arXiv:2511.14064v1 Announce Type: new 
Abstract: Medication recommendation systems play a crucial role in assisting clinicians with personalized treatment decisions. While existing approaches have made significant progress in learning medication representations, they suffer from two fundamental limitations: (i) treating medical entities as independent features without modeling their synergistic effects on medication selection; (ii) employing static causal relationships that fail to adapt to patient-specific contexts and health states. To address these challenges, we propose CafeMed, a framework that integrates dynamic causal reasoning with cross-modal attention for safe and accurate medication recommendation. CafeMed introduces two key components: the Causal Weight Generator (CWG) that transforms static causal effects into dynamic modulation weights based on individual patient states, and the Channel Harmonized Attention Refinement Module (CHARM) that captures complex interdependencies between diagnoses and procedures. This design enables CafeMed to model how different medical conditions jointly influence treatment decisions while maintaining medication safety constraints. Extensive experiments on MIMIC-III and MIMIC-IV datasets demonstrate that CafeMed significantly outperforms state-of-the-art baselines, achieving superior accuracy in medication prediction while maintaining the lower drug--drug interaction rates. Our results indicate that incorporating dynamic causal relationships and cross-modal synergies leads to more clinically-aligned and personalized medication recommendations. Our code is released publicly at https://github.com/rkl71/CafeMed.

كافيميد هو إطار جديد مصمم لتحسين أنظمة توصية الأدوية من خلال دمج التفكير السببي الديناميكي مع الانتباه متعدد الوسائط. غالبًا ما تعالج الأنظمة التقليدية الكيانات الطبية كميزات مستقلة، متجاهلة آثارها التآزرية على اختيار الأدوية. بالإضافة إلى ذلك، تعتمد على علاقات سببية ثابتة لا تتكيف مع السياقات الفردية للمرضى. يعالج كافيميد هذه القيود من خلال مولد الوزن السببي، الذي ينشئ أوزان تعديل ديناميكية بناءً على حالات المرضى، ووحدة تحسين الانتباه المتناغم عبر القنوات، التي تلتقط التداخلات المعقدة بين الكيانات الطبية.

CafeMed es un nuevo marco diseñado para mejorar los sistemas de recomendación de medicamentos al integrar el razonamiento causal dinámico con la atención multimodal. Los sistemas tradicionales a menudo tratan las entidades médicas como características independientes, ignorando sus efectos sinérgicos en la selección de medicamentos. Además, dependen de relaciones causales estáticas que no se adaptan a los contextos individuales de los pacientes. CafeMed aborda estas limitaciones a través de su Generador de Peso Causal, que crea pesos de modulación dinámicos basados en los estados de los pacient…

CafeMed est un nouveau cadre conçu pour améliorer les systèmes de recommandation de médicaments en intégrant un raisonnement causal dynamique avec une attention multimodale. Les systèmes traditionnels traitent souvent les entités médicales comme des caractéristiques indépendantes, négligeant leurs effets synergiques sur la sélection des médicaments. De plus, ils s'appuient sur des relations causales statiques qui ne s'adaptent pas aux contextes individuels des patients. CafeMed répond à ces limitations grâce à son générateur de poids causaux, qui crée des poids de modulation dynamiques basés s…

CafeMed is a new framework designed to enhance medication recommendation systems by integrating dynamic causal reasoning with cross-modal attention. Traditional systems often treat medical entities as independent features, neglecting their synergistic effects on medication selection. Additionally, they rely on static causal relationships that do not adapt to individual patient contexts. CafeMed addresses these limitations through its Causal Weight Generator, which creates dynamic modulation weights based on patient states, and the Channel Harmonized Attention Refinement Module, which captures …

CafeMed: Causal Attention Fusion Enhanced Medication Recommendation

arXiv:2512.08012v1 Announce Type: new 
Abstract: In critical care settings such as the Intensive Care Unit, clinicians face the complex challenge of balancing conflicting objectives, primarily maximizing patient survival while minimizing resource utilization (e.g., length of stay). Single-objective Reinforcement Learning approaches typically address this by optimizing a fixed scalarized reward function, resulting in rigid policies that fail to adapt to varying clinical priorities. Multi-objective Reinforcement Learning (MORL) offers a solution by learning a set of optimal policies along the Pareto Frontier, allowing for dynamic preference selection at test time. However, applying MORL in healthcare necessitates strict offline learning from historical data.
  In this paper, we benchmark three offline MORL algorithms, Conditioned Conservative Pareto Q-Learning (CPQL), Adaptive CPQL, and a modified Pareto Efficient Decision Agent (PEDA) Decision Transformer (PEDA DT), against three scalarized single-objective baselines (BC, CQL, and DDQN) on the MIMIC-IV dataset. Using Off-Policy Evaluation (OPE) metrics, we demonstrate that PEDA DT algorithm offers superior flexibility compared to static scalarized baselines. Notably, our results extend previous findings on single-objective Decision Transformers in healthcare, confirming that sequence modeling architectures remain robust and effective when scaled to multi-objective conditioned generation. These findings suggest that offline MORL is a promising framework for enabling personalized, adjustable decision-making in critical care without the need for retraining.

دراسة حديثة تقيم ثلاثة خوارزميات للتعلم المعزز متعدد الأهداف (MORL) خارج الخط: Conditioned Conservative Pareto Q-Learning وAdaptive CPQL ووكيل القرار Pareto الفعال المعدل، في بيئات الرعاية الحرجة، وخاصة في وحدة العناية المركزة. تهدف هذه الأبحاث إلى معالجة تعقيدات تحقيق التوازن بين بقاء المرضى واستخدام الموارد من خلال التكيف الديناميكي للسياسات بناءً على البيانات التاريخية.

Un estudio reciente evalúa tres algoritmos de Aprendizaje por Refuerzo Multi-Objetivo (MORL) fuera de línea: Conditioned Conservative Pareto Q-Learning, Adaptive CPQL y un Agente de Decisión Pareto Eficiente modificado, en entornos de cuidados críticos, especialmente en la Unidad de Cuidados Intensivos. Esta investigación busca abordar las complejidades de equilibrar la supervivencia del paciente con la utilización de recursos mediante la adaptación dinámica de políticas basada en datos históricos.

Une étude récente évalue trois algorithmes de renforcement multi-objectifs hors ligne (MORL) : Conditioned Conservative Pareto Q-Learning, Adaptive CPQL et un agent de décision modifié Pareto Efficient Decision Transformer, dans des contextes de soins critiques, notamment l'unité de soins intensifs. Cette recherche vise à résoudre les complexités de l'équilibre entre la survie des patients et l'utilisation des ressources grâce à une adaptation dynamique des politiques basée sur des données historiques.

A recent study benchmarks three offline Multi-Objective Reinforcement Learning (MORL) algorithms—Conditioned Conservative Pareto Q-Learning, Adaptive CPQL, and a modified Pareto Efficient Decision Agent Decision Transformer—in critical care settings, particularly the Intensive Care Unit. This research aims to address the complexities of balancing patient survival with resource utilization through dynamic policy adaptation based on historical data.

Benchmarking Offline Multi-Objective Reinforcement Learning in Critical Care

arXiv:2512.07856v1 Announce Type: new 
Abstract: Accurate disease detection is of paramount importance for effective medical treatment and patient care. However, the process of disease detection is often associated with extensive medical testing and considerable costs, making it impractical to perform all possible medical tests on a patient to diagnose or predict hundreds or thousands of diseases. In this work, we propose Collaborative Learning for Disease Detection (CLDD), a novel graph-based deep learning model that formulates disease detection as a collaborative learning task by exploiting associations among diseases and similarities among patients adaptively. CLDD integrates patient-disease interactions and demographic features from electronic health records to detect hundreds or thousands of diseases for every patient, with little to no reliance on the corresponding medical tests. Extensive experiments on a processed version of the MIMIC-IV dataset comprising 61,191 patients and 2,000 diseases demonstrate that CLDD consistently outperforms representative baselines across multiple metrics, achieving a 6.33\% improvement in recall and 7.63\% improvement in precision. Furthermore, case studies on individual patients illustrate that CLDD can successfully recover masked diseases within its top-ranked predictions, demonstrating both interpretability and reliability in disease prediction. By reducing diagnostic costs and improving accessibility, CLDD holds promise for large-scale disease screening and social health security.

تم تقديم نهج جديد يسمى Collaborative Learning for Disease Detection (CLDD)، والذي يستخدم نموذج تعلم عميق قائم على الرسوم البيانية للكشف عن الأمراض دون الحاجة إلى اختبارات طبية موسعة. تستفيد هذه الطريقة من التفاعلات بين المرضى والأمراض والبيانات الديموغرافية من السجلات الصحية الإلكترونية، بهدف تحديد مجموعة واسعة من الأمراض بكفاءة.

Se ha introducido un nuevo enfoque llamado Collaborative Learning for Disease Detection (CLDD), que utiliza un modelo de aprendizaje profundo basado en grafos para detectar enfermedades sin pruebas médicas extensas. Este método aprovecha las interacciones entre pacientes y enfermedades, así como los datos demográficos de los registros de salud electrónicos, con el objetivo de identificar eficientemente una amplia gama de enfermedades.

Une nouvelle approche appelée Collaborative Learning for Disease Detection (CLDD) a été introduite, utilisant un modèle d'apprentissage profond basé sur des graphes pour détecter des maladies sans tests médicaux étendus. Cette méthode exploite les interactions patient-maladie et les données démographiques des dossiers de santé électroniques, visant à identifier efficacement un large éventail de maladies.

A novel approach called Collaborative Learning for Disease Detection (CLDD) has been introduced, utilizing a graph-based deep learning model to detect diseases without extensive medical testing. This method leverages patient-disease interactions and demographic data from electronic health records, aiming to identify a wide range of diseases efficiently.

Medical Test-free Disease Detection Based on Big Data

arXiv:2512.06812v1 Announce Type: new 
Abstract: Discharge Summaries are documents written by medical professionals that detail a patient's visit to a care facility. They contain a wealth of information crucial for patient care, and automating their generation could significantly reduce the effort required from healthcare professionals, minimize errors, and ensure that critical patient information is easily accessible and actionable. In this work, we explore the use of five Large Language Models on this task, from open-source models (Mistral, Llama 2) to proprietary systems (GPT-3, GPT-4, Gemini 1.5 Pro), leveraging MIMIC-III summaries and notes. We evaluate them using exact-match, soft-overlap, and reference-free metrics. Our results show that proprietary models, particularly Gemini with one-shot prompting, outperformed others, producing summaries with the highest similarity to the gold-standard ones. Open-source models, while promising, especially Mistral after fine-tuning, lagged in performance, often struggling with hallucinations and repeated information. Human evaluation by a clinical expert confirmed the practical utility of the summaries generated by proprietary models. Despite the challenges, such as hallucinations and missing information, the findings suggest that LLMs, especially proprietary models, are promising candidates for automatic discharge summary generation as long as data privacy is ensured.

أظهرت الأبحاث الحديثة إمكانية نماذج اللغة الكبيرة (LLMs) في أتمتة إنشاء ملخصات الخروج، وهي مستندات حيوية في رعاية المرضى. قامت الدراسة بتقييم خمسة نماذج، بما في ذلك أنظمة ملكية مثل GPT-4 وGemini 1.5 Pro، ووجدت أن Gemini، خاصة مع التحفيز الأحادي، أنتجت ملخصات كانت الأكثر تشابهًا مع المعايير الذهبية. يمكن أن يؤدي هذا التقدم إلى تقليل عبء العمل على المتخصصين في الرعاية الصحية وتحسين دقة معلومات المرضى.

Investigaciones recientes han demostrado el potencial de los Modelos de Lenguaje de Gran Escala (LLMs) en la automatización de la generación de resúmenes de alta de pacientes, documentos críticos en la atención médica. El estudio evaluó cinco modelos, incluidos sistemas propietarios como GPT-4 y Gemini 1.5 Pro, y encontró que Gemini, especialmente con un solo aviso, producía resúmenes más similares a los estándares de oro. Este avance podría reducir significativamente la carga de trabajo de los profesionales de la salud y mejorar la precisión de la información del paciente.

Des recherches récentes ont démontré le potentiel des modèles de langage de grande taille (LLMs) dans l'automatisation de la génération de résumés de sortie, qui sont des documents critiques dans les soins aux patients. L'étude a évalué cinq modèles, y compris des systèmes propriétaires comme GPT-4 et Gemini 1.5 Pro, et a constaté que Gemini, en particulier avec un prompt unique, produisait des résumés les plus similaires aux normes d'or. Cette avancée pourrait réduire considérablement la charge de travail des professionnels de la santé et améliorer l'exactitude des informations sur les patien…

Recent research has demonstrated the potential of Large Language Models (LLMs) in automating the generation of discharge summaries, which are critical documents in patient care. The study evaluated five models, including proprietary systems like GPT-4 and Gemini 1.5 Pro, and found that Gemini, particularly with one-shot prompting, produced summaries most similar to gold standards. This advancement could significantly reduce the workload of healthcare professionals and enhance the accuracy of patient information.

CafeMed: Causal Attention Fusion Enhanced Medication Recommendation

Was this article worth reading? Share it

LucidQuery AI

Supanote

Twofold Health