Objective.This study aims to address the challenges of imbalanced heartbeat classification using electrocardiogram (ECG). In this proposed novel deep-learning method, the focus is on accurately identifying minority classes in conditions characterized by significant imbalances in ECG data.Approach.We propose a feature fusion neural network enhanced by a dynamic minority-biased batch weighting loss function. This network comprises three specialized branches: the complete ECG data branch for a comprehensive view of ECG signals, the local QRS wave branch for detailed features of the QRS complex, and theRwave information branch to analyzeRwave characteristics. This structure is designed to extract diverse aspects of ECG data. The dynamic loss function prioritizes minority classes while maintaining the recognition of majority classes, adjusting the network\'s learning focus without altering the original data distribution. Together, this fusion structure and adaptive loss function significantly improve the network\'s ability to distinguish between various heartbeat classes, enhancing the accuracy of minority class identification.Main results.The proposed method demonstrated balanced performance within the MIT-BIH dataset, especially for minority classes. Under the intra-patient paradigm, the accuracy, sensitivity, specificity, and positive predictive value for Supraventricular ectopic beat were 99.63%, 93.62%, 99.81%, and 92.98%, respectively, and for Fusion beat were 99.76%, 85.56%, 99.87%, and 84.16%, respectively. Under the inter-patient paradigm, these metrics were 96.56%, 89.16%, 96.84%, and 51.99%for Supraventricular ectopic beat, and 96.10%, 77.06%, 96.25%, and 13.92%for Fusion beat, respectively.Significance.This method effectively addresses the class imbalance in ECG datasets. By leveraging diverse ECG signal information and a novel loss function, this approach offers a promising tool for aiding in the diagnosis and treatment of cardiac conditions.

Accurately identifying potential off-target sites in the CRISPR/Cas9 system is crucial for improving the efficiency and safety of editing. However, the imbalance of available off-target datasets has posed a major obstacle in enhancing prediction performance. Despite several prediction models have been developed to address this issue, there remains a lack of systematic research on handling data imbalance in off-target prediction. This article systematically investigates the data imbalance issue in off-target datasets and explores numerous methods to process data imbalance from a novel perspective. First, we highlight the impact of the imbalance problem on off-target prediction tasks by determining the imbalance ratios present in these datasets. Then, we provide a comprehensive review of various sampling techniques and cost-sensitive methods to mitigate class imbalance in off-target datasets. Finally, systematic experiments are conducted on several state-of-the-art prediction models to illustrate the impact of applying data imbalance solutions. The results show that class imbalance processing methods significantly improve the off-target prediction capabilities of the models across multiple testing datasets. The code and datasets used in this study are available at https://github.com/gzrgzx/CRISPR_Data_Imbalance.

Despite the widespread use of ionizable lipid nanoparticles (LNPs) in clinical applications for messenger RNA (mRNA) delivery, the mRNA drug delivery system faces an efficient challenge in the screening of LNPs. Traditional screening methods often require a substantial amount of experimental time and incur high research and development costs. To accelerate the early development stage of LNPs, we propose TransLNP, a transformer-based transfection prediction model designed to aid in the selection of LNPs for mRNA drug delivery systems. TransLNP uses two types of molecular information to perceive the relationship between structure and transfection efficiency: coarse-grained atomic sequence information and fine-grained atomic spatial relationship information. Due to the scarcity of existing LNPs experimental data, we find that pretraining the molecular model is crucial for better understanding the task of predicting LNPs properties, which is achieved through reconstructing atomic 3D coordinates and masking atom predictions. In addition, the issue of data imbalance is particularly prominent in the real-world exploration of LNPs. We introduce the BalMol block to solve this problem by smoothing the distribution of labels and molecular features. Our approach outperforms state-of-the-art works in transfection property prediction under both random and scaffold data splitting. Additionally, we establish a relationship between molecular structural similarity and transfection differences, selecting 4267 pairs of molecular transfection cliffs, which are pairs of molecules that exhibit high structural similarity but significant differences in transfection efficiency, thereby revealing the primary source of prediction errors. The code, model and data are made publicly available at https://github.com/wklix/TransLNP.

BACKGROUND: In the last decade, long-tail learning has become a popular research focus in deep learning applications in medicine. However, no scientometric reports have provided a systematic overview of this scientific field. We utilized bibliometric techniques to identify and analyze the literature on long-tailed learning in deep learning applications in medicine and investigate research trends, core authors, and core journals. We expanded our understanding of the primary components and principal methodologies of long-tail learning research in the medical field.
METHODS: Web of Science was utilized to collect all articles on long-tailed learning in medicine published until December 2023. The suitability of all retrieved titles and abstracts was evaluated. For bibliometric analysis, all numerical data were extracted. CiteSpace was used to create clustered and visual knowledge graphs based on keywords.
RESULTS: A total of 579 articles met the evaluation criteria. Over the last decade, the annual number of publications and citation frequency both showed significant growth, following a power-law and exponential trend, respectively. Noteworthy contributors to this field include Husanbir Singh Pannu, Fadi Thabtah, and Talha Mahboob Alam, while leading journals such as IEEE ACCESS, COMPUTERS IN BIOLOGY AND MEDICINE, IEEE TRANSACTIONS ON MEDICAL IMAGING, and COMPUTERIZED MEDICAL IMAGING AND GRAPHICS have emerged as pivotal platforms for disseminating research in this area. The core of long-tailed learning research within the medical domain is encapsulated in six principal themes: deep learning for imbalanced data, model optimization, neural networks in image analysis, data imbalance in health records, CNN in diagnostics and risk assessment, and genetic information in disease mechanisms.
CONCLUSIONS: This study summarizes recent advancements in applying long-tail learning to deep learning in medicine through bibliometric analysis and visual knowledge graphs. It explains new trends, sources, core authors, journals, and research hotspots. Although this field has shown great promise in medical deep learning research, our findings will provide pertinent and valuable insights for future research and clinical practice.

BACKGROUND: Medical image registration plays an important role in several applications. Existing approaches using unsupervised learning encounter issues due to the data imbalance problem, as their target is usually a continuous variable.
OBJECTIVE: In this study, we introduce a novel approach known as Unsupervised Imbalanced Registration, to address the challenge of data imbalance and prevent overconfidence while increasing the accuracy and stability of 4D image registration.
METHODS: Our approach involves performing unsupervised image mixtures to smooth the input space, followed by unsupervised image registration to learn the continual target. We evaluated our method on 4D-Lung using two widely used unsupervised methods, namely VoxelMorph and ViT-V-Net.
RESULTS: Our findings demonstrate that our proposed method significantly enhances the mean accuracy of registration by 3%-10% on a small dataset while also reducing the accuracy variance by 10%.
CONCLUSIONS: Unsupervised Imbalanced Registration is a promising approach that is compatible with current unsupervised image registration methods applied to 4D images.

BACKGROUND: After the COVID-19 pandemic, the conflict between limited mental health care resources and the rapidly growing number of patients has become more pronounced. It is necessary for psychologists to borrow artificial intelligence (AI)-based methods to analyze patients\' satisfaction with drug treatment for those undergoing mental illness treatment.
OBJECTIVE: Our goal was to construct highly accurate and transferable models for predicting the satisfaction of patients with mental illness with medication by analyzing their own experiences and comments related to medication intake.
METHODS: We extracted 41,851 reviews in 20 categories of disorders related to mental illnesses from a large public data set of 161,297 reviews in 16,950 illness categories. To discover a more optimal structure of the natural language processing models, we proposed the Unified Interchangeable Model Fusion to decompose the state-of-the-art Bidirectional Encoder Representations from Transformers (BERT), support vector machine, and random forest (RF) models into 2 modules, the encoder and the classifier, and then reconstruct fused \"encoder+classifer\" models to accurately evaluate patients\' satisfaction. The fused models were divided into 2 categories in terms of model structures, traditional machine learning-based models and neural network-based models. A new loss function was proposed for those neural network-based models to overcome overfitting and data imbalance. Finally, we fine-tuned the fused models and evaluated their performance comprehensively in terms of F1-score, accuracy, κ coefficient, and training time using 10-fold cross-validation.
RESULTS: Through extensive experiments, the transformer bidirectional encoder+RF model outperformed the state-of-the-art BERT, MentalBERT, and other fused models. It became the optimal model for predicting the patients\' satisfaction with drug treatment. It achieved an average graded F1-score of 0.872, an accuracy of 0.873, and a κ coefficient of 0.806. This model is suitable for high-standard users with sufficient computing resources. Alternatively, it turned out that the word-embedding encoder+RF model showed relatively good performance with an average graded F1-score of 0.801, an accuracy of 0.812, and a κ coefficient of 0.695 but with much less training time. It can be deployed in environments with limited computing resources.
CONCLUSIONS: We analyzed the performance of support vector machine, RF, BERT, MentalBERT, and all fused models and identified the optimal models for different clinical scenarios. The findings can serve as evidence to support that the natural language processing methods can effectively assist psychologists in evaluating the satisfaction of patients with drug treatment programs and provide precise and standardized solutions. The Unified Interchangeable Model Fusion provides a different perspective on building AI models in mental health and has the potential to fuse the strengths of different components of the models into a single model, which may contribute to the development of AI in mental health.

To address the scarcity and class imbalance of abnormal electrocardiogram (ECG) databases, which are crucial in AI-driven diagnostic tools for potential cardiovascular disease detection, this study proposes a novel quantum conditional generative adversarial algorithm (QCGAN-ECG) for generating abnormal ECG signals. The QCGAN-ECG constructs a quantum generator based on patch method. In this method, each sub-generator generates distinct features of abnormal heartbeats in different segments. This patch-based generative algorithm conserves quantum resources and makes QCGAN-ECG practical for near-term quantum devices. Additionally, QCGAN-ECG introduces quantum registers as control conditions. It encodes information about the types and probability distributions of abnormal heartbeats into quantum registers, rendering the entire generative process controllable. Simulation experiments on Pennylane demonstrated that the QCGAN-ECG could generate completely abnormal heartbeats with an average accuracy of 88.8%. Moreover, the QCGAN-ECG can accurately fit the probability distribution of various abnormal ECG data. In the anti-noise experiments, the QCGAN-ECG showcased outstanding robustness across various levels of quantum noise interference. These results demonstrate the effectiveness and potential applicability of the QCGAN-ECG for generating abnormal ECG signals, which will further promote the development of AI-driven cardiac disease diagnosis systems. The source code is available at github.com/VanSWK/QCGAN_ECG.

Large hospitals can be complex, with numerous discipline and subspecialty settings. Patients may have limited medical knowledge, making it difficult for them to determine which department to visit. As a result, visits to the wrong departments and unnecessary appointments are common. To address this issue, modern hospitals require a remote system capable of performing intelligent triage, enabling patients to perform self-service triage. To address the challenges outlined above, this study presents an intelligent triage system based on transfer learning, capable of processing multilabel neurological medical texts. The system predicts a diagnosis and corresponding department based on the patient\'s input. It utilizes the triage priority (TP) method to label diagnostic combinations found in medical records, converting a multilabel problem into a single-label one. The system considers disease severity and reduces the \"class overlapping\" of the dataset. The BERT model classifies the chief complaint text, predicting a primary diagnosis corresponding to the complaint. To address data imbalance, a composite loss function based on cost-sensitive learning is added to the BERT architecture. The study results indicate that the TP method achieves a classification accuracy of 87.47% on medical record text, outperforming other problem transformation methods. By incorporating the composite loss function, the system\'s accuracy rate improves to 88.38% surpassing other loss functions. Compared to traditional methods, this system does not introduce significant complexity, yet substantially improves triage accuracy, reduces patient input confusion, and enhances hospital triage capabilities, ultimately improving the patient\'s medical experience. The findings could provide a reference for intelligent triage development.

Road crashes are a major problem for traffic safety management, which usually causes flash crowd traffic with a profound influence on traffic management and communication systems. In 2020, the sudden outbreak of the novel coronavirus disease (COVID-19) pandemic led to significant changes in road traffic conditions. In this paper, by analyzing crash data from 2016 to 2020 and new COVID-19 case data in 2020, we find that the average crash severity and crash deaths during this period (a rapid increase of new COVID-19 cases in 2020) are higher than those in previous four years. Hence, it is necessary to exploit a novel road crash risk prediction model for such an emergency. We propose a novel data-adaptive fatigue focal loss (DA-FFL) method by fusing fatigue factors to establish a road crash risk prediction model under the scenario of large-scale emergencies. Finally, the experimental results demonstrate that DA-FFL performs better than the other typical methods in terms of area under curve (AUC) and false alarm rate (FAR) for imbalanced data. Furthermore, DA-FFL has better prediction performance in convolutional neural networks-long short-term memory (CNN-LSTM).

The extraction of drug-drug interactions (DDIs) is an important task in the field of biomedical research, which can reduce unexpected health risks during patient treatment. Previous work indicates that methods using external drug information have a much higher performance than those methods not using it. However, the use of external drug information is time-consuming and resource-costly. In this work, we propose a novel method for extracting DDIs which does not use external drug information, but still achieves comparable performance. First, we no longer convert the drug name to standard tokens such as DRUG0, the method commonly used in previous research. Instead, full drug names with drug entity marking are input to BioBERT, allowing us to enhance the selected drug entity pair. Second, we adopt the Key Semantic Sentence approach to emphasize the words closely related to the DDI relation of the selected drug pair. After the above steps, the misclassification of similar instances which are created from the same sentence but corresponding to different pairs of drug entities can be significantly reduced. Then, we employ the Gradient Harmonizing Mechanism (GHM) loss to reduce the weight of mislabeled instances and easy-to-classify instances, both of which can lead to poor performance in DDI extraction. Overall, we demonstrate in this work that it is better not to use drug blinding with BioBERT, and show that GHM performs better than Cross-Entropy loss if the proportion of label noise is less than 30%. The proposed model achieves state-of-the-art results with an F1-score of 84.13% on the DDIExtraction 2013 corpus (a standard English DDI corpus), which fills the performance gap (4%) between methods that rely on and do not rely on external drug information.