Technology and Health Care最新文献

{"title":"Preliminary study: Low to moderate PEEP effects on ICP in acute neurological injury patients under mechanical ventilation.","authors":"Nan Xiu","doi":"10.1177/09287329241291322","DOIUrl":"https://doi.org/10.1177/09287329241291322","url":null,"abstract":"<p><p>BackgroundAcute respiratory distress syndrome (ARDS) significantly impacts mortality and prognosis in acute neurological injury patients. Positive end-expiratory pressure (PEEP) is essential in mechanical ventilation to enhance oxygenation, yet its application may elevate intracranial pressure (ICP). Studies show conflicting findings regarding PEEP's effect on ICP, particularly at low to moderate levels (5-10cmH2O), warranting further investigation in acute neurological injury cases.ObjectiveTo assess the impact of low to moderate PEEP on ICP in patients with acute neurological injury who require mechanical ventilation.MethodsA retrospective analysis of 62 patients with acute neurological injury requiring mechanical ventilation at our hospital between January 2021 and September 2023 was conducted. Patients were divided into high PEEP (> 10cmH2O) and low to moderate PEEP (5-10cmH2O) groups. Parameters including PaO2, PaCO2, PaO2/FiO2, driving pressure, compliance (Cst), airway resistance, such as heart rate (HR), systolic blood pressure (SBP), diastolic blood pressure (DBP), mean arterial pressure (MAP), central venous pressure (CVP), cardiac index (CI), ICP, and cerebral perfusion pressure (CPP) were recorded pre- and post-ventilation initiation, with correlation analysis performed between ICP and other parameters.ResultsPre-treatment comparisons between the high PEEP and low to moderate PEEP groups revealed no significant differences in PaO2, PaCO2, PaO2/FiO2, driving pressure, Cs, and airway resistance. However, post-treatment analysis showed significant disparities, with the high PEEP group exhibiting higher PaO2 and PaO2/FiO2 levels and lower PaCO2, driving pressure, and airway resistance levels compared to the low to moderate PEEP group. Additionally, hemodynamic parameters such as HR, SBP, DBP, CI, MAP, CVP, ICP, and CPP remained more stable in the low to moderate PEEP group post-treatment, with ICP demonstrating significant correlations with various physiological parameters.ConclusionHigh PEEP improves oxygenation and respiratory mechanics in acute neurological injury patients on mechanical ventilation but may affect hemodynamic parameters, ICP, and CPP. Conversely, low to moderate PEEP has minimal impact on these factors. Hence, personalized adjustment of PEEP levels is essential in clinical management.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":"33 2","pages":"981-988"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659035","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":"Unraveling the genetic mysteries of sarcopenia: A bioinformatics approach.","authors":"Hui Deng, Yuming Wang, Yang Dai, Qian Wang, Hao Lu, Qing Wang","doi":"10.1177/09287329241291323","DOIUrl":"https://doi.org/10.1177/09287329241291323","url":null,"abstract":"<p><p>Background As life expectancy increases and the global population ages, the incidence of sarcopenia is also increasing, highlighting the need for better diagnosis and treatment methods.ObjectiveTo study the genetic expression of sarcopenia using bioinformatics methods.MethodsA Weighted Gene Coexpression Network Analysis (WGCNA) was conducted to construct coexpression networks, along with protein-protein interaction networks. Diagnostic biomarker potential was evaluated using receiver operating characteristic curves. An analysis of Single-Sample Gene Set Enrichment Analysis (ssGSEA) was performed in order to determine the amount of immune cell infiltration. We analyzed Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways and Gene Ontology (GO) enrichment using the KEGG.ResultsWGCNA identified modules linked to bone metabolism, ssGSEA showed unique gene enrichment patterns, and 268 genes were found to be differentially expressed in sarcopenia. Fourteen co-expression modules related to bone metabolism were identified, with one showing a strong positive correlation. KEGG pathway analysis indicated downregulation of the renin-angiotensin system and Alzheimer's disease pathways. The differentially expressed genes were primarily involved in adipocyte differentiation.ConclusionThis study analyzes genetic changes and immune cell patterns in sarcopenia, providing insights into its causes and potential diagnostic markers for future research on treatments.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":"33 2","pages":"1140-1153"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659371","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: Infusion pumps case study.","authors":"Nejra Merdović, Lemana Spahić, Madžida Hundur, Lejla Gurbeta Pokvić, Almir Badnjević","doi":"10.1177/09287329241291415","DOIUrl":"https://doi.org/10.1177/09287329241291415","url":null,"abstract":"<p><p>BackgroundAnalysis of data from incident registries such as MAUDE has identified the need to improve surveillance and maintenance strategies for infusion pumps to enhance patient and healthcare staff safety.ObjectiveThe ultimate goal is to enhance infusion pump management strategies in healthcare facilities, thus transforming the current reactive approach to infusion pump management into a proactive and predictive one.<b>Method:</b> This study utilized real data collected from 2015 to 2021 through the inspection of infusion pumps in Bosnia and Herzegovina. Inspections were conducted by the national laboratory in accordance with the Legal Metrology Framework, accredited to ISO 17020 standard. Out of 988 samples, 790 were used for model training, while 198 samples were set aside for validation (20% of the dataset). Various machine learning algorithms for binary classification of samples (pass/fail status) were considered, including Logistic Regression, Decision Tree, Random Forest, Naive Bayes, and Support Vector Machine. These algorithms were chosen for their ability to handle large datasets and potential for high prediction accuracy.ResultsThrough detailed analysis of the achieved results, it was found that all applied machine learning methods yielded satisfactory results, with accuracy ranging from 0.98% to 1.0%, precision from 0.99% to 1%, sensitivity from 0.98% to 1.0%, and specificity from 0.87% to 1.0%. However, Decision Tree and Random Forest methods proved to be the best, both due to their maximum achieved values of accuracy, precision, sensitivity, and specificity, and due to result interpretability.ConclusionIt has been established that machine learning methods are capable of identifying potential issues before they become critical, thus playing a crucial role in predicting the performance of infusion pumps, potentially enhancing the safety, reliability, and efficiency of healthcare delivery. Further research is needed to explore the potential application of machine learning algorithms in various healthcare domains and to address practical issues related to the implementation of these algorithms in real clinical settings.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":"33 2","pages":"915-921"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659441","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":"Evaluation of wearable device technology in terms of health and safety in firefighters.","authors":"Güler Aksüt, Tamer Eren","doi":"10.1177/09287329241291385","DOIUrl":"10.1177/09287329241291385","url":null,"abstract":"<p><p>BackgroundFirefighting is one of the tasks that is physically difficult to perform and carries a high risk of injury and death. A better understanding of the underlying factors that influence the causes of fire scene injuries can improve firefighters' safety.ObjectiveFor this reason, the study aimed to determine the importance of Smart Personal Protective Equipment and wearable technology in protecting the health and safety of firefighters by using them instead of traditional equipment and systems. According to expert opinions and literature reviews, the dangers faced by firefighters have been determined to be thermal, physical, biological, environmental, and chemical.MethodsAnalytical Hierarchy Process (AHP) and Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE) methods were used in the study. The AHP method was preferred because it is a systematic decision-making method that includes both ranking and comparison techniques. The PROMETHEE method was preferred because it provides the opportunity to make effective decisions in a very short time by basing the decision-making process on a scientific basis. In addition to the graphical representation of the ranking of alternatives, it offers decision-makers the opportunity to make various statistical analyses.ResultsThe weights of the hazards were calculated using the AHP method. Physical hazards accounted for the highest weight. PROMETHEE was used in the ranking of wearable smart technological products to protect the health and safety of firefighters.<b>Conclusions:</b> Products are listed as Personal Protection System, PROeTEX PPE, Wearable IoT Device, Flame Resistant Shirt, Fall Detection Systems, Smart Wearable Underwear, and WASP. With the study, it was concluded that the risk of firefighters being trapped would play an essential role in the prevention of death and injury. Improvements in wearable technological products used in the fire department will yield better results and increase safety.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"726-736"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460225","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":"Hemodynamic evaluation of a novel double lumen cannula for left ventricle assist device system.","authors":"Honglong Yu, Xuefeng Feng, Yao Xie, Qilian Xie, Hu Peng","doi":"10.1177/09287329241290947","DOIUrl":"10.1177/09287329241290947","url":null,"abstract":"<p><p>BackgroundThe left ventricular assist device (LVAD) has been proven to be an effective therapy for providing temporary circulatory support. However, the use of this device can cause myocardial injury due to multiple insertions of various catheters.ObjectiveTherefore, this study aimed to evaluate the hemodynamic performance of a newly developed double-lumen catheter (DLC) for LVAD.MethodsTwo different LVAD DLC prototypes (a semi-circular and a concentric catheter) were designed based on the structure of venous DLC. Computational fluid dynamics (CFD) simulations were performed using the finite element method. The CFD results were confirmed through the testing of the 31 Fr prototype. The aorta is a large vessel with shear rates up to >300 s^-1 and we used a reasonable approximation to model blood as a Newtonian fluid.ResultsAt a flow rate of 5 L/min, the semi-circular prototype achieved an infusion pressure of 74.68 mmHg, while the concentric prototype achieved an infusion pressure of 46.11 mmHg. The CFD results matched the experimental results with a mean percentage error of less than 7%. The peak wall shear stress in the semi-circular prototype (717.5 Pa) was higher than the hemolysis threshold (400 Pa), which could cause blood damage, and it also had a higher hemolysis index compared to concentric prototype. Moreover, both prototypes exhibited areas of blood stagnation and recirculation, suggesting a possible risk of thrombosis.ConclusionBoth prototypes of the LVAD DLC demonstrated similar blood flow rates. The semi-circular prototype showed superior infusion pressure compared to the concentric prototype, but had poorer hemolysis performance. However, the potential risk of thrombosis for both still exists. Therefore, further <i>in vivo</i> experiments are necessary to verify the safety and effectiveness of the LVAD DLC.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"814-830"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460237","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":"A descriptive cross-sectional study on the cumulative frequency of pediatric procedural sedation in 0- to 3-year-old children.","authors":"Tingting Yi, Zhiquan Lv, Hongxia Luo, Shouyong Wang","doi":"10.1177/09287329241292925","DOIUrl":"10.1177/09287329241292925","url":null,"abstract":"<p><p>BackgroundRecurrent illnesses and poor adherence to medical procedures render infants and young children vulnerable to procedural sedation, while repeated or prolonged exposure to anesthetic medications and sedative drugs may potentially exert adverse effects on the developing brain.ObjectiveTo investigate the distribution of cumulative frequency and the use of general anesthetic drugs in pediatric procedural sedation for children aged 0 to 3 years.MethodsThe records of all children treated in the Sedation Clinic of the Children's Medical Center of our university in November 2021 were extracted as the sample. A descriptive cross-sectional study was performed, and the cumulative frequency of pediatric procedural sedation in 0- to 3-year-old children was investigated as the first endpoint.ResultsA total of 3439 independent children were included in this study, 2649 (77.0%), 471 (13.7%), 270 (7.9%) and 49 (1.4%) children with 1 to 3, 3 to 5, 5 to 10 and ≥10 rounds of the cumulative frequency of sedation, respectively, and 929 (27%) of those were identified general anesthetics using. There was no significant difference in the gender ratio of each cumulative frequency strata subgroup compared with that of the total sample.<b>Conclusions:</b> The present study concluded that some 0- to 3-year-old children are at risk of large cumulative frequency of pediatric procedural sedation and high risk of general anesthetics exposure.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"719-725"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460215","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":"Interaction effect between data discretization and data resampling for class-imbalanced medical datasets.","authors":"Min-Wei Huang, Chih-Fong Tsai, Wei-Chao Lin, Jia-Yang Lin","doi":"10.1177/09287329241295874","DOIUrl":"https://doi.org/10.1177/09287329241295874","url":null,"abstract":"<p><p>BackgroundData discretization is an important preprocessing step in data mining for the transfer of continuous feature values to discrete ones, which allows some specific data mining algorithms to construct more effective models and facilitates the data mining process. Because many medical domain datasets are class imbalanced, data resampling methods, including oversampling, undersampling, and hybrid sampling methods, have been widely applied to rebalance the training set, facilitating effective differentiation between majority and minority classes.ObjectiveHerein, we examine the effect of incorporating both data discretization and data resampling as steps in the analytical process on the classifier performance for class-imbalanced medical datasets. The order in which these two steps are carried out is compared in the experiments.MethodsTwo experimental studies were conducted, one based on 11 two-class imbalanced medical datasets and the other using 3 multiclass imbalanced medical datasets. In addition, the two discretization algorithms employed are ChiMerge and minimum description length principle (MDLP). On the other hand, the data resampling algorithms chosen for performance comparison are Tomek links undersampling, synthetic minority oversampling technique (SMOTE) oversampling, and SMOTE-Tomek hybrid sampling algorithms. Moreover, the support vector machine (SVM), C4.5 decision tree, and random forest (RF) techniques were used to examine the classification performances of the different approaches.ResultsThe results show that on average, the combination approaches can allow the classifiers to provide higher area under the ROC curve (AUC) rates than the best baseline approach at approximately 0.8%-3.5% and 0.9%-2.5% for twoclass and multiclass imbalanced medical datasets, respectively. Particularly, the optimal results for two-class imbalanced datasets are obtained by performing the MDLP method first for data discretization and SMOTE second for oversampling, providing the highest AUC rate and requiring the least computational cost. For multiclass imbalanced datasets, performing SMOTE or SMOTE-Tomek first for data resampling and ChiMerge second for data discretization offers the best performances.ConclusionsClassifiers with oversampling can provide better performances than the baseline method without oversampling. In contrast, performing data discretization does not necessarily make the classifiers outperform the baselines. On average, the combination approaches have potential to allow the classifiers to provide higher AUC rates than the best baseline approach.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":"33 2","pages":"1000-1013"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143658962","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":"Segnet unveiled: Robust image segmentation via rigorous K-fold cross-validation analysis.","authors":"Ignatious K Pious, R Srinivasan","doi":"10.1177/09287329241290954","DOIUrl":"https://doi.org/10.1177/09287329241290954","url":null,"abstract":"<p><p>BackgroundIn computer vision, image segmentation is crucial with applications ranging from autonomous driving to medical imaging.ObjectiveTo provide reliable segmentation across varied datasets, this study assesses the performance of an image segmentation model based on SegNet.MethodUsing a five-fold and a K-fold cross-validation method, the SegNet model is thoroughly validated. Intersection over Union (IOU), Dice Coefficient, Precision, Recall, Accuracy, and loss metrics are measured in the study to assess how well the model performs and is optimized throughout training.ResultsThe SegNet model consistently performs well throughout the folds, with Dice Coefficient values ranging from 88.32% to 89.8% and IOU scores ranging from 94.53% to 95.05%. The model's dependability is confirmed by metrics like precision, recall, and accuracy, all of which often exceed 90%. Loss values between 0.495 and 0.547 show that training optimized the system effectively.ConclusionBy enhancing the validation reliability, the K-fold cross-validation method highlights by what means the SegNet model segments objects in images across a range of datasets. These outcomes strengthen the confidence in the model's ability to generalize and highlight its potential for several practical uses in image segmentation.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":"33 2","pages":"863-876"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659298","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-driven multi-omics sequential diagnosis with Hybrid-OmniSeq: Unraveling breast cancer complexity.","authors":"N Banupriya, T Sethukarasi","doi":"10.1177/09287329241296438","DOIUrl":"https://doi.org/10.1177/09287329241296438","url":null,"abstract":"<p><p>BackgroundBreast cancer results from an uncontrolled growth of breast tissue. Many methods of diagnosis are using multi-omics data to better understand the complexity of breast cancer.ObjectiveThe new strategy laid out in this work, called \"Hybrid-OmniSeq,\" is a deep learning-based multi-omics data analysis technology that uses molecular subtypes of breast cancer gene to increase the precision and effectiveness of breast cancer diagnosis.MethodFor preprocessing, the BC-VM procedure is utilized, and for molecular subtype analysis, the BC-MSA procedure is utilized. The implementation of Deep Neural Network (DNN) technology in conjunction with Sequential Forward Floating Selection (SFFS) and Truncated Singular Value Decomposition (TSVD) entropy enable adaptive learning from multi-omics gene data. Five machine learning classifiers are used for classification purpose. Hybrid-OmniSeq uses a variety of machine learning classifiers in a thorough analytical process to achieve remarkable diagnostic accuracy. Deep Learning-based multi-omics sequential approach was evaluated using METABRIC RNA-seq data sets of intrinsic subtypes of breast cancer.ResultsAccording to test results, Logistic Regression (LR) had ER (Estrogen Receptor) status values of 94.51%, ER status values of 96.33%, and HER2 (Human Epidermal growth factor Receptor) status values of 92.3%; Random Forest (RF) had ER status values of 93.77%, ER status values of 95.23%, and HER2 status values of 93.4%.ConclusionLR and RF increase the cancer detection accuracy for all subtypes when compared to alternative machine learning classifiers or the majority voting method, providing a comprehensive understanding of the underlying causes of breast cancer.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":"33 2","pages":"1099-1120"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659482","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":"Machine learning for improved medical device management: A focus on defibrillator performance.","authors":"Lemana Spahić, Luka Jeremić, Ivana Lalatović, Tatjana Muratović, Amra Džuho, Lejla Gurbeta Pokvić, Almir Badnjević","doi":"10.1177/09287329241290944","DOIUrl":"10.1177/09287329241290944","url":null,"abstract":"<p><p>BackgroundPoorly regulated and insufficiently maintained medical devices (MDs) carry high risk on safety and performance parameters impacting the clinical effectiveness and efficiency of patient diagnosis and treatment. After the MD directive (MDD) had been in force for 25 years, in 2017 the new MD Regulation (MDR) was introduced. One of the more stringent requirement is a need for better control of MD safety and performance post-market surveillance mechanisms.ObjectiveTo address this, we have developed an automated system for management of MDs, based on their safety and performance measurement parameters, that use machine learning algorithm as a core of its functioning.MethodsIn total, 1997 samples were collected during the inspection process of defibrillator inspections performed by an ISO 17020 accredited laboratory at various healthcare institutions in Bosnia and Herzegovina. This paper presents solution developed for defibrillators, but proposed system is scalable to any other type of MDs, both diagnostic and therapeutic.ResultsVarious machine learning algorithms were considered, including Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB) and Logistic Regression (LR). In addition, random forest regressor and XG Boost algorithms were tested for their predictive capabilities in the field of defibrillator output error prediction. These algorithms were selected because of their ability to handle large datasets and their potential for achieving high prediction accuracy. The highest accuracy achieved on this dataset was 94.8% using the Naive Bayes algorithm. The XGBoost Regressor with its r² of 0.99 emerged as a powerful tool, showcasing exceptional predictive accuracy and the ability to capture a substantial portion of the dataset's variability.ConclusionThe results of this study demonstrate that clinical engineering (CE) and health technology management (HTM) departments in healthcare institutions can benefit from proposed automatization of defibrillator maintenance scheduling in terms of increased safety and treatment of patients, on one side, and cost optimization in MD management departments, on the other side.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"737-743"},"PeriodicalIF":1.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143460293","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}