Risk factor analysis for diabetic foot ulcer‐related amputation including Controlling Nutritional Status score and neutrophil‐to‐lymphocyte ratio

Abstract

Diabetic foot ulcer often leads to amputation, and both nutritional status and immune function have been associated with this process. We aimed to investigate the risk factors of diabetic ulcer-related amputation including the Controlling Nutritional Status score and neutrophil-to-lymphocyte ratio biomarker. We evaluated data from hospital in patients with diabetic foot ulcer, performing univariate and multivariate analyses to screen for high-risk factors and Kaplan–Meier analysis to correlate high-risk factors with amputation-free survival. Overall, 389 patients underwent 247 amputations over the follow-up period. After correction to relevant variables, we identified five independent risk factors for diabetic ulcer-related amputation: ulcer severity, ulcer site, peripheral arterial disease, neutrophil-to-lymphocyte ratio and nutritional status. Amputation-free survival was lower for the moderate-to-severe versus mild cases, for the plantar forefoot versus hindfoot location, for the concomitant peripheral artery disease versus without and in the high versus low neutrophil-to-lymphocyte ratio (all p < 0.01). The results showed that ulcer severity (p < 0.01), ulcer site (p < 0.01), peripheral artery disease (p < 0.01), neutrophil-to-lymphocyte ratio (p < 0.01) and Controlling Nutritional Status score (p < 0.05) were independent risk factors for amputation in diabetic foot ulcer patients and have predictive values for diabetic foot ulcer progression to amputation.

Data glove-based gesture recognition using CNN-BiLSTM model with attention mechanism

by Jiawei Wu, Peng Ren, Boming Song, Ran Zhang, Chen Zhao, Xiao Zhang

As a novel form of human machine interaction (HMI), hand gesture recognition (HGR) has garnered extensive attention and research. The majority of HGR studies are based on visual systems, inevitably encountering challenges such as depth and occlusion. On the contrary, data gloves can facilitate data collection with minimal interference in complex environments, thus becoming a research focus in fields such as medical simulation and virtual reality. To explore the application of data gloves in dynamic gesture recognition, this paper proposes a data glove-based dynamic gesture recognition model called the Attention-based CNN-BiLSTM Network (A-CBLN). In A-CBLN, the convolutional neural network (CNN) is employed to capture local features, while the bidirectional long short-term memory (BiLSTM) is used to extract contextual temporal features of gesture data. By utilizing attention mechanisms to allocate weights to gesture features, the model enhances its understanding of different gesture meanings, thereby improving recognition accuracy. We selected seven dynamic gestures as research targets and recruited 32 subjects for participation. Experimental results demonstrate that A-CBLN effectively addresses the challenge of dynamic gesture recognition, outperforming existing models and achieving optimal gesture recognition performance, with the accuracy of 95.05% and precision of 95.43% on the test dataset.