Technology and Health Care - Volume 32, issue S1

Authors: Yu, Xia | Ma, Liyong | Wang, Hongjie | Zhang, Yong | Du, Hai | Xu, Kaiyuan | Wang, Lianfang

Article Type: Research Article

Abstract: BACKGROUND: Congenital heart disease (CHD) seriously affects children’s health and quality of life, and early detection of CHD can reduce its impact on children’s health. Tetralogy of Fallot (TOF) and ventricular septal defect (VSD) are two types of CHD that have similarities in echocardiography. However, TOF has worse diagnosis and higher morality than VSD. Accurate differentiation between VSD and TOF is highly important for administrative property treatment and improving affected factors’ diagnoses. OBJECTIVE: TOF and VSD were differentiated using convolutional neural network (CNN) models that classified fetal echocardiography images. METHODS: We collected 105 fetal …echocardiography images of TOF and 96 images of VSD. Four CNN models, namely, VGG19, ResNet50, NTS-Net, and the weakly supervised data augmentation network (WSDAN), were used to differentiate the two congenital heart diseases. The performance of these four models was compared based on sensitivity, accuracy, specificity, and AUC. RESULTS: VGG19 and ResNet50 performed similarly, with AUCs of 0.799 and 0.802, respectively. A superior performance was observed with NTS-Net and WSDAN specific for fine-grained image categorization tasks, with AUCs of 0.823 and 0.873, respectively. WSDAN had the best performance among all models tested. CONCLUSIONS: WSDAN exhibited the best performance in differentiating between TOF and VSD and is worthy of further clinical popularization. Show more

Keywords: Congenital heart disease, fetal echocardiography images, tetralogy of Fallot, ventricular septal defect, deep learning

DOI: 10.3233/THC-248040

Citation: Technology and Health Care, vol. 32, no. S1, pp. 457-464, 2024

Authors: Chen, Rongcan | Wang, Qinglian | Huang, Xiaoyuan

Article Type: Research Article

Abstract: BACKGROUND: Oral cancer is a malignant tumor that usually occurs within the tissues of the mouth. This type of cancer mainly includes tumors in the lining of the mouth, tongue, lips, buccal mucosa and gums. Oral cancer is on the rise globally, especially in some specific risk groups. The early stage of oral cancer is usually asymptomatic, while the late stage may present with ulcers, lumps, bleeding, etc. OBJECTIVE: The objective of this paper is to propose an effective and accurate method for the identification and classification of oral cancer. METHODS: We applied two deep …learning methods, CNN and Transformers. First, we propose a new CANet classification model for oral cancer, which uses attention mechanisms combined with neglected location information to explore the complex combination of attention mechanisms and deep networks, and fully tap the potential of attention mechanisms. Secondly, we design a classification model based on Swim transform. The image is segmented into a series of two-dimensional image blocks, which are then processed by multiple layers of conversion blocks. RESULTS: The proposed classification model was trained and predicted on Kaggle Oral Cancer Images Dataset, and satisfactory results were obtained. The average accuracy, sensitivity, specificity and F1-Socre of Swin transformer architecture are 94.95%, 95.37%, 95.52% and 94.66%, respectively. The average accuracy, sensitivity, specificity and F1-Score of CANet model were 97.00%, 97.82%, 97.82% and 96.61%, respectively. CONCLUSIONS: We studied different deep learning algorithms for oral cancer classification, including convolutional neural networks, converters, etc. Our Attention module in CANet leverages the benefits of channel attention to model the relationships between channels while encoding precise location information that captures the long-term dependencies of the network. The model achieves a high classification effect with an accuracy of 97.00%, which can be used in the automatic recognition and classification of oral cancer. Show more

Keywords: Oral cancer classification, attention mechanism, transformer

DOI: 10.3233/THC-248041

Citation: Technology and Health Care, vol. 32, no. S1, pp. 465-475, 2024

Authors: Park, Chanhee | Yoon, Hyunsik

Article Type: Research Article

Abstract: BACKGROUND: Patients with hemiparetic stroke experience diminished motor function, dynamic balance, and gait speed, which influence their activities of daily living (ADL). OBJECTIVE: This study aimed to determine the therapeutic effects of ultrasound biofeedback core exercise (UBCE) on Fugl-Meyer assessment (FMA), Time up and go (TUG), 10-meter walking test (10MWT) and functional independent measure (FIM) in participants with stroke. METHODS: Twenty-four stroke survivors consistently underwent UBCE or abdominal draw-in maneuver (ADIM) for 30 min/session, 3 days a week for 4 weeks. Clinical outcome measurements – the FMA, TUG, 10MWT, and FIM – were observed pre-and post-intervention. …RESULTS: We detected significant changes in the FMA-lower extremities, TUG, 10MWT, and FIM scores between the UBCE and ADIM groups. UBCE and ADIM showed significant improvements in FMA-lower extremities, TUG, 10MWT, and FIM scores. However, UBCE showed more favorable results than ADIM in patients with stroke. CONCLUSIONS: Our research provides novel therapeutic suggestion of neurorehabilitation in stroke patients. Show more

Keywords: Stroke, somatosensory-evoked potential, balance, gait

DOI: 10.3233/THC-248042

Citation: Technology and Health Care, vol. 32, no. S1, pp. 477-486, 2024

Authors: Liu, Zuoliang | Nie, Jiachen | Yang, Fan | Zheng, Yi | Ding, Li

Article Type: Research Article

Abstract: BACKGROUND: Shoes upper has been shown to affect the shoe microclimate (temperature and humidity). However, the existing data on the correlation between the microclimate inside footwear and the body’s physical factors is still quite limited. OBJECTIVE: This study examined whether shoes air permeability would influence foot microclimate and spatial characteristics of lower limb and body. METHODS: Twelve recreational male habitual runners were instructed to finish an 80 min experimental protocol, wearing two running shoes with different air permeability. RESULTS: Participants wearing CLOSED upper structure shoe exhibited higher in-shoe temperature and relative …humidity. Although there was no significant difference, shank temperature and metabolism in OPEN upper structure shoes were lower. CONCLUSIONS: This indicates that the air permeability of shoes can modify the microclimate of the feet, potentially affecting the lower limb temperature. This study provides relevant information for the design and evaluation of footwear. Show more

Keywords: Footwear, microclimate, thermal comfort, metabolism

DOI: 10.3233/THC-248043

Citation: Technology and Health Care, vol. 32, no. S1, pp. 487-499, 2024

Authors: Li, Xingcen | Li, Qianpeng | Li, Jinhan | Wang, Xiaoyi | Zou, Huaxiu | Wang, Shuyang | Fan, Jingyi

Article Type: Research Article

Abstract: BACKGROUND: The etiology of Burning Mouth Syndrome (BMS) remains unclear. OBJECTIVE: To explore the differences in the therapeutic efficacy of pain improvement between medication therapy and laser therapy in patients with BMS. METHODS: 45 BMS patients were randomly divided into three groups: The Combination therapy group (Group A, n = 15), The Medication therapy group (Group B, n = 15), and the Laser therapy group (Group C, n = 15). The pain condition of the patients was evaluated …using the Numeric Rating Scale (NRS), and the improvement in pain before and after treatment was compared among the three groups. RESULTS: All three groups (A, B, and C) showed a significant reduction in NRS scores after treatment, with statistically significant differences observed among the different groups. Group A exhibited the most significant improvement, with a statistically significant difference before and after treatment. CONCLUSION: Laser and medication therapy are effective methods for reducing oral burning pain * symptoms, and their combined use yields more significant therapeutic effects. Show more

Keywords: Laser therapy, medication therapy, burning mouth syndrome

DOI: 10.3233/THC-248044

Citation: Technology and Health Care, vol. 32, no. S1, pp. 501-509, 2024

Authors: Park, Seonmi | You, Joshua (Sung) H.

Article Type: Research Article

Abstract: BACKGROUND: While the limited ankle dorsiflexion syndrome (ADS) is common in neuro-musculoskeletal conditions, the instrument-assisted mobilization focused on the shortened gastro-soleus myofascial structure (IMI) rather than the homologous structure (both gastrosoleus and tibiliais anterior muscles, HIM). OBJECTIVE: We aimed to compare the immediate therapeutic effects between IMH and IMI treatment groups on the ankle dorsiflexion angle, muscle activation and foot pressure distribution during dynamic gait in ADS. METHODS: Neuromechanical tests including kinematics (ankle mobility), kinetics (center of pressure distribution), and electromyography were used to determine the immediate therapeutic effects between HIM and IMI …treatment groups in 24 participants with ADS. RESULTS: The ankle joint angle analysis demonstrated a more improved active DF angle in the group who received HIM intervention when compared to the group who received IMI intervention. (11.26% and 3.58%, respectively) EMG analysis showed more decreased mean and peak TA activation amplitudes in the group who received HIM intervention (9.1% and 9%) when compared to the group who received IMI intervention (11.48% and 1.48%). Plantar pressure distribution analysis showed difference that the forefoot/area decreased in the group who received HIM intervention (8.1%), but rather increased in the group who received IMI intervention (14.3%). CONCLUSIONS: Our neuromechanical results demonstrated promising positive effects on ankle joint mobility, muscle activation and foot pressure distribution during gait in ADS. Show more

Keywords: Limited ankle dorsiflexion syndrome, instrument-assisted mobilization, electromyography

DOI: 10.3233/THC-248045

Citation: Technology and Health Care, vol. 32, no. S1, pp. 511-522, 2024

Authors: Zeng, Ting | Ling, Caijin | Liang, Yong

Article Type: Research Article

Abstract: BACKGROUND: Colon cancer is the most prevalent and rapidly increasing malignancy globally. It has been suggested that some of the ingredients in the herb pair of Coptidis Rhizoma and ginger (Zingiber officinale ), a traditional Chinese medicine, have potential anti-colon cancer properties. OBJECTIVE: This study aimed to investigate the molecular mechanisms underlying the effects of the Coptidis Rhizoma-ginger herb pair in treating colon cancer, using an integrated approach combining network pharmacology and molecular docking. METHODS: The ingredients of the herb pair Coptidis Rhizoma-ginger, along with their corresponding protein targets, were obtained from the Traditional …Chinese Medicine System Pharmacology and Swiss Target Prediction databases. Target genes associated with colon cancer were retrieved from the GeneCards and OMIM databases. Then, the protein targets of the active ingredients in the herb pair were identified, and the disease-related overlapping targets were determined using the Venn online tool. The protein-protein interaction (PPI) network was constructed using STRING database and analyzed using Cytoscape 3.9.1 to identify key targets. Then, a compound-target-disease-pathway network map was constructed. The intersecting target genes were subjected to Gene Ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses for colon cancer treatment. Molecular docking was performed using the Molecular Operating Environment (MOE) software to predict the binding affinity between the key targets and active compounds. RESULTS: Besides 1922 disease-related targets, 630 targets associated with 20 potential active compounds of the herb pair Coptidis Rhizoma-ginger were collected. Of these, 229 intersection targets were obtained. Forty key targets, including STAT3, Akt1, SRC, and HSP90AA1, were further analyzed using the ClueGO plugin in Cytoscape. These targets are involved in biological processes such as miRNA-mediated gene silencing, phosphatidylinositol 3-kinase (PI3K) signaling, and telomerase activity. KEGG enrichment analysis showed that PI3K-Akt and hypoxia-inducible factor 1 (HIF-1) signaling pathways were closely related to colon cancer prevention by the herb pair Coptidis Rhizoma-ginger. Ten genes (Akt1, TP53, STAT3, SRC, HSP90AA1, JAK2, CASP3, PTGS2, BCl2, and ESR1) were identified as key genes for validation through molecular docking simulation. CONCLUSIONS: This study demonstrated that the herb pair Coptidis Rhizoma-ginger exerted preventive effects against colon cancer by targeting multiple genes, utilizing various active compounds, and modulating multiple pathways. These findings might provide the basis for further investigations into the molecular mechanisms underlying the therapeutic effects of Coptidis Rhizoma-ginger in colon cancer treatment, potentially leading to the development of novel drugs for combating this disease. Show more

Keywords: Colon cancer, Coptidis Rhizoma, ginger, molecular docking, network pharmacology

DOI: 10.3233/THC-248046

Citation: Technology and Health Care, vol. 32, no. S1, pp. 523-542, 2024

Authors: Cao, Yang | Fan, Chunjiang | Li, Gang | Huang, Jian | Zhang, Jinli

Article Type: Research Article

Abstract: BACKGROUND: Aphasia is a communication disorder that affects the ability to process and produce language, which severely impacting their lives. Computer-aid exercise rehabilitation has shown to be highly effective for these patients. OBJECTIVE: In our study, we proposed a speech rehabilitation system with mirrored therapy. The study goal is to construct a effective rehabilitation software for aphasia patients. METHODS: This system collects patients’ facial photos for mirrored video generation and speech synthesis. The visual feedback provided by the mirror creates an engaging and motivating experience for patients. And the evaluation platform employs machine …learning technologies for assessing speech similarity. RESULTS: The sophisticated task-oriented rehabilitation training with mirror therapy is also presented for experiments performing. The performance of three tasks reaches the average scores of 83.9% for vowel exercises, 74.3% for word exercies and 77.8% for sentence training in real time. CONCLUSIONS: The user-friendly application system allows patients to carry out daily training tasks instructed by the therapists or the prompt information of menu. Our work demonstrated a promising intelligent mirror software system for reading-based aphasia rehabilitation. Show more

Keywords: Aphasia, speech rehabilitation, mirrored therapy, video generation

DOI: 10.3233/THC-248047

Citation: Technology and Health Care, vol. 32, no. S1, pp. 543-553, 2024

Authors: Xie, Hefu | Wang, Bingbing | Hong, Yuanzhen

Article Type: Research Article

Abstract: BACKGROUND: Acute Liver Failure (ALF) is a critical medical condition with rapid development, often caused by viral infections, hepatotoxic drug abuse, or other severe liver diseases. Timely and accurate prediction of ALF occurrence is clinically crucial. However, predicting ALF poses challenges due to the diverse physiological differences among patients and the dynamic nature of the disease. OBJECTIVE: This study introduces a deep learning approach that combines fully connected and convolutional neural networks for effective ALF prediction. The goal is to overcome limitations of traditional machine learning methods and enhance predictive model performance and generalization. METHODS: …The proposed model integrates a fully connected neural network for handling basic patient features and a convolutional neural network dedicated to capturing temporal patterns in patient data. The combination allows automatic learning of complex patterns and abstract features present in highly dynamic medical data associated with ALF. RESULTS: The model’s effectiveness is demonstrated through comprehensive experiments and performance evaluations. It outperforms traditional machine learning methods, achieving 94.8% accuracy and superior generalization capabilities. CONCLUSIONS: The study highlights the potential of deep learning in ALF prediction, emphasizing the importance of considering individualized medical factors. Future research should focus on improving model robustness, addressing imbalanced data, and further exploring personalized features for enhanced predictive accuracy in real-world clinical scenarios. Show more

Keywords: Acute liver failure, deep learning, fully connected neural network, convolutional neural network

DOI: 10.3233/THC-248048

Citation: Technology and Health Care, vol. 32, no. S1, pp. 555-564, 2024

Authors: Shin, Eunji | Roh, Hyolyun

Article Type: Research Article

Abstract: BACKGROUND: Many people work in a sitting position where they have to use their upper extremities and hands. Muscle activity in sitting position is affected by the chair height of, the height of the worktable, and the distance to the working target. OBJECTIVE: The purpose of this study is to investigate differences in muscle activity between men and wemen at different chair heghts and working distances. METHODS: Surface electromyography (EMG) was employed to determine the muscle activity of the upper limbs and the trunk, while an arm-stretching task was performed in a sitting position. …RESULTS: Women’s muscle activity was higher than that of men in most muscles as the chair height and working distance changed. CONCLUSIONS: As the height of the chair or the working distance was changed, muscle activity was greater in women than in men for most of the muscles analyzed. Under the same conditions, women may feel more muscle fatigue than men, so it is necessary to consider gender in the working environment. Show more

Keywords: Chair height, working distance, sedentary work, surface EMG

DOI: 10.3233/THC-248049

Citation: Technology and Health Care, vol. 32, no. S1, pp. 565-575, 2024