Large language models in health care: Development, applications, and challenges

Latest developments of generative artificial intelligence and applications in ophthalmology

The emergence of generative artificial intelligence (AI) has revolutionized various fields. In ophthalmology, generative AI has the potential to enhance efficiency, accuracy, personalization and innovation in clinical practice and medical research, through processing data, streamlining medical documentation, facilitating patient-doctor communication, aiding in clinical decision-making, and simulating clinical trials. This review focuses on the development and integration of generative AI models into clinical workflows and scientific research of ophthalmology. It outlines the need for development of a standard framework for comprehensive assessments, robust evidence, and exploration of the potential of multimodal capabilities and intelligent agents. Additionally, the review addresses the risks in AI model development and application in clinical service and research of ophthalmology, including data privacy, data bias, adaptation friction, over interdependence, and job replacement, based on which we summarized a risk management framework to mitigate these concerns. This review highlights the transformative potential of generative AI in enhancing patient care, improving operational efficiency in the clinical service and research in ophthalmology. It also advocates for a balanced approach to its adoption.

Influence of Model Evolution and System Roles on ChatGPT's Performance in Chinese Medical Licensing Exams: Comparative Study

Background

With the increasing application of large language models like ChatGPT in various industries, its potential in the medical domain, especially in standardized examinations, has become a focal point of research.

Objective

The aim of this study is to assess the clinical performance of ChatGPT, focusing on its accuracy and reliability in the Chinese National Medical Licensing Examination (CNMLE).

Methods

The CNMLE 2022 question set, consisting of 500 single-answer multiple choices questions, were reclassified into 15 medical subspecialties. Each question was tested 8 to 12 times in Chinese on the OpenAI platform from April 24 to May 15, 2023. Three key factors were considered: the version of GPT-3.5 and 4.0, the prompt's designation of system roles tailored to medical subspecialties, and repetition for coherence. A passing accuracy threshold was established as 60%. The χ2 tests and κ values were employed to evaluate the model's accuracy and consistency.

Results

GPT-4.0 achieved a passing accuracy of 72.7%, which was significantly higher than that of GPT-3.5 (54%; P<.001). The variability rate of repeated responses from GPT-4.0 was lower than that of GPT-3.5 (9% vs 19.5%; P<.001). However, both models showed relatively good response coherence, with κ values of 0.778 and 0.610, respectively. System roles numerically increased accuracy for both GPT-4.0 (0.3%-3.7%) and GPT-3.5 (1.3%-4.5%), and reduced variability by 1.7% and 1.8%, respectively (P>.05). In subgroup analysis, ChatGPT achieved comparable accuracy among different question types (P>.05). GPT-4.0 surpassed the accuracy threshold in 14 of 15 subspecialties, while GPT-3.5 did so in 7 of 15 on the first response.

Conclusions

GPT-4.0 passed the CNMLE and outperformed GPT-3.5 in key areas such as accuracy, consistency, and medical subspecialty expertise. Adding a system role insignificantly enhanced the model's reliability and answer coherence. GPT-4.0 showed promising potential in medical education and clinical practice, meriting further study.

Disparities in clinical studies of AI enabled applications from a global perspective

Artificial intelligence (AI) has been extensively researched in medicine, but its practical application remains limited. Meanwhile, there are various disparities in existing AI-enabled clinical studies, which pose a challenge to global health equity. In this study, we conducted an in-depth analysis of the geo-economic distribution of 159 AI-enabled clinical studies, as well as the gender disparities among these studies. We aim to reveal these disparities from a global literature perspective, thus highlighting the need for equitable access to medical AI technologies.

Clinical efficacy of pre-trained large language models through the lens of aphasia

The rapid development of large language models (LLMs) motivates us to explore how such state-of-the-art natural language processing systems can inform aphasia research. What kind of language indices can we derive from a pre-trained LLM? How do they differ from or relate to the existing language features in aphasia? To what extent can LLMs serve as an interpretable and effective diagnostic and measurement tool in a clinical context? To investigate these questions, we constructed predictive and correlational models, which utilize mean surprisals from LLMs as predictor variables. Using AphasiaBank archived data, we validated our models' efficacy in aphasia diagnosis, measurement, and prediction. Our finding is that LLMs-surprisals can effectively detect the presence of aphasia and different natures of the disorder, LLMs in conjunction with the existing language indices improve models' efficacy in subtyping aphasia, and LLMs-surprisals can capture common agrammatic deficits at both word and sentence level. Overall, LLMs have potential to advance automatic and precise aphasia prediction. A natural language processing pipeline can be greatly benefitted from integrating LLMs, enabling us to refine models of existing language disorders, such as aphasia.

The Role of Humanization and Robustness of Large Language Models in Conversational Artificial Intelligence for Individuals With Depression: A Critical Analysis

Unlabelled

Large language model (LLM)-powered services are gaining popularity in various applications due to their exceptional performance in many tasks, such as sentiment analysis and answering questions. Recently, research has been exploring their potential use in digital health contexts, particularly in the mental health domain. However, implementing LLM-enhanced conversational artificial intelligence (CAI) presents significant ethical, technical, and clinical challenges. In this viewpoint paper, we discuss 2 challenges that affect the use of LLM-enhanced CAI for individuals with mental health issues, focusing on the use case of patients with depression: the tendency to humanize LLM-enhanced CAI and their lack of contextualized robustness. Our approach is interdisciplinary, relying on considerations from philosophy, psychology, and computer science. We argue that the humanization of LLM-enhanced CAI hinges on the reflection of what it means to simulate "human-like" features with LLMs and what role these systems should play in interactions with humans. Further, ensuring the contextualization of the robustness of LLMs requires considering the specificities of language production in individuals with depression, as well as its evolution over time. Finally, we provide a series of recommendations to foster the responsible design and deployment of LLM-enhanced CAI for the therapeutic support of individuals with depression.

Leveraging Large Language Models in the delivery of post-operative dental care: a comparison between an embedded GPT model and ChatGPT

OBJECTIVE

This study underscores the transformative role of Artificial Intelligence (AI) in healthcare, particularly the promising applications of Large Language Models (LLMs) in the delivery of post-operative dental care. The aim is to evaluate the performance of an embedded GPT model and its comparison with ChatGPT-3.5 turbo. The assessment focuses on aspects like response accuracy, clarity, relevance, and up-to-date knowledge in addressing patient concerns and facilitating informed decision-making.

MATERIAL AND METHODS

An embedded GPT model, employing GPT-3.5-16k, was crafted via GPT-trainer to answer postoperative questions in four dental specialties including Operative Dentistry & Endodontics, Periodontics, Oral & Maxillofacial Surgery, and Prosthodontics. The generated responses were validated by thirty-six dental experts, nine from each specialty, employing a Likert scale, providing comprehensive insights into the embedded GPT model's performance and its comparison with GPT3.5 turbo. For content validation, a quantitative Content Validity Index (CVI) was used. The CVI was calculated both at the item level (I-CVI) and scale level (S-CVI/Ave). To adjust I-CVI for chance agreement, a modified kappa statistic (K*) was computed.

RESULTS

The overall content validity of responses generated via embedded GPT model and ChatGPT was 65.62% and 61.87% respectively. Moreover, the embedded GPT model revealed a superior performance surpassing ChatGPT with an accuracy of 62.5% and clarity of 72.5%. In contrast, the responses generated via ChatGPT achieved slightly lower scores, with an accuracy of 52.5% and clarity of 67.5%. However, both models performed equally well in terms of relevance and up-to-date knowledge.

CONCLUSION

In conclusion, embedded GPT model showed better results as compared to ChatGPT in providing post-operative dental care emphasizing the benefits of embedding and prompt engineering, paving the way for future advancements in healthcare applications.

Sample Size Considerations for Fine-Tuning Large Language Models for Named Entity Recognition Tasks: Methodological Study

BACKGROUND

Large language models (LLMs) have the potential to support promising new applications in health informatics. However, practical data on sample size considerations for fine-tuning LLMs to perform specific tasks in biomedical and health policy contexts are lacking.

OBJECTIVE

This study aims to evaluate sample size and sample selection techniques for fine-tuning LLMs to support improved named entity recognition (NER) for a custom data set of conflicts of interest disclosure statements.

METHODS

A random sample of 200 disclosure statements was prepared for annotation. All "PERSON" and "ORG" entities were identified by each of the 2 raters, and once appropriate agreement was established, the annotators independently annotated an additional 290 disclosure statements. From the 490 annotated documents, 2500 stratified random samples in different size ranges were drawn. The 2500 training set subsamples were used to fine-tune a selection of language models across 2 model architectures (Bidirectional Encoder Representations from Transformers [BERT] and Generative Pre-trained Transformer [GPT]) for improved NER, and multiple regression was used to assess the relationship between sample size (sentences), entity density (entities per sentence [EPS]), and trained model performance (F1-score). Additionally, single-predictor threshold regression models were used to evaluate the possibility of diminishing marginal returns from increased sample size or entity density.

RESULTS

Fine-tuned models ranged in topline NER performance from F1-score=0.79 to F1-score=0.96 across architectures. Two-predictor multiple linear regression models were statistically significant with multiple R2 ranging from 0.6057 to 0.7896 (all P<.001). EPS and the number of sentences were significant predictors of F1-scores in all cases ( P<.001), except for the GPT-2_large model, where EPS was not a significant predictor (P=.184). Model thresholds indicate points of diminishing marginal return from increased training data set sample size measured by the number of sentences, with point estimates ranging from 439 sentences for RoBERTa_large to 527 sentences for GPT-2_large. Likewise, the threshold regression models indicate a diminishing marginal return for EPS with point estimates between 1.36 and 1.38.

CONCLUSIONS

Relatively modest sample sizes can be used to fine-tune LLMs for NER tasks applied to biomedical text, and training data entity density should representatively approximate entity density in production data. Training data quality and a model architecture's intended use (text generation vs text processing or classification) may be as, or more, important as training data volume and model parameter size.

Potential of Large Language Models in Health Care: Delphi Study

BACKGROUND

A large language model (LLM) is a machine learning model inferred from text data that captures subtle patterns of language use in context. Modern LLMs are based on neural network architectures that incorporate transformer methods. They allow the model to relate words together through attention to multiple words in a text sequence. LLMs have been shown to be highly effective for a range of tasks in natural language processing (NLP), including classification and information extraction tasks and generative applications.

OBJECTIVE

The aim of this adapted Delphi study was to collect researchers' opinions on how LLMs might influence health care and on the strengths, weaknesses, opportunities, and threats of LLM use in health care.

METHODS

We invited researchers in the fields of health informatics, nursing informatics, and medical NLP to share their opinions on LLM use in health care. We started the first round with open questions based on our strengths, weaknesses, opportunities, and threats framework. In the second and third round, the participants scored these items.

RESULTS

The first, second, and third rounds had 28, 23, and 21 participants, respectively. Almost all participants (26/28, 93% in round 1 and 20/21, 95% in round 3) were affiliated with academic institutions. Agreement was reached on 103 items related to use cases, benefits, risks, reliability, adoption aspects, and the future of LLMs in health care. Participants offered several use cases, including supporting clinical tasks, documentation tasks, and medical research and education, and agreed that LLM-based systems will act as health assistants for patient education. The agreed-upon benefits included increased efficiency in data handling and extraction, improved automation of processes, improved quality of health care services and overall health outcomes, provision of personalized care, accelerated diagnosis and treatment processes, and improved interaction between patients and health care professionals. In total, 5 risks to health care in general were identified: cybersecurity breaches, the potential for patient misinformation, ethical concerns, the likelihood of biased decision-making, and the risk associated with inaccurate communication. Overconfidence in LLM-based systems was recognized as a risk to the medical profession. The 6 agreed-upon privacy risks included the use of unregulated cloud services that compromise data security, exposure of sensitive patient data, breaches of confidentiality, fraudulent use of information, vulnerabilities in data storage and communication, and inappropriate access or use of patient data.

CONCLUSIONS

Future research related to LLMs should not only focus on testing their possibilities for NLP-related tasks but also consider the workflows the models could contribute to and the requirements regarding quality, integration, and regulations needed for successful implementation in practice.

Accuracy and consistency of chatbots versus clinicians for answering pediatric dentistry questions: A pilot study

OBJECTIVES

Artificial Intelligence has applications such as Large Language Models (LLMs), which simulate human-like conversations. The potential of LLMs in healthcare is not fully evaluated. This pilot study assessed the accuracy and consistency of chatbots and clinicians in answering common questions in pediatric dentistry.

METHODS

Two expert pediatric dentists developed thirty true or false questions involving different aspects of pediatric dentistry. Publicly accessible chatbots (Google Bard, ChatGPT4, ChatGPT 3.5, Llama, Sage, Claude 2 100k, Claude-instant, Claude-instant-100k, and Google Palm) were employed to answer the questions (3 independent new conversations). Three groups of clinicians (general dentists, pediatric specialists, and students; n = 20/group) also answered. Responses were graded by two pediatric dentistry faculty members, along with a third independent pediatric dentist. Resulting accuracies (percentage of correct responses) were compared using analysis of variance (ANOVA), and post-hoc pairwise group comparisons were corrected using Tukey's HSD method. ACronbach's alpha was calculated to determine consistency.

RESULTS

Pediatric dentists were significantly more accurate (mean±SD 96.67 %± 4.3 %) than other clinicians and chatbots (p < 0.001). General dentists (88.0 % ± 6.1 %) also demonstrated significantly higher accuracy than chatbots (p < 0.001), followed by students (80.8 %±6.9 %). ChatGPT showed the highest accuracy (78 %±3 %) among chatbots. All chatbots except ChatGPT3.5 showed acceptable consistency (Cronbach alpha>0.7).

CLINICAL SIGNIFICANCE

Based on this pilot study, chatbots may be valuable adjuncts for educational purposes and for distributing information to patients. However, they are not yet ready to serve as substitutes for human clinicians in diagnostic decision-making.

CONCLUSION

In this pilot study, chatbots showed lower accuracy than dentists. Chatbots may not yet be recommended for clinical pediatric dentistry.

Comparing Open-Access Database and Traditional Intensive Care Studies Using Machine Learning: Bibliometric Analysis Study

BACKGROUND

Intensive care research has predominantly relied on conventional methods like randomized controlled trials. However, the increasing popularity of open-access, free databases in the past decade has opened new avenues for research, offering fresh insights. Leveraging machine learning (ML) techniques enables the analysis of trends in a vast number of studies.

OBJECTIVE

This study aims to conduct a comprehensive bibliometric analysis using ML to compare trends and research topics in traditional intensive care unit (ICU) studies and those done with open-access databases (OADs).

METHODS

We used ML for the analysis of publications in the Web of Science database in this study. Articles were categorized into "OAD" and "traditional intensive care" (TIC) studies. OAD studies were included in the Medical Information Mart for Intensive Care (MIMIC), eICU Collaborative Research Database (eICU-CRD), Amsterdam University Medical Centers Database (AmsterdamUMCdb), High Time Resolution ICU Dataset (HiRID), and Pediatric Intensive Care database. TIC studies included all other intensive care studies. Uniform manifold approximation and projection was used to visualize the corpus distribution. The BERTopic technique was used to generate 30 topic-unique identification numbers and to categorize topics into 22 topic families.

RESULTS

A total of 227,893 records were extracted. After exclusions, 145,426 articles were identified as TIC and 1301 articles as OAD studies. TIC studies experienced exponential growth over the last 2 decades, culminating in a peak of 16,378 articles in 2021, while OAD studies demonstrated a consistent upsurge since 2018. Sepsis, ventilation-related research, and pediatric intensive care were the most frequently discussed topics. TIC studies exhibited broader coverage than OAD studies, suggesting a more extensive research scope.

CONCLUSIONS

This study analyzed ICU research, providing valuable insights from a large number of publications. OAD studies complement TIC studies, focusing on predictive modeling, while TIC studies capture essential qualitative information. Integrating both approaches in a complementary manner is the future direction for ICU research. Additionally, natural language processing techniques offer a transformative alternative for literature review and bibliometric analysis.

Large language models as decision aids in neuro-oncology: a review of shared decision-making applications

Shared decision-making (SDM) is crucial in neuro-oncology, fostering collaborations between patients and healthcare professionals to navigate treatment options. However, the complexity of neuro-oncological conditions and the cognitive and emotional burdens on patients present significant barriers to achieving effective SDM. This discussion explores the potential of large language models (LLMs) such as OpenAI's ChatGPT and Google's Bard to overcome these barriers, offering a means to enhance patient understanding and engagement in their care. LLMs, by providing accessible, personalized information, could support but not supplant the critical insights of healthcare professionals. The hypothesis suggests that patients, better informed through LLMs, may participate more actively in their treatment choices. Integrating LLMs into neuro-oncology requires navigating ethical considerations, including safeguarding patient data and ensuring informed consent, alongside the judicious use of AI technologies. Future efforts should focus on establishing ethical guidelines, adapting healthcare workflows, promoting patient-oriented research, and developing training programs for clinicians on the use of LLMs. Continuous evaluation of LLM applications will be vital to maintain their effectiveness and alignment with patient needs. Ultimately, this exploration contends that the thoughtful integration of LLMs into SDM processes could significantly enhance patient involvement and strengthen the patient-physician relationship in neuro-oncology care.

A Comprehensive Evaluation of Large Language Models in Mining Gene Interactions and Pathway Knowledge

Background

Understanding complex biological pathways, including gene-gene interactions and gene regulatory networks, is critical for exploring disease mechanisms and drug development. Manual literature curation of biological pathways is useful but cannot keep up with the exponential growth of the literature. Large-scale language models (LLMs), notable for their vast parameter sizes and comprehensive training on extensive text corpora, have great potential in automated text mining of biological pathways.

Method

This study assesses the effectiveness of 21 LLMs, including both API-based models and open-source models. The evaluation focused on two key aspects: gene regulatory relations (specifically, 'activation', 'inhibition', and 'phosphorylation') and KEGG pathway component recognition. The performance of these models was analyzed using statistical metrics such as precision, recall, F1 scores, and the Jaccard similarity index.

Results

Our results indicated a significant disparity in model performance. Among the API-based models, ChatGPT-4 and Claude-Pro showed superior performance, with an F1 score of 0.4448 and 0.4386 for the gene regulatory relation prediction, and a Jaccard similarity index of 0.2778 and 0.2657 for the KEGG pathway prediction, respectively. Open-source models lagged their API-based counterparts, where Falcon-180b-chat and llama1-7b led with the highest performance in gene regulatory relations (F1 of 0.2787 and 0.1923, respectively) and KEGG pathway recognition (Jaccard similarity index of 0.2237 and 0. 2207, respectively).

Conclusion

LLMs are valuable in biomedical research, especially in gene network analysis and pathway mapping. However, their effectiveness varies, necessitating careful model selection. This work also provided a case study and insight into using LLMs as knowledge graphs.

Redefining Virtual Assistants in Health Care: The Future With Large Language Models

This editorial explores the evolving and transformative role of large language models (LLMs) in enhancing the capabilities of virtual assistants (VAs) in the health care domain, highlighting recent research on the performance of VAs and LLMs in health care information sharing. Focusing on recent research, this editorial unveils the marked improvement in the accuracy and clinical relevance of responses from LLMs, such as GPT-4, compared to current VAs, especially in addressing complex health care inquiries, like those related to postpartum depression. The improved accuracy and clinical relevance with LLMs mark a paradigm shift in digital health tools and VAs. Furthermore, such LLM applications have the potential to dynamically adapt and be integrated into existing VA platforms, offering cost-effective, scalable, and inclusive solutions. These suggest a significant increase in the applicable range of VA applications, as well as the increased value, risk, and impact in health care, moving toward more personalized digital health ecosystems. However, alongside these advancements, it is necessary to develop and adhere to ethical guidelines, regulatory frameworks, governance principles, and privacy and safety measures. We need a robust interdisciplinary collaboration to navigate the complexities of safely and effectively integrating LLMs into health care applications, ensuring that these emerging technologies align with the diverse needs and ethical considerations of the health care domain.