Disease Concept-Embedding Based on the Self-Supervised Method for Medical Information Extraction from Electronic Health Records and Disease Retrieval: Algorithm Development and Validation Study

The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review

BACKGROUND

Artificial intelligence (AI), more specifically large language models (LLMs), holds significant potential in revolutionizing emergency care delivery by optimizing clinical workflows and enhancing the quality of decision-making. Although enthusiasm for integrating LLMs into emergency medicine (EM) is growing, the existing literature is characterized by a disparate collection of individual studies, conceptual analyses, and preliminary implementations. Given these complexities and gaps in understanding, a cohesive framework is needed to comprehend the existing body of knowledge on the application of LLMs in EM.

OBJECTIVE

Given the absence of a comprehensive framework for exploring the roles of LLMs in EM, this scoping review aims to systematically map the existing literature on LLMs' potential applications within EM and identify directions for future research. Addressing this gap will allow for informed advancements in the field.

METHODS

Using PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) criteria, we searched Ovid MEDLINE, Embase, Web of Science, and Google Scholar for papers published between January 2018 and August 2023 that discussed LLMs' use in EM. We excluded other forms of AI. A total of 1994 unique titles and abstracts were screened, and each full-text paper was independently reviewed by 2 authors. Data were abstracted independently, and 5 authors performed a collaborative quantitative and qualitative synthesis of the data.

RESULTS

A total of 43 papers were included. Studies were predominantly from 2022 to 2023 and conducted in the United States and China. We uncovered four major themes: (1) clinical decision-making and support was highlighted as a pivotal area, with LLMs playing a substantial role in enhancing patient care, notably through their application in real-time triage, allowing early recognition of patient urgency; (2) efficiency, workflow, and information management demonstrated the capacity of LLMs to significantly boost operational efficiency, particularly through the automation of patient record synthesis, which could reduce administrative burden and enhance patient-centric care; (3) risks, ethics, and transparency were identified as areas of concern, especially regarding the reliability of LLMs' outputs, and specific studies highlighted the challenges of ensuring unbiased decision-making amidst potentially flawed training data sets, stressing the importance of thorough validation and ethical oversight; and (4) education and communication possibilities included LLMs' capacity to enrich medical training, such as through using simulated patient interactions that enhance communication skills.

CONCLUSIONS

LLMs have the potential to fundamentally transform EM, enhancing clinical decision-making, optimizing workflows, and improving patient outcomes. This review sets the stage for future advancements by identifying key research areas: prospective validation of LLM applications, establishing standards for responsible use, understanding provider and patient perceptions, and improving physicians' AI literacy. Effective integration of LLMs into EM will require collaborative efforts and thorough evaluation to ensure these technologies can be safely and effectively applied.

Large Language Models in Neurology Research and Future Practice

Recent advancements in generative artificial intelligence, particularly using large language models (LLMs), are gaining increased public attention. We provide a perspective on the potential of LLMs to analyze enormous amounts of data from medical records and gain insights on specific topics in neurology. In addition, we explore use cases for LLMs, such as early diagnosis, supporting patient and caregivers, and acting as an assistant for clinicians. We point to the potential ethical and technical challenges raised by LLMs, such as concerns about privacy and data security, potential biases in the data for model training, and the need for careful validation of results. Researchers must consider these challenges and take steps to address them to ensure that their work is conducted in a safe and responsible manner. Despite these challenges, LLMs offer promising opportunities for improving care and treatment of various neurologic disorders.

Association between independent practice time and patient outcomes in the emergency department: a retrospective study of residents in three urban hospitals in Taiwan

BACKGROUND

The purpose of the study was to investigate the relationship between the independent practice time of residents and the quality of care provided in the Emergency Department (ED) across three urban hospitals in Taiwan. The study focused on non-pediatric and non-obstetric complaints, aiming to provide insights into the optimal balance between resident autonomy and patient safety.

METHODS

A comprehensive retrospective study was conducted using de-identified electronic health records (EHRs) from the hospital's integrated medical database (iMD) from August 2015 to July 2019. The independent practice time was defined as the duration from the first medical order by a resident to the first modifications by the attending physician. The primary outcome was revisits to the ED within 72 h following discharge. Statistical analysis was conducted using RStudio and pyGAM.

RESULTS

The study identified several factors associated with shorter independent practice times (< 30 minutes), including older patient age, male sex, higher body temperature, higher heart rate, lower blood pressure, and the presence of certain comorbidities. Residents practicing independently for 30-120 minutes were associated with similar adjusted odds of patient revisits to the ED (OR 1.034, 95% CI 0.978-1.093) and no higher risk of 7-day mortality (OR 0.674, 95% CI 0.592-0.767) compared to the group with less autonomy. However, independent practice times exceeding 120 minutes were associated with higher odds of revisiting the ED within 72 h. For the group with 120-210 minutes of independent practice time, the OR was 1.113 (95% CI: 1.025-1.208, p = 0.011). For the group with > 210 minutes, the OR was 1.259 (95% CI: 1.094-1.449, p = 0.001), indicating an increased risk of adverse outcomes as the independent practice time increasing.

CONCLUSIONS

The study concludes that while providing residents an independent practice time between 30 to 120 minutes may be beneficial, caution should be exercised when this time exceeds 120 minutes. The findings underscore the importance of optimal supervision in enhancing patient care quality and safety. Further research is recommended to explore the long-term effects of different levels of resident autonomy on patient outcomes and the professional development of the residents themselves.

Clinically Labeled Contrastive Learning for OCT Biomarker Classification

This article presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety of labels for data that serve different purposes at different stages of a diagnostic and treatment process. Clinical labels and biomarker labels are two examples. In general, clinical labels are easier to obtain in larger quantities because they are regularly collected during routine clinical care, while biomarker labels require expert analysis and interpretation to obtain. Within the field of ophthalmology, previous work has shown that clinical values exhibit correlations with biomarker structures that manifest within optical coherence tomography (OCT) scans. We exploit this relationship by using the clinical data as pseudo-labels for our data without biomarker labels in order to choose positive and negative instances for training a backbone network with a supervised contrastive loss. In this way, a backbone network learns a representation space that aligns with the clinical data distribution available. Afterwards, we fine-tune the network trained in this manner with the smaller amount of biomarker labeled data with a cross-entropy loss in order to classify these key indicators of disease directly from OCT scans. We also expand on this concept by proposing a method that uses a linear combination of clinical contrastive losses. We benchmark our methods against state of the art self-supervised methods in a novel setting with biomarkers of varying granularity. We show performance improvements by as much as 5% in total biomarker detection AUROC.

Pre-training in Medical Data: A Survey

Medical data refers to health-related information associated with regular patient care or as part of a clinical trial program. There are many categories of such data, such as clinical imaging data, bio-signal data, electronic health records (EHR), and multi-modality medical data. With the development of deep neural networks in the last decade, the emerging pre-training paradigm has become dominant in that it has significantly improved machine learning methods’ performance in a data-limited scenario. In recent years, studies of pre-training in the medical domain have achieved significant progress. To summarize these technology advancements, this work provides a comprehensive survey of recent advances for pre-training on several major types of medical data. In this survey, we summarize a large number of related publications and the existing benchmarking in the medical domain. Especially, the survey briefly describes how some pre-training methods are applied to or developed for medical data. From a data-driven perspective, we examine the extensive use of pre-training in many medical scenarios. Moreover, based on the summary of recent pre-training studies, we identify several challenges in this field to provide insights for future studies.

Deep Dynamic Patient Similarity Analysis: Model Development and Validation in ICU

BACKGROUND

Personalized medicine requires the patient similarity analysis for providing specific treatments tailed for each patient. However, the patient similarity analysis in personalized clinical scenarios encounters challenges, which are twofold. First, heterogeneous and multi-type data are usually recorded to Electronic Health Records (EHRs) during the course of admissions, which makes it difficult to measure the patient similarity. Second, disease progression manifests diverse disease states at different times, which brings sequential complexity to dynamically retrieve similar patients' sequences.

MATERIALS AND METHODS

To overcome the above-mentioned challenges, we propose a novel dynamic patient similarity analysis model based on deep learning. Specifically, the proposed model embeds the multi-type and heterogeneous data into hidden representations with a specially designed embedding and attention module. Thereafter, the proposed model retrieves similar patients' sequences based on these hidden representations in a dynamic manner. More importantly, we adopt two clinical tasks, i.e., diagnosis prediction and medication recommendation, to validate the effectiveness of the proposed model. It is worth noticing that the proposed model integrates a drug-drug interaction (DDI) knowledge graph in the medication recommendation task to reduce adverse reactions caused by combinational treatments, such that a more rational strategy can be realized. We evaluate our proposed model using the critical care database MIMIC-III, which includes 5,430 patients covering 14,096 clinical visits.

RESULTS

The proposed model outperforms several state-of-the-art methods. For diagnosis prediction, the average PR-AUC score of the proposed model reaches 0.6200, which is significantly higher than that of the baseline models (0.2497∼0.5407). Meanwhile, for medication recommendation, the average PR-AUC of the proposed model is 0.6682 (Jaccard: 0.4070; F1: 0.5672; Recall: 0.7832) whereas the K-nearest model can only reach 0.3805 (Jaccard: 0.3911; F1: 0.5465; Recall: 0.5705). In addition, our proposed model achieves a lower DDI rate.

CONCLUSION

We propose a novel dynamic patient similarity analysis model, which can be implemented into a decision support system for clinical tasks including diagnosis prediction, surgical procedure selection, medication recommendation, etc. Also, the proposed model serves as an explainable protocol in clinical practice thanks to its analogy to real clinical reasoning where a doctor diagnoses diseases and prescribes medications according to the previous cured patients empirically.

Predictive value of neutrophil-to-lymphocyte ratio for the fatality of COVID-19 patients complicated with cardiovascular diseases and/or risk factors

Previous studies have reported that a high neutrophil-to-lymphocyte ratio (NLR) is associated with disease severity and poor prognosis in COVID-19 patients. We aimed to investigate the clinical implications of NLR in patients with COVID-19 complicated with cardiovascular diseases and/or its risk factors (CVDRF). In total, 601 patients with known NLR values were selected from the CLAVIS-COVID registry for analysis. Patients were categorized into quartiles (Q1, Q2, Q3, and Q4) according to baseline NLR values, and demographic and clinical parameters were compared between the groups. Survival analysis was conducted using the Kaplan-Meier method. The diagnostic performance of the baseline and follow-up NLR values was tested using receiver operating characteristic (ROC) curve analysis. Finally, two-dimensional mapping of patient characteristics was conducted using t-stochastic neighborhood embedding (t-SNE). In-hospital mortality significantly increased with an increase in the baseline NLR quartile (Q1 6.3%, Q2 11.0%, Q3 20.5%; and Q4, 26.6%; p < 0.001). The cumulative mortality increased as the quartile of the baseline NLR increased. The paired log-rank test revealed significant differences in survival for Q1 vs. Q3 (p = 0.017), Q1 vs. Q4 (p < 0.001), Q2 vs. Q3 (p = 0.034), and Q2 vs. Q4 (p < 0.001). However, baseline NLR was not identified as an independent prognostic factor using a multivariate Cox proportional hazards regression model. The area under the curve for predicting in-hospital death based on baseline NLR was only 0.682, whereas that of follow-up NLR was 0.893. The two-dimensional patient map with t-SNE showed a cluster characterized by high mortality with high NLR at follow-up, but these did not necessarily overlap with the population with high NLR at baseline. NLR may have prognostic implications in hospitalized COVID-19 patients with CVDRF, but its significance depends on the timing of data collection.