IFMBE Research Articles

Scoping Meta-Review of Methods Used to Assess Artificial Intelligence-Based Medical Devices for Heart Failure.

Artificial intelligence and machine learning (AI/ML) are playing increasingly important roles, permeating the field of medical devices (MDs). This rapid progress has not yet been matched by the Health Technology Assessment (HTA) process, which still needs to define a common methodology for assessing AI/ML-based MDs. To collect existing evidence from the literature about the methods used to assess AI-based MDs, with a specific focus on those used for the management of heart failure (HF), the International Federation of Medical and Biological Engineering (IFMBE) conducted a scoping meta-review. This manuscript presents the results of this search, which covered the period from January 1974 to October 2022. After careful independent screening, 21 reviews, mainly conducted in North America and Europe, were retained and included. Among the findings were that deep learning is the most commonly utilised method and that electronic health records and registries are among the most prevalent sources of data for AI/ML algorithms. Out of the 21 included reviews, 19 focused on risk prediction and/or the early diagnosis of HF. Furthermore, 10 reviews provided evidence of the impact on the incidence/progression of HF, and 13 on the length of stay. From an HTA perspective, the main areas requiring improvement are the quality assessment of studies on AI/ML (included in 11 out of 21 reviews) and their data sources, as well as the definition of the criteria used to assess the selection of the most appropriate AI/ML algorithm.

Unravelling the magic of latent safety threats

Sterile processing errors in medical and dental offices are ranked the third highest hazard according to the annual ECRI ‘Top 10 Health Technology Hazards’ 2020 report. Other experts have raised similar concerns with sterilisation processes. For example, the WHO and the Clinical Engineering Division of International Federation of Medical and Biological Engineering (IFMBE) have partnered to provide a series of webinars with international experts exchanging knowledge on COVID-19 related critical topics. A recent webinar addressed the critical challenge of decontamination and disinfection of COVID-19 medical equipment in low-income and middle-income countries. During the webinar, participants asked about methodologies to assess whether the transmission of infection is borne by technological tools used to fight the disease. How can critical lifesaving breathing equipment be safely and quickly sterilised and moved from one patient to the next? The WHO/IFMBE webinar2 stated that ‘engineers and infection control professionals seem to be working in different silos’. Such silos must be dismantled because medical technology is indispensable in the provisioning of healthcare services. Disinfection and sterilisation of medical equipment are key concerns for healthcare organisations, and they require serious consideration of sociotechnical system interactions. The annual ‘top 10 Health Technology Hazards report’ is based on retrospective studies, yet management of COVID-19 safety requires capacity to process real- time data and the input of experts to predict where risks may occur and how to deploy plans to maintain a safe healthcare environment.

Efficiency index of a pedaling monitor system depend on load power, cadence and body weight

Background: In recent years, a variety of power meters for bicycles has become commercially available (Allen & Coggan, 2010: Training and Racing with a Power Meter (2nd edn.). Boulder, Velopress). In particular, a pedaling monitoring system (SGY-PM900H90, SGX-CA900: Pioneer Corporation, Kawasaki, Japan) is a device that displays a pedaling force vector to decompose the tangential and normal direction of pedaling force (Pioneer Cyclesports, “Pedaling Monitor Sensor”. Retrieved 20 March, 2014, from http://pioneer-cyclesports.com/us-en/). No other such devices exist except for those used experimentally. This device can display the efficiency index of the pedaling force. Although we can see the pedaling force vector diagram and the efficiency index change every second, it is difficult to understand the state of the averaged pedaling force vectors (Bibbo et al., 2008: A wireless integrated system to evaluate efficiency indexes in real time during cycling, 4th European Conference of the IFMBE Proceedings, 22: 89–92). Purpose: The purpose of this study was to reveal the influence of load power, cadence, and body weight on the efficiency index of the pedaling monitor system by averaging the pedaling force vector signal obtained from the pedaling monitor system over a measuring period. Methods: Twenty-eight participants were given the pedaling load step up from ~150 W to ~300 W by a bicycle trainer (Powerbeam Pro-trainer: CycleOps, Madison, WI). The pedaling force vectors during the step load were recorded. Cadence was not specified: each participant had decided on a comfortable cadence. Using a pedaling force vector obtained from the experiment, the pedaling force vector was averaged at each load step, and the efficiency index was determined from the averaged pedaling force vector. Multiple regression analysis was conducted with the efficiency index as an objective variable, and load power, cadence, and body weight were set as explanatory variables. Results: The efficiency index was significantly correlated (multiple correlation coefficient: r = 0.732, p-value = 4.6 x10-21) with load power (regression coefficient: i¢i€ = 0.078%, p = 3.2 x10-16), cadence (i¢i€ = -0.429%,  p = 2.0 x10-10), and body weight (i¢i€ = -0.383%, p = 1.4x10-7). Using the coefficient value of the multiple regression analysis, the efficiency index was compensated to remove the effects of these factors (load power, cadence, and body weight). As a result, the average compensated efficiency index was 50.2% at 250 W, 100 rpm, 65 kg, and the standard deviation was 5.2%. Discussion: The result was considered to be due to the influence of the load effect, which was applied to the pedal by centrifugal force and gravity of the leg weight. The variation in the compensated efficiency index was small, after removing the effects of load power, cadence, and body weight. It was considered that the features of pedaling of the participant were reflected in the compensated efficiency index. According to the actual pedaling force vector, the effect of downward force in the recovery phase was large. Conclusion: In order to reveal the influence of load power, cadence, and body weight on the efficiency index of the pedaling force vector, multiple regression analysis was made with the efficiency index calculated from the averaged pedaling force vector. As a result, the following became clear: (1) the efficiency index can be compensated to remove the effects of these factors (load power, cadence, and body weight), and (2) it is possible to understand the features of the participant's pedaling technique from the compensated efficiency index.

A Brief History of USNCB: Motivation and Formation

A Brief History of USNCB: Motivation and Formation

Warm welcome to the new MBEC Editor-in-Chief and his team

In 2012, the year of celebration of the 50th Anniversary of Medical & Biological Engineering & Computing (MBEC), the International Federation of Medical and Biological Engineering (IFMBE) was searching for a new Editor-in-Chief for the journal. The previous Editor, Jos A.E. Spaan, decided to retire after 7 years of dedicated service ensuring timely release of monthly issues of the MBEC journal. The task of selecting the new MBEC Editor-in-Chief (EiC) was undoubtedly arduous and the necessary procedures took substantial amount of time mainly because the Administrative Council of IFMBE wanted to ensure the selection of the right person to lead the efforts in making MBEC a top quality journal. I am pleased to welcome Nitish Thakor who has accepted the position of MBEC Editor-in-Chief. Let me give you some of the major considerations which led to his appointment as the EiC for MBEC.

Acknowledgment of Reviewer performance in 2008

It is going well with Medical & Biological Engineering & Computing (MBEC)! As explained in a series of editorials over the past few years, structural changes were implemented in the journal at practically all levels [2–5]. The most important changes were teaming with a new publisher, Springer, and establishing a new editorial team. The aim, clearly underwritten by the Administrative Council of the International Federation of Medical and Biological Engineering (IFMBE), was to increase the impact of MBEC as measured by the indices published on the Web of Science [1] (http://science.thomsonreuters.com), (i.e., the Impact Factor, IF). We have always seen this as a joint effort of all involved. We also knew that this was a slow process, especially because the indices used to compute the IF cover the journal’s production and influence over a series of years. For understanding and support to this process, I am grateful to the efforts of IFMBE’s Federation Journal Committee over these last years. Recently the indices have been updated and indeed success is now measureable and reported publically. Our IF for 2008 increased by 40% to 1.38, but more importantly, we anticipate a further significant increase next year based on the citations to MBEC papers published in 2007 and 2008. Another indication of the MBEC’s increased visibility is the observation that the number of citations to all papers published in MBEC over the 47 years of its existence, increased in 2008 by 30%. This increased citation rate is to MBEC papers accepted under responsibilities of the former editors. Our Journal ranks second in the list of Biomedical Engineering journals when sorted by cited half-life manuscripts, which is 9.8 years. This implies that we have many hallmark publications that are cited even after 10 years. Essential for the journal is the willingness of our reviewers to evaluate the manuscripts that are submitted to the journal in a timely fashion. We thought it was a good moment to recognize their contributions by publishing their names and indicate the number of reports they wrote in 2008. We are grateful to the international community of reviewers and authors for contributing to the continuation of our success in serving the Medical and Biological Engineering Community. Jos AE Spaan. Editor in Chief Deputy Editor: Ruben Coronel, Academic Medical Center, Amsterdam, The Netherlands Associates Editors: Jenny Dankelman, University of Technology, Delft, The Netherlands Dario Farina, Aalborg University, Aalborg, Denmark Andrew McCulloch, University of California, San Diego, USA Nico A. M. Schellart, Academic Medical Center, Amsterdam, The Netherlands Maria Siebes, Academic Medical Center, Amsterdam, The Netherlands Andreas Wahle, University of Iowa, Iowa, USA

IFMBE CED Chairman Announcement

IFMBE CED Chairman Announcement