Technology and Health Care - Volume 32, issue 3

Authors: Zou, Li | Dong, Wei | Ai, Ying | Li, Yantao | Cheng, Yun | Feng, Yun

Article Type: Research Article

Abstract: BACKGROUND: Recurrent spontaneous abortion affects approximately 1–2% of reproductive-age women, with roughly half of RSA cases classified as unexplained recurrent spontaneous abortion (URSA). Genetic polymorphisms in eNOS gene have been shown to have significant implications across various disease processes. Nevertheless, the potential impact of eNOS gene polymorphisms on the susceptibility to URSA in Yunnan population has yet to be explored or documented. OBJECTIVE: This study aims to investigate the potential association between specific variations in the eNOS gene (VNTR 4b/a, - 786T > C, and + 894G > …T) and the risk of URSA in Yunnan population. METHODS: A total of 243 URSA patients and 241 healthy females are involved in this study. We conducted amplification of the eNOS gene fragment and performed sanger sequencing to detect the specific eNOS gene polymorphisms, including VNTR 4b/a, - 786T > C, and + 894G > T. Using a multivariate logistic regression model, we evaluate the potential association between eNOS gene polymorphisms (VNTR 4b/a, - 786T > C, and + 894G > T) and the risk of URSA. Furthermore, serum NO levels were measured in URSA patients. RESULTS: The presence of VNTR 4a, - 786C, and + 894T alleles was found to be associated with an increased risk of URSA. Additionally, our study revealed a significant association between the G-C-4b haplotype of the investigated eNOS gene polymorphisms and a predisposition to URSA. Notably, these eNOS polymorphisms were shown to reduce serum NO levels in URSA patients. CONCLUSION: This study provides evidence supporting the association between eNOS gene polymorphisms, VNTR 4b/a, - 786T > C, and + 894G > T, and the occurrence of URSA in Yunnan Province, China. Show more

Keywords: eNOS, URSA, VNTR 4b/a, -786T > C, +894G > T

DOI: 10.3233/THC-230934

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1871-1879, 2024

Authors: Zhou, Quan | Chen, Xurui

Article Type: Research Article

Abstract: BACKGROUND: The need for personalised care in the long-term management of patient health is paramount due to the variability in individual features and responses to specific medication. With the availability of large quantities of electronic patient records, big data analysis presents a valuable opportunity to gain insights into disease presentation and patient impact. OBJECTIVE: This study aims to utilise data science in the medical field to extract unknown information from databases, validate previously obtained data, and enhance personalised patient care. METHODS: An analytics suite is developed for monitoring patient health and treating cholesterol, …thyroid, and diabetes disorders. This suite employs exploratory, predictive, and visual analytics to categorise patient data into multiple tiers and forecast related complication risk and treatment response. RESULTS: The study found that the analytics suite could successfully identify correlations between various biological indicators of patients and disorders. The suite also showcased potential in predicting health risks and responses to treatments. CONCLUSION: The analytics employed in this study suggest advanced methods of data analysis, which could serve as potential decision-making tools for healthcare providers. These methods might lead to improved treatment outcomes, contributing significantly to personalised patient care. Show more

Keywords: Data analytics, neural networks, decision support system, patient monitoring, survival probability and visualization

DOI: 10.3233/THC-230980

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1881-1896, 2024

Authors: Chang, Jihui | Zhang, Shuang | Qiu, XuZhong | Huang, HaiJun | Zhang, Yun | Li, Kai

Article Type: Research Article

Abstract: BACKGROUND: Humeral fracture is a common long bone fracture in orthopedic clinical diagnosis and treatment. OBJECTIVE: To investigate the local temperature increase owing to changes in the specific absorption ratio (SAR) of the human body caused by humeral bone nails during magnetic resonance imaging (MRI). METHODS: A refined geometric model of the upper body was constructed via data segmentation and post-processing using the digital human image dataset. Finally, the geometric model was imported into COMSOL, a 3-T magnetic resonance coil was built, and the operating frequency (128 MHz) was set to analyze the …SAR of the bone-nail pair and temperature changes. RESULTS: The analysis of the changes after bone-nail implantation under different tissue conditions revealed that the SAR and temperature after implantation and fixation were three times higher than those before, and the areas with abrupt changes in SAR and temperature were primarily concentrated in the bone-nail area. CONCLUSION: In MRI, metal implants can cause local elevation of the SAR near the implant in the human body, resulting in a temperature increase around the implant. Consequently, long-term scanning can damage the human body. Show more

Keywords: Bone nails, magnetic resonance imaging, temperature rise effect, specific absorption ratio, digital human

DOI: 10.3233/THC-230995

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1897-1907, 2024

Authors: Loganathan, Prakash Kannan | Dorkins, Charles | Marlow, George | Zahra, James | Tulsianey, Mudit A. | Rowles, Toby J. | Chadwick, Paula

Article Type: Research Article

Abstract: BACKGROUND: Newborn hypothermia at birth remains as global challenge across all settings. The prevention of delivery room hypothermia at birth could potentially reduce neonatal morbidity and mortality. OBJECTIVE: To compare the heat conservation efficacy of Neohelp and Neowrap and evaluate the heat production efficacy of trans-warmer infant mattress (TWM) in a laboratory setting. METHODS: A beaker of water was heated at 60 ∘ C was covered by Neohelp or two layers of Neowrap and left to cool in an open room for 90 minutes and calculated the decay constant. Using …infra-red camera, we measured the maximum temperature and time taken to reach the temperature in the TWM. RESULTS: Neowrap took 863 seconds for the temperature to drop from 37∘ C to 35∘ C, compared with 941 seconds with Neohelp. When activated TWM reached a maximum temperature of 39.3 ± 0.1∘ C. It took 30 seconds when the activator was placed in the centre, compared with 88 seconds when it was at the corner. CONCLUSION: Compared to Neowrap, Neohelp had better heat conservation properties. Activating the metal disk from the TWM center would deliver quicker heat. Show more

Keywords: Hypothermia, neohelp, neowrap, trans-warmer mattress

DOI: 10.3233/THC-231001

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1909-1914, 2024

Authors: Wang, Xiangyun | Chen, Yuanjing | Ai, Hongjun | Li, Panpan | Zhu, Chengjie | Yuan, Jiaying

Article Type: Research Article

Abstract: BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a prevalent respiratory complication among the elderly, and its severity can escalate to respiratory failure as the disease progresses. OBJECTIVE: To evaluate the application value of non-invasive ventilation in the clinical treatment of patients with COPD and lung cancer. This study assesses its therapeutic effects and its impact on patients’ quality of life (QoL) as measured by the Functional Assessment of Cancer Therapy-Lung (FACT-L) scale. METHODS: A retrospective analysis was conducted on clinical data from 102 patients with COPD and lung cancer. Patients were divided into …two groups: the control group (n = 48), who received conventional treatment, and the observation group (n = 54), who received non-invasive positive pressure ventilation (NIPPV) in addition to conventional treatment. Relevant indicators of curative effect, including blood gas indices, incidence of dyspnoea, improvements in mental health and appetite, and FACT-L QoL scores, were analysed at 2 weeks, 1 month, and 6 months post-treatment. RESULTS: At 2 weeks post-treatment, the observation group who had used NIPPV showed significant improvements in blood gas indices, dyspnoea, mental state and self-care ability compared with the control group (p < 0.05). At 1 month, these benefits persisted and included improved maintenance of body weight (p < 0.05). By 6 months, the observation group had a lower incidence of pulmonary encephalopathy (p < 0.05), and QoL, as measured by the FACT-L scale, improved significantly in the observation group but declined in the control group (p < 0.05). CONCLUSION: NIPPV demonstrates significant efficacy in treating COPD patients with lung cancer, particularly in enhancing curative effects and improving patients’ QoL. Show more

Keywords: Non-invasive ventilation, lung cancer, respiratory failure, quality of life

DOI: 10.3233/THC-231063

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1915-1923, 2024

Authors: Netto, Ann Nita | Abraham, Lizy | Philip, Saji

Article Type: Research Article

Abstract: BACKGROUND: Cardiac diseases are highly detrimental illnesses, responsible for approximately 32% of global mortality [1]. Early diagnosis and prompt treatment can reduce deaths caused by cardiac diseases. In paediatric patients, it is challenging for paediatricians to identify functional murmurs and pathological murmurs from heart sounds. OBJECTIVE: The study intends to develop a novel blended ensemble model using hybrid deep learning models and softmax regression to classify adult, and paediatric heart sounds into five distinct classes, distinguishing itself as a groundbreaking work in this domain. Furthermore, the research aims to create a comprehensive 5-class paediatric phonocardiogram (PCG) …dataset. The dataset includes two critical pathological classes, namely atrial septal defects and ventricular septal defects, along with functional murmurs, pathological and normal heart sounds. METHODS: The work proposes a blended ensemble model (HbNet-Heartbeat Network) comprising two hybrid models, CNN-BiLSTM and CNN-LSTM, as base models and Softmax regression as meta-learner. HbNet leverages the strengths of base models and improves the overall PCG classification accuracy. Mel Frequency Cepstral Coefficients (MFCC) capture the crucial audio signal characteristics relevant to the classification. The amalgamation of these two deep learning structures enhances the precision and reliability of PCG classification, leading to improved diagnostic results. RESULTS: The HbNet model exhibited excellent results with an average accuracy of 99.72% and sensitivity of 99.3% on an adult dataset, surpassing all the existing state-of-the-art works. The researchers have validated the reliability of the HbNet model by testing it on a real-time paediatric dataset. The paediatric model’s accuracy is 86.5%. HbNet detected functional murmur with 100% precision. CONCLUSION: The results indicate that the HbNet model exhibits a high level of efficacy in the early detection of cardiac disorders. Results also imply that HbNet has the potential to serve as a valuable tool for the development of decision-support systems that aid medical practitioners in confirming their diagnoses. This method makes it easier for medical professionals to diagnose and initiate prompt treatment while performing preliminary auscultation and reduces unnecessary echocardiograms. Show more

Keywords: Blended ensemble, mel frequency cepstral coefficient, meta-learner, phonocardiogram, softmax regression

DOI: 10.3233/THC-231290

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1925-1945, 2024

Authors: Liu, Lili

Article Type: Research Article

Abstract: BACKGROUND: Osteoporosis is a medical disorder that causes bone tissue to deteriorate and lose density, increasing the risk of fractures. Applying Neural Networks (NN) to analyze medical imaging data and detect the presence or severity of osteoporosis in patients is known as osteoporosis classification using Deep Learning (DL) algorithms. DL algorithms can extract relevant information from bone images and discover intricate patterns that could indicate osteoporosis. OBJECTIVE: DCNN biases must be initialized carefully, much like their weights. Biases that are initialized incorrectly might affect the network’s learning dynamics and hinder the model’s ability to converge to …an ideal solution. In this research, Deep Convolutional Neural Networks (DCNNs) are used, which have several benefits over conventional ML techniques for image processing. METHOD: One of the key benefits of DCNNs is the ability to automatically Feature Extraction (FE) from raw data. Feature learning is a time-consuming procedure in conventional ML algorithms. During the training phase of DCNNs, the network learns to recognize relevant characteristics straight from the data. The Squirrel Search Algorithm (SSA) makes use of a combination of Local Search (LS) and Random Search (RS) techniques that are inspired by the foraging habits of squirrels. RESULTS: The method made it possible to efficiently explore the search space to find prospective values while using promising areas to refine and improve the solutions. Effectively recognizing optimum or nearly optimal solutions depends on balancing exploration and exploitation. The weight in the DCNN is optimized with the help of SSA, which enhances the performance of the classification. CONCLUSION: The comparative analysis with state-of-the-art techniques shows that the proposed SSA-based DCNN is highly accurate, with 96.57% accuracy. Show more

Keywords: Osteoporosis, classification, accuracy, optimization, bias, neural network, and squirrel search

DOI: 10.3233/THC-231517

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1947-1965, 2024

Authors: Sun, Yi | Ren, Tao | Ji, Xueli

Article Type: Research Article

Abstract: BACKGROUND: Currently, cerebral infarction (CI) is mainly treated by emergency craniotomy or conservative treatment. However, some studies have questioned the functional recovery of patients after hyperbaric oxygen therapy (HBOT)-specialized care. OBJECTIVE: This paper mainly explores the influence of HBOT-specialized care on limb motor function (LMF) and mental state of CI patients with hemiplegia. METHODS: The medical records of 113 CI patients with hemiplegia treated in our hospital from March 2020 to March 2022 were collected. Of these, 53 received routine care nursing (conventional group) and 60 cases were given HBOT-specialized care (research group). …Patient general data, scores of Fugl-Meyer Assessment (FMA), National Institutes of Health Stroke Scale (NIHSS), Self-rating Anxiety/Depression Scale (SAS/SDS) and Barthel Index (BI), and nursing efficiency were comparatively analyzed. RESULTS: The two groups showed comparability in general data. FMA and BI scores were increased in the research group after rehabilitation treatment, higher than the baseline and those of the conventional group, while NIHSS, SAS, and SDS scores were reduced, lower compared with baseline and those of the conventional group. In addition, significantly higher nursing efficiency was determined in the research group. CONCLUSION: HBOT-specialized care has beneficial effects on LMF, mental state, negative emotions and self-care ability of CI patients with hemiplegia and can enhance nursing efficacy, which deserves clinical popularization. Show more

Keywords: Hyperbaric oxygen therapy-specialized care, hyperbaric oxygen, cerebral infarction, motor function, mental state

DOI: 10.3233/THC-231643

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1967-1976, 2024

Authors: Wu, Mingzhen | Luan, Jixin | Zhang, Di | Fan, Hua | Qiao, Lishan | Zhang, Chuanchen

Article Type: Research Article

Abstract: BACKGROUND: Histopathological evaluation is currently the gold standard for grading gliomas; however, this technique is invasive. OBJECTIVE: This study aimed to develop and validate a diagnostic prediction model for glioma by employing multiple machine learning algorithms to identify risk factors associated with high-grade glioma, facilitating the prediction of glioma grading. METHODS: Data from 1114 eligible glioma patients were obtained from The Cancer Genome Atlas (TCGA) database, which was divided into a training set (n = 781) and a test set (n = 333). …Fifty machine learning algorithms were employed, and the optimal algorithm was selected to construct a prediction model. The performance of the machine learning prediction model was compared to the clinical prediction model in terms of discrimination, calibration, and clinical validity to assess the performance of the prediction model. RESULTS: The area under the curve (AUC) values of the machine learning prediction models (training set: 0.870 vs. 0.740, test set: 0.863 vs. 0.718) were significantly improved from the clinical prediction models. Furthermore, significant improvement in discrimination was observed for the Integrated Discrimination Improvement (IDI) (training set: 0.230, test set: 0.270) and Net Reclassification Index (NRI) (training set: 0.170, test set: 0.170) from the clinical prognostic model. Both models showed a high goodness of fit and an increased net benefit. CONCLUSION: A strong prediction accuracy model can be developed using machine learning algorithms to screen for high-grade glioma risk predictors, which can serve as a non-invasive prediction tool for preoperative diagnostic grading of glioma. Show more

Keywords: Glioma, machine learning, prediction model, grading, risk predictors

DOI: 10.3233/THC-231645

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1977-1990, 2024

Authors: Muniasamy, Anandhavalli | Begum, Arshiya | Sabahath, Asfia | yaqub, Humara | Karunakaran, Gauthaman

Article Type: Research Article

Abstract: BACKGROUND: Coronary heart disease (CHD) is one of the deadliest diseases and a risk prediction model for cardiovascular conditions is needed. Due to the huge number of features that lead to heart problems, it is often difficult for an expert to evaluate these huge features into account. So, there is a need of appropriate feature selection for the given CHD dataset. For early CHD detection, deep learning modes (DL) show promising results in the existing studies. OBJECTIVE: This study aimed to develop a deep convolution neural network (CNN) model for classification with a selected number of …efficient features using the LASSO (least absolute shrinkage and selection operator) technique. Also, aims to compare the model with similar studies and analyze the performance of the proposed model using accuracy measures. METHODS: The CHD dataset of NHANES (National Health and Nutritional Examination Survey) was examined with 49 features using LASSO technique. This research work is an attempt to apply an improved CNN model for the classification of the CHD dataset with huge features CNN model with feature extractor consists of a fully connected layer with two convolution 1D layers, and classifier part consists of two fully connected layers with SoftMax function was trained on this dataset. Metrics like accuracy recall, specificity, and ROC were used for the evaluation of the proposed model. RESULTS: The feature selection was performed by applying the LASSO model. The proposed CNN model achieved 99.36% accuracy, while previous studies model achieved over 80 to 92% accuracy. CONCLUSION: The application of the proposed CNN with the LASSO model for the classification of CHD can speed up the diagnosis of CHD and appears to be effective in predicting cardiovascular disease based on risk features. Show more

Keywords: Coronary heart disease, deep learning, machine learning, LASSO, convolutional neural network

DOI: 10.3233/THC-231807

Citation: Technology and Health Care, vol. 32, no. 3, pp. 1991-2007, 2024