An Antimicrobial Prescription Surveillance System that Learns from Experience

Inappropriate prescribing of antimicrobials is a major clinical concern that affects as many as 50 percent of prescriptions. One of the difficulties of antimicrobial prescribing lies in the necessity to sequentially adjust the treatment of a patient as new clinical data become available. The lack of specialized healthcare resources and the overwhelming amount of information to process make manual surveillance unsustainable. To solve this problem, we have developed and deployed an automated antimicrobial prescription surveillance system that assists hospital pharmacists in identifying and reporting inappropriate prescriptions. Since its deployment, the system has improved antimicrobial prescribing and decreased antimicrobial use. However, the highly sensitive knowledge base used by the system leads to many false alerts. As a remedy, we are developing a machine learning algorithm that combines instance-based learning and rule induction techniques to discover new rules for detecting inappropriate prescriptions from previous false alerts. In this article, we describe the system, point to results and lessons learned so far and provide insight into the machine learning capability.

[1]  Walter E. Haefeli,et al.  A similarity measure for case based reasoning modeling with temporal abstraction based on cross-correlation , 2006, Comput. Methods Programs Biomed..

[2]  Ervina Resetar,et al.  Implementing a Commercial Rule Base as a Medication Order Safety Net , 2003, AMIA.

[3]  Mohammed J. Zaki,et al.  PlanMine: Predicting Plan Failures Using Sequence Mining , 1998, Artificial Intelligence Review.

[4]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[5]  Peter Clark,et al.  The CN2 Induction Algorithm , 1989, Machine Learning.

[6]  Yuval Shahar,et al.  A Framework for Knowledge-Based Temporal Abstraction , 1997, Artif. Intell..

[7]  Riccardo Bellazzi,et al.  Temporal data mining for the quality assessment of hemodialysis services , 2005, Artif. Intell. Medicine.

[8]  Luigi Portinale,et al.  Case-based retrieval to support the treatment of end stage renal failure patients , 2006, Artif. Intell. Medicine.

[9]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[10]  Pedro M. Domingos.  Unifying Instance-Based and Rule-Based Induction , 1996, Machine Learning.

[11]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[12]  L. Valiquette,et al.  Impact of a reduction in the use of high-risk antibiotics on the course of an epidemic of Clostridium difficile-associated disease caused by the hypervirulent NAP1/027 strain. , 2007, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[13]  J. Meer,et al.  Optimizing antimicrobial therapy. A method for antimicrobial drug use evaluation. , 1992, The Journal of antimicrobial chemotherapy.

[14]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.

[15]  Riccardo Bellazzi,et al.  Mining Healthcare Data with Temporal Association Rules: Improvements and Assessment for a Practical Use , 2009, AIME.

[16]  Padhraic Smyth,et al.  Rule Induction Using Information Theory , 1991, Knowledge Discovery in Databases.

[17]  J. Burke,et al.  Infectious Diseases Society of America and the Society for Healthcare Epidemiology of America guidelines for developing an institutional program to enhance antimicrobial stewardship. , 2007, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.