Imaging Pearls ❯ Deep Learning ❯ Drug Development
|
-- OR -- |
|
- “This study found modest use of AI for drug development focused primarily on early-stage applications and on anticancer and neurological therapies. Possible explanations include a lack of high-quality data available in the subsequent stages of drug discovery and uncertain regulatory expectations concerning late-stage AI applications. Study limitations included relying upon public disclosures by drug manufacturers. Ultimately, this study’s results suggest that greater clarity from medicines regulators is needed to guide sponsors over acceptable AI standards and applications to satisfy marketing authorization requirements.”
Use of Artificial Intelligence in Drug Development.
Druedahl LC, Price WN 2nd, Minssen T, Sarpatwari A.
JAMA Netw Open. 2024 May 1;7(5) - “Considerable focus has been placed on the health care applications of artificial intelligence (AI). Already, machine learning, a subset of AI that involves “the use of data and algorithms to imitate the way that humans learn”1 has been used to predict diseases, while AI-powered smartphone apps have been developed to promote mental health and weight loss. Owing in part to such successes, the market for AI in health care has been forecasted to increase more than 1000% between 2022 and 2029, from $13.8 billion to $164.1 billion.”
Use of Artificial Intelligence in Drug Development.
Druedahl LC, Price WN 2nd, Minssen T, Sarpatwari A.
JAMA Netw Open. 2024 May 1;7(5) - “One area of substantial promise is drug development, which is poised to benefit from advances in the use of AI to predict protein folding, molecular interactions, and cellular disease processes.5 Successful application of AI to drug development, however, faces several obstacles, including poor model performance caused by nondiverse training data and shortcut learning. Additionally, the often opaque ways that AI systems reach their predictions conflict with regulatory approval frameworks that require a rationale for decision-making. Given these obstacles, we sought to identify the scope and breadth of AI use in drug development.”
Use of Artificial Intelligence in Drug Development.
Druedahl LC, Price WN 2nd, Minssen T, Sarpatwari A.
JAMA Netw Open. 2024 May 1;7(5) - CMS currently possesses the authority to investigate hospitals and mandate the development of a corrective action plan if they find their processes and procedures do not protect patient safety regardless of the etiology of the error. If an error that caused harm to a patient is due to something intrinsic to an algorithm, then we believe it is important for safety incidences, including errors without harm, to be reported at minimum to the manufacturer/developer, and risks to be managed and controlled by the implementer. If the issue relates to poor implementation, then the hospital should be obligated to ensure that the QAPI process is used to minimize any further error and details around the root-cause of safety risks to be reported to manufacturer/developer. If the AI technology is FDA cleared, then the requirement is that the medical harm is reported to the FDA and themanufacturer.
Artificial Intelligence Can Be Regulated Using Current Patient Safety Procedures and Infrastructure in Hospitals.
Fleisher LA, Economou-Zavlanos NJ.
JAMA Health Forum. 2024 Jun 7;5(6):e241369. - If the AI technology is not FDA cleared, then it will be important for the health care ecosystem and the federal regulators to think about the mechanism to report AI-influenced medical errors and findings of any QAPI program be reported back to the manufacturer. It is essential for CMS and the HHS to leverage their existing authority under the CoPs to ensure the safe implementation of AI in hospitals, leaving the assessment of algorithms or tools to the FDA and other bodies yet to befully defined. While AI has the potential to improve patient outcomes and care, the critical goal is to employ AI in enhancing safety, not in creating new sources of medical harm without a clearmechanism for continuously improving and learning from any medical errors.
Artificial Intelligence Can Be Regulated Using Current Patient Safety Procedures and Infrastructure in Hospitals.
Fleisher LA, Economou-Zavlanos NJ.
JAMA Health Forum. 2024 Jun 7;5(6):e241369.