The management of complex diseases and patient-centered personalized needs is increasingly demanding. While significant progress has been made in research on single-objective disease management and personalized medicine, there remains a lack of an integrated solution for coordinating multi-objective strategies and dynamically adjusting personalized approaches. This paper introduces a decision support system based on a computer-argumentation engine. This system builds an evidence-based knowledge repository from clinical and rehabilitation guidelines and constructs a patient-centered hierarchical conceptual framework for PROMs to evaluate goal realization benefits. It automates the recommendation of optimal treatments based on the reasoning of conflicts between objectives, incorporating patient preferences and priority of objectives to dynamically adjust daily health management decisions. Through a regular feedback mechanism via PROMs, the system iteratively updates and dynamically adjusts its argumentation based on user states and preferences. A prototype system has been designed and implemented, focusing on multi-objective management for breast cancer patients, to demonstrate the feasibility of this system.

Agents in medical decision support have been extensively researched, particularly in areas like evidence support, multimorbidity management, and patient-specific needs. However, current approaches lack a unified method to address real-time evidence updates, manage multiple diseases independently, and incorporate personalized patient needs. Existing Large Language Model (LLM) agents are limited by their reliance on static knowledge bases, hindering their ability to promptly update clinical guidelines and meet diverse patient requirements. Moreover, the interpretability of LLMs remains a significant concern, leading to skepticism in their medical application. To address these challenges, we developed MedGen, a multi-agent architecture that decomposes the clinical decision-making process into stages such as clinical goal setting, data collection, argumentation linking, and plan selection. This structured approach allows LLM agents to provide both reasoning evidence and a transparent reasoning process, enhancing the reliability and interpretability of outcomes. Finally, a case study of breast cancer and depression is combined to illustrate our architecture.

Clinical decision support is aimed at delivering the best evidence available encapsulated in practice guidelines. The current challenges in reaching this goal include keeping guidelines up-to-date, linking them to address multi-morbidity, and flexible customization to fit patient preferences. Although a variety of solutions have been proposed to address these challenges, a comprehensive approach for their systematic integration remains absent. We propose PICOAS, a knowledge linking model composed of three modes, to establish the relationship between knowledge sources of guidelines, medical literature, and patient reviews. An LLM-Agent architecture is developed, which is capable of understanding and providing decision support informed by the knowledge link model. We demonstrate the feasibility and effectiveness of our approach using a study of breast cancer. An experiment was conducted for evaluating its capabilities in addressing the three challenges.

The continuous development in the medical field faces multiple challenges in managing a large amount of literature and research results using traditional ontology and knowledge graph construction methods. These challenges include high labor costs, limited coverage, and poor dynamism of traditional ontology and knowledge graph construction methods. Large language models (LLMs) can solve various natural language processing tasks and can understand and generate human-like natural language, which makes automated construction of ontology expansion and knowledge graphs (KGs) possible. This paper proposes an ontology expansion method based on LLMs, using LLMs to formulate competency questions (CQs) to extend the initial ontology, and then constructing the knowledge graph based on the extended ontology. We demonstrated the feasibility of the method by creating a knowledge graph for breast cancer treatment. The combination of LLMs-based medical ontology and knowledge graph can achieve more efficient medical knowledge management and application, promoting the informatization and intelligent development of the medical field.

Clinical decision support systems (CDSS) assist physicians in making medical decisions by relying on fixed rules and guidelines. However, these systems often lack sufficient consideration of individual differences and struggle to adapt to complex clinical scenarios. This paper proposes a novel CDSS based on an extended argumentation framework, integrating patient data and individual preferences to provide more personalized treatment recommendations. By employing critical questions and argument schemes from computational argumentation, and utilizing multiple data sources—including official medical guidelines, comprehensive drug information databases, and patient reviews—we enhance the system's decision-making capability. We developed a prototype system to validate this approach and its outcomes.

Independently developed clinical guidelines present a systematic challenge in managing patients with multi-morbidity in a consistent and integrated manner. Existing approaches mainly focus on combining multiple guidelines and lack approaches that combine with additional medical resources. The correlations and conflicts between treatment plans in the management of multi-morbidity are well-documented in medical literature but are less explored in the Clinical Decision Support line of research. In this paper, we propose a literature-based guideline interlinking method to address these challenges through the integration of clinical guidelines and the harmonization of conflicting recommendations, thereby providing a more holistic and efficient way to manage patients with multi-morbidity conditions. This method employs an ontology model and knowledge graph technology to represent and analyze the complexity and interrelations of diseases, with the aim of transcending the limitations of traditional single disease guidelines and providing a holistic and integrated framework for multi-morbidity management. The objective is to construct a multi-morbidity knowledge graph by correlating medical literature with clinical guidelines and to provide optimal decision support for patients with multi-morbidity complications in a clinical decision support system (CDSS).

The misalignment between RGB and thermal images significantly impairs RGB-Thermal semantic segmentation accuracy. Current non-end-to-end methods treat RGB-Thermal registration independently of semantic segmentation, resulting in fusion errors, redundant computations, and poor real-time performance. Semantic segmentation accuracy directly correlates with registration precision: better registration yields more accurate segmentation. Moreover, regions with identical semantic labels, indicating the same object, tend to share similar registration offsets. Based on these correlations, we propose an end-to-end multimodal registration and segmentation method using flexible deformation fields. Our method utilizes a shared encoder for registration and semantic segmentation to reduce redundancy. Unlike traditional non-end-to-end approaches, it directly registers high-level perceptual features, thereby optimizing computational efficiency and real-time performance. Additionally, we employ a flexible deformation field to register RGB-Thermal data, addressing limitations of traditional affine transformations in handling non-coplanar and non-rigid registrations. However, the increased flexibility of deformation fields compared to affine transformations, and the sacrificing of geometric feature preservation, pose training challenges. To overcome this, we introduce a semantic alignment loss function to train the alignment module. This function calculates the semantic segmentation loss between the predictions from registered thermal features and RGB semantic labels. It shortens the gradient backpropagation path, aligning the objectives of registration and segmentation. We validate our end-to-end approach through extensive experiments, achieving significant performance enhancements. On the IR SEG dataset, our end-to-end method achieves state-of-the-art results with a mean Intersection over Union (mIoU) of 61.1% and a mean accuracy (mAcc) of 76.0%.

This paper describes the process of embedding ChatGPT-4 (Large Scale Natural Language Modeling) in a CDSS (Clinical Decision Support System) to generate multiple types of decision recommendations. First, given enquiry data, the CDSS generates a specific type of decision recommendations and gives the questions and answers to ChatGPT-4 to generate the related type of decision recommendations. To categorize the same type of decision recommendations in CDSS and ChatGPT-4 together, Word2Vec model was used to learn the semantic relationships of words in medical texts and evaluate the model. Then, the similarity between the decision recommendations generated by CDSS and ChatGPT-4 is determined by calculating the cosine similarity, and a suitable threshold is set to decide whether to fuse these decision recommendations or not. Through this method, the decision recommendations generated by CDSS and ChatGPT-4 can be effectively fused to provide more comprehensive and precise clinical decision support.

Semantic segmentation using RGB and thermal images is crucial in a variety of applications, including autonomous driving and video surveillance. However, the validity of information differs between modalities, which is typically addressed by weighting image features using complex and inefficient networks. To address this issue, we propose a Multi-Expert Fusion Network (MEFNet) that decouples the three-dimensional attention matrix of image features into a two-dimensional modal weight matrix and a channel attention vector. This approach focuses more on modal and channel differences while excluding interferences from other factors. Specifically, MEFNet multiplies RGB and thermal features by their respective modal weights, and then uses channel attention to select important feature channels. Comprehensive experiments demonstrate that MEFNet is competitive with state-of-the-art methods, achieving 62.6% mIoU on the IR SEG dataset.