Aug 2026· IEEE journal of biomedical and health informatics· Vol PP· 0 citations
Medicine
TL;DR
Experimental results show that the proposed GuardMLLM improves performance on tasks such as predicting patient mortality and ICU length of stay, and effectively alleviates overconfidence in LLM.
Abstract
Early outcome prediction for intensive care unit (ICU) patients using multimodal electronic health records (EHRs) is crucial for timely intervention and resource allocation. Recent methods for clinical reasoning on EHRs using large language models (LLMs), which involve textualizing structured data and concatenating it with unstructured data for reasoning. However, these methods lose information about numerical trends because they convert structured data into static text. Furthermore, LLMs often exhibit overconfidence, producing highly certain but unreliable predictions. To address these issues, we propose GuardMLLM, a dynamic fusion framework that perceives overconfidence for multi-tasking early ICU outcome prediction.Specifically, GuardMLLM learns complex temporal relationships from structured data through temporal modeling and aggregation. Simultaneously, it transforms structured data into clinical narratives containing trend information and combines this with unstructured data. Task prediction is then performed using an LLM clinical inference engine. Furthermore, we designed a multi-indicator overconfidence detector and applied temperature calibration to quantify and correct unreliable LLM confidence. An adaptive, gated dynamic fusion module balances temporal representations and LLM-derived inference features to suppress LLM overconfidence.We verify our method on two large public medical datasets, Medical Information Mart for Intensive Care and Collaborative Research Database. Experimental results show that our method improves performance on tasks such as predicting patient mortality and ICU length of stay, and effectively alleviates overconfidence in LLM.
Electronic health record (EHR) data are inherently multimodal, and leveraging multiple modalities can improve predictive performance. However, most existing approaches rely on deep fusion, which obscures how individual modalities contribute to predictions and limits the interpretability of multimodal reasoning. We propose an explicit multimodal routing framework for clinical prediction that enables interpretable, robust, and auditable reasoning across three EHR modalities: structured longitudinal variables (L), clinical notes (N), and chest X-rays (I). Our model constructs discrete unimodal, directional bimodal, and trimodal routes to capture both individual modality signals and asymmetric cross-modal interactions. To audit multimodal reasoning and assess robustness, we introduce inference-time route masking, which simulates missing modalities and reweights the remaining routes without retraining. We analyze changes in performance and routing weights under these scenarios to understand model decision-making. We evaluate our framework on multi-label phenotype prediction (K = 25) and binary ICU mortality prediction using trimodal patient stays from MIMIC-IV, revealing systematic differences in modality reliance across clinical condition groups. Overall, our framework offers a transparent, auditable, and practical approach to multimodal clinical prediction, providing interpretability, robustness, and insights into how different data sources drive model decisions.
Nikkie Hooman, Zhongjie Wu, Eric C. Larson et al.· 0 citations
Clinical decisions, such as diagnosing conditions, prescribing medications, and recommending procedures, are rarely made with absolute certainty. Instead, they reflect probabilistic judgments shaped by evolving patient information and incomplete evidence. However, current EHR systems and knowledge graphs encode such decisions as deterministic triples, lacking a mechanism to represent the subjective confidence inherent in clinical reasoning. We present JudgEHR, a framework for clinical decision confidence estimation that leverages large language models (LLMs) to perform cohort-based collective inference over structured patient records by representing clinical events as knowledge graph triples and integrating them into LLM prompts. JudgEHR groups related clinical concepts into cohorts using LLM-driven relational inference, and then jointly evaluates the plausibility of all clinical decision triples within each cohort by considering patient visit history and background medical knowledge. We apply our method to the MIMIC-III dataset. Our statistical analysis shows that JudgEHR generates semantically consistent confidence scores, with similar concepts receiving closer values, whereas dissimilar replacements yield large confidence differences. Experiments on the MIMIC-III dataset show that incorporating the confidence into a zero-shot LLM-based pipeline improves relative AUROC by ${1 4. 6 \%}$ and AUPRC by 21.8% on the mortality prediction task.
Kexuan Xin, Guillaume Pelat, Jonathan Vitale et al.· International Conference on...· 0 citations
BERT-LER is presented, a BERT-style model for coded EHR timelines pretrained and fine-tuned from a de-identified EHR dataset of 75 million patients, that encodes laboratory test results as discrete tokens while retaining graded information through percentile-based binning, paired with Integrated Gradients for token-level attributions grounded in the input EHR sequence.
Jun Ni Du, Lukas Adamek, Maxim A Kryukov et al.· 0 citations
Artificial intelligence (AI) systems for intensive care units (ICUs) must support early risk prediction while producing explanations that clinicians can inspect, question, and relate to physiological reasoning. Deep neural networks (DNNs) can learn complex temporal patterns from electronic health records (EHRs), but their internal representations are often difficult to translate into clinically actionable explanations. Gradient-boosted decision trees (GBDTs) offer more transparent decision rules, yet they may not capture the full temporal and nonlinear structure of high-dimensional ICU data. This paper presents a causal-pathway-guided DNN–GBDT distillation framework for interpretable ICU decision support. The framework first estimates a directed acyclic graph (DAG), denoted by G, from multivariate ICU time-series data and then uses the graph to guide representation learning in a DNN teacher model through causal gating. The learned teacher is distilled into a GBDT student model using soft predictive targets and a causal attribution-guided split-selection procedure, so that the final model approximates the teacher predictions while prioritizing tree splits aligned with plausible physiological pathways. Experiments using Medical Information Mart for Intensive Care IV (MIMIC-IV) data evaluate sepsis onset and in-hospital mortality prediction through discrimination, precision–recall performance, calibration-oriented reporting, causal consistency, and clinical utility indicators. The proposed causal-aware distilled GBDT achieves stronger predictive performance than conventional interpretable baselines and substantially higher causal consistency than black-box temporal models. The results suggest that causal structure can serve as an inductive bias for converting complex temporal prediction into interpretable rule-based clinical reasoning. The paper also discusses limitations related to observational causal discovery, unmeasured confounding, temporal stationarity, and clinical deployment, following recent reporting expectations for AI-based clinical prediction models.
An evaluation framework based on the MedMCQA dataset consisting of two complementary uncertainty settings is proposed, which introduces linguistic uncertainty cues through prompt modifications to simulate ambiguous clinical contexts and observes significant variation across models in their ability to abstain when the correct answer is unavailable.
Maryam Tahermazandarani, Adnan Mahmood, Fahmida Islam et al.· International Conference on...· 0 citations
A hybrid framework for a comprehensive evaluation of machine learning and transformer-based models for cardiovascular risk prediction by integrating structured clinical data with unstructured clinical narratives is included in this study. The structured data includes demographic and diagnostic variables like patient information and test results, while unstructured data is derived from electronic health records such as clinical notes. Through preprocessing, feature engineering, and semantic embedding using transformer-based models, the system leverages the complementary strengths of both data types. By analysing and processing this unstructured information, this project aims to improve the predictions for heart disease. The results show that it is feasible to make better predictions and gain valuable insights by merging these two types of data. Such analysis is essential because structured data alone often overlooks fine-grained clinical indicators found in narrative texts. Integrating unstructured data allows for a more holistic view of patient health, leading to earlier detection, personalized interventions, and improved decision-making in clinical settings.