Shun Liu

Thao Minh Nguyen Phan, Cong-Tinh Dao, Chenwei Wu et al.

Electronic health records (EHRs) are multimodal by nature, consisting of structured tabular features like lab tests and unstructured clinical notes. In real-life clinical practice, doctors use complementary multimodal EHR data sources to get a clearer picture of patients' health and support clinical decision-making. However, most EHR predictive models do not reflect these procedures, as they either focus on a single modality or overlook the inter-modality interactions/redundancy. In this work, we propose MEDFuse, a Multimodal EHR Data Fusion framework that incorporates masked lab-test modeling and large language models (LLMs) to effectively integrate structured and unstructured medical data. MEDFuse leverages multimodal embeddings extracted from two sources: LLMs fine-tuned on free clinical text and masked tabular transformers trained on structured lab test results. We design a disentangled transformer module, optimized by a mutual information loss to 1) decouple modality-specific and modality-shared information and 2) extract useful joint representation from the noise and redundancy present in clinical notes. Through comprehensive validation on the public MIMIC-III dataset and the in-house FEMH dataset, MEDFuse demonstrates great potential in advancing clinical predictions, achieving over 90% F1 score in the 10-disease multi-label classification task.

Shun Liu, Jianan Zhang, Ruocheng Song et al.

Object detection and localization are crucial tasks for biomedical image analysis, particularly in the field of hematology where the detection and recognition of blood cells are essential for diagnosis and treatment decisions. While attention-based methods have shown significant progress in object detection in various domains, their application in medical object detection has been limited due to the unique challenges posed by medical imaging datasets. To address this issue, we propose ADA-YOLO, a light-weight yet effective method for medical object detection that integrates attention-based mechanisms with the YOLOv8 architecture. Our proposed method leverages the dynamic feature localisation and parallel regression for computer vision tasks through \textit{adaptive head} module. Empirical experiments were conducted on the Blood Cell Count and Detection (BCCD) dataset to evaluate the effectiveness of ADA-YOLO. The results showed that ADA-YOLO outperforms the YOLOv8 model in mAP (mean average precision) on the BCCD dataset by using more than 3 times less space than YOLOv8. This indicates that our proposed method is effective. Moreover, the light-weight nature of our proposed method makes it suitable for deployment in resource-constrained environments such as mobile devices or edge computing systems. which could ultimately lead to improved diagnosis and treatment outcomes in the field of hematology.

Shun Liu

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they operate as opaque "black boxes" that obscure the rationale behind their decisions. This lack of transparency can limit understanding of the models' underlying principles and impede their deployment in sensitive domains, such as healthcare or finance. To address this challenge, our research team has proposed an innovative framework designed to reconcile the trade-off between model performance and interpretability. Our approach is centered around modular operations on high-dimensional data, which enable end-to-end processing while preserving interpretability. By fusing diverse interpretability techniques and modularized data processing, our framework sheds light on the decision-making processes of complex models without compromising their performance. We have extensively tested our framework and validated its superior efficacy in achieving a harmonious balance between computational efficiency and interpretability. Our approach addresses a critical need in contemporary machine learning applications by providing unprecedented insights into the inner workings of complex models, fostering trust, transparency, and accountability in their deployment across diverse domains.