Benchmarking LLMs for Predictive Applications in the Intensive Care Units

• URL: http://arxiv.org/abs/2512.20520v1
• Date: Tue, 23 Dec 2025 17:08:31 GMT
• Title: Benchmarking LLMs for Predictive Applications in the Intensive Care Units
• Authors: Chehak Malhotra, Mehak Gopal, Akshaya Devadiga, Pradeep Singh, Ridam Pal, Ritwik Kashyap, Tavpritesh Sethi,
• Abstract summary: This study compares large language models, including GatorTron-Base (trained on clinical data), Llama 8B, and Mistral 7B, against models like BioBERT, DocBERT, BioClinicalBERT, Word2Vec, and Doc2Vec.<n>To achieve meaningful clinical outcomes, future efforts in training LLMs should prioritize developing models capable of predicting clinical trajectories.
• Score: 2.301368952468297
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the advent of LLMs, various tasks across the natural language processing domain have been transformed. However, their application in predictive tasks remains less researched. This study compares large language models, including GatorTron-Base (trained on clinical data), Llama 8B, and Mistral 7B, against models like BioBERT, DocBERT, BioClinicalBERT, Word2Vec, and Doc2Vec, setting benchmarks for predicting Shock in critically ill patients. Timely prediction of shock can enable early interventions, thus improving patient outcomes. Text data from 17,294 ICU stays of patients in the MIMIC III database were scored for length of stay > 24 hours and shock index (SI) > 0.7 to yield 355 and 87 patients with normal and abnormal SI-index, respectively. Both focal and cross-entropy losses were used during finetuning to address class imbalances. Our findings indicate that while GatorTron Base achieved the highest weighted recall of 80.5%, the overall performance metrics were comparable between SLMs and LLMs. This suggests that LLMs are not inherently superior to SLMs in predicting future clinical events despite their strong performance on text-based tasks. To achieve meaningful clinical outcomes, future efforts in training LLMs should prioritize developing models capable of predicting clinical trajectories rather than focusing on simpler tasks such as named entity recognition or phenotyping.

Related papers

• LiveClin: A Live Clinical Benchmark without Leakage [50.45415584327275]
  LiveClin is a live benchmark designed for approximating real-world clinical practice.<n>We transform authentic patient cases into complex, multimodal evaluation scenarios that span the entire clinical pathway.<n>Our evaluation of 26 models on LiveClin reveals the profound difficulty of these real-world scenarios, with the top-performing model achieving a Case Accuracy of just 35.7%.
  arXiv  Detail & Related papers  (2026-02-18T03:59:46Z)
• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Learning temporal embeddings from electronic health records of chronic kidney disease patients [5.2561388030590965]
  We investigate whether temporal embedding models trained on longitudinal electronic health records can learn clinically meaningful representations without compromising predictive performance.<n>We compare three recurrent architectures: a vanilla LSTM, an attention-augmented LSTM, and a time-aware LSTM.<n>The T-LSTM produces more structured embeddings, achieving a lower Davies-Bouldin Index (DBI = 9.91) and higher CKD stage classification accuracy (0.74) than the vanilla LSTM.<n>For in-ICU mortality prediction, embedding models consistently outperform end-to-end predictors, improving accuracy from 0.72-0.75 to 0.82-
  arXiv  Detail & Related papers  (2026-01-26T16:50:50Z)
• COPE: Chain-Of-Thought Prediction Engine for Open-Source Large Language Model Based Stroke Outcome Prediction from Clinical Notes [23.044580867637105]
  Chain-of-Thought (CoT) Outcome Prediction Engine (COPE) is a reasoning-enhanced large language model framework for predicting outcomes from unstructured clinical notes.<n>This study included 464 acute ischemic stroke (AIS) patients with discharge summaries and 90-day modified Rankin Scale (mRS) scores.<n>COPE achieved an MAE of 1.01 ( 95% CI 0.92-1.11), +/-1 accuracy of 74.4% (69.9, 78.8%), and exact accuracy of 32.8% (28.0, 37.6%).
  arXiv  Detail & Related papers  (2025-12-02T07:44:20Z)
• OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction [2.904892426557913]
  Large language models (LLMs) have shown strong performance in biomedical NLP.<n>We present a unified, multi-task learning framework that aligns autoregressive LLMs with clinical reasoning for outcome prediction.<n>Our findings underscore the importance of reasoning-aware alignment in multi-task clinical modeling.
  arXiv  Detail & Related papers  (2025-10-20T13:35:12Z)
• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [49.1574468325115]
  This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset.<n>The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer)
  arXiv  Detail & Related papers  (2025-05-23T14:06:42Z)
• Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling [2.466324275447403]
  Emergency department (ED) returns for mental health conditions pose a major healthcare burden, with 24-27% of patients returning within 30 days.<n>To assess whether integrating large language models (LLMs) with machine learning improves predictive accuracy and clinical interpretability of ED mental health return risk models.
  arXiv  Detail & Related papers  (2025-01-21T15:41:20Z)
• AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling [53.54623137152208]
  We introduce AutoElicit to extract knowledge from large language models and construct priors for predictive models.<n>We show these priors are informative and can be refined using natural language.<n>We find that AutoElicit yields priors that can substantially reduce error over uninformative priors, using fewer labels, and consistently outperform in-context learning.
  arXiv  Detail & Related papers  (2024-11-26T10:13:39Z)
• Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions [7.002143951776267]
  This research aims to develop a lifestyle intervention system, called MoveSense, that forecasts a patient's activity behavior. We conduct two clinical studies involving 58 prediabetic veterans and 60 patients with obstructive sleep apnea.
  arXiv  Detail & Related papers  (2024-10-12T20:44:00Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)
• Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching [49.78442796596806]
  We propose an innovative privacy-aware data augmentation approach for patient-trial matching (LLM-PTM) Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%.
  arXiv  Detail & Related papers  (2023-03-24T03:14:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.