Design and Evaluation of a CDSS for Drug Allergy Management Using LLMs and Pharmaceutical Data Integration

• URL: http://arxiv.org/abs/2409.16395v1
• Date: Tue, 24 Sep 2024 18:55:10 GMT
• Title: Design and Evaluation of a CDSS for Drug Allergy Management Using LLMs and Pharmaceutical Data Integration
• Authors: Gabriele De Vito, Filomena Ferrucci, Athanasios Angelakis,
• Abstract summary: Heliot is an innovative CDSS for drug allergy management. It integrates Large Language Models (LLMs) with a comprehensive pharmaceutical data repository. Heliot's high accuracy, precision, recall, and F1 score, uniformly reaching 100% across multiple experimental runs.
• Score: 3.2627279988912194
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Medication errors significantly threaten patient safety, leading to adverse drug events and substantial economic burdens on healthcare systems. Clinical Decision Support Systems (CDSSs) aimed at mitigating these errors often face limitations, including reliance on static databases and rule-based algorithms, which can result in high false alert rates and alert fatigue among clinicians. This paper introduces HELIOT, an innovative CDSS for drug allergy management, integrating Large Language Models (LLMs) with a comprehensive pharmaceutical data repository. HELIOT leverages advanced natural language processing capabilities to interpret complex medical texts and synthesize unstructured data, overcoming the limitations of traditional CDSSs. An empirical evaluation using a synthetic patient dataset and expert-verified ground truth demonstrates HELIOT's high accuracy, precision, recall, and F1 score, uniformly reaching 100\% across multiple experimental runs. The results underscore HELIOT's potential to enhance decision support in clinical settings, offering a scalable, efficient, and reliable solution for managing drug allergies.

Related papers

• Addressing Overprescribing Challenges: Fine-Tuning Large Language Models for Medication Recommendation Tasks [46.95099594570405]
  Medication recommendation systems have garnered attention within healthcare for their potential to deliver personalized and efficacious drug combinations based on patient's clinical data. Existing methodologies encounter challenges in adapting to diverse Electronic Health Records (EHR) systems. We propose Language-Assisted Medication Recommendation (LAMO), which employs a parameter-efficient fine-tuning approach to tailor open-source LLMs for optimal performance in medication recommendation scenarios.
  arXiv  Detail & Related papers  (2025-03-05T17:28:16Z)
• Medical Hallucinations in Foundation Models and Their Impact on Healthcare [53.97060824532454]
  Foundation Models that are capable of processing and generating multi-modal data have transformed AI's role in medicine. We define medical hallucination as any instance in which a model generates misleading medical content. Our results reveal that inference techniques such as Chain-of-Thought (CoT) and Search Augmented Generation can effectively reduce hallucination rates. These findings underscore the ethical and practical imperative for robust detection and mitigation strategies.
  arXiv  Detail & Related papers  (2025-02-26T02:30:44Z)
• VeriFact: Verifying Facts in LLM-Generated Clinical Text with Electronic Health Records [2.8078482678056527]
  VeriFact is an artificial intelligence system for fact-checking large language models (LLM) in clinical medicine. It decomposes Brief Hospital Course narratives into simple statements with clinician annotations for whether each statement is supported by the patient's EHR clinical notes. It achieves up to 92.7% agreement when compared to a denoised and adjudicated average human clinican ground truth.
  arXiv  Detail & Related papers  (2025-01-28T03:13:16Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning. Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow [33.8495939261319]
  We develop an advanced simulated patient system with AIPatient Knowledge Graph (AIPatient KG) as the input and Reasoning Retrieval-Augmented Generation (Reasoning RAG) as the generation backbone. Reasoning RAG leverages six LLM powered agents spanning tasks including retrieval, KG query generation, abstraction, checker, rewrite, and summarization. Our system also presents high readability (median Flesch Reading Ease 77.23; median Flesch Kincaid Grade 5.6), robustness (ANOVA F-value 0.6126, p>0.1), and stability (ANOVA F-value 0.782, p>0.1)
  arXiv  Detail & Related papers  (2024-09-27T17:17:15Z)
• TCKAN:A Novel Integrated Network Model for Predicting Mortality Risk in Sepsis Patients [0.0]
  Sepsis poses a major global health threat, accounting for millions of deaths annually and significant economic costs. Current methods typically utilize only one type of data--either constant, temporal, or ICD codes. Time-Constant Kolmogorov-Arnold Network (TCKAN) uniquely integrates temporal data, constant data, and ICD codes within a single predictive model.
  arXiv  Detail & Related papers  (2024-07-09T05:37:50Z)
• The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem [0.6965384453064829]
  Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, deployments in high-risk and safety-critical domains pose unique challenges, notably the issue of hallucinations. This is particularly concerning in settings such as drug safety, where inaccuracies could lead to patient harm. We have developed and demonstrated a proof of concept suite of guardrails specifically designed to mitigate certain types of hallucinations and errors for drug safety.
  arXiv  Detail & Related papers  (2024-07-01T19:52:41Z)
• TrialBench: Multi-Modal Artificial Intelligence-Ready Clinical Trial Datasets [57.067409211231244]
  This paper presents meticulously curated AIready datasets covering multi-modal data (e.g., drug molecule, disease code, text, categorical/numerical features) and 8 crucial prediction challenges in clinical trial design. We provide basic validation methods for each task to ensure the datasets' usability and reliability. We anticipate that the availability of such open-access datasets will catalyze the development of advanced AI approaches for clinical trial design.
  arXiv  Detail & Related papers  (2024-06-30T09:13:10Z)
• Mixed-Integer Projections for Automated Data Correction of EMRs Improve Predictions of Sepsis among Hospitalized Patients [7.639610349097473]
  We introduce an innovative projections-based method that seamlessly integrates clinical expertise as domain constraints. We measure the distance of corrected data from the constraints defining a healthy range of patient data, resulting in a unique predictive metric we term as "trust-scores" We show an AUROC of 0.865 and a precision of 0.922, that surpasses conventional ML models without such projections.
  arXiv  Detail & Related papers  (2023-08-21T15:14:49Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• 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)
• SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization [50.01382938451978]
  We introduce a model-agnostic pipeline that employs soft prompts to diminish variance while preserving the advantages of prompt-based summarization. Experimental findings indicate that our method not only bolsters performance but also effectively curbs variance for various language models.
  arXiv  Detail & Related papers  (2023-03-23T04:47:46Z)
• Classifying Cyber-Risky Clinical Notes by Employing Natural Language Processing [9.77063694539068]
  Recently, some states within the United States of America require patients to have open access to their clinical notes. This research investigates methods for identifying security/privacy risks within clinical notes.
  arXiv  Detail & Related papers  (2022-03-24T00:36:59Z)
• Transformer-based unsupervised patient representation learning based on medical claims for risk stratification and analysis [3.5492837081144204]
  Transformer-based Multimodal AutoEncoder (TMAE) can learn efficient patient representation by encoding meaningful information from the claims data. We trained TMAE using a real-world pediatric claims dataset containing more than 600,000 patients.
  arXiv  Detail & Related papers  (2021-06-23T21:29:50Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups [84.63561578944183]
  This paper proposes a novel Bayesian design, SDF-Bayes, for finding the maximum tolerated dose (MTD) of a drug in a clinical trial. Rather than the conventional principle of escalating or de-escalating the current dose of one drug, SDF-Bayes proceeds by cautious optimism. Extensive experiments based on both synthetic and real-world datasets demonstrate the advantages of SDF-Bayes over state of the art DC trial designs.
  arXiv  Detail & Related papers  (2021-01-26T18:59:26Z)
• EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoders [34.22731849545798]
  We propose EHR Variational Autoencoder (EVA) for synthesizing sequences of discrete EHR encounters and encounter features. We illustrate that EVA can produce realistic sequences, account for individual differences among patients, and can be conditioned on specific disease conditions. We assess the utility of the methods on large real-world EHR repositories containing over 250, 000 patients.
  arXiv  Detail & Related papers  (2020-12-18T02:37:49Z)
• Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints [84.09488581365484]
  Phase I dose-finding trials are increasingly challenging as the relationship between efficacy and toxicity of new compounds becomes more complex. Most commonly used methods in practice focus on identifying a Maximum Tolerated Dose (MTD) by learning only from toxicity events. We present a novel adaptive clinical trial methodology that aims at maximizing the cumulative efficacies while satisfying the toxicity safety constraint with high probability.
  arXiv  Detail & Related papers  (2020-06-09T03:06:45Z)

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.