首页|Researchers Submit Patent Application, 'Direct Medical Treatment Predictions Usi ng Artificial Intelligence', for Approval (USPTO 20240347159)
Researchers Submit Patent Application, 'Direct Medical Treatment Predictions Usi ng Artificial Intelligence', for Approval (USPTO 20240347159)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
News editors obtained the following quote from the background information suppli ed by the inventors: “This invention relates generally to using artificial intel ligence (AI) to directly determine a patient specific treatment or management of a disease that will benefit that patient, rather than manual selection based on a diagnosis.Currently, autonomous AI systems use machine learning or other opt imization techniques to determine the diagnosis of a patient, and clinicians the n use this AI diagnosis, in addition to other relevant patient and population in formation, to subjectively determine patient specific management or prescribe a patient specific treatment (also referred to herein as an “intervention”).Thus, Autonomous AI diagnosis, while capable of determining a diagnosis without human oversight, still relies on a clinician to interpret the diagnosis in terms of t he patient’s entire case and then decide the intervention.However, this interme diate, subjective decision step is subject to high inter- and intra clinician va riability, temporal and other drift.Moreover, the interaction between artificia l intelligence and the clinician is variable with often unanticipated risks, and has been known to worsen rather than improve outcome.Moreover, obtaining the h ighest quality reference standard (‘ground truth’) to train autonomous AI models for producing a diagnosis can be ethically problematic, and expensive.Where th e reference standard is dependent on clinician expertise, such as subjective rea ding of images, the reference standard can be noisy.Instead, when clinical outc ome, (which combines the effects of both the accuracy of the diagnostic process as well as the precision of the treatment or management selection process) rathe r than the interim diagnosis can be used as reference standard for training the AI, this subjective, noisy step is eliminated, with the potential to have higher performance.”
Artificial IntelligenceCyborgsEmergi ng TechnologiesMachine LearningPatent Application
NETL
NSTL
