (64%), Llama3.1-70b (58.3%), and Mixtral-8x7b (54.3%). Among the quantized open-source models, the 6-bit quantized Phi3-14b (48.7%) performed best. The scores of the quantized models were comparable to those of the full-precision models Llama2-7b, Llama2--13b, and Gemma2-9b. Notably, VLM performance on image-containing questions did not improve when the images were provided and worsened when LLM-generated captions were provided. In contrast, a 10% increase in accuracy was observed when images were accompanied by human-crafted image descriptions. Conclusion: In conclusion, while LLMs exhibit robust zero-shot performance in medical reasoning, the integration of visual data remains a challenge for VLMs. Effective deployment involves carefully determining optimal model configurations, encouraging users to consider either the high performance of proprietary models or the flexible adaptability of open-source models.

Akhil Vaid, Joy Jiang, Ashwin Sawant et al.

The electrocardiogram (ECG) is a ubiquitous diagnostic modality. Convolutional neural networks (CNNs) applied towards ECG analysis require large sample sizes, and transfer learning approaches result in suboptimal performance when pre-training is done on natural images. We leveraged masked image modeling to create the first vision-based transformer model, HeartBEiT, for electrocardiogram waveform analysis. We pre-trained this model on 8.5 million ECGs and then compared performance vs. standard CNN architectures for diagnosis of hypertrophic cardiomyopathy, low left ventricular ejection fraction and ST elevation myocardial infarction using differing training sample sizes and independent validation datasets. We show that HeartBEiT has significantly higher performance at lower sample sizes compared to other models. Finally, we also show that HeartBEiT improves explainability of diagnosis by highlighting biologically relevant regions of the EKG vs. standard CNNs. Thus, we present the first vision-based waveform transformer that can be used to develop specialized models for ECG analysis especially at low sample sizes.

Mohammadreza Ghaffarzadeh-Esfahani, Mahdi Ghaffarzadeh-Esfahani, Arian Salahi-Niri et al.

This study compared the performance of classical feature-based machine learning models (CMLs) and large language models (LLMs) in predicting COVID-19 mortality using high-dimensional tabular data from 9,134 patients across four hospitals. Seven CML models, including XGBoost and random forest (RF), were evaluated alongside eight LLMs, such as GPT-4 and Mistral-7b, which performed zero-shot classification on text-converted structured data. Additionally, Mistral- 7b was fine-tuned using the QLoRA approach. XGBoost and RF demonstrated superior performance among CMLs, achieving F1 scores of 0.87 and 0.83 for internal and external validation, respectively. GPT-4 led the LLM category with an F1 score of 0.43, while fine-tuning Mistral-7b significantly improved its recall from 1% to 79%, yielding a stable F1 score of 0.74 during external validation. Although LLMs showed moderate performance in zero-shot classification, fine-tuning substantially enhanced their effectiveness, potentially bridging the gap with CML models. However, CMLs still outperformed LLMs in handling high-dimensional tabular data tasks. This study highlights the potential of both CMLs and fine-tuned LLMs in medical predictive modeling, while emphasizing the current superiority of CMLs for structured data analysis.

Braja Gopal Patra, Lauren A. Lepow, Praneet Kasi Reddy Jagadeesh Kumar et al.

Background: Social support (SS) and social isolation (SI) are social determinants of health (SDOH) associated with psychiatric outcomes. In electronic health records (EHRs), individual-level SS/SI is typically documented as narrative clinical notes rather than structured coded data. Natural language processing (NLP) algorithms can automate the otherwise labor-intensive process of data extraction. Data and Methods: Psychiatric encounter notes from Mount Sinai Health System (MSHS, n=300) and Weill Cornell Medicine (WCM, n=225) were annotated and established a gold standard corpus. A rule-based system (RBS) involving lexicons and a large language model (LLM) using FLAN-T5-XL were developed to identify mentions of SS and SI and their subcategories (e.g., social network, instrumental support, and loneliness). Results: For extracting SS/SI, the RBS obtained higher macro-averaged f-scores than the LLM at both MSHS (0.89 vs. 0.65) and WCM (0.85 vs. 0.82). For extracting subcategories, the RBS also outperformed the LLM at both MSHS (0.90 vs. 0.62) and WCM (0.82 vs. 0.81). Discussion and Conclusion: Unexpectedly, the RBS outperformed the LLMs across all metrics. Intensive review demonstrates that this finding is due to the divergent approach taken by the RBS and LLM. The RBS were designed and refined to follow the same specific rules as the gold standard annotations. Conversely, the LLM were more inclusive with categorization and conformed to common English-language understanding. Both approaches offer advantages and are made available open-source for future testing.

Akhil Vaid, Joshua Lampert, Juhee Lee et al.

Generative Large Language Models (LLMs) hold significant promise in healthcare, demonstrating capabilities such as passing medical licensing exams and providing clinical knowledge. However, their current use as information retrieval tools is limited by challenges like data staleness, resource demands, and occasional generation of incorrect information. This study assessed the potential of LLMs to function as autonomous agents in a simulated tertiary care medical center, using real-world clinical cases across multiple specialties. Both proprietary and open-source LLMs were evaluated, with Retrieval Augmented Generation (RAG) enhancing contextual relevance. Proprietary models, particularly GPT-4, generally outperformed open-source models, showing improved guideline adherence and more accurate responses with RAG. The manual evaluation by expert clinicians was crucial in validating models' outputs, underscoring the importance of human oversight in LLM operation. Further, the study emphasizes Natural Language Programming (NLP) as the appropriate paradigm for modifying model behavior, allowing for precise adjustments through tailored prompts and real-world interactions. This approach highlights the potential of LLMs to significantly enhance and supplement clinical decision-making, while also emphasizing the value of continuous expert involvement and the flexibility of NLP to ensure their reliability and effectiveness in healthcare settings.

Faris F. Gulamali, Ashwin S. Sawant, Lora Liharska et al.

The adoption of diagnosis and prognostic algorithms in healthcare has led to concerns about the perpetuation of bias against disadvantaged groups of individuals. Deep learning methods to detect and mitigate bias have revolved around modifying models, optimization strategies, and threshold calibration with varying levels of success. Here, we generate a data-centric, model-agnostic, task-agnostic approach to evaluate dataset bias by investigating the relationship between how easily different groups are learned at small sample sizes (AEquity). We then apply a systematic analysis of AEq values across subpopulations to identify and mitigate manifestations of racial bias in two known cases in healthcare - Chest X-rays diagnosis with deep convolutional neural networks and healthcare utilization prediction with multivariate logistic regression. AEq is a novel and broadly applicable metric that can be applied to advance equity by diagnosing and remediating bias in healthcare datasets.

Stefan Konigorski, Sarah Wernicke, Tamara Slosarek et al.

N-of-1 trials are the gold standard study design to evaluate individual treatment effects and derive personalized treatment strategies. Digital tools have the potential to initiate a new era of N-of-1 trials in terms of scale and scope, but fully-functional platforms are not yet available. Here, we present the open source StudyU platform which includes the StudyU designer and StudyU app. With the StudyU designer, scientists are given a collaborative web application to digitally specify, publish, and conduct N-of-1 trials. The StudyU app is a smartphone application with innovative user-centric elements for participants to partake in the published trials and assess the effects of different interventions on their health. Thereby, the StudyU platform allows clinicians and researchers worldwide to easily design and conduct digital N-of-1 trials in a safe manner. We envision that StudyU can change the landscape of personalized treatments both for patients and healthy individuals, democratize and personalize evidence generation for self-optimization and medicine, and can be integrated in clinical practice.

Dhavalkumar Patel, Ganesh Raut, Satya Narayan Cheetirala et al.

Generative AI is transforming enterprise application development by enabling machines to create content, code, and designs. These models, however, demand substantial computational power and data management. Cloud computing addresses these needs by offering infrastructure to train, deploy, and scale generative AI models. This review examines cloud services for generative AI, focusing on key providers like Amazon Web Services (AWS), Microsoft Azure, Google Cloud, IBM Cloud, Oracle Cloud, and Alibaba Cloud. It compares their strengths, weaknesses, and impact on enterprise growth. We explore the role of high-performance computing (HPC), serverless architectures, edge computing, and storage in supporting generative AI. We also highlight the significance of data management, networking, and AI-specific tools in building and deploying these models. Additionally, the review addresses security concerns, including data privacy, compliance, and AI model protection. It assesses the performance and cost efficiency of various cloud providers and presents case studies from healthcare, finance, and entertainment. We conclude by discussing challenges and future directions, such as technical hurdles, vendor lock-in, sustainability, and regulatory issues. Put together, this work can serve as a guide for practitioners and researchers looking to adopt cloud-based generative AI solutions, serving as a valuable guide to navigating the intricacies of this evolving field.

Satya Narayana Cheetirala, Ganesh Raut, Dhavalkumar Patel et al.

Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text segments can match the performance of processing entire clinical notes with large context LLMs. We begin by splitting clinical documents into smaller chunks, converting them into vector embeddings, and storing these in a FAISS index. We then retrieve the top 4,000 words most pertinent to the classification query and feed these consolidated segments into an LLM. We evaluated three LLMs (GPT4o, LLaMA, and Mistral) on a surgical complication identification task. Metrics such as AUC ROC, precision, recall, and F1 showed no statistically significant differences between the RAG based approach and whole-text processing (p > 0.05p > 0.05). These findings indicate that RAG can significantly reduce token usage without sacrificing classification accuracy, providing a scalable and cost effective solution for analyzing lengthy clinical documents.

Mohammad Amin Khalafi, Seyed Amir Ahmad Safavi-Naini, Ameneh Salehi et al.

Introduction: This study provides a comprehensive performance assessment of vision-language models (VLMs) against established convolutional neural networks (CNNs) and classic machine learning models (CMLs) for computer-aided detection (CADe) and computer-aided diagnosis (CADx) of colonoscopy polyp images. Method: We analyzed 2,258 colonoscopy images with corresponding pathology reports from 428 patients. We preprocessed all images using standardized techniques (resizing, normalization, and augmentation) and implemented a rigorous comparative framework evaluating 11 distinct models: ResNet50, 4 CMLs (random forest, support vector machine, logistic regression, decision tree), two specialized contrastive vision language encoders (CLIP, BiomedCLIP), and three general-purpose VLMs ( GPT-4 Gemini-1.5-Pro, Claude-3-Opus). Our performance assessment focused on two clinical tasks: polyp detection (CADe) and classification (CADx). Result: In polyp detection, ResNet50 achieved the best performance (F1: 91.35%, AUROC: 0.98), followed by BiomedCLIP (F1: 88.68%, AUROC: [AS1] ). GPT-4 demonstrated comparable effectiveness to traditional machine learning approaches (F1: 81.02%, AUROC: [AS2] ), outperforming other general-purpose VLMs. For polyp classification, performance rankings remained consistent but with lower overall metrics. ResNet50 maintained the highest efficacy (weighted F1: 74.94%), while GPT-4 demonstrated moderate capability (weighted F1: 41.18%), significantly exceeding other VLMs (Claude-3-Opus weighted F1: 25.54%, Gemini 1.5 Pro weighted F1: 6.17%). Conclusion: CNNs remain superior for both CADx and CADe tasks. However, VLMs like BioMedCLIP and GPT-4 may be useful for polyp detection tasks where training CNNs is not feasible.

Tingyi Wanyan, Hossein Honarvar, Suraj K. Jaladanki et al.

Machine Learning (ML) models typically require large-scale, balanced training data to be robust, generalizable, and effective in the context of healthcare. This has been a major issue for developing ML models for the coronavirus-disease 2019 (COVID-19) pandemic where data is highly imbalanced, particularly within electronic health records (EHR) research. Conventional approaches in ML use cross-entropy loss (CEL) that often suffers from poor margin classification. For the first time, we show that contrastive loss (CL) improves the performance of CEL especially for imbalanced EHR data and the related COVID-19 analyses. This study has been approved by the Institutional Review Board at the Icahn School of Medicine at Mount Sinai. We use EHR data from five hospitals within the Mount Sinai Health System (MSHS) to predict mortality, intubation, and intensive care unit (ICU) transfer in hospitalized COVID-19 patients over 24 and 48 hour time windows. We train two sequential architectures (RNN and RETAIN) using two loss functions (CEL and CL). Models are tested on full sample data set which contain all available data and restricted data set to emulate higher class imbalance.CL models consistently outperform CEL models with the restricted data set on these tasks with differences ranging from 0.04 to 0.15 for AUPRC and 0.05 to 0.1 for AUROC. For the restricted sample, only the CL model maintains proper clustering and is able to identify important features, such as pulse oximetry. CL outperforms CEL in instances of severe class imbalance, on three EHR outcomes with respect to three performance metrics: predictive power, clustering, and feature importance. We believe that the developed CL framework can be expanded and used for EHR ML work in general.