Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2011 Mar;3(1):47-52.
doi: 10.1007/s12551-011-0045-8. Epub 2011 Mar 8.

Deriving biomedical diagnostics from NMR spectroscopic data

Ian C P Smith  1 , Ray L Somorjai  2
Affiliations
Review

Deriving biomedical diagnostics from NMR spectroscopic data

Ian C P Smith et al. Biophys Rev. 2011 Mar.

Abstract

Biomedical spectroscopic experiments generate large volumes of data. For accurate, robust diagnostic tools the data must be analyzed for only a few characteristic observations per subject, and a large number of subjects must be studied. We describe here two of the current data analytic approaches applied to this problem: SIMCA (principal component analysis, partial least squares), and the statistical classification strategy (SCS). We demonstrate the application of the SCS by three examples of its use in analyzing 1H NMR spectra: screening for colon cancer, characterization of thyroid cancer, and distinguishing cancer from cholangitis in the biliary tract.

Keywords: 1H NMR spectra; Biomedical spectroscopy; Cancer screening; Soft independent modelling of class analogies (SIMCA); Statistical classification strategy (SCS).

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Representation of the risks of reaching conclusions with a sparse data set. Increasing the number of subjects generally lowers the accuracy, but this is much closer to the true accuracy. The lower accuracy solution will also be more robust: challenging the resultant classifier with new specimens will yield accuracy similar to that found by a reliable classifier
Fig. 2
Fig. 2
Representation of the bootstrapping procedure. The data for the normals and the cancer patients are divided randomly into two groups. A classifier is calculated from one and tested by the other (TR1 and VL1). Two different random sets (TR2 and VL2 ) are then extracted from the entire data set and the process used for the TR1/VL1 split repeated. This procedure is carried out many times (thousands) yielding many classifiers from which the VL-weighted, highest quality combined classifier is determined
Fig. 3
Fig. 3
NMR spectra (360 MHz, 27°C) of fecal water from healthy controls and from patients with advanced colon cancer (Bezabeh et al. 2009)
See this image and copyright information in PMC

References

    1. Albiin N, Smith ICP, Arnelo V, Lindberg B, Berquist A, Dolenko B, Bryksina N, Bezabeh T. A detection of cholangiocarcinoma with magnetic resonance spectroscopy of bile in patients with and without primary sclerosing cholangitis. Acta Radiol. 2008;49:855–862. doi: 10.1080/02841850802220092. - DOI - PubMed
    1. Bezabeh T, Somorjai RL, Dolenko B, Bryskina N, Levin B, Bernstein CN, Jeyrajah E, Steinhart AH, Rubin D, Smith ICP. Detecting colorectal cancer by 1H magnetic resonance spectroscopy of fecal extracts. NMR Biomed. 2009;22:593–600. doi: 10.1002/nbm.1372. - DOI - PubMed
    1. Duda RO, Hart PE, Stork DG. Pattern classification. 2. New York: Wiley-Interscience; 2001.
    1. Eriksson L, Johansson E, Kettaneh-Wold N, Wold S (2001) Multi- and megavariate data analysis—principles and applications. Umetrics, Umea
    1. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction, 2nd edn. Springer, Berlin

LinkOut - more resources