Multi-Response Preference Optimization with Augmented Ranking Dataset

Recent advancements in Large Language Models (LLMs) have been remarkable, with new models consistently surpassing their predecessors. These advancements are underpinned by extensive research on various training mechanisms. Among these, Preference Optimization has played a significant role in improving the performance of LLMs by incorporating human preferences into the training process. However, constructing preference optimization datasets is challenging and the optimization process is highly sensitive to the dataset quality. In this study, we propose a novel approach to augment Preference Optimization datasets. Additionally, we introduce a Multi-response-based Preference Optimization training method that enables the simultaneous learning of multiple responses.

Enhancing Clinical Efficiency through LLM: Discharge Note Generation for Cardiac Patients

Medical documentation, including discharge notes, is crucial for ensuring patient care quality, continuity, and effective medical communication. However, the manual creation of these documents is not only time-consuming but also prone to inconsistencies and potential errors. The automation of this documentation process using artificial intelligence (AI) represents a promising area of innovation in healthcare. This study directly addresses the inefficiencies and inaccuracies in creating discharge notes manually, particularly for cardiac patients, by employing AI techniques, specifically large language model (LLM). Utilizing a substantial dataset from a cardiology center, encompassing wide-ranging medical records and physician assessments, our research evaluates the capability of LLM to enhance the documentation process. Among the various models assessed, Mistral-7B distinguished itself by accurately generating discharge notes that significantly improve both documentation efficiency and the continuity of care for patients. These notes underwent rigorous qualitative evaluation by medical expert, receiving high marks for their clinical relevance, completeness, readability, and contribution to informed decision-making and care planning. Coupled with quantitative analyses, these results confirm Mistral-7B's efficacy in distilling complex medical information into concise, coherent summaries. Overall, our findings illuminate the considerable promise of specialized LLM, such as Mistral-7B, in refining healthcare documentation workflows and advancing patient care. This study lays the groundwork for further integrating advanced AI technologies in healthcare, demonstrating their potential to revolutionize patient documentation and support better care outcomes.

InMD-X: Large Language Models for Internal Medicine Doctors

In this paper, we introduce InMD-X, a collection of multiple large language models specifically designed to cater to the unique characteristics and demands of Internal Medicine Doctors (IMD). InMD-X represents a groundbreaking development in natural language processing, offering a suite of language models fine-tuned for various aspects of the internal medicine field. These models encompass a wide range of medical sub-specialties, enabling IMDs to perform more efficient and accurate research, diagnosis, and documentation. InMD-X's versatility and adaptability make it a valuable tool for improving the healthcare industry, enhancing communication between healthcare professionals, and advancing medical research. Each model within InMD-X is meticulously tailored to address specific challenges faced by IMDs, ensuring the highest level of precision and comprehensiveness in clinical text analysis and decision support. This paper provides an overview of the design, development, and evaluation of InMD-X, showcasing its potential to revolutionize the way internal medicine practitioners interact with medical data and information. We present results from extensive testing, demonstrating the effectiveness and practical utility of InMD-X in real-world medical scenarios.

NOTE: Notable generation Of patient Text summaries through Efficient approach based on direct preference optimization

The discharge summary is a one of critical documents in the patient journey, encompassing all events experienced during hospitalization, including multiple visits, medications, tests, surgery/procedures, and admissions/discharge. Providing a summary of the patient's progress is crucial, as it significantly influences future care and planning. Consequently, clinicians face the laborious and resource-intensive task of manually collecting, organizing, and combining all the necessary data for a discharge summary. Therefore, we propose "NOTE", which stands for "Notable generation Of patient Text summaries through an Efficient approach based on direct preference optimization". NOTE is based on Medical Information Mart for Intensive Care- III dataset and summarizes a single hospitalization of a patient. Patient events are sequentially combined and used to generate a discharge summary for each hospitalization. In the present circumstances, large language models' application programming interfaces (LLMs' APIs) are widely available, but importing and exporting medical data presents significant challenges due to privacy protection policies in healthcare institutions. Moreover, to ensure optimal performance, it is essential to implement a lightweight model for internal server or program within the hospital. Therefore, we utilized DPO and parameter efficient fine tuning (PEFT) techniques to apply a fine-tuning method that guarantees superior performance. To demonstrate the practical application of the developed NOTE, we provide a webpage-based demonstration software. In the future, we will aim to deploy the software available for actual use by clinicians in hospital. NOTE can be utilized to generate various summaries not only discharge summaries but also throughout a patient's journey, thereby alleviating the labor-intensive workload of clinicians and aiming for increased efficiency.

UniHPF : Universal Healthcare Predictive Framework with Zero Domain Knowledge

Despite the abundance of Electronic Healthcare Records (EHR), its heterogeneity restricts the utilization of medical data in building predictive models. To address this challenge, we propose Universal Healthcare Predictive Framework (UniHPF), which requires no medical domain knowledge and minimal pre-processing for multiple prediction tasks. Experimental results demonstrate that UniHPF is capable of building large-scale EHR models that can process any form of medical data from distinct EHR systems. We believe that our findings can provide helpful insights for further research on the multi-source learning of EHRs.

Unifying Heterogenous Electronic Health Records Systems via Text-Based Code Embedding

EHR systems lack a unified code system forrepresenting medical concepts, which acts asa barrier for the deployment of deep learningmodels in large scale to multiple clinics and hos-pitals. To overcome this problem, we introduceDescription-based Embedding,DescEmb, a code-agnostic representation learning framework forEHR. DescEmb takes advantage of the flexibil-ity of neural language understanding models toembed clinical events using their textual descrip-tions rather than directly mapping each event toa dedicated embedding. DescEmb outperformedtraditional code-based embedding in extensiveexperiments, especially in a zero-shot transfertask (one hospital to another), and was able totrain a single unified model for heterogeneousEHR datasets.

Deep reinforcement learning for guidewire navigation in coronary artery phantom

In percutaneous intervention for treatment of coronary plaques, guidewire navigation is a primary procedure for stent delivery. Steering a flexible guidewire within coronary arteries requires considerable training, and the non-linearity between the control operation and the movement of the guidewire makes precise manipulation difficult. Here, we introduce a deep reinforcement learning(RL) framework for autonomous guidewire navigation in a robot-assisted coronary intervention. Using Rainbow, a segment-wise learning approach is applied to determine how best to accelerate training using human demonstrations with deep Q-learning from demonstrations (DQfD), transfer learning, and weight initialization. `State' for RL is customized as a focus window near the guidewire tip, and subgoals are placed to mitigate a sparse reward problem. The RL agent improves performance, eventually enabling the guidewire to reach all valid targets in `stable' phase. Our framework opens anew direction in the automation of robot-assisted intervention, providing guidance on RL in physical spaces involving mechanical fatigue.

T-Net: Encoder-Decoder in Encoder-Decoder architecture for the main vessel segmentation in coronary angiography

In this paper, we proposed T-Net containing a small encoder-decoder inside the encoder-decoder structure (EDiED). T-Net overcomes the limitation that U-Net can only have a single set of the concatenate layer between encoder and decoder block. To be more precise, the U-Net symmetrically forms the concatenate layers, so the low-level feature of the encoder is connected to the latter part of the decoder, and the high-level feature is connected to the beginning of the decoder. T-Net arranges the pooling and up-sampling appropriately during the encoder process, and likewise during the decoding process so that feature-maps of various sizes are obtained in a single block. As a result, all features from the low-level to the high-level extracted from the encoder are delivered from the beginning of the decoder to predict a more accurate mask. We evaluated T-Net for the problem of segmenting three main vessels in coronary angiography images. The experiment consisted of a comparison of U-Net and T-Nets under the same conditions, and an optimized T-Net for the main vessel segmentation. As a result, T-Net recorded a Dice Similarity Coefficient score (DSC) of 0.815, 0.095 higher than that of U-Net, and the optimized T-Net recorded a DSC of 0.890 which was 0.170 higher than that of U-Net. In addition, we visualized the weight activation of the convolutional layer of T-Net and U-Net to show that T-Net actually predicts the mask from earlier decoders. Therefore, we expect that T-Net can be effectively applied to other similar medical image segmentation problems.

Automated detection of vulnerable plaque in intravascular ultrasound images

Acute Coronary Syndrome (ACS) is a syndrome caused by a decrease in blood flow in the coronary arteries. The ACS is usually related to coronary thrombosis and is primarily caused by plaque rupture followed by plaque erosion and calcified nodule. Thin-cap fibroatheroma (TCFA) is known to be the most similar lesion morphologically to a plaque rupture. In this paper, we propose methods to classify TCFA using various machine learning classifiers including Feed-forward Neural Network (FNN), K-Nearest Neighbor (KNN), Random Forest (RF) and Convolutional Neural Network (CNN) to figure out a classifier that shows optimal TCFA classification accuracy. In addition, we suggest pixel range based feature extraction method to extract the ratio of pixels in the different region of interests to reflect the physician's TCFA discrimination criteria. A total of 12,325 IVUS images were labeled with corresponding OCT images to train and evaluate the classifiers. We achieved 0.884, 0.890, 0.878 and 0.933 Area Under the ROC Curve (AUC) in the order of using FNN, KNN, RF and CNN classifier. As a result, the CNN classifier performed best and the top 10 features of the feature-based classifiers (FNN, KNN, RF) were found to be similar to the physician's TCFA diagnostic criteria.

ECG arrhythmia classification using a 2-D convolutional neural network

In this paper, we propose an effective electrocardiogram (ECG) arrhythmia classification method using a deep two-dimensional convolutional neural network (CNN) which recently shows outstanding performance in the field of pattern recognition. Every ECG beat was transformed into a two-dimensional grayscale image as an input data for the CNN classifier. Optimization of the proposed CNN classifier includes various deep learning techniques such as batch normalization, data augmentation, Xavier initialization, and dropout. In addition, we compared our proposed classifier with two well-known CNN models; AlexNet and VGGNet. ECG recordings from the MIT-BIH arrhythmia database were used for the evaluation of the classifier. As a result, our classifier achieved 99.05% average accuracy with 97.85% average sensitivity. To precisely validate our CNN classifier, 10-fold cross-validation was performed at the evaluation which involves every ECG recording as a test data. Our experimental results have successfully validated that the proposed CNN classifier with the transformed ECG images can achieve excellent classification accuracy without any manual pre-processing of the ECG signals such as noise filtering, feature extraction, and feature reduction.