Lifecycle Regulation of Artificial Intelligence– and Machine Learning–Based Software Devices in Medicine

Hwang, Thomas J.; Kesselheim, Aaron S.; Vokinger, Kerstin Noëlle

doi:10.1001/jama.2019.16842

Cited by 93 publications

(54 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The target population of model use is also specified in both the "Uses and directions" and "Validation and performance" sections. The version of the "Model Facts" label is documented and version control with documentation of changes should be accessible to all end users 22 . Use of the model and the "Model Facts" label also needs to be approved by governance structures that function similarly to pharmacy and therapeutics committees that monitor use of medications and adverse outcomes.…”

Section: Related Workmentioning

confidence: 99%

Presenting machine learning model information to clinical end users with model facts labels

et al. 2020

View full text Add to dashboard Cite

There is tremendous enthusiasm surrounding the potential for machine learning to improve medical prognosis and diagnosis. However, there are risks to translating a machine learning model into clinical care and clinical end users are often unaware of the potential harm to patients. This perspective presents the "Model Facts" label, a systematic effort to ensure that front-line clinicians actually know how, when, how not, and when not to incorporate model output into clinical decisions. The "Model Facts" label was designed for clinicians who make decisions supported by a machine learning model and its purpose is to collate relevant, actionable information in 1-page. Practitioners and regulators must work together to standardize presentation of machine learning model information to clinical end users in order to prevent harm to patients. Efforts to integrate a model into clinical practice should be accompanied by an effort to clearly communicate information about a machine learning model with a "Model Facts" label.

show abstract

Section: Related Workmentioning

confidence: 99%

Presenting machine learning model information to clinical end users with model facts labels

et al. 2020

View full text Add to dashboard Cite

show abstract

“…But AI algorithms are of high risk when they are a driver of clinical decision-making in acute disease. Requirements for AI-based software will need to: carefully review of the safety and effectiveness of such software; address the allowable post-approval modifications to the software; and manage unanticipated divergence in the software’s eventual performance from the original product which was approved ( Hwang et al , 2019 ). Regulatory agencies, institutions and industries will need to formulate guidelines and policies regarding the use of patient data to underpin commercialization of algorithms developed using patient data.…”

Section: Ethical Principles Are Imperative In the Fast-changing Fieldmentioning

confidence: 99%

Artificial intelligence for clinical decision support in neurology

Pedersen

Verspoor

Jenkinson

et al. 2020

Brain Communications

View full text Add to dashboard Cite

Abstract Artificial intelligence is one of the most exciting methodological shifts in our era. It holds the potential to transform healthcare as we know it, to a system where humans and machines work together to provide better treatment for our patients. It is now clear that cutting edge artificial intelligence models in conjunction with high-quality clinical data will lead to improved prognostic and diagnostic models in neurological disease, facilitating expert-level clinical decision tools across healthcare settings. Despite the clinical promise of artificial intelligence, machine and deep learning algorithms are not a one-size-fits-all solution for all types of clinical data and questions. In this paper, we provide an overview of the core concepts of artificial intelligence, particularly contemporary deep learning methods, to give clinician and neuroscience researchers an appreciation of how artificial intelligence can be harnessed to support clinical decisions. We clarify and emphasise the data quality and the human expertise needed to build robust clinical artificial intelligence models in neurology. Given that artificial intelligence is a rapidly evolving field, we take the opportunity to iterate important ethical principles to guide the field of medicine is it moves into an artificial intelligence enhanced future.

show abstract

“…When intended to prevent a disease (complication), ML-based software is defined as a medical device under the Food, Drug, and Cosmetic Act with regulatory steps which must be fulfilled before implementation into a clinical practice. Most ML-based products could be developed via the 510(k) pathway or through the de novo pathway [213]. However, concerns have arisen, for example, about a change in product outputs after the product is distributed.…”

Section: Contribution Of Machine Learning To Prevention Of Pjimentioning

confidence: 99%

Prevention of Prosthetic Joint Infection: From Traditional Approaches towards Quality Improvement and Data Mining

Gallo

Nieslanikova

2020

JCM

View full text Add to dashboard Cite

A projected increased use of total joint arthroplasties will naturally result in a related increase in the number of prosthetic joint infections (PJIs). Suppression of the local peri-implant immune response counters efforts to eradicate bacteria, allowing the formation of biofilms and compromising preventive measures taken in the operating room. For these reasons, the prevention of PJI should focus concurrently on the following targets: (i) identifying at-risk patients; (ii) reducing “bacterial load” perioperatively; (iii) creating an antibacterial/antibiofilm environment at the site of surgery; and (iv) stimulating the local immune response. Despite considerable recent progress made in experimental and clinical research, a large discrepancy persists between proposed and clinically implemented preventative strategies. The ultimate anti-infective strategy lies in an optimal combination of all preventative approaches into a single “clinical pack”, applied rigorously in all settings involving prosthetic joint implantation. In addition, “anti-infective” implants might be a choice in patients who have an increased risk for PJI. However, further progress in the prevention of PJI is not imaginable without a close commitment to using quality improvement tools in combination with continual data mining, reflecting the efficacy of the preventative strategy in a particular clinical setting.

show abstract

Lifecycle Regulation of Artificial Intelligence– and Machine Learning–Based Software Devices in Medicine

Cited by 93 publications

References 2 publications

Presenting machine learning model information to clinical end users with model facts labels

Presenting machine learning model information to clinical end users with model facts labels

Artificial intelligence for clinical decision support in neurology

Prevention of Prosthetic Joint Infection: From Traditional Approaches towards Quality Improvement and Data Mining

Contact Info

Product

Resources

About