LSU Health Digital Scholar (Louisiana State Univ.)
Not a member yet
8182 research outputs found
Sort by
Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning with Biosensor Signals
Get PDFDiabetes is a growing global health concern, affecting millions and leading to severe complications if not properly managed. The primary challenge in diabetes management is maintaining blood glucose levels (BGLs) within a safe range to prevent complications such as renal failure, cardiovascular disease, and neuropathy. Traditional methods, such as finger-prick testing, often result in low patient adherence due to discomfort, invasiveness, and inconvenience. Consequently, there is an increasing need for non-invasive techniques that provide accurate BGL measurements. Photoplethysmography (PPG), a photosensitive method that detects blood volume variations, has shown promise for non-invasive glucose monitoring. Deep neural networks (DNNs) applied to PPG signals can predict BGLs with high accuracy. However, training DNN models requires large and diverse datasets, which are typically distributed across multiple healthcare institutions. Privacy concerns and regulatory restrictions further limit data sharing, making conventional centralized machine learning (ML) approaches less effective. To address these challenges, this study proposes a federated learning (FL)-based solution that enables multiple healthcare organizations to collaboratively train a global model without sharing raw patient data, thereby enhancing model performance while ensuring data privacy and security. In the data preprocessing stage, continuous wavelet transform (CWT) is applied to smooth PPG signals and remove baseline drift. Adaptive cycle-based segmentation (ACBS) is then used for signal segmentation, followed by particle swarm optimization (PSO) for feature selection, optimizing classification accuracy. The proposed system was evaluated on diverse datasets, including VitalDB and MUST, under various conditions with data collected during surgery and anesthesia. The model achieved a root mean square error (RMSE) of 19.1 mg/dL, demonstrating superior predictive accuracy. Clarke error grid analysis (CEGA) confirmed the model’s clinical reliability, with 99.31% of predictions falling within clinically acceptable limits. The FL-based approach outperformed conventional deep learning models, making it a promising method for non-invasive, privacy-preserving glucose monitoring
Unlocking precision using k-means++- improved genetic algorithm-radial basis function neural network: data-driven evolution of smart gloves for gesture recognition
Get PDFHuman-computer interaction technologies have been used since the 1970s but have only gained growing popularity in recent years with new design paradigms. Ongoing research and development in gesture recognition systems with broad application prospects have focused on improving accuracy and real-time performance as well as the robustness of specific machine learning algorithms against environmental conditions. This paper addresses the accuracy enhancement of a novel Fifth Dimension Technologies data-glove-based gesture recognition system using a genetic-algorithm (GA)-trained k-means++-improved radial basis function (RBF) or GK-RBF neural network. First, we analyzed and modeled the sensor distribution in the data glove and proposed joint constraints based on the finger joint angle and sensor mapping. Then, we trained the model and conducted experimental verification to demonstrate the model’s excellent real-time performance. Our results showed a training accuracy of 100%, a reduction in training error rate by 89.3%, and an accuracy rate improvement of at least 3.5% between the different static gestures, even with different operators. Specifically, the GK-RBF neural network outperforms the RBF and GA-modified models by 4.36 and 2.21 abs.%, respectively, in terms of recognition accuracy. The 99.85-% accuracy rate of 10-fold cross validation proves a high degree of compatibility with data-glove-based recognition systems
The NIH is a sound investment for the US taxpayer
Get PDFResearch funded by the National Institutes of Health is essential for improving the health of Americans and developing new drugs and treatments for a wide range of diseases
Metabolic syndrome in childhood, adolescent, and young adult cancer survivors: recommendations for surveillance from the International Late Effects of Childhood Cancer Guideline Harmonization Group
No full textObjective: Survivors of childhood, adolescent, and young adult (CAYA) cancer have an increased risk of metabolic syndrome (MetS). MetS describes the clustering of cardiovascular risk factors including overweight or obesity, hypertension, (pre)diabetes, and dyslipidaemia. While associated cardiovascular sequelae can be serious, MetS is preventable, manageable, and potentially reversible with the appropriate pharmacological and/or behavioral interventions. To optimize health outcomes in CAYA cancer survivors, international, harmonized surveillance recommendations are essential. Design: Systematic review and guideline development. Methods: A multidisciplinary guideline panel evaluated concordances and discordances across national guidelines for MetS surveillance and performed a systematic literature review. The Grading of Recommendations Assessment, Development and Evaluation methodology was used to grade the available evidence and formulate recommendations considering the strength of the underlying evidence as well as potential harms and benefits associated with MetS surveillance. In case evidence was lacking, recommendations were based on expert opinion. In addition, recommendations for surveillance modalities were derived from existing guidelines for MetS components where applicable. Results: The systematic literature review included 20 studies and highlighted 2 high-risk groups, namely CAYA cancer survivors treated with total body irradiation and those treated with cranial or craniospinal irradiation (moderate-quality evidence). Recommendations were formulated for MetS surveillance in these risk groups, covering preferred screening modalities, age at screening initiation, and surveillance frequency. Conclusions: In this international surveillance guideline for MetS in CAYA cancer survivors, we provide evidence-based recommendations for clinical practice, with the aim of ensuring optimal MetS surveillance for CAYA cancer survivors
Practical Atlas of Ultrasound for Anesthesia in Chronic Pain
No full textThoracic outlet syndrome (TOS) is a complex neurovascular disorder affecting any of the three anatomical compartments: the interscalene triangle, the costoclavicular space, and the retropectoralis minor space [1]. Compression of the nerves, veins, and arteries in the thoracic outlet produces neurosensory and pain symptoms affecting the neck, upper chest, shoulder, arm, and hand [2]. Subcategories of TOS include neurogenic TOS (NTOS), arterial TOS (ATOS), and venous TOS (VTOS), with nearly 90% of all TOS cases consisting of neurologic origin [1]. Accurate diagnosis of TOS has proven to be difficult due to its complex etiology, as well as there being no existing definitive diagnostic test [1, 2]. Current advances in diagnostic methods include provocative injections using local anesthetic, which test for positive pain relief [2]. Treatment for NTOS ranges from conservative approaches, such as physical therapy, to more invasive approaches. Invasive treatment consists of injections of local anesthetic or botulinum toxin type A (BTX-A) prior to/in conjunction with surgery [1, 2]. Presently, scalene and pectoralis injections for NTOS may yield positive temporary relief and serve as a minimally invasive treatment compared to decompressive surgery [1, 2]
A First Response Gap: Implementing Naloxone Training for Campus Security Amid New Orleans’ Opioid Crisis
Get PDF
