论文信息 - Automated Classification of Computer-Based Medical Device Recalls: An Application of Natural Language Processing and Statistical Learning

Automated Classification of Computer-Based Medical Device Recalls: An Application of Natural Language Processing and Statistical Learning

This paper presents MedSafe, a framework for automated classification of computer-based medical device recalls. The data is collected from the U.S. Food and Drug Administration (FDA) recalls database. We combined techniques in natural language processing and statistical learning to automatically identify the computer-related recalls, by interpreting the natural language semantics of recall descriptions. We evaluated MedSafe on over 16K recall records submitted to the FDA between years 2007-2013.

[1] D. Richard Kuhn,et al. FAILURE MODES IN MEDICAL DEVICE SOFTWARE: AN ANALYSIS OF 15 YEARS OF RECALL DATA , 2001 .

[2] William A. Hyman,et al. An Analysis of Software-Related Recalls of Medical Devices , 2010 .

[3] Nicolas Pallikarakis,et al. Analysis and Classification of Medical Device Recalls , 2007 .

[4] Ravishankar K. Iyer,et al. Analysis of Safety-Critical Computer Failures in Medical Devices , 2013, IEEE Security & Privacy.

[5] Hinrich Schütze,et al. Introduction to information retrieval , 2008 .

[6] Kevin Fu,et al. Security and Privacy Qualities of Medical Devices: An Analysis of FDA Postmarket Surveillance , 2012, PloS one.