IEEE Journal of Biomedical and Health Informatics最新文献

Optical coherence tomography (OCT) is a widely used non-invasive imaging modality for ophthalmic diagnosis. However, the inherent speckle noise becomes the leading cause of OCT image quality, and efficient speckle removal algorithms can improve image readability and benefit automated clinical analysis. As an ill-posed inverse problem, it is of utmost importance for speckle removal to learn suitable priors. In this work, we develop a score prior guided iterative solver (SPIS) with logarithmic space to remove speckles in OCT images. Specifically, we model the posterior distribution of raw OCT images as a data consistency term and transform the speckle removal from a nonlinear into a linear inverse problem in the logarithmic domain. Subsequently, the learned prior distribution through the score function from the diffusion model is utilized as a constraint for the data consistency term into the linear inverse optimization, resulting in an iterative speckle removal procedure that alternates between the score prior predictor and the subsequent non-expansive data consistency corrector. Experimental results on the private and public OCT datasets demonstrate that the proposed SPIS has an excellent performance in speckle removal and out-of-distribution (OOD) generalization. Further downstream automatic analysis on the OCT images verifies that the proposed SPIS can benefit clinical applications. The data and code are available at https://github.com/ lisanqian1212/SPIS.

Evidence-based medicine (EBM) represents a paradigm of providing patient care grounded in the most current and rigorously evaluated research. Recent advances in large language models (LLMs) offer a potential solution to transform EBM by automating labor-intensive tasks and thereby improving the efficiency of clinical decision-making. This study explores integrating LLMs into the key stages in EBM, evaluating their ability across evidence retrieval (PICO extraction, biomedical question answering), synthesis (summarizing randomized controlled trials), and dissemination (medical text simplification). We conducted a comparative analysis of seven LLMs, including both proprietary and open-source models, as well as those fine-tuned on medical corpora. Specifically, we benchmarked the performance of various LLMs on each EBM task under zero-shot settings as baselines, and employed prompting techniques, including in-context learning, chain-of-thought reasoning, and knowledge-guided prompting to enhance their capabilities. Our extensive experiments revealed the strengths of LLMs, such as remarkable understanding capabilities even in zero-shot settings, strong summarization skills, and effective knowledge transfer via prompting. Promoting strategies such as knowledge-guided prompting proved highly effective (e.g., improving the performance of GPT-4 by 13.10% over zero-shot in PICO extraction). However, the experiments also showed limitations, with LLM performance falling well below state-of-the-art baselines like PubMedBERT in handling named entity recognition tasks. Moreover, human evaluation revealed persisting challenges with factual inconsistencies and domain inaccuracies, underscoring the need for rigorous quality control before clinical application. This study provides insights into enhancing EBM using LLMs while highlighting critical areas for further research. The code is publicly available on Github.

Predicting drug-drug interactions (DDIs) is a significant concern in the field of deep learning. It can effectively reduce potential adverse consequences and improve therapeutic safety. Graph neural network (GNN)-based models have made satisfactory progress in DDI event prediction. However, most existing models overlook crucial drug structure and interaction information, which is necessary for accurate DDI event prediction. To tackle this issue, we introduce a new method called MRGCDDI. This approach employs contrastive learning, but unlike conventional methods, it does not require data augmentation, thereby avoiding additional noise. MRGCDDI maintains the semantics of the graphical data during encoder perturbation through a simple yet effective contrastive learning approach, without the need for manual trial and error, tedious searching, or expensive domain knowledge to select enhancements. The approach presented in this study effectively integrates drug features extracted from drug molecular graphs and information from multi-relational drug-drug interaction (DDI) networks. Extensive experimental results demonstrate that MRGCDDI outperforms state-of-the-art methods on both datasets. Specifically, on Deng's dataset, MRGCDDI achieves an average increase of 4.33% in accuracy, 11.57% in Macro-F1, 10.97% in Macro-Recall, and 10.64% in Macro-Precision. Similarly, on Ryu's dataset, the model shows improvements with an average increase of 2.42% in accuracy, 3.86% in Macro-F1, 3.49% in Macro-Recall, and 2.75% in Macro-Precision. All the data and codes of this work are available at https://github.com/Nokeli/MRGCDDI.

Blood glucose level (BGL) prediction contributes to more effective management of type 1 diabetes. Physical activity (PA) is a crucial factor in diabetes management. It affects BGL, and it is imperative to effectively deploy PA in BGL prediction to support diabetes management systems by incorporating this crucial factor. Due to the erratic nature of PA's impact on BGL inter- and intra-patients and insufficient knowledge, deploying PA in BGL prediction is challenging. Hence, optimal approaches for PA fusion with BGL are demanded to improve the performance of BGL prediction. To address this gap, we propose novel methodologies for extracting and integrating information from PA data into BGL prediction. This paper proposes several novel PA-informed prediction models by developing different approaches for extracting information from PA data and fusing this information with BGL data in signal, feature, and decision levels to find the optimal approach for deploying PA in BGL prediction models. For signal-level fusion, different automatically-recorded PA data are fused with BGL data. Also, three feature engineering approaches are developed for feature-level fusion: subjective assessments of PA, objective assessments of PA, and statistics of PA. Furthermore, in decision-level fusion, ensemble learning is used to combine predictions from models trained with different inputs. Then, a comparative investigation is performed between the developed PA-informed approaches and the no-fusion approach, as well as between themselves. The analyses are performed on the publicly available Ohio dataset with rigorous evaluation. The results show that deploying PA can statistically significantly improve BGL prediction performance. The results show that deploying PA can statistically significantly improve BGL prediction performance. Also, among the developed approaches to leveraging PA in BGL prediction, fusing heart rate data at the signal-level and PA intensity categories at the feature-level with BGL data are the most effective ways. Our developed methodologies contribute to determining optimal approaches, including the kind of PA information and fusion method, to improve the performance of BGL prediction effectively.

Tumor heterogeneity presents a significant challenge in predicting drug responses, especially as missense mutations within the same gene can lead to varied outcomes such as drug resistance, enhanced sensitivity, or therapeutic ineffectiveness. These complex relationships highlight the need for advanced analytical approaches in oncology. Due to their powerful ability to handle heterogeneous data, graph convolutional networks (GCNs) represent a promising approach for predicting drug responses. However, simple bipartite graphs cannot accurately capture the complex relationships involved in missense mutation and drug response. Furthermore, Deep learning models for drug response are often considered "black boxes", and their interpretability remains a widely discussed issue. To address these challenges, we propose an Interpretable Dynamic Directed Graph Convolutional Network (IDDGCN) framework, which incorporates four key features: (1) the use of directed graphs to differentiate between sensitivity and resistance relationships, (2) the dynamic updating of node weights based on node-specific interactions, (3) the exploration of associations between different mutations within the same gene and drug response, and (4) the enhancement of interpretability models through the integration of a weighted mechanism that accounts for the biological significance, alongside a ground truth construction method to evaluate prediction transparency. The experimental results demonstrate that IDDGCN outperforms existing state-of-the-art models, exhibiting excellent predictive power. Both qualitative and quantitative evaluations of its interpretability further highlight its ability to explain predictions, offering a fresh perspective for precision oncology and targeted drug development.

This study introduces an innovative deep-learning model for cuffless blood pressure estimation using PPG and ECG signals, demonstrating state-of-the-art performance on the largest clean dataset, PulseDB. The rU-Net architecture, a fusion of U-Net and ResNet, enhances both generalization and feature extraction accuracy. Accurate multi-scale feature capture is facilitated by short-time Fourier transform (STFT) time-frequency distributions and multi-head attention mechanisms, allowing data-driven feature selection. The inclusion of demographic parameters as supervisory information further elevates performance. On the calibration-based dataset, our model excels, achieving outstanding accuracy (SBP MAE ± std: 4.49 ± 4.86 mmHg, DBP MAE ± std: 2.69 ± 3.10 mmHg), surpassing AAMI standards and earning a BHS Grade A rating. Addressing the challenge of calibration-free data, we propose a fine-tuning-based transfer learning approach. Remarkably, with only 10% data transfer, our model attains exceptional accuracy (SBP MAE ± std: 4.14 ± 5.01 mmHg, DBP MAE ± std: 2.48 ± 2.93 mmHg). This study sets the stage for the development of highly accurate and reliable wearable cuffless blood pressure monitoring devices.

Existing respiratory monitoring techniques primarily focus on respiratory rate measurement, neglecting the potential of using thoracoabdominal patterns of respiration for infant lung health assessment. To bridge this gap, we exploit the unique advantage of spatial redundancy of a camera sensor to analyze the infant thoracoabdominal respiratory motion. Specifically, we propose a camera-based respiratory imaging (CRI) system that utilizes optical flow to construct a spatio-temporal respiratory imager for comparing the infant chest and abdominal respiratory motion, and employs deep learning algorithms to identify infant abdominal, thoracoabdominal synchronous, and thoracoabdominal asynchronous patterns of respiration. To alleviate the challenges posed by limited clinical training data and subject variability, we introduce a novel multiple-expert contrastive learning (MECL) strategy to CRI. It enriches training samples by reversing and pairing different-class data, and promotes the representation consistency of same-class data through multi-expert collaborative optimization. Clinical validation involving 44 infants shows that MECL achieves 70% in sensitivity and 80.21% in specificity, which validates the feasibility of CRI for respiratory pattern recognition. This work investigates a novel video-based approach for assessing the infant thoracoabdominal patterns of respiration, revealing a new value stream of video health monitoring in neonatal care.

The lack of explainability in using relevant clinical knowledge hinders the adoption of artificial intelligence-powered analysis of unstructured clinical dialogue. A wealth of relevant, untapped Mental Health (MH) data is available in online communities, providing the opportunity to address the explainability problem with substantial potential impact as a screening tool for both online and offline applications. Inspired by how clinicians rely on their expertise when interacting with patients, we leverage relevant clinical knowledge to classify and explain depression-related data, reducing manual review time and engendering trust. We developed a method to enhance attention in contemporary transformer models and generate explanations for classifications that are understandable by mental health practitioners (MHPs) by incorporating external clinical knowledge. We propose a domain-general architecture called ProcesS knowledgeinfused cross ATtention (PSAT) that incorporates clinical practice guidelines (CPG) when computing attention. We transform a CPG resource focused on depression, such as the Patient Health Questionnaire (e.g. PHQ-9) and related questions, into a machine-readable ontology using SNOMED-CT. With this resource, PSAT enhances the ability of models like GPT-3.5 to generate application-relevant explanations. Evaluation of four expert-curated datasets related to depression demonstrates PSAT's applicationrelevant explanations. PSAT surpasses the performance of twelve baseline models and can provide explanations where other baselines fall short.

Electrocardiography (ECG) is the gold standard for monitoring heart function and is crucial for preventing the worsening of cardiovascular diseases (CVDs). However, the inconvenience of ECG acquisition poses challenges for long-term continuous monitoring. Consequently, researchers have explored non-invasive and easily accessible photoplethysmography (PPG) as an alternative, converting it into ECG. Previous studies have focused on peaks or simple mapping to generate ECG, ignoring the inherent periodicity of cardiovascular signals. This results in an inability to accurately extract physiological information during the cycle, thus compromising the generated ECG signals' clinical utility. To this end, we introduce a novel PPG-to-ECG translation model called CATransformer, capable of adaptive modeling based on the cardiac cycle. Specifically, CATransformer automatically extracts the cycle using a cycle-aware module and creates multiple semantic views of the cardiac cycle. It leverages a transformer to capture detailed features within each cycle and the dynamics across cycles. Our method outperforms existing approaches, exhibiting the lowest RMSE across five paired PPG-ECG databases. Additionally, extensive experiments are conducted on four cardiovascular-related tasks to assess the clinical utility of the generated ECG, achieving consistent state-of-the-art performance. Experimental results confirm that CATransformer generates highly faithful ECG signals while preserving their physiological characteristics.

Facial expressions vary with different health conditions, making a facial expression recognition (FER) system valuable within a healthcare framework. Achieving accurate recognition of facial expressions is a considerable challenge due to the difficulty in capturing subtle features. This research introduced an ensemble neural random forest method that utilizes convolutional neural network (CNN) architecture for feature extraction and optimized random forest for classification. For feature extraction, four convolutional layers with different numbers of filters and kernel sizes are used. Further, the maxpooling, batch normalization, and dropout layers are used in the model to expedite the process of feature extraction and avoid the overfitting of the model. The extracted features are provided to the optimized random forest for classification, which is based on the number of trees, criterion, maximum tree depth, maximum terminal nodes, minimum sample split, and maximum features per tree, and applied to the classification process. To demonstrate the significance of the proposed model, we conducted a thorough assessment of the proposed neural random forest through an extensive experiment encompassing six publicly available datasets. The remarkable weighted average recognition rate of 97.3% achieved across these diverse datasets highlights the effectiveness of our approach in the context of FER systems.