Thursday, 24 September 2020

Studies on Development of New Method for the Prediction of Clinical Trial Results Using Compressive Sensing of Artificial Intelligence | Chapter 9 | Theory and Practice of Mathematics and Computer Science Vol.2

 

We applied the compressive sensing in this analysis to an observational sample of clinical trials consisting of two groups. Each group needed time data from 25 patients, but in order to accommodate alpha and beta errors, data from 12 more patients had to be acquired. Thus, the unknown knowledge was predicted using the process of compressive sensing. For each one, the calculation was repeated 1,000 times, and 1 million (= 1,0002) log-rank tests were performed between the two classes, after which a P-value histogram was obtained. Information obtained by repeated estimates on the distribution of expected data represents the likelihood of statistical significance. This technique will be   It is useful for clinical trials studying rare diseases or if the registration process is delayed.

Author (s) Details

Y. Miyagi
Department of Gynecology, Miyake Ofuku Clinic, Okayama City, Japan and Department of Artificial Intelligence, Medical Data Labo, Okayama City, Japan.

K. Fujiwara
Department of Gynecologic Oncology, Saitama Medical University International Medical Center, Hidaka City, Japan.

T. Oda
Department of Obstetrics and Gynecology, Miyake Clinic, Okayama City, Japan.

T. Miyake
Department of Gynecology, Miyake Ofuku Clinic, Okayama City, Japan. and Department of Obstetrics and Gynecology, Miyake Clinic, Okayama City, Japan.

R. L. Coleman
Department of Gynecologic Oncology and Reproductive Medicine, University of Texas MD Anderson Cancer Center, Houston, Texas, USA.

View Book :-
https://bp.bookpi.org/index.php/bpi/catalog/book/271

No comments:

Post a Comment