Evidence-based clinical engineering: Machine learning algorithms for prediction of defibrillator performance

Abstract

Please refer to published version for the most recent bibliographic citation information. If a published version is known of, the repository item page linked to above, will contain details on accessing it.

Clinical needs and technical requirements for ventilators for COVID-19 treatment critical patients: an evidence-based comparison for adult and pediatric age

“…Historically, clinical engineering has been based on best practices and clinical engineers have been less involved in research activities as well as in publishing their activities' results in peer reviewed journals. However, in the past 10 years, clinical engineering has been growing globally [15], with the first peer reviewed journal papers on evidence-based being published in 2019 [16,17]. Similarly to what Pecchia et al did for personal protective equipment [18], starting from the clinical indications spread by WHO and the Italian Ministry of Health, we joined our efforts to conscientiously share the minimum technical requirements that an ICU ventilator might meet to be considered acceptable for treating COVID-19 patients in severe to critical illnesses, comparing and, at the same time, combining in an easily readable way, all the indications publicly available in order to provide a unified and global vision.…”

A Systematic Review of Medical Equipment Reliability Assessment in Improving the Quality of Healthcare Services

“…Equipment features comprise several characteristics designed for the equipment and exist since the unit is manufactured. One of the parameters used to assess the medical equipment condition is age ( 19 , 20 , 22 – 24 , 26 , 27 , 29 – 31 ). The equipment age reflects the overall condition of the equipment.…”

“…However, as the age increases, the equipment starts to degrade. In another studies conducted by Badnjevic et al ( 20 ) and Kovacevic et al ( 19 ), manufacturer's name and equipment's modality are another two parameters that were included in their reliability assessment. Prior to that, Faisal et al ( 24 ), included the service availability as one of the input parameters in assessing the equipment condition for the RP prioritisation.…”

“…The results obtained from the studies made by Badnjevic et al ( 20 ) and Kovacevic et al ( 19 ) showed that the generated output achieved above 89% accuracy where Random Forest and Decision Tree reached around 99% of accuracy in predicting both selected medical equipment performance. Therefore, both authors concluded that improved supervision, quality and safety in managing medical equipment maintenance could be achieved which eventually optimised the cost of maintenance.…”

“…The relevant data were collected, processed, calculated, and analysed accordingly based on the identified criteria. Only one scientific methodological technique was involved in generating the expected output by referring to the 12 articles (19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30). Nevertheless, according to Ben Houria et al (31), a combination of three techniques generated the expected output.…”