Technology and Health Care最新文献

{"title":"FHD deep learning prognosis approach: Early detection of fetal heart disease (FHD) using ultrasonography image-based IROI combined multiresolution DCNN.","authors":"Someshwaran G, Sarada V","doi":"10.1177/09287329241310981","DOIUrl":"https://doi.org/10.1177/09287329241310981","url":null,"abstract":"<p><p>Fetal Heart Disease (FHD) is the most prevalent root cause of infant demise which accounts for 21% of all congenital abnormalities, with most instances being catastrophic, thereby rendering the need for early prognosis. Ultrasonography is the forefront imaging modality for assessing fetal growth in four-chamber and blood vessel malformation. Clinically diagnosing the abnormality is time-consuming and requires the skill of a radiologist. In subsequent, numerous preceding research strategies ideal to meta-heuristic and deep learning's Faster Artificial Neural Network (FANN), Dense Recurrent Neural Network (DRNN), Mask-Regional Convolution Neural Network (M RCNN) and Enhanced Deep Learning-assisted CNN aid in the identification of FHD. However, the prediction models have encountered multiple challenges owing to imprecise hinders and irrelevant adhesion. Hence, we propose the automated hierarchical network-driven findings of FHD in four-chamber and blood vessels using ultrasonic 2D imaging which undergoes 3 consequential processes of Enhanced-Adaptive Median Filtering (EAMF) pre-process concerning noise variations i.e., test for SNR distortion and image enhancement i.e., visual quality, Intensified Region of Interest (IROI) segmentation for exploiting feature selection via spatial mask-labeling and Multiresolution Deep Convolutional Neural Network (MDCNN) classification in the detection of diseased pattern via confusion metrics (CM). The lesion findings of CM is determined using MATLAB R2023b with an overall substantial efficiency of 99.79% in both normal and abnormal conditions with a significant potential to assist cardiologists in the prognosis of FHD.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241310981"},"PeriodicalIF":1.4,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143505259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measuring Mini SmartApp usability for ankylosing spondylitis from the perspective of patients and health providers.","authors":"Zepu Wang, Longji Chen, Anqi Wang, Lin Cheng, Jiaxin Fan, Ting Fu, Yan Sang, Hongwu Shen","doi":"10.1177/09287329241312489","DOIUrl":"https://doi.org/10.1177/09287329241312489","url":null,"abstract":"<p><strong>Objective: </strong>To identify beneficial experiences, areas needing improvement, and potential additional value, with a view to providing a reference for the application of mobile health management in clinical practice.</p><p><strong>Methods: </strong>This study applied a mixed research approach to measure the mini smartApp usability among participants who were diagnosed with ankylosing spondylitis at rheumatology and immunology department of the Affiliated Hospital of Nantong University between October 2022 to March 2023 and research staff. This study lasted two weeks. We using the Post-Study System Usability Questionnaire (PSSUQ) and face-to-face semi-structured interview to evaluate the mini smartApp's usability.</p><p><strong>Results: </strong>Altogether 105 participants having follow-up data at 2 weeks were included, of which 94 were AS patients and 13 were research staff. All participants thought the mini SmartApp was useful, with regard to the scores of PSSUQ between baseline was 1.1 (SD:0.63) and 2-week intervention period was 0.98 (SD:0.53). Four themes emerged from test of usability, participants thought mini SmartApp easy to use and can bring several benefits. However, the theme of needing more useful function revealed that mini SmartApp need further improvement in future use.</p><p><strong>Conclusion: </strong>Overall, the mini SmartApp has the potential to be a valuable tool in assisting AS patients with home-based exercise and improving their overall management of the disease.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241312489"},"PeriodicalIF":1.4,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143494388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of elderly patients with inter-trochanteric fracture and failure of postoperative internal fixation.","authors":"Xuepeng Xu, Xin Hu, Lincong Fei, Shi Shen","doi":"10.1177/09287329241307391","DOIUrl":"https://doi.org/10.1177/09287329241307391","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to compare the efficacy and safety of Proximal Femoral Nail Anti-Rotation (PFNA) versus Dynamic Hip Screw (DHS) in the treatment of intertrochanteric fractures (IF) in elderly patients. We specifically evaluate perioperative indicators, postoperative hip function, and the rate of internal fixation failure.</p><p><strong>Methods: </strong>300 elderly IF patients treated in our hospital from July 2018 to May 2022 were divided into the PFNA group (n = 150), control group (n = 150), PFNA group treated with PFNA, and control group treated with mobility hip screw (DHS). Perioperative bleeding, operation time, postoperative time and hospital time were observed in the two groups: fracture reduction, hip function at 1 and 6 months after surgery, and failure of internal fixation. Observe the postoperative internal fixation failure in the PFNA group.</p><p><strong>Results: </strong>The intraoperative blood loss, operation time, first postoperative time and hospital time in the PFNA group were less than in the control group (P < 0.05). One month after surgery, the Harris score of the PFNA group was less than that of the control group (P < 0.05); the Harris score was not different at 6 months (P > 0.05). The excellent rate of fracture reduction in the PFNA group was greater than that in the control group (P < 0.05). The failure rate of internal fixation in the PFNA group was less than that in the control group (P < 0.05). By univariate analysis, Sing Index classification, Evans classification, 25 min and underlying disease were risk factors for postoperative internal fixation failure in PFNA patients (P < 0.05). After multivariate Logistic regression analysis, Sing Index grade, Evans classification, and tip distance 25min were independent risk factors for postoperative internal fixation failure in PFNA patients (P < 0.05).</p><p><strong>Conclusion: </strong>The treatment of elderly IF patients with PFNA has the advantages of small trauma, good fracture reduction, firm internal fixation, low failure rate of internal fixation, and quick postoperative recovery. Sing index classification, Evans classification, and 25min tip distance mainly caused internal fixation failure in patients with PFNA.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241307391"},"PeriodicalIF":1.4,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncovering potential molecular markers and pathological mechanisms of Parkinson's disease and myocardial infarction based on bioinformatics analysis.","authors":"Jian Liu, Lu Xing, Tianye Lan, Qiang Wang, Yitong Wang, Xuenan Chen, Weimin Zhao, Liwei Sun","doi":"10.1177/09287329241307805","DOIUrl":"https://doi.org/10.1177/09287329241307805","url":null,"abstract":"<p><strong>Background: </strong>The direct association between Parkinson's disease (PD) and Myocardial infarction (MI) has been the subject of relatively limited research.</p><p><strong>Objective: </strong>The purpose of this study was to identify the genes most associated with PD and MI to explore their common pathogenesis.</p><p><strong>Methods: </strong>The gene expression profiles of PD and MI were downloaded from GEO database. Differential expression analysis was performed to identify the common differential expression genes (DEGs) of PD and MI, followed by functional annotation. Subsequently, protein-protein interaction network were constructed, and hub DEGs were identified based on CytoHubba plugin and LASSO regression analysis. To explore the potential molecular mechanism of hub DEGs, GSEA analysis, immune correlation analysis, drug prediction and molecular docking were performed, and transcription factors (TF) and lncRNA-miRNA-mRNA (ceRNA) regulatory networks were constructed.</p><p><strong>Results: </strong>A total of 48 DEGs with the same expression trend were identified in the MI vs. normal control (NC) and PD vs. NC groups. Functional annotation results showed that the common DEGs were significantly enriched in immune and inflammation-related pathways. RPS4Y1 and UTY were the most relevant hub DEGs for PD and MI, and may be involved in the HALLMARK_MYC_TARGETS_V1 and HALLMARK_PROTEIN_SECRETION pathways. TP63 was a common TF of RPS4Y1 and UTY. The PVT1/KCNQ1OT1-hsa-miR-31-5p-RPS4Y1 and KCNQ1OT1-hsa-let-7a-5p/hsa-miR-19b-3p-UTY axes may play an important role in regulating PD and MI. CYCLOHEXIMIDE and ATALAREN may be potential drugs for the treatment of PD and MI comorbidity. In addition, PD and MI exhibit different patterns of immune cell infiltration and immune function status, which may be related to the specific pathological processes of the disease.</p><p><strong>Conclusions: </strong>This study revealed for the first time that RPS4Y1 and UTY may be common biomarkers of PD and MI and may be potential therapeutic targets. This study provides new perspective on the common molecular mechanisms between PD and MI.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241307805"},"PeriodicalIF":1.4,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence based BCI using SSVEP signals with single channel EEG.","authors":"Venkatesh Kanagaluru, Sasikala M","doi":"10.1177/09287329241302740","DOIUrl":"https://doi.org/10.1177/09287329241302740","url":null,"abstract":"<p><strong>Background: </strong>Brain-Computer Interfaces (BCIs) enable direct communication between the brain and external devices. Steady-state visual-evoked potentials (SSVEPs) are particularly useful in BCIs because of their rapid communication capabilities and minimal calibration requirements. Although SSVEP-based BCIs are highly effective, traditional classification methods face challenges in maintaining high accuracy with minimal EEG channels, especially in real-world applications. There is a growing need for improved classification techniques to enhance performance and efficiency.</p><p><strong>Objective: </strong>The aim of this research is to improve the classification of SSVEP signals using machine-learning algorithms. This involves extracting dominant frequency features from SSVEP data and applying classifiers such as Decision Tree (DT), Linear Discriminant Analysis (LDA), and Support Vector Machine (SVM) to achieve high accuracy while reducing the number of EEG channels required, making the method practical for BCI applications.</p><p><strong>Methods: </strong>SSVEP data were collected from the Benchmark Dataset at Tsinghua BCI Lab using 64 EEG channels per subject. The Oz channel was selected as the dominant channel for analysis. Wavelet decomposition (db4) was used to extract frequency features in the range 7.8 Hz to 15.6 Hz. The frequency of the maximum amplitude within a 5-s window was extracted as the key feature, and machine learning models (DT, LDA, and SVM) were applied to classify these features.</p><p><strong>Results: </strong>The proposed method achieved a high classification accuracy, with 95.8% for DT and 96.7% for both LDA and SVM. These results show significant improvement over existing methods, indicating the potential of this approach for BCI applications.</p><p><strong>Conclusion: </strong>This study demonstrates that SSVEP classification using machine-learning models improves accuracy and efficiency. The use of wavelet decomposition for feature extraction and machine learning for classification offers a robust method for SSVEP-based BCIs. This method is promising for assistive technologies and other BCI applications.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241302740"},"PeriodicalIF":1.4,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characteristic features of infants with pneumonia testing positive for specific immunoglobulin E.","authors":"Li Hao, Songqing Wang, Wei Ji","doi":"10.1177/09287329241301643","DOIUrl":"https://doi.org/10.1177/09287329241301643","url":null,"abstract":"<p><strong>Objective: </strong>To analyse the characteristic features of infants with pneumonia who test positive for serum milk-specific immunoglobulin E (sIgE) and to provide a reference for the diagnosis, management and prevention of the condition.</p><p><strong>Methods: </strong>We retrospectively analysed data from 284 infants admitted to our hospital with pneumonia between January 2017 and December 2020 who underwent serum allergen testing. Based on the results, patients were categorised into three groups: pure milk sIgE-positive; mixed milk sIgE-positive; and allergen sIgE-negative. We then compared the general conditions, clinical characteristics, laboratory tests, imaging results and pathogenic data across these groups.</p><p><strong>Results: </strong>Among the patient population, 16.20% (46/284) tested positive for pure milk sIgE, 32.75% (93/284) tested positive for mixed milk sIgE and 51.06% (145/284) were negative for any allergen sIgE. Statistically significant differences were observed among the three groups in terms of general conditions, breastfeeding status, pre-existing respiratory infections and history of respiratory infections (>3 times) (<i>p </i>< 0.05 for each). The median length of hospital stay was longer in the pure milk sIgE-positive group and the mixed milk sIgE-positive group (8 [range 7-10] days) compared with the allergen sIgE-negative group (8 [range 6-9] days) (<i>p </i>< 0.05). The eosinophil counts of the mixed milk sIgE-positive group were significantly higher than in the other two groups (<i>p </i>< 0.05). <i>Haemophilus influenzae</i> of the pure milk sIgE-positive group was significantly higher than in the other two groups (<i>p </i>< 0.05).</p><p><strong>Conclusion: </strong>The presence of mixed milk sIgE allergens does not exacerbate clinical symptoms. However, infants who test positive solely for milk sIgE and have pneumonia require longer hospitalisation. This suggests that extra attention is necessary for infants with milk allergies when they develop pneumonia.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241301643"},"PeriodicalIF":1.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pharmacological mechanisms of carvacrol against hepatocellular carcinoma by network pharmacology and molecular docking.","authors":"Lu Liu, Ping Yu, Zhongwei Zhao, Hongyuan Yang, Risheng Yu","doi":"10.1177/09287329241306192","DOIUrl":"https://doi.org/10.1177/09287329241306192","url":null,"abstract":"<p><strong>Background: </strong>Preclinical studies have demonstrated that carvacrol possesses various biological and pharmacological properties, including anti-hepatocellular carcinoma (HCC) effects. However, the molecular basis of its therapeutic action on HCC remains unclear.</p><p><strong>Objective: </strong>The aim of this study was to investigate and further validate the multi-target therapeutic mechanism of carvacrol against HCC.</p><p><strong>Methods: </strong>The chemical structure of carvacrol was obtained from the PubChem database, and its potential targets were identified using SwissTargetPrediction, HERB, and BATMAN-TCM. HCC-specific genes were screened from the TCGA-LIHC cohort. The therapeutic targets of carvacrol against HCC were determined through the intersection of these datasets. Subsequently, a multivariate Cox regression prognostic model was established. Molecular docking was performed to analyze the interactions between carvacrol and its therapeutic targets. Additionally, molecular dynamics simulations were conducted to validate the molecular docking results using Discovery Studio 2019 software.</p><p><strong>Results: </strong>A total of 223 carvacrol targets and 882 HCC-specific genes were identified. Fifteen therapeutic targets of carvacrol against HCC were obtained, including CA2, AR, ALB, AURKA, ALPL, EPHX2, BCHE, IL1RN, AGRN, CRP, DMGDH, APOA1, SOX9, HPX, and CHKA. The prognostic model accurately and independently predicted survival outcomes. AGRN and AURKA were significantly associated with HCC overall survival. Molecular docking and molecular dynamics simulations demonstrated that carvacrol exhibited strong potential for stable binding to the therapeutic targets AGRN and AURKA.</p><p><strong>Conclusion: </strong>Our findings elucidate the multi-target mechanism of action of carvacrol against HCC, providing a foundation for future research on its application in HCC management.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241306192"},"PeriodicalIF":1.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Skin disease classification using hybrid deep learning model.","authors":"K Jeyageetha, K Vijayalakshmi, S Suresh, A Bhuvanesh","doi":"10.1177/09287329241312628","DOIUrl":"https://doi.org/10.1177/09287329241312628","url":null,"abstract":"<p><p>Among the many cancers that people face today, skin cancer is among the deadliest and most dangerous. As a result, improving patients' chances of survival requires skin cancer to be identified and classified early. Therefore, it is critical to assist radiologists in detecting skin cancer through the development of Computer Aided Diagnosis (CAD) techniques. The diagnostic procedure currently makes heavy use of Deep Learning (DL) techniques for disease identification. In addition, skin lesion extraction and improved classification performance are achieved through Region Growing (RG) based segmentation. At the outset of this study, noise is reduced using an Adaptive Wiener Filter (AWF), and hair is removed using a Maximum Gradient Intensity (MGI). Then, the best RG, which is the result of integrating RG with the Modified Honey Badger Optimiser (MHBO), does the segmentation. Finally, several forms of skin cancer are classified using the DL model MobileSkinNetV2. The experiments were conducted on the ISIC dataset and the results show that the accuracy and precision were improved to 99.01% and 98.6%, respectively. In comparison to existing models, the experimental results show that the proposed model performs competitively, which is great news for dermatologists treating cancer.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241312628"},"PeriodicalIF":1.4,"publicationDate":"2025-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based AI model for sinusitis diagnosis.","authors":"Jingfei Zhang, Dianyi Wang, Wentao Li, Jingyi Wang","doi":"10.1177/09287329241309799","DOIUrl":"https://doi.org/10.1177/09287329241309799","url":null,"abstract":"<p><strong>Problem statement: </strong>While CT (Computed Tomography) is commonly used, its diagnostic accuracy for chronic sinusitis remains uncertain. Moreover, the high cost of CT examinations limits its use as a routine diagnostic method. There is an urgent need to develop an AI-assisted diagnostic model for sinusitis.</p><p><strong>Objective: </strong>The primary aim of this study is to develop an AI-assisted diagnostic model for sinusitis that can improve diagnostic accuracy and accessibility compared to traditional CT methods.</p><p><strong>Methodology: </strong>This study utilized a retrospective approach, focusing on patients diagnosed with chronic sinusitis via CT and normal patients admitted to the People's Hospital between January 2018 and January 2019. A total of 5000 sinus CT images were collected. All cases underwent T (targeted) coronal plain scans in the hospital's CT room, ensuring complete CT images. In constructing the chronic sinusitis classification model based on deep learning, 5000 CT images of soft tissue windows and sinuses were gathered. This included 1000 CT images for each of the four groups diagnosed with sphenoid sinusitis, frontal sinusitis, ethmoid sinusitis, and maxillary sinusitis, along with 1000 images from normal cases (250 images per group). The sigmoid function replaced the softmax function, and the binary cross-entropy function was used to assess the model's predictive accuracy.</p><p><strong>Results: </strong>The model achieved an accuracy of 85.8%, outperforming doctors with low (71.7%), medium (78.4%), and senior (73.4%) qualifications. The model demonstrated high accuracy, superior feature extraction, and resolution capabilities.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241309799"},"PeriodicalIF":1.4,"publicationDate":"2025-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancement of post-market surveillance of medical devices leveraging artificial intelligence: ECG devices case study.","authors":"Madžida Hundur, Lemana Spahić, Faruk Bećirović, Lejla Gurbeta Pokvić, Almir Badnjević","doi":"10.1177/09287329241303727","DOIUrl":"https://doi.org/10.1177/09287329241303727","url":null,"abstract":"<p><strong>Background: </strong>After 25 years of implementing the Medical Devices Directive (MDD), in 2017, the new Medical Devices Regulation (MDR) came into force, establishing stricter requirements for post-market surveillance of the safety and performance of medical devices (MD). For electrocardiogram (ECG) devices, which are crucial for monitoring cardiac activities, these requirements are essential to ensure the reliability and accuracy of diagnosing cardiac conditions and timely treatment.</p><p><strong>Objective: </strong>This study aims to enhance post-market surveillance of ECG devices by leveraging Machine Learning (ML) algorithms to predict the operational status of these devices. Specifically, the research focuses on classifying the success or failure of ECG device operations based on performance and safety parameters. The ultimate goal is to improve the management strategies of ECG devices in healthcare institutions, ensuring optimal functionality and increasing the reliability of diagnostic procedures.</p><p><strong>Method: </strong>During the inspection process of ECG devices conducted by an accredited laboratory in accordance with ISO 17020 standard in numerous healthcare institutions in Bosnia and Herzegovina, a total of 5577 samples were collected. Various machine learning algorithms, including Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Gaussian Naive Bayes (NB), and Support Vector Machine (SVM), were employed for result comparison and selection of the most accurate algorithm.</p><p><strong>Results: </strong>All algorithms demonstrated good performance, but the Random Forest (RF) algorithm stood out, achieving 100% accuracy in predicting the success/unsuccess status of the device. While the results of this research are specific to the collected data from EKG devices, the developed algorithms can be applied to other similar datasets, offering opportunities for broader use in the medical environment.</p><p><strong>Conclusion: </strong>Implementing machine learning algorithms for automated systems in healthcare institutions can significantly enhance the quality of patient diagnosis and treatment. Additionally, these systems can optimize costs associated with managing medical devices. Improved post-market surveillance using ML can address challenges related to ensuring device reliability and safety.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"9287329241303727"},"PeriodicalIF":1.4,"publicationDate":"2025-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}