Physicians make critical time-constrained decisions every day. Clinical predictive models can help physicians and administrators make decisions by forecasting clinical and operational events. Existing structured data-based clinical predictive models have limited use in everyday practice owing to complexity in data processing, as well as model development and deployment1-3. Here we show that unstructured clinical notes from the electronic health record can enable the training of clinical language models, which can be used as all-purpose clinical predictive engines with low-resistance development and deployment. Our approach leverages recent advances in natural language processing4,5 to train a large language model for medical language (NYUTron) and subsequently fine-tune it across a wide range of clinical and operational predictive tasks. We evaluated our approach within our health system for five such tasks: 30-day all-cause readmission prediction, in-hospital mortality prediction, comorbidity index prediction, length of stay prediction, and insurance denial prediction. We show that NYUTron has an area under the curve (AUC) of 78.7-94.9%, with an improvement of 5.36-14.7% in the AUC compared with traditional models. We additionally demonstrate the benefits of pretraining with clinical text, the potential for increasing generalizability to different sites through fine-tuning and the full deployment of our system in a prospective, single-arm trial. These results show the potential for using clinical language models in medicine to read alongside physicians and provide guidance at the point of care. 

Health system-scale language models are all-purpose prediction engines

Large language models (LLMs) such as GPT-4 hold great promise as transformative tools in health care, ranging from automating administrative tasks to augmenting clinical decision making. However, these models also pose a danger of perpetuating biases and delivering incorrect medical diagnoses, which can have a direct, harmful impact on medical care. We aimed to assess whether GPT-4 encodes racial and gender biases that impact its use in health care.Using the Azure OpenAI application interface, this model evaluation study tested whether GPT-4 encodes racial and gender biases and examined the impact of such biases on four potential applications of LLMs in the clinical domain-namely, medical education, diagnostic reasoning, clinical plan generation, and subjective patient assessment. We conducted experiments with prompts designed to resemble typical use of GPT-4 within clinical and medical education applications. We used clinical vignettes from NEJM Healer and from published research on implicit bias in health care. GPT-4 estimates of the demographic distribution of medical conditions were compared with true US prevalence estimates. Differential diagnosis and treatment planning were evaluated across demographic groups using standard statistical tests for significance between groups.We found that GPT-4 did not appropriately model the demographic diversity of medical conditions, consistently producing clinical vignettes that stereotype demographic presentations. The differential diagnoses created by GPT-4 for standardised clinical vignettes were more likely to include diagnoses that stereotype certain races, ethnicities, and genders. Assessment and plans created by the model showed significant association between demographic attributes and recommendations for more expensive procedures as well as differences in patient perception.Our findings highlight the urgent need for comprehensive and transparent bias assessments of LLM tools such as GPT-4 for intended use cases before they are integrated into clinical care. We discuss the potential sources of these biases and potential mitigation strategies before clinical implementation.Priscilla Chan and Mark Zuckerberg. 

Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study.

Abstract The United States Medical Licensing Examination (USMLE) has been a subject of performance study for artificial intelligence (AI) models. However, their performance on questions involving USMLE soft skills remains unexplored. This study aimed to evaluate ChatGPT and GPT-4 on USMLE questions involving communication skills, ethics, empathy, and professionalism. We used 80 USMLE-style questions involving soft skills, taken from the USMLE website and the AMBOSS question bank. A follow-up query was used to assess the models’ consistency. The performance of the AI models was compared to that of previous AMBOSS users. GPT-4 outperformed ChatGPT, correctly answering 90% compared to ChatGPT’s 62.5%. GPT-4 showed more confidence, not revising any responses, while ChatGPT modified its original answers 82.5% of the time. The performance of GPT-4 was higher than that of AMBOSS's past users. Both AI models, notably GPT-4, showed capacity for empathy, indicating AI's potential to meet the complex interpersonal, ethical, and professional demands intrinsic to the practice of medicine. 

Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments

Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles 

A whole-slide foundation model for digital pathology from real-world data.

There are enormous enthusiasm and concerns in applying large language models (LLMs) to healthcare. Yet current assumptions are based on general-purpose LLMs such as ChatGPT, which are not developed for medical use. This study develops a generative clinical LLM, GatorTronGPT, using 277 billion words of text including (1) 82 billion words of clinical text from 126 clinical departments and approximately 2 million patients at the University of Florida Health and (2) 195 billion words of diverse general English text. We train GatorTronGPT using a GPT-3 architecture with up to 20 billion parameters and evaluate its utility for biomedical natural language processing (NLP) and healthcare text generation. GatorTronGPT improves biomedical natural language processing. We apply GatorTronGPT to generate 20 billion words of synthetic text. Synthetic NLP models trained using synthetic text generated by GatorTronGPT outperform models trained using real-world clinical text. Physicians' Turing test using 1 (worst) to 9 (best) scale shows that there are no significant differences in linguistic readability (p = 0.22; 6.57 of GatorTronGPT compared with 6.93 of human) and clinical relevance (p = 0.91; 7.0 of GatorTronGPT compared with 6.97 of human) and that physicians cannot differentiate them (p < 0.001). This study provides insights into the opportunities and challenges of LLMs for medical research and healthcare. 

pdf/a-study-of-generative-large-language-model-for-medical-4a21u4puej.pdf

A study of generative large language model for medical research and healthcare

Traditional evaluation metrics for classiﬁcation in natural language processing such as accuracy and area under the curve fail to diﬀerentiate between models with diﬀerent predictive behaviors despite their similar performance metrics. We introduce sensitivity score, a metric that scrutinizes models’ behaviors at the vocabulary level to pro-vide insights into disparities in their decision-making logic. We assess the sensitivity score on a set of represen-tative words in the test set using two classiﬁers trained for hospital readmission classiﬁcation with similar performance statistics. Our experiments compare the decision-making logic of clinicians and classiﬁers based on rank correlations of sensitivity scores. The results indicate that the language model’s sensitivity score aligns better with the professionals than the xgboost classiﬁer on tf-idf embeddings, which suggests that xgboost uses some spurious features. Overall, this metric oﬀers a novel perspective on assessing models’ robustness by quantifying their discrep-ancy with professional opinions. Our code is available on GitHub. 1

Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction


 
 Existing clinical prediction algorithms mostly leverage small cohorts of structured data (e.g., medical imaging or laboratory data). However, large language models have demonstrated the ability to utilize unstructured data to outperform other machine learning approaches given sufficient data. Training large language models on unstructured clinical notes offers a possible alternative to structured data algorithm development in clinical tasks.
 
 
 
 An unlabeled dataset of over seven million unstructured clinical notes (e.g., radiology reports and patient histories) was collected from four hospitals within the NYU Langone Health (NYULH) system and utilized to pre-train a bidirectional encoder representation with transformer (BERT) model. This model was further fine-tuned using a labeled dataset of discharge summaries to predict 30-day all-cause readmission. The resulting model, termed NYUTron, was assessed using a held-out retrospective cohort of patients from June to December 2021.
 
 
 
 Over the period of the retrospective study, there were a total 1,072 neurosurgery patients. The BERT model achieved an area under the receiver operating curve of 0.7883, a recall of 95.1% at a precision of 27.3%, and an accuracy of 82.1%.
 
 
 
 This study demonstrates how large language models and unstructured clinical notes can be used to provide information to physicians on clinical tasks with a flexible framework that is amenable to modification for other clinical tasks.


754 Prediction of 30-day All-Cause Readmission of Neurosurgery Patients Using Large Language Models

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Mingzi Cao

Author Tools

Chat about Author

Papers

Health system-scale language models are all-purpose prediction engines

Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

754 Prediction of 30-day All-Cause Readmission of Neurosurgery Patients Using Large Language Models