Biomedical Engineering Letters最新文献

Cardiovascular diseases (CVD) are the leading cause of death worldwide, with heart failure (HF) being one of the most fatal conditions within CVD, greatly impacting patients' quality of life and imposing a heavy socioeconomic burden. Early intervention can significantly reduce HF mortality and hospitalization rates. However, current diagnostic methods are often expensive and complex, leading to delayed detection. To address this issue, this paper proposes a multimodal model, ECGEL, which combines electrocardiogram (ECG) and clinical text data for heart failure prediction. The model first denoises 12-lead ECG signals using LUNet, then converts the ECG signals into spectrograms via fast Fourier transform, extracting ECG features using EfficientNetv2. Simultaneously, clinical text is preprocessed with Bert, and textual features are extracted using BiLSTM. Finally, the ECG and text features are fused for heart failure prediction. Experimental results show that the ECGEL model achieved outstanding performance on a private dataset, with accuracy of 97.9%, recall of 98.3%, and F1 score of 97.6%. This model offers an efficient and accurate solution for the early diagnosis of heart failure, showing significant potential for clinical application.

Recent research has made significant progress with definitively identifying individuals with Parkinson's disease (PD) using speech analysis techniques. However, these studies have often treated the early and advanced stages of PD as equivalent, overlooking the distinct speech impairments and symptoms that can vary significantly across the various stages. This research aims to enhance diagnostic accuracy by utilizing advanced optimization strategies to combine speech recognition results (character error rates) with the acoustic features of vowels for more rigorous diagnostic precision. The dysphonia features of three sustained Korean vowels /아/ (a), /이/ (i), and /우/ (u) were examined for their diversity and strong correlations. Four recognized machine-learning classifiers: Random Forest, Support Vector Machine, k-Nearest Neighbors, and Multi-Layer Perceptron, were employed for consistent and reliable analysis. By fine-tuning the Whisper model specifically for PD speech recognition and optimizing it for each severity level of PD, we significantly improved the discernibility between PD severity levels. This enhancement, when combined with vowel data, allowed for a more precise classification, achieving an improved detection accuracy of 5.87% for a 3-level severity classification over the PD "ON"-state dataset, and an improved detection accuracy of 7.8% for a 3-level severity classification over the PD "OFF"-state dataset. This comprehensive approach not only evaluates the effectiveness of different feature extraction methods but also minimizes the variance across final classification models, thus detecting varying severity levels of PD more effectively.

Feature extraction follows the American Academy of Sleep Medicine (AASM) sleep score manually and applies it to machine learning with a focus on the generalization of sleep data to enable data-centric artificial intelligence. In real-world clinical testing, the manual scoring of sleep stages is time-consuming and requires significant expertise. Additionally, it is subject to interobserver subjective bias. Machine-learning techniques offer a way to overcome these limitations through automation. However, machine learning for sleep phase prediction can perform poorly for small classes. If the distribution of the training data was unbalanced, the model was trained with a bias toward the majority class. To address this, we experimented with loss function adjustment and resampling methods that assign more weight to the prediction errors of minority classes in sleep scoring to determine how to overcome the data imbalance problem. Machine learning can also be used to compare the accuracy of each channel in identifying electrodes, which should be monitored more closely in real-world clinical testing. Owing to the small amount of data available for machine learning in this study, we used various machine learning classifiers by increasing or decreasing the dataset using sampling techniques and weighting different classes of sleep stages. In our experiments, the best-performing model for classifying sleep stages had an accuracy of 91.9%, kappa of 0.899, and F1-score of 86.9%.

The performance and image quality of positron emission tomography (PET) systems can be enhanced by strategically employing multiple different scintillators, particularly those with different decay times. Two cutting-edge PET detector technologies employing different scintillators with different decay times are the phoswich detector and the emerging metascintillator. In PET imaging, accurate and precise energy measurement is important for effectively rejecting scattered gamma-rays and estimating scatter distribution. However, traditional measures of light output, such as amplitude or integration values of photosensor output pulses, cannot accurately indicate the deposit energy of gamma-rays across multiple scintillators. To address these issues, this study explores two methods for energy estimation in PET detectors that employ multiple scintillators. The first method uses pseudo-inverse matrix generated from the unique pulse profile of each crystal, while the second employs an artificial neural network (ANN) to estimate the energy deposited in each crystal. The effectiveness of the proposed methods was experimentally evaluated using three heavy and dense inorganic scintillation crystals (BGO, LGSO, and GAGG) and three fast plastic scintillators (EJ200, EJ224, and EJ232). The energy estimation method employing ANNs consistently demonstrated superior accuracy across all crystal combinations when compared to the approach utilizing the pseudo-inverse matrix. In the pseudo-inverse matrix approach, there is a negligible difference in accuracy when applying integral-based energy labels as opposed to amplitude-based energy labels. On the other hand, in ANN approach, employing integral-based energy labels consistently outperforms the use of amplitude-based energy labels. This study contributes to the advancement of PET detector technology by proposing and evaluating two methods for estimating the energy in the detector using multiple scintillators. The ANN approach appears to be a promising solution for improving the accuracy of energy estimation, addressing challenges posed by mixed scintillation pulses.

Stroke is a major global health problem that causes mortality and morbidity. Predicting the outcomes of stroke intervention can facilitate clinical decision-making and improve patient care. Engaging and developing deep learning techniques can help to analyse large and diverse medical data, including brain scans, medical reports, and other sensor information, such as EEG, ECG, EMG, and so on. Despite the common data standardisation challenge within the medical image analysis domain, the future of deep learning in stroke outcome prediction lies in using multimodal information, including final infarct data, to achieve better prediction of long-term functional outcomes. This article provides a broad review of recent advances and applications of deep learning in the prediction of stroke outcomes, including (i) the data and models used, (ii) the prediction tasks and measures of success, (iii) the current challenges and limitations, and (iv) future directions and potential benefits. This comprehensive review aims to provide researchers, clinicians, and policy makers with an up-to-date understanding of this rapidly evolving and promising field.

Purpose: To ensure accurate blood pressure (BP) measurement, it is important to follow guidelines, such as wearing the cuff on the bare arm. However, this recommendation is often challenging due to patients being dressed. This study quantitatively evaluates how wearing a cuff over clothing impacts BP accuracy using oscillometric waveform analysis.

Methods: BP was measured under three conditions: thick sleeve (3.5 mm), thin sleeve (1.5 mm), and bare arm. Oscillometric waveform envelopes (OMWE) were analyzed to extract features like maximum amplitude, width, and slope for each condition. BP measurements and extracted features from the bare arm condition were compared with those from each sleeve condition.

Results: The mean systolic blood pressure (SBP) and pulse pressure (PP) increased by 11.73 and 10.04 mmHg under thick sleeve conditions. These also increased by 4.308 and 4.731 mmHg under thin sleeve conditions (Thick: p < 0.001, Thin: p < 0.05). The mean of mean arterial pressure (MAP) and OMWE width increased by 5.039 and 5.059 mmHg under thick sleeve conditions (Thick: p < 0.025). The mean of maximum amplitude of OMWE under thick and thin sleeves decreased by 0.9428 and 0.4017 mmHg (Thick, Thin: p < 0.001). Diastolic blood pressure (DBP) increased under thick sleeve conditions; however, this was not statistically significant.

Conclusion: Wearing the cuff over clothing altered OMWE morphology, resulting in a lower, flatter shape similar to that seen in hypertensives. This significantly affected BP readings, particularly SBP. Therefore, following guidelines for cuff placement on bare arms is crucial for accurate BP measurement.

Trial registration number and date: Clinical Research Information Service (CRIS) KCT0008511, 22.05.2023.

To investigate the biomechanical effects of medial collateral ligament (MCL) stiffness adjustments on knee kinematics-medial femoral rollback, femoral rotation, and joint contact forces-in mechanically aligned posterior-substituting (PS) total knee arthroplasty (TKA). A musculoskeletal model simulating squatting was developed using the AnyBody modeling system. A PS-TKA prosthesis was implanted, and MCL stiffness was modified in 20% increments. The effects on femoral rollback, femoral rotation, and joint forces were evaluated. Medial femoral rollback was not significantly affected by changes in MCL stiffness. However, when MCL stiffness exceeded 20% above normal, the pattern and magnitude of lateral femoral rollback were altered compared to other conditions. Increased MCL stiffness also altered internal-external femoral rotation and raised joint contact forces in the medial compartment. Muscle activity was largely unaffected by changes in MCL stiffness, although hamstring activity increased slightly during early flexion (0°-5°) when MCL stiffness exceeded 20%. Excessive MCL stiffness (over 20% above normal) affects lateral femoral rollback and increases joint contact forces, potentially elevating the risk of prosthetic wear. Maintaining MCL stiffness within physiological limits is critical for optimizing outcomes in varus knee TKA.

Sarcopenia is a rapidly rising health concern in the fast-aging countries, but its demanding diagnostic process is a hurdle for making timely responses and devising active strategies. To address this, our study developed and evaluated a novel sarcopenia diagnosis system using Stimulated Muscle Contraction Signals (SMCS), aiming to facilitate rapid and accessible diagnosis in community settings. We recruited 199 adults from Wonju Severance Christian Hospital between July 2022 and October 2023. SMCS data were collected using surface electromyography sensors with the wearable device exoPill. Their skeletal muscle mass index, handgrip strength, and gait speed were also measured as the reference. Binary classification models were trained to classify each criterion for diagnosing sarcopenia based on the AWGS cutoffs. The binary classification models achieved high discriminative abilities with an AUC score near 0.9 in each criterion. When combining these criteria evaluations, the proposed sarcopenia diagnosis system performance achieved an accuracy of 89.4% in males and 92.4% in females, sensitivities of 81.3% and 87.5%, and specificities of 91.0% and 93.8%, respectively. This system significantly enhances sarcopenia diagnostics by providing a quick, reliable, and non-invasive method, suitable for broad community use. The promising result indicates that SMCS contains extensive information about the neuromuscular system, which could be crucial for understanding and managing muscle health more effectively. The potential of SMCS in remote patient care and personal health management is significant, opening new avenues for non-invasive health monitoring and proactive management of sarcopenia and potentially other neuromuscular disorders.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-025-00461-z.

Purpose: Unethical attempts to misuse and overdose opioids have led to strict prescription limits, necessitating frequent hospital visits and prescriptions for long-term severe pain management. Therefore, this study aimed to develop a prototype wearable device that facilitates the extended delivery of opioid drugs while incorporating abuse-deterrent functionality, referred to as the abuse deterrent device (ADD).

Methods: The ADD was designed and fabricated using 3D-printed components, including reservoirs for the drug and contaminant, as well as an actuator. In vitro tests were conducted using a skin-mimicking layer and phosphate-buffered saline (PBS) to evaluate the drug release profile and the effectiveness of the ADD abuse-deterrent mechanism.

Results: Under simulated skin attachment, ADD demonstrated sustained drug release with the potential to persist for up to 200 days. Upon detachment from the skin mimic, the mechanical components of the ADD facilitated immediate exposure of the contaminant to the drug and effectively halted further drug exposure throughout-diffusion.

Conclusion: Wearable ADD provides a secure and practical solution for the long-term treatment of high-risk medications such as opioids, enhances patient convenience, and addresses important public health concerns.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-025-00459-7.

The automated identification of the first and second heart sounds (S1 and S2, respectively) in phonocardiogram (PCG) signals plays a pivotal role in the detection of heart valve diseases based on the known occurrence of heart murmurs between S1-S2 or S2-S1 in valve disorders. Traditional neural network-based methods cannot differentiate between heart sounds and background noise, leading to decreased accuracy in the identification of crucial cardiac events. Therefore, a deep learning-based segmentation on PCG signals that can distinguish S1 and S2 heart sounds with the Convolutional Fourier transform (CF) modules, which are two sequentially connected CF modules, was proposed in this study. Internal datasets, alongside the publicly available PhysioNet 2016 dataset, were used for the training and validation of the CF modules to ensure a robust comparison against existing state-of-the-art models, specifically the logistic regression-Hidden semi-Markov model (LR-HSMM). The efficacy of the CF modules was further evaluated using external datasets, including the PhysioNet 2022 and the Asan Medical Center (AMC) datasets. The CF modules exhibited superior robustness and accuracy in segmenting S1 and S2, achieving an average F1 score of 97.64% for S1 and S2 segmentation, which indicated better performance compared with that of the previous best model, LR-HSMM. The integration of the CF modules ensures the robust performance of PCG segmentation even amidst heart murmurs and background noise, significantly contributing to the advancement of cardiac diagnostics. All code is available at https://github.com/mi2rl/PCG_FTseg.