Algorithms Outperform Metabolite Tests in Predicting Response of Patients With Inflammatory Bowel Disease to Thiopurines
published online 15 October 2009.
Background & Aims
Levels of the thiopurine metabolites 6-thioguanine nucleotide (6-TGN) and 6-methylmercaptopurine commonly are monitored during thiopurine therapy for inflammatory bowel disease despite this test's high cost and poor prediction of clinical response (sensitivity, 62%; specificity, 72%). We investigated whether patterns in common laboratory parameters might be used to identify appropriate immunologic responses to thiopurine and whether they are more accurate than measurements of thiopurine metabolites in identifying patients who respond to therapy.
Methods
We identified 774 patients with inflammatory bowel disease on thiopurine therapy using metabolite and standard laboratory tests over a 24-hour time period. Machine learning algorithms were developed using laboratory values and age in a random training set of 70% of the cases; these algorithms were tested in the remaining 30% of the cases.
Results
A random forest algorithm was developed based on laboratory and age data; it differentiated clinical responders from nonresponders in the test set with an area under the receiver operating characteristic (AUROC) curve of 0.856. In contrast, 6-TGN levels differentiated clinical responders from nonresponders with an AUROC of 0.594 (P < .001). Algorithms developed to identify thiopurine nonadherence (AUROC, 0.813) and thiopurine shunters (AUROC, 0.797) were accurate.
Conclusions
Algorithms that use age and laboratory values can differentiate clinical response, nonadherence, and shunting of thiopurine metabolism among patients who take thiopurines. This approach was less costly and more accurate than 6-TGN metabolite measurements in predicting clinical response. If validated, this approach would provide a low-cost, rapid alternative to metabolite measurements for monitoring thiopurine use.
⁎Division of Gastroenterology, Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan
‡General Clinical Research Center, University of Michigan, Ann Arbor, Michigan
∥Department of Statistics, University of Michigan, Ann Arbor, Michigan
§Department of Statistics, University of Wisconsin, Madison, Wisconsin
Reprint requests Address requests for reprints to: Peter D. R. Higgins, MD, PhD, MSc, Division of Gastroenterology, University of Michigan, 6520 MSRB I, Box 0682, 1150 West Medical Center Drive, Ann Arbor, Michigan 48109. fax: (734) 763-2535
Conflicts of interest The authors disclose the following: The Regents of the University of Michigan, along with authors Peter Higgins, Akbar Waljee, Joel Joyce, Sijian Wang, and Ji Zhu, have applied for a patent on the application of machine learning to patterns in the complete blood count and differential and the comprehensive chemistry panel to the prediction of clinical response to thiopurines. As of December 20, 2009, no patent has yet been granted. The remaining authors disclose no conflicts.
ABSTRACT
Algorithms Outperform Metabolite Tests in Predicting Response of Patients With Inflammatory Bowel Disease to Thiopurines