Data-driven Analysis of Clinical Trials
Name
cho-joonhyuk-sm-eecs-2024-thesis.pdf
Description
Thesis PDF
Size
516.06 KB
Format
Adobe PDF
Checksum (MD5)
ba213400dbe5177529b1bcf1258ab390
Author(s)
Cho, Joonhyuk
Advisor(s)
Lo, Andrew W.
Date Issued
February 2024
Publisher
Massachusetts Institute of Technology
Abstract
The research combines two studies in the field of clinical trials. The first evaluates the amyotrophic lateral sclerosis (ALS) drug AMX0035 using Bayesian decision analysis (BDA), balancing FDA safety standards with patient needs. This method provides a quantitative way to consider both the patient’s perspective and the disease’s impact. The second study uses machine learning models to predict how long clinical trials will take. By analyzing a large dataset, it identifies factors that affect trial duration, helping to streamline the trial process and potentially reduce costs. Together, these studies offer new ways to evaluate and manage clinical trials, combining patient-focused evaluation with efficient trial design.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
