Technology and Health Care最新文献

Background: With the advent of artificial intelligence technology, machine learning algorithms have been widely used in the area of disease prediction.

Objective: Cardiovascular disease (CVD) seriously jeopardizes human health worldwide, thereby needing the establishment of an effective CVD prediction model that can be of great significance for controlling the risk of the disease and safeguarding the physical and mental health of the population.

Methods: Considering the UCI heart disease dataset as an example, initially, a single machine learning prediction model was constructed. Subsequently, six methods such as Pearson, chi-squared, RFE and LightGBM were comprehensively used for the feature screening. On the basis of the base classifiers, Soft Voting fusion and Stacking fusion was carried out to build a prediction model for cardiovascular diseases, in order to realize an early warning and disease intervention for high-risk populations. To address the data imbalance problem, the SMOTE method was adopted to process the data set, and the prediction effect of the model was analyzed using multi-dimensional and multi-indicators.

Results: In the single classifier model, the MLP algorithm performed optimally on the preprocessed heart disease dataset. After feature selection, five features eliminated. The ENSEM_SV algorithm that combines the base classifiers to determine the prediction results by soft voting on the results of the classifiers achieved the optimal value on five metrics such as Accuracy, Jaccard_Score, Hamm_Loss, AUC, etc., and the AUC value reached 0.951. The RF, ET, GBDT, and LGB algorithms were employed in the first stage sub-model composed of base classifiers. The AB algorithm was selected as the second stage model, and the ensemble algorithm ENSEM_ST, obtained by Stacking fusion of the two stages exhibited the best performance on 7 indicators such as Accuracy, Sensitivity, F1_Score, Mathew_Corrcoef, etc., and the AUC reached 0.952. Furthermore, a comparison of the algorithms' classification effects based on different training set occupancy was carried out. The results indicated that the prediction performance of both the fusion models was better than the single models, and the overall effect of ENSEM_ST fusion was stronger than the ENSEM_SV fusion.

Conclusions: The fusion model established in this study improved the overall classification accuracy and stability of the model to a significant extent. It has a good application value in the predictive analysis of CVD diagnosis, and can provide a valuable reference in the disease diagnosis and intervention strategies.

Background: The dominant feature of Alzheimer's dementia (AD) is gradual cognitive decline, which can be reflected by reduced finger dexterity.

Objective: This review analyzed reports on hand function in AD patients to determine the possibility of using it for an early diagnosis and for monitoring the disease progression of AD.

Methods: PubMed, Web of Science, EMBASE, and Cochrane library were searched systematically (search dates: 2000-2022), and relevant articles were cross-checked for related and relevant publications.

Results: Seventeen studies assessed the association of the handgrip strength or dexterity with cognitive performance. The hand dexterity was strongly correlated with the cognitive function in all studies. In the hand dexterity test using the pegboard, there was little difference in the degree of decline in hand function between the healthy elderly (HE) group and the mild cognitive impairment (MCI) group. On the other hand, there was a difference in the hand function between the HE group and the AD group. In addition, the decline in hand dexterity is likely to develop from moderate to severe dementia. In complex hand movements, movement speed variations were greater in the AD than in the HE group, and the automaticity, regularity, and rhythm were reduced.

Conclusions: HE and AD can be identified by a simple hand motion test using a pegboard. The data can be used to predict dementia progression from moderate dementia to severe dementia. An evaluation of complex hand movements can help predict the transition from MCI to AD and the progression from moderate to severe dementia.

Background: The number of studies which investigate the association between TLR9 gene polymorphism and Helicobacter pylori (H.pylori) infection is low and their results are not consistent.

Objective: To get a better understanding of the association between TLR9 gene polymorphism and H.pylori infection, providing basis and risk assessment for precision nursing for hospital nurses.

Methods: A total of 630 normal physical examination subjects were collected including 240 H.pylori (+) and 390 H.pylori (-) subjects. PCR-RFLP was applied to investigate the present polymorphism. At the same time, the meta-analysis was performed between TLR9 gene polymorphism and H.pylori infection risk.

Results: Three genotypes (TT, TC, and CC) were observed for TLR9 gene rs187084 polymorphism. CC genotype and C allele were responsible for the significant associations (all P< 0.05). Meta-analysis found no significant associations were found by any genetic models (all P> 0.05).

Conclusion: TLR9 polymorphism has a crucial role in H.pylori infection risk and CC genotype confers increased risk to H.pylori infection in the Southern Chinese population. After understanding the influence of TLR9 gene polymorphism on H.pylori infection, nurses can improve the risk assessment of Helicobacter pylori infection and provide health education more personally.

Background: The most effective clinical treatment for hepatocellular carcinoma (HCC) is surgery, but most patients are diagnosed when the disease has progressed.

Objective: To examine the long-term prognosis and clinical effectiveness of PD-L1 inhibitor-targeted therapy for patients suffering from HCC.

Methods: Ninety-six patients with advanced HCC who were admitted to our hospital between December 2019 and April 2022 were split into two groups based on the treatment plan after a retrospective analysis: 43 patients in the control group underwent sorafenib-based targeted therapy, while dulvalizumab was used to treat 53 patients in the observation group. Observation indexes were used to assess the clinical effectiveness and long-term prognosis of HCC patients receiving targeted therapy with dulvalizumab, which included the disease control rate, tumor markers, immune function, survival, quality of survival, and the occurrence of unfavorable side effects such as thrombocytopenia, leukopenia, vomiting, and rash.

Results: The initial KPS scores, CEA, CA199, AFP, CD3+, CD4+, CD4+/CD8+, IgG, IgM, and IgA levels did not differ significantly between the two groups (P> 0.05). After treatment, the observation group showed a significantly higher disease control rate (92.45% vs. 74.42%) and improved KPS score, OS, PFS, CD3+, CD4+, CD4+/CD8+, IgG, IgM, and IgA levels compared to the control group. Additionally, the observation group exhibited significantly reduced CEA, CA199, and AFP levels, and a lower overall incidence of adverse reactions (16.98% vs. 51.16%) compared to the control group (P< 0.05).

Conclusion: The clinical efficacy of dulvalizumab-targeted treatment of HCC among PD-L1 inhibitors is better, enhancing the disease's ability to be controlled considerably lowering patients' levels of tumor markers. This greatly boosts patients' immune systems, extends their lives and improves the quality of their survival. The frequency of negative reactions is minimal and safe.

Background: A gradually reducing radius (GRADIUS) design implant can facilitate a smooth transition from stability through full range of motion in total knee arthroplasty (TKA). Nonetheless, patient-specific factors associated with good knee flexion remain unclear.

Objective: This study aimed to determine the factors associated with good knee flexion after cruciate-retaining TKA with a GRADIUS prosthesis in an Asian population.

Methods: This retrospective study included 135 patients that were stratified according to postoperative knee flexion angle (KFA) into Group F (⩾ 120∘; 85 patients [63.2%]) and Group NF (< 120∘; 50 patients [36.8%]).

Results: Patients in Group F were taller and had a lower body mass index (BMI) smaller preoperative hipkneeankle angle and better preoperative extension and flexion angle than Group NF patients. The multivariable analysis revealed that patients' height (odds ratio [OR]: 1.07, P= 0.0150), BMI (OR: 0.85, P= 0.0049), and preoperative flexion angle (OR: 1.06, P= 0.0008) predicted good KFA. The ROC curve analysis showed that the cutoff values of a good KFA were height 155.1 cm, BMI 22.1 kg/m2, and preoperative KFA 120∘.

Conclusions: Patient height, BMI, and preoperative KFA were independent factors affecting good postoperative KFA in patients of Asian descent who underwent cruciate-retaining TKA with a GRADIUS design.

Background: The theory of Chinese medicine (TCM) constitution contributes to the optimisation of individualised healthcare programmes. However, at present, TCM constitution identification mainly relies on inefficient questionnaires with subjective bias. Efficient and accurate TCM constitution identification can play an important role in individualised medicine and healthcare.

Objective: Building an efficient model for identifying traditional Chinese medicine constitutions using objective tongue features and machine learning techniques.

Methods: The DS01-A device was applied to collect tongue images and extract features. We trained and evaluated five machine learning models: Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), LightGBM (LGBM), and CatBoost (CB). Among these, we selected the model with the best performance as the base classifier for constructing our heterogeneous ensemble learning model. Using various performance metrics, including classification accuracy, precision, recall, F1 score, and area under curve (AUC), to comprehensively evaluate model performance.

Results: A total of 1149 tongue images were obtained and 45 features were extracted, forming dataset 1. RF, LGBM, and CB were selected as the base learners for the RLC-Stacking. On dataset 1, RLC-Stacking1 achieved an accuracy of 0.8122, outperforming individual classifiers. After feature selection, the classification accuracy of RLC-Stacking2 improved to 0.8287, an improvement of 0.00165 compared to RLC-Stacking1. RLC-Stacking2 achieved an accuracy exceeding 0.85 for identifying each TCM constitution type, indicating excellent identification performance.

Conclusion: The study provides a reliable method for the accurate and rapid identification of TCM constitutions and can assist clinicians in tailoring individualized medical treatments based on personal constitution types and guide daily health care. The information extracted from tongue images serves as an effective marker for objective TCM constitution identification.

Background: This study presents a comprehensive comparison between a marker-based motion capture system (MMC) and a video-based motion capture system (VMC) in the context of kinematic analysis using musculoskeletal models.

Objective: Focusing on joint angles, the study aimed to evaluate the accuracy of VMC as a viable alternative for biomechanical research.

Methods: Eighteen healthy subjects performed isolated movements with 17 joint degrees of freedom, and their kinematic data were collected using both an MMC and a VMC setup. The kinematic data were entered into the AnyBody Modelling System, which enables the calculation of joint angles. The mean absolute error (MAE) was calculated to quantify the deviations between the two systems.

Results: The results showed good agreement between VMC and MMC at several joint angles. In particular, the shoulder, hip and knee joints showed small deviations in kinematics with MAE values of 4.8∘, 6.8∘ and 3.5∘, respectively. However, the study revealed problems in tracking hand and elbow movements, resulting in higher MAE values of 13.7∘ and 27.7∘. Deviations were also higher for head and thoracic movements.

Conclusion: Overall, VMC showed promising results for lower body and shoulder kinematics. However, the tracking of the wrist and pelvis still needs to be refined. The research results provide a basis for further investigations that promote the fusion of VMC and musculoskeletal models.

Background: Medical imaging techniques have improved to the point where security has become a basic requirement for all applications to ensure data security and data transmission over the internet. However, clinical images hold personal and sensitive data related to the patients and their disclosure has a negative impact on their right to privacy as well as legal ramifications for hospitals.

Objective: In this research, a novel deep learning-based key generation network (Deep-KEDI) is designed to produce the secure key used for decrypting and encrypting medical images.

Methods: Initially, medical images are pre-processed by adding the speckle noise using discrete ripplet transform before encryption and are removed after decryption for more security. In the Deep-KEDI model, the zigzag generative adversarial network (ZZ-GAN) is used as the learning network to generate the secret key.

Results: The proposed ZZ-GAN is used for secure encryption by generating three different zigzag patterns (vertical, horizontal, diagonal) of encrypted images with its key. The zigzag cipher uses an XOR operation in both encryption and decryption using the proposed ZZ-GAN. Encrypting the original image requires a secret key generated during encryption. After identification, the encrypted image is decrypted using the generated key to reverse the encryption process. Finally, speckle noise is removed from the encrypted image in order to reconstruct the original image.

Conclusion: According to the experiments, the Deep-KEDI model generates secret keys with an information entropy of 7.45 that is particularly suitable for securing medical images.

Background: Delayed onset muscle soreness (DOMS) is one of the most prevalent musculoskeletal symptoms in individuals engaged in strenuous exercise programs.

Objective: This study investigated the effects of wearable low-intensity continuous ultrasound on muscle biomechanical properties during DOMS.

Methods: Twenty volunteers were distributed into a wearable ultrasound stimulation group (WUG) (n= 10) and medical ultrasound stimulation group (MUG) (n= 10). All subjects performed wrist extensor muscle strength exercises to induce DOMS. At the site of pain, ultrasound of frequency 3 MHz was applied for 1 h or 5 min in each subject of the WUG or MUG, respectively. Before and after ultrasound stimulation, muscle biomechanical properties (tone, stiffness, elasticity, stress relaxation time, and creep) and body temperature were measured, and pain was evaluated.

Results: A significant decrease was found in the tone, stiffness, stress relaxation time, and creep in both groups after ultrasound stimulation (all p< 0.05). A significant decrease in the pain and increases in temperature were observed in both groups (all p< 0.05). No significant differences were observed between the groups in most evaluations.

Conclusion: The stiffness and pain caused by DOMS were alleviated using a wearable ultrasound stimulator. Furthermore, the effects of the wearable ultrasound stimulator were like those of a medical ultrasound stimulator.

Background: Matrine has been reported inhibitory effects on ovarian cancer (OC) cell progression, development, and apoptosis. However, the molecular targets of matrine against OC and the underlying mechanisms of action remain elusive.

Objective: This study endeavors to unveil the potential targets of matrine against OC and to explore the intricate relationships between these targets and the pathogenesis of OC.

Methods: The effects of matrine on the OC cells (A2780 and AKOV3) viability, apoptosis, migration, and invasion was investigated through CCK-8, flow cytometry, wound healing, and Transwell analyses, respectively. Next, Matrine-related targets, OC-related genes, and ribonucleic acid (RNA) sequence data were harnessed from publicly available databases. Differentially expressed analyses, protein-protein interaction (PPI) network, and Venn diagram were involved to unravel the core targets of matrine against OC. Leveraging the GEPIA database, we further validated the expression levels of these core targets between OC cases and controls. Mendelian randomization (MR) study was implemented to delve into potential causal associations between core targets and OC. The AutoDock software was used for molecular docking, and its results were further validated using RT-qPCR in OC cell lines.

Results: Matrine reduced the cell viability, migration, invasion and increased the cell apoptosis of A2780 and AKOV3 cells (P< 0.01). A PPI network with 578 interactions among 105 candidate targets was developed. Finally, six core targets (TP53, CCND1, STAT3, LI1B, VEGFA, and CCL2) were derived, among which five core targets (TP53, CCND1, LI1B, VEGFA, and CCL2) differential expressed in OC and control samples were further picked for MR analysis. The results revealed that CCND1 and TP53 were risk factors for OC. Molecular docking analysis demonstrated that matrine had good potential to bind to TP53, CCND1, and IL1B. Moreover, matrine reduced the expression of CCND1 and IL1B while elevating P53 expression in OC cell lines.

Conclusions: We identified six matrine-related targets against OC, offering novel insights into the molecular mechanisms underlying the therapeutic effects of matrine against OC. These findings provide valuable guidance for developing more efficient and targeted therapeutic approaches for treating OC.