Medical & Biological Engineering & Computing最新文献

Early detection of adverse drug reactions (ADRs) is crucial for patient safety but remains challenging due to underreporting and delayed data in traditional pharmacovigilance. This study proposes a computationally efficient and interpretable framework for ADR detection by integrating Low-Rank Adaptation (LoRA) and SHapley Additive Explanations (SHAP) with encoder-based transformer models (BERT, DistilBERT, RoBERTa). Leveraging over 3,900 annotated tweets, our approach demonstrates that LoRA reduces trainable parameters and training costs by up to 50%, while preserving high classification accuracy (above 98%) across three disease classes. SHAP analysis provides actionable interpretability, revealing that the models consistently rely on clinically relevant terms, such as drug names and symptoms, to drive predictions. Compared to traditional finetuning, LoRA and Efficient Finetuning of Quantized LLMs (QLoRA) offer a robust and scalable alternative for processing noisy, informal social media data, making real-time ADR monitoring feasible in resource-constrained healthcare settings. This framework strikes a balance between computational efficiency, interpretability, and predictive performance, supporting the integration of pharmacovigilance into clinical decision support systems for safer patient care.

In patients with developmental dysplasia of the hip (DDH), complications such as head dislocation and cup instability after total hip arthroplasty (THA) are often caused by poor cup positioning. However, no planning algorithm currently considers both the cup bony coverage rate (BCR) and the hip impingement-free range of motion (IFROM) simultaneously due to the high variability in cup position and the difficulty in parameterizing IFROM after THA. This study proposed an algorithm to efficiently calculate the BCR and IFROM for all potential cup positions, filtering out the cup's optimal implant position. The IFROM evaluation coefficients (EC_IFROM) were calculated based on the maximum IFROM for each cup position. Cup positions meeting the BCR requirement and ranking in the top 10% of EC_IFROM were selected as the optimal implant positions. The algorithm was tested on three bone models with varying degrees of DDH to compare BCR and optimal implant position. The algorithm developed in this study is versatile, reliable, and efficient. Calculations in three patients showed that (1) the roof BCR is usually greater than the 3D BCR, and (2) the EC_IFROM makes it easier to select the optimal implant position of the cup. This method can calculate the BCR and IFROM for all cup positions, providing surgeons with a reference to determine the optimal cup position and whether augmentation is needed to improve cup stability in patients with DDH, thereby reducing the incidence of impingement after THA.

The healthcare institutions have started inculcating practices towards personalized care to its patients. Genomic data has now become an inevitable component of healthcare data allowing realization of personalize care of the patients. Medical practitioners are utilizing different technologies for efficient clinical interpretations of genomic data. The genomic data poses many challenges related to its management, amongst which data size and sensitivity are critical. The blockchain technology, a recent and still evolving technology, provides a single integrated solution for the various challenges encountered in managing healthcare data, both genomic and non-genomic. But still there are many challenges yet to be resolved in the domain of genomics and connected technological solutions. This paper presents a systematic literature review covering the research done on genomic data management using blockchain technology in healthcare. The review has incorporated 44 research and 43 review papers. We have designed our study based on 4 research questions targeted to cover efforts on genomic data management via blockchain technology. To our knowledge, majority of the research has focused on data sharing, privacy and security of genomic data. This systematic literature review (SLR) will contribute in identifying research gaps and directions for untouched areas.

Inter-muscular coordination is closely linked to cortical activation and is essential for effective motor control. However, the relationship between cortical activity and inter-muscular coordination has not been thoroughly investigated, partly due to insufficient neural information. This study proposes a weighted EEG-fNIRS (Electroencephalography-functional Near-Infrared Spectroscopy) integration model to enhance the cortical representation of inter-muscular coordination. EEG and fNIRS data were collected from 15 participants performing one-dimensional (1D) and two-dimensional (2D) myoelectric-controlled interface (MCI)tracking tasks. These tasks were driven by myoelectric signals generated by the isometric contraction of specific muscles, including the biceps brachii and triceps brachii. The integration method involves extracting hybrid time-phase-frequency features from EEG signals, and it computes their classification accuracy to generate dynamic weights. These weights are then used to modulate fNIRS hemodynamic signals. To establish a baseline, representing a simplified reference model, where constant weights were calculated as the average of dynamic weights across time points. The classification accuracy of the time-phase-frequency features, serving as task-related weights, was higher than that of single features, achieving the highest within-class similarity (1DMCI: F = 5.08, p < 0.001; 2DMCI: F = 5.63, p < 0.001). Compared to the baseline model, the weighted integration model demonstrated higher within-class similarity (1D: p = 0.018, F = 8.38; 2D: p = 0.011, F = 10.46) and improved task discrimination by reducing irrelevant channels. These findings demonstrate that the weighted integration model effectively enhance the cortical representation of inter-muscular coordination, and has promising applications in brain research and clinical rehabilitation.

Gauze sponges are the items most commonly retained from surgery. The additional time required to find the missing gauze sponge increases anesthetic risk and causes a delay for the next surgery. In minimally invasive surgery, a digital camera can record any object on the screen during surgical procedure. This study aimed to compare modern object detection methods and propose a gauze tracking model to detect and trace the location of gauze sponges in surgical videos. The model consisted of a detection module and a regulating module. The methods used in the detection module included the YOLO series and faster R-CNN with different backbones. The regulating module was designed to reduce false positive detections. The model detected gauze and converted an entire video into a timeline to illustrate segments when gauze appeared on the screen. The timeline was compared frame-by-frame with human annotations. Faster R-CNN, with ResNet101-FPN as the backbone, outperformed other methods. Adding a regulating module further increased the accuracy and F1-score to 0.94 and 0.862, respectively. The model was trained and tested using human surgical videos. The presence of gauze sponge identified by the model was consistent with human annotations. The results are promising for the possibility of real-time gauze tracking during surgery. The model is able to provide critical information to help surgeons locate missing gauze sponges.

This study presents a novel muscle control algorithm for finite element (FE) human body models to simulate neck muscles' active contraction, thereby enhancing the biomechanical realism under whiplash loading. The algorithm (based on a Hill-type muscle model) autonomously maintained the head-neck posture under 1 G load conditions and was implemented into a calibrated FE model of the head-neck complex that reflected physiological cervical kinematics. The model maintained stable posture control across various initial positions and responded robustly to dynamic disturbances. Moreover, it successfully reproduced the characteristic S-shaped cervical deformation of the whiplash motion in a rear-end collision simulation. Notably, significant tensile strains were observed in facet joint capsules, particularly at the C2-C3 and C4-C5 levels-regions potentially associated with soft tissue damage. Although the algorithm relies on certain assumptions regarding neutral posture and antagonist muscle activation, it remains computationally efficient and applicable to models with varying anthropometry. In conclusion, this algorithm markedly improves FE models' predictive accuracy for whiplash injury analysis and offers a promising tool for developing more effective and personalized automotive safety systems. Future work will expand its applicability to vulnerable populations and evaluate the role of head restraints in injury mitigation.

Extracorporeal membrane oxygenation (ECMO) is a life-support modality that supports cardiopulmonary function in critically ill patients. Veno-arterial (VA)-ECMO, which reinfuses blood through the femoral artery, can cause upper body hypoxemia due to uneven oxygen distribution within the aorta. In this study, computational haemodynamic simulations were performed using a patient-specific aorta geometry to simulate blood flow and quantify oxygen saturation (SO₂) levels in the arch branches under varying ECMO support levels. A single-phase flow model coupled with oxygen transport was employed and compared to the multiphase flow model used in previous studies. Simulation results were analysed to evaluate the locations of watershed zones formed by the interplay of native cardiac and ECMO flows and the corresponding oxygen levels. Our findings demonstrate that the single-phase model predicted IA SO₂ ranging from 71.1% to 94.2%, whereas the multiphase model predicted 70.0-86.7%, indicating an underestimation of oxygen saturation in the aortic arch branches. Additionally, lower ECMO support levels shift the watershed region distally, reducing oxygen delivery to the arch branches. This study highlights the potential of computational haemodynamic simulations for assessing oxygen transport and haemodynamic behaviour in patients undergoing VA-ECMO. The approach provides insights to support clinical decision-making and improve personalised treatment outcomes.

Brain-Computer Interfaces (BCIs) enable direct communication between the brain and external devices without requiring physical movement, offering a transformative solution particularly for individuals with impaired or lost motor functions. By providing an alternative communication pathway, BCIs hold considerable promise for both clinical interventions and cognitive neuroscience research. In this study, we introduce ThinkSTra, a novel Transformer-based framework for classifying inner speech commands from electroencephalography (EEG) signals. Unlike conventional models, ThinkSTra jointly captures the temporal dynamics and spatial distributions of neural activity, thereby enabling a more comprehensive representation of the complex structure inherent in EEG signals. We systematically evaluated ThinkSTra on multiple datasets, including the sentence-level TSEEG dataset and the Kumar EEG datasets encompassing character, digit, and visual object classification. To rigorously examine its robustness and generalizability, we additionally performed region- and channel-wise contribution analyses, conducted pretraining and cross-validation experiments, and visualized the learned feature representations using t-SNE. ThinkSTra consistently surpassed existing state-of-the-art approaches, achieving accuracies of 100% on sentence-level, 98.10% on character recognition, 98.34% on digit classification, and 99.5% on visual object tasks. Overall, this study advances inner speech decoding by introducing a robust Transformer-based framework and uncovering how distinct cortical regions contribute to this process, offering both methodological and neuroscientific insights for future brain-computer interfaces.

Schwannomas (SCH) and meningiomas (MEN), the two most common primary spinal cord tumors, present a clinical diagnostic challenge due to their overlapping clinical and radiological manifestations. To address this, we developed a deep learning-based object detection model for automated detection of these tumors using magnetic resonance imaging (MRI), which could facilitate early diagnosis and alleviate clinical decision-making burdens. Our study retrospectively analyzed MRI scans from 103 pathologically confirmed SCH and MEN cases at a local hospital (July 2015-August 2024). First, we took YOLOv8n as the baseline model, introduced selective kernel fusion (SKFusion) module to replace the feature fusion layer of the original neck part, added recursive gated convolution (gnConv), and then trained the improved feature fusion model (YOLOv8n-SKNeck). The proposed model achieved notable performance metrics: 91.20% mean accuracy, 90.92% mean recall, and 91.03% mean F1-score for SCH/MEN detection. These results demonstrate that our optimized deep learning framework can effectively automate the detection and differential diagnosis of spinal SCH and MEN through MRI analysis. Thus, the novel method holds significant potential for advancing computer-aided diagnosis and facilitating innovative applications in future clinical practice.