A Preliminary Scoping Study of Federated Learning for the Internet of Medical Things.

This paper presents a scoping review of federated learning for the Internet of Medical Things (IoMT) and demonstrates the limited amount of research work in an area which has potential to improve patient care. Federated Learning and IoMT - as standalone technologies - have already proved to be highly disruptive but there is a need for further research to apply federated learning to the IoMT.

Quantifying Missingness in Wearable Heart Rate Recordings.

Wrist-worn photoplethysmography (PPG) heart rate monitoring devices are increasingly used in clinical applications despite the potential for data missingness and inaccuracy. This paper provides an analysis of the intermittency of experimental wearable data recordings. Devices recorded heart rate with gaps of 5 or more minutes 41.6% of the time and 15 or more minutes 3.8% of the time.

Investigation of wearable health tracker version updates.

BACKGROUND: Wearable fitness trackers are increasingly used in healthcare applications; however, the frequent updating of these devices is at odds with traditional medical device practices. OBJECTIVE: Our objective was to explore the nature and frequency of wearable tracker updates recorded in device changelogs, to reveal the chronology of updates and to estimate the intervals where algorithm updates could impact device validations. METHOD: Updates for devices meeting selection criteria (that included their use in clinical trials) were independently labelled by four researchers according to simple function and specificity schema. RESULTS: Device manufacturers have diverse approaches to update reporting and changelog practice. Visual representations of device changelogs reveal the nature and chronology of device iterations. 13% of update items were unspecified and 32% possibly affected validations with as few as 5 days between updates that may affect validation. CONCLUSION: Manufacturers could aid researchers and health professionals by providing more informative device update changelogs.

Version Reporting and Assessment Approaches for New and Updated Activity and Heart Rate Monitors.

This paper addresses the significant need for improvements in device version reporting and practice across the academic and technical activity monitoring literature, and it recommends assessments for new and updated consumer sensing devices. Reproducibility and data veracity are central to good scholarship, and particularly significant in clinical and health applications. Across the literature there is an absence of device version reporting and a failure to recognize that device validity is not maintained when firmware and software updates can, and do, change device performance and parameter estimation. In this paper, we propose the use of tractable methods to assess devices at their current version and provide an example empirical approach. Experimental results for heart rate and step count acquisitions during walking and everyday living activities from Garmin Vivosmart 3 (v4.10) wristband monitors are presented and analyzed, and the reliability issues of optically-acquired heart rates, especially during periods of activity, are demonstrated and discussed. In conclusion, the paper recommends the empirical assessment of new and updated activity monitors and improvements in device version reporting across the academic and technical literature.

Evaluation of AllergiSense Smartphone Tools for Adrenaline Injection Training.

Anaphylaxis is an increasingly prevalent life-threatening allergic condition that requires people with anaphylaxis and their caregivers to be trained in the avoidance of allergen triggers and in the administration of adrenaline autoinjectors. The prompt and correct administration of autoinjectors in the event of an anaphylactic reaction is a significant challenge in the management of anaphylaxis. Unfortunately, many people do not know how to use autoinjectors and either fail to use them or fail to use them correctly. This is due in part to deficiencies in training and also to the lack of a system encouraging continuous practice with feedback. Assistive smartphone healthcare technologies have demonstrated potential to support the management of chronic conditions such as diabetes and cardiovascular disease, but there have been deficiencies in their evaluation and there has been a lack of application to anaphylaxis. This paper describes AllergiSense, a smartphone app and sensing system for anaphylaxis management, and presents the results of a randomized, controlled, prepost evaluation of AllergiSense injection training and feedback tools with healthy participants. Participants whose training was supplemented with AllergiSense injection feedback achieved significantly better practiced injections with 90.5% performing correct injections compared to only 28.6% in the paper-only control group. In addition, the results provide insights into possible self-efficacy failings in traditional training and the benefits of embedding self-efficacy theory into the technology design process.

A wavelet-based region of interest encoder for the compression of angiogram video sequences.

A new method for the compression of angiogram video sequences is presented. The method is based on the philosophy that diagnostically significant areas of the image should be allocated the greatest proportion of the total allocated bit budget. The approach uses a three-dimensional wavelet-coder based on the popular set partitioning in hierarchical trees algorithm. Incorporated into this framework are a region-of-interest (ROI) detection stage and a texture-modeling stage. The combined result is an approach that models the high-frequency wavelet coefficients for some diagnostically unimportant regions of the image in an extremely efficient manner. This allows additional bits to be used within the ROI to improve the quality of the diagnostically significant areas. Results are compared for a number of real data sets and evaluated by trained cardiologists.