This study introduces a deep learning approach for classifying medical devices to help improve the accuracy of inventory information in health care facilities. For this purpose, we constructed and made publicly available the MedDev5 dataset, which includes images of medical devices such as anesthesia machines, ventilators, ECGs, and patient and fetal monitors. For experimental results, the features of MedDev5 images were first extracted using MobileNetV2 and GoogLeNet CNN models. These features were then concatenated to achieve high classification performance. Following this, to eliminate redundant and unnecessary features and select the most informative features, the fMRMR feature selection method was used. Finally, medical device image classification was performed using support vector machines (SVM). The experiments showed that the classification of the medical devices in the MedDev5 dataset was achieved with a high accuracy of 95.80% using 500 selected features. This result indicates that we may frequently encounter artificial intelligence applications in clinical engineering in the near future.
This study aims to develop a comprehensive medical equipment management program tailored to the Sudanese health care context. The research employed a structured questionnaire targeting biomedical engineers, medical professionals, and administrative personnel across several hospitals. Key findings revealed that 58% of respondents reported that the impact of war on equipment management was severe (≥75%). Sixty-five percent indicated a complete absence of maintenance plans during the conflict period. Seventy-five percent observed major operational disruptions, including service halts. Fifty-eight percent stated that malfunctions were addressed without standard protocols. All participants noted a 100 % increase in patient load alongside reduced staffing levels. Based on these findings, the study proposes a holistic program consisting of clear procurement policies, efficient inventory systems, preventive maintenance schedules, proper disposal protocols, and targeted staff training. The program also integrates modern technologies such as barcode tracking, remote monitoring, and cloud-based asset management to enhance operational efficiency. The study concludes that collaboration with the Ministry of Health and international partners is essential for the standardization and sustainability of equipment management practices. Furthermore, improving emergency preparedness in conflict-affected zones is critical to maintaining essential health services during crises.
The detection of genomic mutations plays a central role in understanding cancer biology, enabling more precise diagnostic, prognostic, and therapeutic strategies. However, accurate mutation detection is often hindered in low-resource settings due to the limited availability of high-quality sequencing data, computational infrastructure, and expert annotation. These constraints are particularly problematic for key cancer-related genes such as TP53, which is frequently mutated in breast cancer and strongly associated with disease progression and treatment resistance. In recent years, deep learning approaches have shown significant promise in various genomics tasks, including variant calling, sequence classification, and gene expression analysis. Nevertheless, such models typically require large, well-annotated datasets to achieve reliable performance—a condition that is not always feasible in clinical or resource-constrained environments. Transfer learning, a machine learning technique in which knowledge learned from a large source dataset is transferred to a related target task, offers a potential solution to this limitation. It allows for the reuse of pretrained models, reducing the need for large amounts of labeled data while improving generalization. In this study, we propose and evaluate a deep learning framework for detecting TP53 mutations in breast cancer using either gene expression data or DNA sequences. We benchmark the performance of several architectures—namely, fully connected neural networks (FCNN), convolutional neural networks (CNN), bidirectional long short-term memory networks (BiLSTM), Transformers trained from scratch, and DNABERT models both trained from scratch and fine-tuned via transfer learning. All models were trained and tested on a curated subset of TCGA-BRCA samples labeled with TP53 mutation status. Our results show that DNABERT with transfer learning achieved the highest performance across all evaluation metrics, with an accuracy of 92%, F1-score of 0.90, and AUROC of 0.95. In contrast, traditional models such as FCNN and CNN using gene expression data yielded moderate performance (accuracy: 0.81–0.83), while models trained from scratch—including BiLSTM and Transformer—performed better when applied to DNA sequences (accuracy: 0.85–0.87). The consistent superiority of DNABERT highlights the value of pretrained genomic language models and transfer learning in resource-constrained scenarios. These findings underscore the promise of transformer-based models for scalable and accurate mutation detection, especially in clinical settings with limited-data availability. On the basis of our findings, we recommend adopting transfer learning approaches such as DNABERT in clinical genomics applications, integrating gene expression and sequence data to boost accuracy, and extending this framework to additional cancer-related genes to improve model generalizability.
The quality of a laboratory depends on accuracy, reliability, and timely reporting of test results. Laboratory results must be as accurate as possible, all aspects of laboratory operations must be reliable, and reports must be submitted in a timely manner so that they are useful at clinical or public health sites. In a quality management system, all practical aspects of the laboratory, including organizational structure, processes and procedures, should be quality assurance oriented. A comparative analysis of complete blood count (CBC) results from 4 different laboratories for a single individual revealed notable discrepancies in measurement between the laboratories.
Evidence suggests that many medical device manufacturers are reluctant to conduct elective human factors activities or user research of any kind until they are compelled to do so by regulatory requirements. This reportedly stems from a communication gap between human factors practitioners and other disciplines regarding whether and how adopting a user-centered design approach benefits the broader corporate agenda. The goal of this article is to help bridge this gap by highlighting entirely practical business reasons to prioritize human factors throughout the medical device design process. This contribution thus supports internal advocacy efforts and promotes best practices across the industry.
The measurement of ECG-derived heart rate variability (HRV) provides early diagnosis and prevention of cardiac events such as coronary artery disease (CAD) and myocardial infarction (MI). The disease severity causes ECG shape deformation, leading to difficulty in R-wave detection required for heart rate variability (HRV) analysis. Therefore, the study aimed to optimize R-wave threshold filters at 50%, 60%, 70%, and 80% within the framework of HRV analysis for better diagnosis of MI and CAD. Lead-II ECG was recorded from CAD (n=15), MI (n=15), and Control (n=10) group participants using an MP45 amplifier (Biopac Systems Inc., USA). The ECG morphologic features were extracted to analyze the change in R-wave amplitude. The R-R interval time series was extracted at different threshold filters (50%, 60%, 70%, and 80%) and used for heart rate variability (HRV) analysis. The HRV features extracted using Kubios V2.0 in time, frequency, and nonlinear domains at different threshold filters were compared. The obtained findings revealed that R-wave amplitude was suppressed under the CAD and MI groups in comparison to the control subjects. The observed results also suggested 70% threshold filters for optimum detection of R-wave under CAD and MI. Further, the time and frequency domains presented the best result in comparison to the nonlinear HRV domain. The present study suggested that HRV analysis may be made more predictive for various cardiac diseases by optimizing R-wave threshold filters.
The training of clinical engineering professionals is essential to ensure the safety and efficiency of medical technology management. This study developed a competency-based training pathway for the maintenance and operation of infusion pumps, utilizing a competency matrix validated by specialists. The results demonstrated a significant increase in participants’ knowledge: in “preventive maintenance,” the advanced level rose from 0% to 63.2%, and in “calibration and configuration,” from 15.8% to 47.4%. The study confirms the effectiveness of training in improving technical skills, contributing to the quality of hospital services.
Currently, one of the most challenging decisions in the management of medical equipment is the replacement of a device, given the limited nature of financial resources. Many replacement decision-making processes occur reactively, considering factors related to the age of the device, a malfunction, or solely subjective criteria, which can result in acquisitions that are not aligned with the actual needs of the health care service. These services must have appropriately sized and reliable equipment to ensure the quality and safety of health care professionals in patient care, as well as the optimization of resources for the institution. Therefore, it is essential to seek tools capable of facilitating and systematizing the process of selection and prioritization of medical equipment replacement, amidst other external demands. Thus, a model called the “iSUB Methodology (Replacement Index)” was developed, which formulates several objective variables derived from most asset management software systems. This is a case study describing the tool used for the study of medical equipment replacement in a federal university hospital. The “iSUB Methodology” tool utilizes the parameters of age, failure rate, maintenance cost, and equipment severity—through a matrix scoring system, producing results on a scale from 0 to 10. The result is a ranked, nonexhaustive list of devices that need to be replaced. This methodology can be adopted by any health care service that manages its medical equipment inventory through an information system and possesses data on the variables used in the model. The model enables clinical engineers and the ones responsible for managing medical equipment to make more accurate decisions regarding the renewal of them, based on clear and objective evidence, classifying and identifying technologies with the highest potential for replacement.
This study evaluates service contracts for medical equipment maintenance, focusing on the total cost of ownership (TCO) as a key factor in decision-making for health care facilities. Through a comparative analysis of Full-Service, Shared Service, and Parts-Only contracts, this research examines their financial and operational impacts. A tool was developed to standardize data collection, normalize costs, and enable value-based comparisons. The findings emphasize the significance of internal resource capabilities, OEM support, and contract scalability in selecting optimal service models. Recommendations include adopting failure codes for work orders, standardizing maintenance data, capturing comprehensive contract criteria, implementing periodic contract evaluations, and establishing a national hospital network for sharing maintenance experiences. These strategies aim to improve the efficiency of service contract management and optimize TCO in maintaining medical equipment.
This analysis references the articles “Benchmarking comparison between Zhejiang province and American hospitals” by Zheng, Wang, and Feng (2016), and “Benchmarking comparison between Beijing and American hospitals” by Wang and Deng (2020). These studies aim to compare health care technology management (HTM), also known as clinical engineering (CE), practices between hospitals in China and the United States, using key indicators related to equipment, costs, and productivity. Following a similar methodology to those studies, a parallel analysis is conducted for the Virgen del Rocío University Hospital (HUVR). This examination considers relevant metrics that include equipment density, operational costs, and the productivity of the CE department, adapting them to the specific context of HUVR. The goal is to identify similarities, differences, and opportunities for improvement in the management of electromedical technology, using observed data from American and Chinese hospitals for comparison. This approach positions HUVR within an international comparative framework, providing a foundation for evaluating its performance and exploring strategies to optimize the management of technological resources in the hospital. By systematically analyzing the metrics, the aim is to highlight the hospital’s strengths and propose areas for improvement aligned with global practices in HTM.
