Search

Background: Artificial intelligence (AI) and large language models (LLMs) can play a critical role in emergency room operations by augmenting decision-making about patient admission. However, there are no studies for LLMs using real-world data and scenarios, in comparison to and being informed by traditional supervised machine learning (ML) models. We evaluated the performance of GPT-4 for predicting patient admissions from emergency department (ED) visits. We compared performance to traditional ML models both naively and when informed by few-shot examples and/or numerical probabilities., Methods: We conducted a retrospective study using electronic health records across 7 NYC hospitals. We trained Bio-Clinical-BERT and XGBoost (XGB) models on unstructured and structured data, respectively, and created an ensemble model reflecting ML performance. We then assessed GPT-4 capabilities in many scenarios: through Zero-shot, Few-shot with and without retrieval-augmented generation (RAG), and with and without ML numerical probabilities., Results: The Ensemble ML model achieved an area under the receiver operating characteristic curve (AUC) of 0.88, an area under the precision-recall curve (AUPRC) of 0.72 and an accuracy of 82.9%. The naïve GPT-4's performance (0.79 AUC, 0.48 AUPRC, and 77.5% accuracy) showed substantial improvement when given limited, relevant data to learn from (ie, RAG) and underlying ML probabilities (0.87 AUC, 0.71 AUPRC, and 83.1% accuracy). Interestingly, RAG alone boosted performance to near peak levels (0.82 AUC, 0.56 AUPRC, and 81.3% accuracy)., Conclusions: The naïve LLM had limited performance but showed significant improvement in predicting ED admissions when supplemented with real-world examples to learn from, particularly through RAG, and/or numerical probabilities from traditional ML models. Its peak performance, although slightly lower than the pure ML model, is noteworthy given its potential for providing reasoning behind predictions. Further refinement of LLMs with real-world data is necessary for successful integration as decision-support tools in care settings., (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Background: Predicting hospitalization from nurse triage notes has the potential to augment care. However, there needs to be careful considerations for which models to choose for this goal. Specifically, health systems will have varying degrees of computational infrastructure available and budget constraints., Objective: To this end, we compared the performance of the deep learning, Bidirectional Encoder Representations from Transformers (BERT)-based model, Bio-Clinical-BERT, with a bag-of-words (BOW) logistic regression (LR) model incorporating term frequency-inverse document frequency (TF-IDF). These choices represent different levels of computational requirements., Methods: A retrospective analysis was conducted using data from 1,391,988 patients who visited emergency departments in the Mount Sinai Health System spanning from 2017 to 2022. The models were trained on 4 hospitals' data and externally validated on a fifth hospital's data., Results: The Bio-Clinical-BERT model achieved higher areas under the receiver operating characteristic curve (0.82, 0.84, and 0.85) compared to the BOW-LR-TF-IDF model (0.81, 0.83, and 0.84) across training sets of 10,000; 100,000; and ~1,000,000 patients, respectively. Notably, both models proved effective at using triage notes for prediction, despite the modest performance gap., Conclusions: Our findings suggest that simpler machine learning models such as BOW-LR-TF-IDF could serve adequately in resource-limited settings. Given the potential implications for patient care and hospital resource management, further exploration of alternative models and techniques is warranted to enhance predictive performance in this critical domain., International Registered Report Identifier (irrid): RR2-10.1101/2023.08.07.23293699., (©Dhavalkumar Patel, Prem Timsina, Larisa Gorenstein, Benjamin S Glicksberg, Ganesh Raut, Satya Narayan Cheetirala, Fabio Santana, Jules Tamegue, Arash Kia, Eyal Zimlichman, Matthew A Levin, Robert Freeman, Eyal Klang. Originally published in JMIR AI (https://ai.jmir.org), 27.08.2024.)

This study was designed to assess how different prompt engineering techniques, specifically direct prompts, Chain of Thought (CoT), and a modified CoT approach, influence the ability of GPT-3.5 to answer clinical and calculation-based medical questions, particularly those styled like the USMLE Step 1 exams. To achieve this, we analyzed the responses of GPT-3.5 to two distinct sets of questions: a batch of 1000 questions generated by GPT-4, and another set comprising 95 real USMLE Step 1 questions. These questions spanned a range of medical calculations and clinical scenarios across various fields and difficulty levels. Our analysis revealed that there were no significant differences in the accuracy of GPT-3.5's responses when using direct prompts, CoT, or modified CoT methods. For instance, in the USMLE sample, the success rates were 61.7% for direct prompts, 62.8% for CoT, and 57.4% for modified CoT, with a p-value of 0.734. Similar trends were observed in the responses to GPT-4 generated questions, both clinical and calculation-based, with p-values above 0.05 indicating no significant difference between the prompt types. The conclusion drawn from this study is that the use of CoT prompt engineering does not significantly alter GPT-3.5's effectiveness in handling medical calculations or clinical scenario questions styled like those in USMLE exams. This finding is crucial as it suggests that performance of ChatGPT remains consistent regardless of whether a CoT technique is used instead of direct prompts. This consistency could be instrumental in simplifying the integration of AI tools like ChatGPT into medical education, enabling healthcare professionals to utilize these tools with ease, without the necessity for complex prompt engineering., (© 2024. The Author(s).)

The decision to extubate patients on invasive mechanical ventilation is critical; however, clinician performance in identifying patients to liberate from the ventilator is poor. Machine Learning-based predictors using tabular data have been developed; however, these fail to capture the wide spectrum of data available. Here, we develop and validate a deep learning-based model using routinely collected chest X-rays to predict the outcome of attempted extubation. We included 2288 serial patients admitted to the Medical ICU at an urban academic medical center, who underwent invasive mechanical ventilation, with at least one intubated CXR, and a documented extubation attempt. The last CXR before extubation for each patient was taken and split 79/21 for training/testing sets, then transfer learning with k-fold cross-validation was used on a pre-trained ResNet50 deep learning architecture. The top three models were ensembled to form a final classifier. The Grad-CAM technique was used to visualize image regions driving predictions. The model achieved an AUC of 0.66, AUPRC of 0.94, sensitivity of 0.62, and specificity of 0.60. The model performance was improved compared to the Rapid Shallow Breathing Index (AUC 0.61) and the only identified previous study in this domain (AUC 0.55), but significant room for improvement and experimentation remains.

Background and Aim: We analyzed an inclusive gradient boosting model to predict hospital admission from the emergency department (ED) at different time points. We compared its results to multiple models built exclusively at each time point., Methods: This retrospective multisite study utilized ED data from the Mount Sinai Health System, NY, during 2015-2019. Data included tabular clinical features and free-text triage notes represented using bag-of-words. A full gradient boosting model, trained on data available at different time points (30, 60, 90, 120, and 150 min), was compared to single models trained exclusively at data available at each time point. This was conducted by concatenating the rows of data available at each time point to one data matrix for the full model, where each row is considered a separate case., Results: The cohort included 1,043,345 ED visits. The full model showed comparable results to the single models at all time points (AUCs 0.84-0.88 for different time points for both the full and single models)., Conclusion: A full model trained on data concatenated from different time points showed similar results to single models trained at each time point. An ML-based prediction model can use used for identifying hospital admission.