AI/ML Models to Aid in the Diagnosis of COVID-19 Illness from Forced Cough Vocalizations: Good Machine Learning Practice and Good Clinical Practices from Concept to Consumer for AI/ML Software Devices

From a comprehensive and systematic search of the relevant literature on signal data signature (SDS)-based artificial intelligence/machine learning (AI/ML) systems designed to aid in the diagnosis of COVID-19 illness, we identified the highest quality articles with statistically significant data sets for a head-to-head comparison to our own model in development. Further comparisons were made to the recently released "Good Machine Learning Practice (GMLP) for Medical Device Development: Guiding Principles" and, in conclusions, we proposed supplemental principles aimed at bringing AI/ML technologies in closer alignment GMLP and Good Clinical Practices (GCP).

A continuum of human factors considerations, from medical device development to hospital implementation

Today’s medical devices are the product of many human factors considerations. Beyond the device design, healthcare organizations increasingly incorporate usability as a factor in medical device procurement. Yet, organizations’ visibility into evidence of a product’s usability is often constrained to marketing materials or results of studies executed using in-house resources. In the process from medical device development to implementation in clinical environments, a communication gap remains between the human factors professionals in medical device development and those in healthcare organizations studying the same product for adoption and implementation. This gap limits organizations’ ability to accurately review product options. This gap also results in lost opportunities for healthcare organizations to inform manufacturers’ future medical device development. A new paradigm for communicating human factors work across the full continuum of the product life cycle is essential for both manufacturers and healthcare organizations seeking to improve patient safety and effective use.