Critical factor identification in medical device development through supervised learning

DS 75-3: Proceedings of the 19th International Conference on Engineering Design (ICED13) Design For Harmonies, Vol. 3: Design Organisation and Management, Seoul, Korea 19-22.08.2013

Year: 2013
Editor: Udo Lindemann, Srinivasan V, Yong Se Kim, Sang Won Lee, John Clarkson, Gaetano Cascini
Author: Jankovic, Marija; Medina, Lourdes; Kremer, Gül; Yannou, Bernard
Series: ICED
Institution: 1: Ecole Centrale Paris, France; 2: Pennsylvania State University; 3: University of Puerto Rico
Page(s): 211-222
ISBN: 978-1-904670-46-9
ISSN: 2220-4334

Abstract

This paper investigates the impact of different variables in Medical Device Development (MDD), where FDA (Food and Drug Administration) approval time is considered as a performance variable. To analyze the significance of the variables supervised Bayesian learning, the Minimal Description Length (MDL) algorithm, is used. A set of real FDA data, representing 474 different companies in USA medical device markets, from 2400 FDA approved orthopedic devices is used. The aim of the study is to identify which product, company and regulation factors contribute most to the variations in FDA decision time.

Keywords: Medical device development, key factors, FDA (Food and Drug administration) processus

Download