Nuclear magnetic resonance (NMR) spectroscopy has emerged as a technology that can provide metabolite information within organ systems in vivo. In this study, we introduced a new method of employing a clustering algorithm to develop a diagnostic model that can differentially diagnose a single unknown subject in a disease with well-defined group boundaries. We used three tests to assess the suitability and the accuracy required for diagnostic purposes of the four clustering algorithms we investigated (K-means, Fuzzy, Hierarchical, and Medoid Partitioning). To accomplish this goal, we studied the striatal metabolomic profile of R6/2 Huntington disease (HD) transgenic mice and that of wild type (WT) mice using high field in vivo proton NMR spectroscopy (9.4. T). We tested all four clustering algorithms (1) with the original R6/2 HD mice and WT mice, (2) with unknown mice, whose status had been determined via genotyping, and (3) with the ability to separate the original R6/2 mice into the two age subgroups (8 and 12 weeks old). Only our diagnostic models that employed ROC-supervised Fuzzy, unsupervised Fuzzy, and ROC-supervised K-means Clustering passed all three stringent tests with 100% accuracy, indicating that they may be used for diagnostic purposes.
Bibliographical noteFunding Information:
We would like to thank C. Dirk Keene and Ivan Tkac for helping us with the acquisition of spectra and Janet M. Dubinsky for providing us with the spectral data of 20 unknown mice. This study was funded by the National Institutes of Health (NIH) —grant numbers: T32 DA007097 and R03 NS060059 .
- Clustering analyses
- Diagnostic methods
- Fuzzy Clustering
- Hierarchical Clustering
- Huntington disease
- K-means Clustering
- Medoid Partitioning Clustering
- Nuclear magnetic resonance spectroscopy
- Receiver operating characteristic (ROC) curve analysis