If Your AI Can’t Explain Itself, Can FDA Authorize It?
Why is algorithmic transparency becoming an increasingly important consideration in FDA’s review of AI/ML medical devices?
Why is algorithmic transparency becoming an increasingly important consideration in FDA’s review of AI/ML medical devices?
The value-based care model, with a substantial monetary budget, necessitates on-time and correct risk stratification. As a result, new and incumbent care providers and payers are reinventing healthcare delivery, looking towards cutting-edge GenAI and machine learning technology to radically transform the healthcare delivery paradigm. This article explores how GenAI and machine learning-based risk stratification are revolutionizing a new era of personalized care, resulting in improved healthcare functions for payers and providers.
This blog explores the transformative potential of AI assistants in healthcare management and delves into the benefits for providers, medical assistants, and obviously, patients.
As medical technology products and services move through the development pipeline, they face the challenge of both showing safety and efficacy for regulatory approval and articulating the value of the diagnostic, treatment or monitoring technology to obtain reimbursement from payers. A 2024 MedExec Women Conference panel highlighted strategies to bridge the evidence needs for regulatory approval and reimbursement to more efficiently bring products to market.
Researchers have developed a new machine-learning model that can precisely make prognosis predictions for patients with osteosarcoma, based on the density of viable tumor cells post-treatment.
Traditional screening tests suffer from a range of challenges. From logistical barriers to concerns regarding accuracy and reliability, achieving accurate diagnosis is frequently arduous. Imagine a revolutionary approach where early disease screening becomes as simple as collecting a breath sample. Thanks to cutting-edge sensor technology and advanced artificial intelligence, this vision is now on the brink of realization.
In February, Hologic received FDA clearance for its Genius Digital Diagnostics System, which combines advanced imaging with AI-assisted review for cervical cancer screening. We spoke with Mike Quick, who led the development of the technology, and Dr. Hans Ikenberg, director of one of the first labs to work with the system.
Not all use cases are good candidates for machine learning. In this column we look at cases where AI/ML may be appropriate and when building a traditional algorithm to solve a problem is a better choice.
“Using Artificial Intelligence and Machine Learning in the Development of Drug and Biological Products” and “Artificial Intelligence in Drug Manufacturing” were developed to support the use of AI/ML while addressing concerns related to security, bias and risk, and spur feedback and discussion from stakeholders.