| Download | - View accepted manuscript: Diagnosis of type II diabetes based on non-glucose regions of ¹H NMR spectra of urine : a metabonomic approach (PDF, 989 KiB)
|
|---|
| Author | Search for: Nicolescu, Alina; Search for: Dolenko, Brion1; Search for: Bezabeh, Tedros1; Search for: Stefan, Lorena-Ivona; Search for: Ciurtin, Coziana; Search for: Kovacs, Eugenia; Search for: Smith, Ian C. P.1; Search for: Simionescu, Bogdan C.; Search for: Deleanu, Calin |
|---|
| Affiliation | - National Research Council of Canada. NRC Institute for Biodiagnostics
|
|---|
| Format | Text, Article |
|---|
| Subject | NMR spectroscopy; urinary metabolites; diabetes; statistical classification; chemometry |
|---|
| Abstract | A NMR dataset with non-buffered urine samples consisting of 73 controls and 94 type II diabetes was suojeci to an in-house statistical classifier. A model was developed based on two glucose-free regions of the spectrum and those maximally discriminatory subregions selected most often by the algorithm were noted. The final classifier achieved 83.0% sensitivity and 83.6% specificity, with 83.2% overall accuracy. There were five spectral subregions selected by the algorithm as most relevant for discrimination. The protocol works well with non-buffered samples and has the potential for an automated clinical diagnosis of diabetes. |
|---|
| Publication date | 2011-12 |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 19688663 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 3807bbf3-7f74-4532-8207-3e8cdd0a8fb2 |
|---|
| Record created | 2012-03-22 |
|---|
| Record modified | 2020-04-21 |
|---|
