Algorithm development for diagnostic biomarker assays

• Published in: Biomarkers of Neurological and Psychiatric Disease Vol. 101; pp. 279 - 298
• Main Authors: Izmailov, Rauf, Guest, Paul C., Bahn, Sabine, Schwarz, Emanuel
• Format: Book Chapter Journal Article
• Language: English
• Published: United States Elsevier Science & Technology 2011
• Subjects: Algorithms; Biomarkers - analysis; Biomarkers - blood; classification; diagnosis; feature selection; Humans; Immunoassay - methods; Immunoassay - trends; Molecular Diagnostic Techniques - methods; Molecular Diagnostic Techniques - trends; Neurology & clinical neurophysiology; Neurosciences; Predictive Value of Tests; Psychiatry; Reproducibility of Results; schizophrenia; Schizophrenia - blood; Schizophrenia - diagnosis; Schizophrenia - physiopathology; serum-based test; SVM; diagnosis; schizophrenia; SVM; classification; serum-based test; feature selection
• ISBN: 0123877180; 9780123877185
• ISSN: 0074-7742; 2162-5514; 2162-5514
• DOI: 10.1016/B978-0-12-387718-5.00011-0

This chapter describes the ground-breaking development of a serum-based test to help confirm the diagnosis of schizophrenia. A multiplex panel of 51 immunoassays was developed that allowed reproducible identification of schizophrenia patients compared to controls with high sensitivity and specificity. Validation of this test consisted of developing a linear support vector machine decision rule and testing its performance using cross-validation. This resulted in readjustment of the panel and algorithm to a smaller set of 40 robust assays, along with a simple procedure for maintenance and recalibration across future measurement changes associated with different reagent lots. The resulting decision rule delivered a sensitive and specific prediction for presence of schizophrenia in subjects compared to matched controls, with a receiver operating characteristic area under the curve of 88%. Performance of the recalibrated decision rule remained constant across lot changes, ensuring consistency and accuracy.