Technology and Health Care - Volume 32, issue 6

Authors: K. P, Ajitha Gladis | D, Roja Ramani | N, Mohana Suganthi | P, Linu Babu

Article Type: Research Article

Abstract: BACKGROUND: Gastrointestinal tract (GIT) diseases impact the entire digestive system, spanning from the mouth to the anus. Wireless Capsule Endoscopy (WCE) stands out as an effective analytic instrument for Gastrointestinal tract diseases. Nevertheless, accurately identifying various lesion features, such as irregular sizes, shapes, colors, and textures, remains challenging in this field. OBJECTIVE: Several computer vision algorithms have been introduced to tackle these challenges, but many relied on handcrafted features, resulting in inaccuracies in various instances. METHODS: In this work, a novel Deep SS-Hexa model is proposed which is a combination two different deep …learning structures for extracting two different features from the WCE images to detect various GIT ailment. The gathered images are denoised by weighted median filter to remove the noisy distortions and augment the images for enhancing the training data. The structural and statistical (SS) feature extraction process is sectioned into two phases for the analysis of distinct regions of gastrointestinal. In the first stage, statistical features of the image are retrieved using MobileNet with the support of SiLU activation function to retrieve the relevant features. In the second phase, the segmented intestine images are transformed into structural features to learn the local information. These SS features are parallelly fused for selecting the best relevant features with walrus optimization algorithm. Finally, Deep belief network (DBN) is used classified the GIT diseases into hexa classes namely normal, ulcer, pylorus, cecum, esophagitis and polyps on the basis of the selected features. RESULTS: The proposed Deep SS-Hexa model attains an overall average accuracy of 99.16% in GIT disease detection based on KVASIR and KID datasets. The proposed Deep SS-Hexa model achieves high level of accuracy with minimal computational cost in the recognition of GIT illness. CONCLUSIONS: The proposed Deep SS-Hexa Model progresses the overall accuracy range of 0.04%, 0.80% better than GastroVision, Genetic algorithm based on KVASIR dataset and 0.60%, 1.21% better than Modified U-Net, WCENet based on KID dataset respectively. Show more

Keywords: Gastrointestinal tract, wireless capsule endoscopy, mobile network, structural and statistical features, deep belief network

DOI: 10.3233/THC-240603

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4453-4473, 2024

Authors: Teng, Xiaohuan | Sun, Yanrong | Zhao, Landi | Kang, Yingxian

Article Type: Research Article

Abstract: BACKGROUND: In 2019, approximately 330 million individuals in China were affected by cardiovascular diseases, with 11.4 million cases specifically attributed to coronary artery disease (CAD). A national public health report indicated that the mortality rate for CAD ranged from 121.59 to 130.14 per 100,000 individuals in 2019. The treatments for CAD include lifestyle changes, medications, percutaneous coronary intervention (PCI) and coronary artery bypass grafting. OBJECTIVE: To investigate the management effect of a digital health program in patients with coronary artery disease (CAD) after percutaneous coronary intervention (PCI). METHODS: This retrospective study compares …blood pressure, blood glucose, low-density lipoprotein cholesterol (LDL-C), medication adherence, lifestyle modification, and readmission rate between digital health users and traditional follow-up in post-PCI CAD patients. RESULTS: In this study of 698 CAD patients, the 6-month readmission rate of all patients was 27.4%, with digital health users showing lower rates than those in traditional follow-up (22.6% vs. 32.1%, p = 0.005). Digital health users had significantly higher target achievements rates in blood pressure (79.7% vs. 54.7%, p < 0.001), blood glucose (98.9% vs. 82.5%, p < 0.001) and LDL-C level (71.3% vs. 52.7%, p < 0.001) at 6-month post-PCI. The digital health group had more patients adopting lifestyle changes, including quitting smoking, maintaining a healthy diet, and exercising regularly. In risk factor analysis, digital health utilization (OR = 0.60, 95%CI: 0.40–0.90, p = 0.014) and multivessel disease (double: OR = 1.72, 95%CI: 1.09—2.72, p = 0.02; triple: OR = 2.59, 95%CI: 1.61–4.17, p < 0.001) were independent predictors of CAD-related cardiovascular readmissions. CONCLUSIONS: Post-PCI patients using digital health platforms exhibited improved blood pressure, glucose, and LDL-C control, greater treatment adherence, enhanced lifestyle changes, and reduced six-month readmission rates versus those with traditional follow-up. Show more

Keywords: Coronary artery disease, PCI, disease management, digital health

DOI: 10.3233/THC-240621

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4475-4484, 2024

Authors: Radhakrishnan, Menaka | Ramamurthy, Karthik | Shanmugam, Saranya | Prasanna, Gaurav | S, Vignesh | Y, Surya | Won, Daehan

Article Type: Research Article

Abstract: BACKGROUND: Autism Spectrum Disorder (ASD) is a condition with social interaction, communication, and behavioral difficulties. Diagnostic methods mostly rely on subjective evaluations and can lack objectivity. In this research Machine learning (ML) and deep learning (DL) techniques are used to enhance ASD classification. OBJECTIVE: This study focuses on improving ASD and TD classification accuracy with a minimal number of EEG channels. ML and DL models are used with EEG data, including Mu Rhythm from the Sensory Motor Cortex (SMC) for classification. METHODS: Non-linear features in time and frequency domains are extracted and ML …models are applied for classification. The EEG 1D data is transformed into images using Independent Component Analysis-Second Order Blind Identification (ICA-SOBI), Spectrogram, and Continuous Wavelet Transform (CWT). RESULTS: Stacking Classifier employed with non-linear features yields precision, recall, F1-score, and accuracy rates of 78%, 79%, 78%, and 78% respectively. Including entropy and fuzzy entropy features further improves accuracy to 81.4%. In addition, DL models, employing SOBI, CWT, and spectrogram plots, achieve precision, recall, F1-score, and accuracy of 75%, 75%, 74%, and 75% respectively. The hybrid model, which combined deep learning features from spectrogram and CWT with machine learning, exhibits prominent improvement, attained precision, recall, F1-score, and accuracy of 94%, 94%, 94%, and 94% respectively. Incorporating entropy and fuzzy entropy features further improved the accuracy to 96.9%. CONCLUSIONS: This study underscores the potential of ML and DL techniques in improving the classification of ASD and TD individuals, particularly when utilizing a minimal set of EEG channels. Show more

Keywords: Independent component analysis – Second Order Blind Identification (ICA – SOBI), Continuous Wavelet transform (CWT), stacking classifier, hybrid model, spectrogram, electroencephalogram

DOI: 10.3233/THC-240644

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4485-4503, 2024

Authors: Cui, Lin | Zhang, Xueyan | Wen, Yingying | Li, Cuihua | Zhang, Jianyun | Cui, XiWei | Sun, Hao | Chang, Liu

Article Type: Research Article

Abstract: BACKGROUND: Endoscopic submucosal dissection (ESD) is a well-established treatment for gastrointestinal tumors and enables en bloc resection. Adequate counter traction with good visualization is important for safe and effective dissection. OBJECTIVE: Based on magnetic anchor-guided endoscopic submucosal dissection (MAG-ESD), we would like to explore the feasibility of magnetic hydrogel as an internal magnetic anchor that can be injected into the submucosa through an endoscopic needle to assist colonic endoscopic submucosal dissection. METHODS: This prospective trial was conducted on 20 porcine colons ex vivo. We injected magnetic hydrogel into submucosa of the porcine colons …ex vivo for MAG-ESD to evaluate the traction effect and operation satisfaction. RESULTS: Magnetic hydrogel assisted ESD was successfully performed on 20 porcine colons ex vivo. Adequate counter traction with good visualization was successfully obtained during the procedure of dissection. CONCLUSION: Magnetic hydrogel assisted MAG-ESD is feasible and effective. Show more

Keywords: Magnetic surgery, magnetic hydrogel, magnetic anchor-guided endoscopic submucosal dissection, colonic tumorsMain points:•Magnetic hydrogel can play the role of target magnet during ESD, which can provide adequate counter traction with good visualization and effective dissection;•Magnetic hydrogel can make ESD more simple and efficient, shorten the procedure time, improve the endoscopists’ satisfaction, especially for ESD beginners more friendly.

DOI: 10.3233/THC-240653

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4505-4514, 2024

Authors: Zhao, Zhifeng | Yua, Yadong

Article Type: Research Article

Abstract: BACKGROUND: Lung cancer (LC) is one of the leading causes of death worldwide. Treatment methodologies such as chemotherapy and radiotherapy have improved patient survival rates. Nevertheless, these treatments can also lead to adverse reactions and impact patients’ nutritional status and quality of life (QOL). Antibiotics are commonly used for treating infections, but there is still controversy regarding their potential adverse effects on LC patients. OBJECTIVE: This work aimed to investigate the impact of antibiotic adoption on the nutritional status and QOL of LC patients undergoing radiotherapy or chemotherapy, providing valuable insights for the clinical management of …LC. METHODS: A meta-analysis approach was employed to comprehensively evaluate the relationship by synthesizing relevant literature. Published studies were identified through searches in databases such as PubMed, EMBASE, Cochrane Library, Web of Science, and CNKI. The inclusion criteria encompassed randomized controlled trials, cohort studies, and cross-sectional studies. Assessment indicators included patient weight, BMI, hemoglobin levels, and QOL. Meta-analysis was conducted using software such as the Cochrane Collaboration and RevMan5.3. Heterogeneity was evaluated using the Higgins I 2 index, where values between 25% and 50% indicate moderate heterogeneity, and values greater than 50% indicate substantial heterogeneity. RESULTS: 12 eligible studies involving 1,917 patients were finally included. LC patients who received antibiotics during radiotherapy or chemotherapy were found to have a higher risk of malnutrition. The antibiotic group exhibited a more significant decrease in body mass index (BMI) (P < 0.05) and lower serum albumin levels (P < 0.05) versus the control (C) group. Additionally, the overall QOL scores in the antibiotic group were dramatically lower than those in the C group, showing a significant difference with P < 0.05. Sensitivity analysis indicated that the overall conclusions of this work were robust and unbiased. CONCLUSION: Antibiotics in LC patients undergoing radiotherapy or chemotherapy may increase the risk of malnutrition and decrease their QOL. Hence, physicians should carefully consider antibiotics and take necessary preventive measures and supportive treatments to improve LC patients’ nutritional status and QOL. Show more

Keywords: Antibiotics, lung cancer patients, radiotherapy, chemotherapy, nutritional status, quality of life

DOI: 10.3233/THC-240660

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4515-4536, 2024

Authors: Takahashi, Hakuo | Yamashita, Shingo | Yakura, Nobuki

Article Type: Research Article

Abstract: BACKGROUND: Blood pressure (BP) naturally undergoes fluctuations and variations, particularly during anesthesia administration during surgery, hemodialysis, upper and lower gastrointestinal endoscopy, exercise testing, arterial and venous catheterization, and rehabilitation. These changes in BP may lead to life-threatening events. OBJECTIVES: The performance of the Omron HBP-M4500 device in monitoring blood pressure (BP) in the upper arm was validated according to the International Organization for Standardization (ISO) 81060-2:2018+ amendment (Amd) 1:2020 protocol. METHODS: The device was used to assess 113 participants in the inflation mode, and 107 participants in the deflation mode. All …the patients fulfilled the inclusion criteria, including the arm circumference range and systolic and diastolic BP levels, outlined in the protocol. Data validation and analysis were performed according to the manufacturer’s instructions. RESULTS: In criterion 1, the mean ± standard deviation (SD) values of the differences between the test device and reference BP were - 0.6 ± 5.80/2.8 ± 6.78 mmHg (systolic/diastolic) and - 1.0 ± 5.35/3.2 ± 6.52 mmHg for the inflation and deflation modes, respectively. These data fulfilled the ISO81060-2:2018+ Amd1:2020 requirements of ⩽ 5 ± ⁣ ⩽ 8 mmHg. In criterion 2, the differences were - 0.6 ± 4.44/2.8 ± 6.26 and - 1.0 ± 3.84/3.2 ± 6.09 mmHg for the inflation and deflation modes, respectively, fulfilling criterion 2 with SD values of ⩽ 6.91 and ⩽ 6.87 for systolic BP and ⩽ 6.34 and ⩽ 6.14 for diastolic BP in the inflation and deflation modes, respectively. These two criteria were fulfilled in both studies. CONCLUSION: The Omron HBP-M4500 device, either in inflation or deflation mode, fulfilled the criteria outlined in the ISO protocol. Therefore, this device is valuable for BP measurement in clinical and hospital settings. Show more

Keywords: Blood pressure monitoring device, validation study, international protocol

DOI: 10.3233/THC-240676

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4537-4544, 2024

Authors: Mansoor, C.M.M. | Chettri, Sarat Kumar | Naleer, H.M.M.

Article Type: Research Article

Abstract: BACKGROUND: Heart disease is a severe health issue that results in high fatality rates worldwide. Identifying cardiovascular diseases such as coronary artery disease (CAD) and heart attacks through repetitive clinical data analysis is a significant task. Detecting heart disease in its early stages can save lives. The most lethal cardiovascular condition is CAD, which develops over time due to plaque buildup in coronary arteries, causing incomplete blood flow obstruction. Machine Learning (ML) is progressively used in the medical sector to detect CAD disease. OBJECTIVE: The primary aim of this work is to deliver a state-of-the-art approach …to enhancing CAD prediction accuracy by using a DL algorithm in a classification context. METHODS: A unique ML technique is proposed in this study to predict CAD disease accurately using a deep learning algorithm in a classification context. An ensemble voting classifier classification model is developed based on various methods such as Naïve Bayes (NB), Logistic Regression (LR), Decision Tree (DT), XGBoost, Random Forest (RF), Convolutional Neural Network (CNN), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Bidirectional LSTM and Long Short-Term Memory (LSTM). The performance of the ensemble models and a novel model are compared in this study. The Alizadeh Sani dataset, which consists of a random sample of 216 cases with CAD, is used in this study. Synthetic Minority Over Sampling Technique (SMOTE) is used to address the issue of imbalanced datasets, and the Chi-square test is used for feature selection optimization. Performance is assessed using various assessment methodologies, such as confusion matrix, accuracy, recall, precision, f1-score, and auc-roc. RESULTS: When a novel algorithm achieves the highest accuracy relative to other algorithms, it demonstrates its effectiveness in several ways, including superior performance, robustness, generalization capability, efficiency, innovative approaches, and benchmarking against baselines. These characteristics collectively contribute to establishing the novel algorithm as a promising solution for addressing the target problem in machine learning and related fields. CONCLUSION: Implementing the novel model in this study significantly improved performance, achieving a prediction accuracy rate of 92% in the detection of CAD. These findings are competitive and on par with the top outcomes among other methods. Show more

Keywords: Machine learning, coronary artery disease, heart disease, feature selection, classification

DOI: 10.3233/THC-240740

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4545-4569, 2024

Authors: Liu, Fengjie | Wang, Buquan | Mao, Chenggang

Article Type: Research Article

Abstract: BACKGROUND: Allergic Rhinitis (AR), a prevalent condition in otorhinolaryngology, is mediated by Type 1 hypersensitivity through IgE, characterized by Type 2 inflammatory response and eosinophil infiltration in the nasal mucosa. Since AR disease exhibits significant heterogeneity in symptom severity, an objective assessment of AR severity may facilitate better individualized treatment. OBJECTIVE: To explore the changes in peripheral blood IL-9, Th9, and BAFF levels of allergic rhinitis (AR) in patients and the clinical significance associated with it. METHODS: A retrospective study selected 80 AR patients admitted from January 2022 to October 2022 as the …case group, dividing them into mild and moderate-to-severe groups based on symptom scores. Concurrently, 50 patients without AR, who were treated for nasal bone fractures or underwent septoplasty, were selected as the group for comparison. Alterations in the expression levels of peripheral blood IL-9, Th9, and BAFF were analyzed and compared among the different groups. The diagnostic value of serum BAFF for the severity of AR was analyzed using the receiver operating characteristic (ROC) curve. RESULTS: Noticeable variations were observed in clinical variables among the three groups such as, total IgE levels, peripheral blood eosinophil count and proportion, TNSS, and VAS (P < 0.05), while no statistically significant differences were observed in other variables (P > 0.05). The comparison of IL-9, Th9, and BAFF among the three groups revealed statistically significant differences (P < 0.05). Analysis using multivariate logistic regression revealed that IL-9 (OR = 2.365), Th9 (OR = 2.186), BAFF (OR = 2.307) were influencing factors of moderate-to-severe AR (P < 0.05). The ROC curve indicated that the AUC for the diagnosis of moderate-to-severe AR by IL-9, Th9, BAFF were 0.770, 0.734, 0.761, respectively, and the combined detection AUC was 0.888, an area under the curve higher than individual testing. CONCLUSION: Changes in peripheral blood IL-9, Th9, and BAFF levels in AR patients may function as indicators to assess the level of severity in diagnostic procedures. Show more

Keywords: Allergic rhinitis, peripheral blood, IL-9, Th9, BAFF, clinical significance

DOI: 10.3233/THC-240756

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4571-4580, 2024

Authors: Cai, Zhuhua | Guo, Xueke | Zheng, Ge | Xiang, Junmiao | Liu, Lingyun | Lin, Dongmei | Deng, Xiaohui

Article Type: Research Article

Abstract: BACKGROUND: Elevated levels of tumor necrosis factor-alpha (TNF-α ) have been associated with adverse pregnancy outcomes, specifically recurrent pregnancy loss (RPL). These elevated levels may be associated with the presence of autoantibodies. Although TNF-α inhibitors have shown promise in improving pregnancy rates, further research is needed to comprehend their impact and mechanisms in RPL patients. OBJECTIVE: This study aims to investigate the association between elevated TNF-α levels and autoantibodies in RPL patients, as well as evaluate the effect of TNF-α inhibition on pregnancy outcomes. …METHODS: A total of 249 RPL patients were included in this study. Serum levels of TNF-α , autoantibodies, and complement were measured and monitored. Among these patients, 138 tested positive for TNF-α , while 111 tested negative. The medical records of these patients were retrospectively evaluated. Additionally, 102 patients with elevated TNF-α levels were treated with TNF-α inhibitors, and their pregnancy outcomes were assessed. RESULTS: TNF-α -positive RPL patients had higher levels of complement C1q, anti-cardiolipin (ACL)-IgA, ACL-IgM ,ACL-IgG, thyroglobulin antibody, and Anti-phosphatidylserine/prothrombin IgM antibody, as well as a higher positive rate of antinuclear antibodies compared to TNF-α -negative patients (23.19% vs. 12.6%, P < 0.05). Conversely, complement C3 were lower in TNF-α -positive patients (t test, P < 0.05). The use of TNF-α inhibitors led to a reduction in the early abortion rate (13.7% vs. 44.4%, P < 0.001) and an improvement in term delivery rate (52.0% vs. 27.8%, P = 0.012). Furthermore, patients who used TNF-α inhibitors before 5 weeks of pregnancy had a lower early abortion rate (7.7% vs. 24.3%, P = 0.033) and a higher term delivery rate (69.2% vs. 48.6%, P = 0.033). CONCLUSION: TNF-α plays a role in the occurrence and development of RPL, and its expression is closely associated with autoantibodies and complements. TNF-α inhibitors increase the term delivery rate in TNF-α -positive RPL patients, and their use before 5 weeks of pregnancy may more beneficial. Show more

Keywords: Antinuclear antibodies, anti-phospholipid antibodies, estrogen, human chorionic gonadotropin, pregnancy, pregnancy outcome, tumor necrosis factor

DOI: 10.3233/THC-240757

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4581-4591, 2024

Authors: Hu, Xia | Jiang, Huiqing | Liu, Peizhen | Li, Zhiquan | Zhang, Ruiying

Article Type: Research Article

Abstract: BACKGROUND: The Stepped Care Model (SCM) is an evidence-based treatment approach that tailors treatment intensity based on patients’ health status, aiming to achieve the most positive treatment outcomes with the least intensive and cost-effective interventions. Currently, the effectiveness of the Stepped Care Model in postoperative rehabilitation for TKA (Total Knee Arthroplasty) patients has not been reported. OBJECTIVE: The present study aimed to investigate whether the stepped care model could improve early-stage self-report quality of life and knee function after total knee arthroplasty via a prospective randomized controlled design. METHODS: It was a mono-center, …parallel-group, open-label, prospective randomized controlled study. Patients who aging from 60–75 years old as well as underwent unilateral primary total knee arthroplasty due to end-stage knee osteoarthritis between 2020.06 to 2022.02 were enrolled. Participants were randomized and arranged into two groups in a 1:1 allocation. The control group was given traditional rehabilitation guidance, while the stepped care model group was given continued stepped care. Hospital for special surgery knee score, daily living ability (ADL), knee flexion range, and adverse events at 1, 3, and 6 months after total knee arthroplasty were recorded. RESULTS: 88 patients proceeded to the final analysis. There was no significant difference of age, gender, length of stay, BMI, and educational level between the two groups at the baseline. After specific stepped care model interventions, patients showed significant improvements in HHS in 1 month (85.00 (82.25, 86.00) vs. 80.00 (75.00, 83.00), p < 0.001), 3 months (88.00 (86.00, 92.00) vs. 83.00 (76.75, 85.00), p < 0.001), and 6 months (93.00 (90.25, 98.00) vs. 88.00 (84.25, 91.75), p < 0.001) when compared with the control group. Similar results were also found in both daily living ability and knee flexion angle measurements. No adverse event was observed during the follow-up. CONCLUSION: The present study found that the stepped care model intervention significantly improved early-stage knee function and self-reported life quality after total knee arthroplasty due to knee osteoarthritis. Female patients and those less than 70 years old benefit more from the stepped care model intervention after total knee arthroplasty. Show more

Keywords: Stepped care model, total knee arthroplasty, randomized controlled trail, knee function, life quality

DOI: 10.3233/THC-240780

Citation: Technology and Health Care, vol. 32, no. 6, pp. 4593-4601, 2024