An official website of the United States government
Abstract Medical devices play a crucial role in modern healthcare, providing innovative solutions for diagnosing, preventing, monitoring, and treating ailments. Artificial Intelligence is transforming the field of medical devices, offering unprecedented opportunities through diagnostic accuracy, personalized treatment plans, and enhancing patient outcomes. This review outlines the applications of artificial intelligence-based medical devices in healthcare specialties, especially in dentistry, medical imaging, ophthalmology, mental health, autism spectrum disorder diagnosis, oncology, and general medicine. Specifically, the review highlights advancements such as improved diagnostic accuracy, tailored treatment planning, and enhanced clinical outcomes in the above-mentioned applications. Regulatory approval remains a key issue, where medical devices must be approved or cleared by the United States Food and Drug Administration to establish their safety and efficacy. The regulatory guidance pathway for artificial intelligence-based medical devices is presented and moreover the critical technical, ethical, and implementation challenges that must be addressed for large-scale adoption are discussed. The review concludes that the intersection of artificial intelligence with the medical device domain and internet-enabled or enhanced technology, such as biotechnology, nanotechnology, and personalized therapeutics, enables an enormous opportunity to accelerate customized and patient-centered care. By evaluating these advancements and challenges, the study aims to present insights into the future trajectory of smart medical technologies and their role in advancing personalized, patient-centered care.
more »
« less
Marketing and US Food and Drug Administration Clearance of Artificial Intelligence and Machine Learning Enabled Software in and as Medical Devices: A Systematic Review
Importance The marketing of health care devices enabled for use with artificial intelligence (AI) or machine learning (ML) is regulated in the US by the US Food and Drug Administration (FDA), which is responsible for approving and regulating medical devices. Currently, there are no uniform guidelines set by the FDA to regulate AI- or ML-enabled medical devices, and discrepancies between FDA-approved indications for use and device marketing require articulation. Objective To explore any discrepancy between marketing and 510(k) clearance of AI- or ML-enabled medical devices. Evidence Review This systematic review was a manually conducted survey of 510(k) approval summaries and accompanying marketing materials of devices approved between November 2021 and March 2022, conducted between March and November 2022, following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline. Analysis focused on the prevalence of discrepancies between marketing and certification material for AI/ML enabled medical devices. Findings A total of 119 FDA 510(k) clearance summaries were analyzed in tandem with their respective marketing materials. The devices were taxonomized into 3 individual categories of adherent, contentious, and discrepant devices. A total of 15 devices (12.61%) were considered discrepant, 8 devices (6.72%) were considered contentious, and 96 devices (84.03%) were consistent between marketing and FDA 510(k) clearance summaries. Most devices were from the radiological approval committees (75 devices [82.35%]), with 62 of these devices (82.67%) adherent, 3 (4.00%) contentious, and 10 (13.33%) discrepant; followed by the cardiovascular device approval committee (23 devices [19.33%]), with 19 of these devices (82.61%) considered adherent, 2 contentious (8.70%) and 2 discrepant (8.70%). The difference between these 3 categories in cardiovascular and radiological devices was statistically significant ( P < .001). Conclusions and Relevance In this systematic review, low adherence rates within committees were observed most often in committees with few AI- or ML-enabled devices. and discrepancies between clearance documentation and marketing material were present in one-fifth of devices surveyed.
more »
« less
- PAR ID:
- 10454772
- Date Published:
- Journal Name:
- JAMA Network Open
- Volume:
- 6
- Issue:
- 7
- ISSN:
- 2574-3805
- Page Range / eLocation ID:
- e2321792
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract New drug production, from target identification to marketing approval, takes over 12 years and can cost around $2.6 billion. Furthermore, the COVID-19 pandemic has unveiled the urgent need for more powerful computational methods for drug discovery. Here, we review the computational approaches to predicting protein–ligand interactions in the context of drug discovery, focusing on methods using artificial intelligence (AI). We begin with a brief introduction to proteins (targets), ligands (e.g. drugs) and their interactions for nonexperts. Next, we review databases that are commonly used in the domain of protein–ligand interactions. Finally, we survey and analyze the machine learning (ML) approaches implemented to predict protein–ligand binding sites, ligand-binding affinity and binding pose (conformation) including both classical ML algorithms and recent deep learning methods. After exploring the correlation between these three aspects of protein–ligand interaction, it has been proposed that they should be studied in unison. We anticipate that our review will aid exploration and development of more accurate ML-based prediction strategies for studying protein–ligand interactions.more » « less
-
null (Ed.)There have been significant advances in the technologies for robot-assisted lower-limb rehabilitation in the last decade. However, the development of similar systems for children has been slow despite the fact that children with conditions such as cerebral palsy (CP), spina bifida (SB) and spinal cord injury (SCI) can benefit greatly from these technologies. Robotic assisted gait therapy (RAGT) has emerged as a way to increase gait training duration and intensity while decreasing the risk of injury to therapists. Robotic walking devices can be coupled with motion sensing, electromyography (EMG), scalp electroencephalography (EEG) or other noninvasive methods of acquiring information about the user’s intent to design Brain-Computer Interfaces (BCI) for neuromuscular rehabilitation and control of powered exoskeletons. For users with SCI, BCIs could provide a method of overground mobility closer to the natural process of the brain controlling the body’s movement during walking than mobility by wheelchair. For adults there are currently four FDA approved lower-limb exoskeletons that could be incorporated into such a BCI system, but there are no similar devices specifically designed for children, who present additional physical, neurological and cognitive developmental challenges. The current state of the art for pediatric RAGT relies on large clinical devices with high costs that limit accessibility. This can reduce the amount of therapy a child receives and slow rehabilitation progress. In many cases, lack of gait training can result in a reduction in the mobility, independence and overall quality of life for children with lower-limb disabilities. Thus, it is imperative to facilitate and accelerate the development of pediatric technologies for gait rehabilitation, including their regulatory path. In this paper an overview of the U.S. Food and Drug Administration (FDA) clearance/approval process is presented. An example device has been used to navigate important questions facing device developers focused on providing lower limb rehabilitation to children in home-based or other settings beyond the clinic.more » « less
-
In this study, we introduce BedDot, the first contact-free and bed-mounted continuous blood pressure monitoring sensor. Equipped with a seismic sensor, BedDot eliminates the need for external wearable devices and physical contact, while avoiding privacy or radiation concerns associated with other technologies such as cameras or radars. Using advanced preprocessing techniques and innovative AI algorithms, we extract time-series features from the collected bedseismogram signals and accurately estimate blood pressure with remarkable stability and robustness. Our user-friendly prototype has been tested with over 75 participants, demonstrating exceptional performance that meets all three major industry standards, which are the Association for the Advancement of Medical Instrumentation (AAMI) and Food and Drug Administration (FDA), and outperforms current state-of-the-art deep learning models for time series analysis. As a non-invasive solution for monitoring blood pressure during sleep and assessing cardiovascular health, BedDot holds immense potential for revolutionizing the field.more » « less
-
The healthcare industry has experienced a re-markable digital transformation through the adoption of IoT technologies, resulting in a significant increase in the volume and variety of medical data generated. Challenges in processing, analyzing, and sharing healthcare data persist. Traditional cloud computing approaches, while useful for processing healthcare data, have drawbacks, including delays in data transfer, data privacy concerns, and the risk of data unavailability. In this paper, we propose a software-defined 5G and AI-enabled distributed edge-cloud collaboration platform to classify healthcare data at the edge devices, facilitate realtime service delivery, and create AI/ML-based models for identifying patients' potential medical conditions. In our architecture, we have incorporated a federated learning scheme based on homomorphic encryption to provide privacy in data sharing and processing. The proposed framework ensures secure and efficient data communication and processing, ultimately fostering effective collaboration among healthcare institutions. The models will be validated by performing a comparative time analysis, and the interplay between edge and cloud computing will be investigated to support realtime healthcare applications.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1001/jamanetworkopen.2023.21792
