Enhancing Multimodal Medical Image Classification using Cross-Graph Modal Contrastive Learning

The classification of medical images is a pivotal aspect of disease diagnosis, often enhanced by deep learning techniques. However, traditional approaches typically focus on unimodal medical image data, neglecting the integration of diverse non-image patient data. This paper proposes a novel Cross-Graph Modal Contrastive Learning (CGMCL) framework for multimodal medical image classification. The model effectively integrates both image and non-image data by constructing cross-modality graphs and leveraging contrastive learning to align multimodal features in a shared latent space. An inter-modality feature scaling module further optimizes the representation learning process by reducing the gap between heterogeneous modalities. The proposed approach is evaluated on two datasets: a Parkinson's disease (PD) dataset and a public melanoma dataset. Results demonstrate that CGMCL outperforms conventional unimodal methods in accuracy, interpretability, and early disease prediction. Additionally, the method shows superior performance in multi-class melanoma classification. The CGMCL framework provides valuable insights into medical image classification while offering improved disease interpretability and predictive capabilities.

MEDFuse: Multimodal EHR Data Fusion with Masked Lab-Test Modeling and Large Language Models

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.

EHR-Based Mobile and Web Platform for Chronic Disease Risk Prediction Using Large Language Multimodal Models

Traditional diagnosis of chronic diseases involves in-person consultations with physicians to identify the disease. However, there is a lack of research focused on predicting and developing application systems using clinical notes and blood test values. We collected five years of Electronic Health Records (EHRs) from Taiwan's hospital database between 2017 and 2021 as an AI database. Furthermore, we developed an EHR-based chronic disease prediction platform utilizing Large Language Multimodal Models (LLMMs), successfully integrating with frontend web and mobile applications for prediction. This prediction platform can also connect to the hospital's backend database, providing physicians with real-time risk assessment diagnostics. The demonstration link can be found at https://www.youtube.com/watch?v=oqmL9DEDFgA.

Identification of Craving Maps among Marijuana Users via Analysis of Functional Brain Networks with High-Order Attention Graph Neural Networks

The consumption of high doses of marijuana can have significant psychological and social impacts. In this study, we propose an interpretable novel framework called the HOGAB (High-Order Graph Attention Neural Networks) model for addictive Marijuana classification and analysis of the localized network clusters that demonstrated abnormal brain activities among chronic marijuana users. The HOGAB integrates dynamic intrinsic functional networks with LSTM technology to capture temporal patterns in fMRI time series of marijuana users. We employed the high-order attention module in neighborhood nodes for information fusion and message passing, enhancing community clustering analysis for long-term marijuana users. Furthermore, we improve the overall classification ability of the model by incorporating attention mechanisms, achieving an AUC of 85.1% and an accuracy of 80.7% in classification, higher than the comparison algoirthms. Specifically, we identified the most relevant subnetworks and cognitive regions that are influenced by persistent marijuana usage, revealing that chronic marijuana consumption adversely affects cognitive control, particularly within the Dorsal Attention and Frontoparietal networks, which are essential for attentional, cognitive and higher cognitive functions. The results show that our proposed model is capable of accurately predicting craving bahavior and identifying brain maps associated with long-term cravings, and thus pinpointing brain regions that are important for analysis.

Large Language Multimodal Models for 5-Year Chronic Disease Cohort Prediction Using EHR Data

Chronic diseases such as diabetes are the leading causes of morbidity and mortality worldwide. Numerous research studies have been attempted with various deep learning models in diagnosis. However, most previous studies had certain limitations, including using publicly available datasets (e.g. MIMIC), and imbalanced data. In this study, we collected five-year electronic health records (EHRs) from the Taiwan hospital database, including 1,420,596 clinical notes, 387,392 laboratory test results, and more than 1,505 laboratory test items, focusing on research pre-training large language models. We proposed a novel Large Language Multimodal Models (LLMMs) framework incorporating multimodal data from clinical notes and laboratory test results for the prediction of chronic disease risk. Our method combined a text embedding encoder and multi-head attention layer to learn laboratory test values, utilizing a deep neural network (DNN) module to merge blood features with chronic disease semantics into a latent space. In our experiments, we observe that clinicalBERT and PubMed-BERT, when combined with attention fusion, can achieve an accuracy of 73% in multiclass chronic diseases and diabetes prediction. By transforming laboratory test values into textual descriptions and employing the Flan T-5 model, we achieved a 76% Area Under the ROC Curve (AUROC), demonstrating the effectiveness of leveraging numerical text data for training and inference in language models. This approach significantly improves the accuracy of early-stage diabetes prediction.

Parkinson Disease classification Using Contrastive Graph Cross-View Learning with Multimodal Fusion of SPECT Images and Clinical Features

Parkinson's Disease (PD) is a neurodegenerative neurological disorder that impacts movement and afflicts over 10 million people worldwide. Previous researches have come up with deep learning models for predicting Parkinson's disease primarily using medical images and didn't leverage the manifold structure in the dataset. Our study introduces a multimodal approach with both image and non-image features with a contrastive cross-view graph fusion for Parkinson's disease classification. Specifically, we designed a multimodal co-attention module to integrate embeddings from two distinct graph views derived from low dimensional representation of images and clinical features, enabling the extraction of more stable and structured features from the multiview data. Additionally, we have devised a simplified fusion method utilizing a contrastive loss for positive and negative pairs, to enhance the model's overall cross-view fusion learning capabilities. In our experiments, the graph-view multimodal approach can achieve an accuracy rate of 91% and an AUC of 92.8% in five-fold cross-validation, and it also demonstrates superior predictive capabilities on non-image data as compared to methods that rely solely on machine learning methods.

Sequential Graph Attention Learning for Predicting Dynamic Stock Trends (Student Abstract)

The stock market is characterized by a complex relationship between companies and the market. This study combines a sequential graph structure with attention mechanisms to learn global and local information within temporal time. Specifically, our proposed "GAT-AGNN" module compares model performance across multiple industries as well as within single industries. The results show that the proposed framework outperforms the state-of-the-art methods in predicting stock trends across multiple industries on Taiwan Stock datasets.

Hospital transfer risk prediction for COVID-19 patients from a medicalized hotel based on Diffusion GraphSAGE

The global COVID-19 pandemic has caused more than six million deaths worldwide. Medicalized hotels were established in Taiwan as quarantine facilities for COVID-19 patients with no or mild symptoms. Due to limited medical care available at these hotels, it is of paramount importance to identify patients at risk of clinical deterioration. This study aimed to develop and evaluate a graph-based deep learning approach for progressive hospital transfer risk prediction in a medicalized hotel setting. Vital sign measurements were obtained for 632 patients and daily patient similarity graphs were constructed. Inductive graph convolutional network models were trained on top of the temporally integrated graphs to predict hospital transfer risk. The proposed models achieved AUC scores above 0.83 for hospital transfer risk prediction based on the measurements of past 1, 2, and 3 days, outperforming baseline machine learning methods. A post-hoc analysis on the constructed diffusion-based graph using Local Clustering Coefficient discovered a high-risk cluster with significantly older mean age, higher body temperature, lower SpO2, and shorter length of stay. Further time-to-hospital-transfer survival analysis also revealed a significant decrease in survival probability in the discovered high-risk cluster. The obtained results demonstrated promising predictability and interpretability of the proposed graph-based approach. This technique may help preemptively detect high-risk patients at community-based medical facilities similar to a medicalized hotel.

Dopamine Transporter SPECT Image Classification for Neurodegenerative Parkinsonism via Diffusion Maps and Machine Learning Classifiers

Neurodegenerative parkinsonism can be assessed by dopamine transporter single photon emission computed tomography (DaT-SPECT). Although generating images is time consuming, these images can show interobserver variability and they have been visually interpreted by nuclear medicine physicians to date. Accordingly, this study aims to provide an automatic and robust method based on Diffusion Maps and machine learning classifiers to classify the SPECT images into two types, namely Normal and Abnormal DaT-SPECT image groups. In the proposed method, the 3D images of N patients are mapped to an N by N pairwise distance matrix and are visualized in Diffusion Maps coordinates. The images of the training set are embedded into a low-dimensional space by using diffusion maps. Moreover, we use Nystr\"om's out-of-sample extension, which embeds new sample points as the testing set in the reduced space. Testing samples in the embedded space are then classified into two types through the ensemble classifier with Linear Discriminant Analysis (LDA) and voting procedure through twenty-five-fold cross-validation results. The feasibility of the method is demonstrated via Parkinsonism Progression Markers Initiative (PPMI) dataset of 1097 subjects and a clinical cohort from Kaohsiung Chang Gung Memorial Hospital (KCGMH-TW) of 630 patients. We compare performances using Diffusion Maps with those of three alternative manifold methods for dimension reduction, namely Locally Linear Embedding (LLE), Isomorphic Mapping Algorithm (Isomap), and Kernel Principal Component Analysis (Kernel PCA). We also compare results using 2D and 3D CNN methods. The diffusion maps method has an average accuracy of 98% for the PPMI and 90% for the KCGMH-TW dataset with twenty-five fold cross-validation results. It outperforms the other three methods concerning the overall accuracy and the robustness in the training and testing samples.