Variable selection and chemometric models for discriminating symptomatic gout based on a metabolic target analysis

In clinical practice, uric acid is frequently used as a diagnostic criterion in gout. However, gout is commonly confused with other diseases, including rheumatoid arthritis, soft tissue joint injury, and hyperuricosuric calcium oxalate urolithiasis. Two new strategies—graphical index of separation and subwindow permutation analysis—were applied to understand the metabolic changes induced by gout. Metabolic target analysis was performed using high performance liquid chromatography with a diode array detector. Compared with the nongout samples, the concentrations of uric acid, uracil, inosine, adenosine, and tryptophan are different in gout samples, and these metabolites could be used as important diagnostic markers. However, the uric acid, uracil, phenylalanine, tryptophan, and adenine concentrations differed between acute and chronic gout. We confirmed the metabolic disorder of uracil during the basic development of gout. In the gout and nongout groups, the recognition rate of the model reached 0.98, whereas the value of recognition ability was only 0.79 when uric acid was used as a single variable. In the acute and chronic class of gout, the recognition rate of the model was 0.90 and that of uric acid was only 0.62. Variable selection combined with chemometric models can be used as a supplementary method for the diagnosis and prognosis of gout in clinical practice.