Deriving biomedical diagnostics from NMR spectroscopic data.

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.

MR metabolomics of fecal extracts: applications in the study of bowel diseases.

NMR-based metabolomics is becoming a useful tool in the study of body fluids and has a strong potential to contribute to disease diagnosis. While applications on urine and serum have been the focus to date, there are a number of other body fluids that are readily available and could potentially be used for metabolomics-based disease diagnosis. One such body fluid is stool or fecal extract. Given its contact with and transient stay in the colon and rectum, stool carries a lot of useful information regarding the health/disease status of both the colon and the rectum. This could be particularly useful for the non-invasive diagnosis of colorectal cancer and inflammatory bowel disease--the two bowel diseases that are very common and pose significant public health problems. Different methodological considerations including the collection of sample, the storage of sample, the preparation of sample, NMR acquisition parameters, experimental conditions and data analysis methods are discussed. Results obtained in the detection of colorectal cancer and in the differentiation of the two major forms of inflammatory bowel disease (i.e. ulcerative colitis and Crohn's disease) are presented. This is concluded with a brief discussion on the future of MR metabolomics of fecal extracts.

Rapid etiological classification of meningitis by NMR spectroscopy based on metabolite profiles and host response.

Bacterial meningitis is an acute disease with high mortality that is reduced by early treatment. Identification of the causative microorganism by culture is sensitive but slow. Large volumes of cerebrospinal fluid (CSF) are required to maximise sensitivity and establish a provisional diagnosis. We have utilised nuclear magnetic resonance (NMR) spectroscopy to rapidly characterise the biochemical profile of CSF from normal rats and animals with pneumococcal or cryptococcal meningitis. Use of a miniaturised capillary NMR system overcame limitations caused by small CSF volumes and low metabolite concentrations. The analysis of the complex NMR spectroscopic data by a supervised statistical classification strategy included major, minor and unidentified metabolites. Reproducible spectral profiles were generated within less than three minutes, and revealed differences in the relative amounts of glucose, lactate, citrate, amino acid residues, acetate and polyols in the three groups. Contributions from microbial metabolism and inflammatory cells were evident. The computerised statistical classification strategy is based on both major metabolites and minor, partially unidentified metabolites. This data analysis proved highly specific for diagnosis (100% specificity in the final validation set), provided those with visible blood contamination were excluded from analysis; 6-8% of samples were classified as indeterminate. This proof of principle study suggests that a rapid etiologic diagnosis of meningitis is possible without prior culture. The method can be fully automated and avoids delays due to processing and selective identification of specific pathogens that are inherent in DNA-based techniques.

Metabolomic biomarkers in a model of asthma exacerbation: urine nuclear magnetic resonance.

RATIONALE: Airway obstruction in patients with asthma is associated with airway dysfunction and inflammation. Objective measurements including sputum analysis can guide therapy, but this is often not possible in typical clinical settings. Metabolomics is the study of molecules generated by metabolic pathways. We hypothesize that airway dysfunction and inflammation in an animal model of asthma would produce unique patterns of urine metabolites measured by multivariate statistical analysis of high-resolution proton nuclear magnetic resonance ((1)H NMR) spectroscopy data. OBJECTIVES: To develop a noninvasive means of monitoring asthma status by metabolomics and urine sampling. METHODS: Five groups of guinea pigs were studied: control, control treated with dexamethasone, sensitized (ovalbumin, administered intraperitoneally), sensitized and challenged (ovalbumin, administered intraperitoneally, plus ovalbumin aerosol), and sensitized-challenged with dexamethasone. Airway hyperreactivity (AHR) to histamine (administered intravenously) and inflammation were measured. Multivariate statistical analysis of NMR spectra based on a library of known urine metabolites was performed by partial least-squares discriminant analysis. In addition, the raw NMR spectra exported as xy-trace data underwent linear discriminant analysis. MEASUREMENTS AND MAIN RESULTS: Challenged guinea pigs developed AHR and increased inflammation compared with sensitized or control animals. Dexamethasone significantly improved AHR. Using concentration differences in metabolites, partial least-squares discriminant analysis could discriminate challenged animals with 90% accuracy. Using only three or four regions of the NMR spectra, linear discriminant analysis-based classification demonstrated 80-90% separation of the animal groups. CONCLUSIONS: Urine metabolites correlate with airway dysfunction in an asthma model. Urine NMR analysis is a promising, noninvasive technique for monitoring asthma in humans.

Pattern recognition approaches for classifying proteomic mass spectra of biofluids.

The statistical classification strategy we have developed for magnetic resonance, infrared, and Raman spectra for the analysis of biomedical data is discussed, particularly as it applies to proteomic mass spectra. A general discussion of the current use of pattern recognition methods is given, with caveats and suggestions relevant for clinical applicability.

A pattern recognition application framework for biomedical datasets.

Scopira facilitates the development of high-performance applications by providing many useful subsystems, flexible and efficient data models, low-level tools such as memory management and serialization, GUI constructs, high-level visualization modules, and the ability to implement parallel algorithms with MPI. Scopira plug-in extensions have been developed to enable Matlab scripts to easily call any Scopira module, thus facilitating the migration of prototypes to highly efficient C++ applications. Scopira is continuously under development and future capabilities will include the ability to develop distributed programs using agents, applicable to grid-computing data mining applications. Scopira has proven to be a successful programming framework for implementing high-performance biomedical data analysis applications. It is based on C++, an efficient object-oriented language, and the source code is available as an open-source project for other researchers to use and adapt to their own research endeavours. Scopira has been compiled to work on Linux and Windows XP operating systems with a port to the Mac OS under development. Scopira, EvIdent and RDP are freely available for download from www.scopira.org.

Magnetic resonance spectroscopy detects biochemical changes in the brain associated with chronic low back pain: a preliminary report.

Magnetic resonance (MR) spectroscopy is a noninvasive technique that can be used to detect and measure the concentration of metabolites and neurotransmitters in the brain and other organs. We used in vivo (1)H MR spectroscopy in subjects with low back pain compared with control subjects to detect alterations in biochemistry in three brain regions associated with pain processing. A pattern recognition approach was used to determine whether it was possible to discriminate accurately subjects with low back pain from control subjects based on MR spectroscopy. MR spectra were obtained from the prefrontal cortex, anterior cingulate cortex, and thalamus of 32 subjects with low back pain and 33 control subjects without pain. Spectra were analyzed and compared between groups using a pattern recognition method (Statistical Classification Strategy). Using this approach, it was possible to discriminate between subjects with low back pain and control subjects with accuracies of 100%, 99%, and 97% using spectra obtained from the anterior cingulate cortex, thalamus, and prefrontal cortex, respectively. These results demonstrate that MR spectroscopy, in combination with an appropriate pattern recognition approach, is able to detect brain biochemical changes associated with chronic pain with a high degree of accuracy.

A rapid screening test to distinguish between Candida albicans and Candida dubliniensis using NMR spectroscopy.

Nuclear magnetic resonance (NMR) spectroscopy combined with a statistical classification strategy (SCS) successfully distinguished between Candida albicans and Candida dubliniensis. 96% of the isolates from an independent test set were identified correctly. This proves that this rapid approach is a valuable method for the identification and chemotaxonomic characterisation of closely related taxa. Most discriminatory regions were correlated with metabolite profiles, indicating biochemical differences between the two species.

Determination of grade and receptor status from the primary breast lesion by magnetic resonance spectroscopy.

Magnetic resonance spectra (MRS) from fine needle aspiration biopsies (FNAB) from primary breast lesions were analysed using a pattern recognition method, Statistical Classification Strategy, to assess tumor grade and oestrogen receptor (ER) and progesterone receptor (PgR) status. Grade 1 and 2 breast cancers were separated from grade 3 cancers with a sensitivity and specificity of 96% and 95%, respectively. The ER status was predicted with a sensitivity of 91% and a specificity of 90%, and the PgR status with a sensitivity of 91% and a specificity of 86%. These classifiers provide rapid and reliable, computerized information and may offer an objective method for determining these prognostic indicators simultaneously with the diagnosis of primary pathology and lymph node involvement.

Rapid identification of Candida species by using nuclear magnetic resonance spectroscopy and a statistical classification strategy.

Nuclear magnetic resonance (NMR) spectra were acquired from suspensions of clinically important yeast species of the genus Candida to characterize the relationship between metabolite profiles and species identification. Major metabolites were identified by using two-dimensional correlation NMR spectroscopy. One-dimensional proton NMR spectra were analyzed by using a staged statistical classification strategy. Analysis of NMR spectra from 442 isolates of Candida albicans, C. glabrata, C. krusei, C. parapsilosis, and C. tropicalis resulted in rapid, accurate identification when compared with conventional and DNA-based identification. Spectral regions used for the classification of the five yeast species revealed species-specific differences in relative amounts of lipids, trehalose, polyols, and other metabolites. Isolates of C. parapsilosis and C. glabrata with unusual PCR fingerprinting patterns also generated atypical NMR spectra, suggesting the possibility of intraspecies discontinuity. We conclude that NMR spectroscopy combined with a statistical classification strategy is a rapid, nondestructive, and potentially valuable method for identification and chemotaxonomic characterization that may be broadly applicable to fungi and other microorganisms.

Pathology of Barrett's esophagus by proton magnetic resonance spectroscopy and a statistical classification strategy.

BACKGROUND: Barrett's esophagus is thought to be a precursor of adenocarcinoma. The incidence of adenocarcinoma of the lower esophagus in the Western world is rising and accounts for more than 40% of esophageal carcinomas in males. It is not possible to identify which Barrett's patients are at high risk of developing malignancy. Here we applied a statistical classification strategy to the analysis of magnetic resonance spectroscopy and histopathological data from esophageal biopsies to ascertain whether this risk could be identified in Barrett's patients. METHODS: Tissue specimens from 72 patients (29 noncancer-bearing and 43 cancer-bearing) were analyzed by one-dimensional proton magnetic resonance spectroscopy at 8.5 Tesla. Diagnostic correlation was performed between the magnetic resonance spectra and histopathology. The magnetic resonance magnitude spectra were preprocessed, followed by identification of optimal spectral regions, and were then classified by cross-validated linear discriminant analysis of rank orders of the first derivative of magnetic resonance spectra. RESULTS: Magnetic resonance spectroscopy combined with a statistical classification strategy analysis distinguished normal esophagus from adenocarcinoma and Barrett's epithelium with an accuracy of 100%. Barrett's epithelium and adenocarcinoma were distinguished with an accuracy of 98.6% but only when 4 of the Barrett's specimens and 7 of the carcinoma specimens, determined to be "fuzzy" (ie, unable to be accurately assigned to either class) were withdrawn. The 7 cancer and 4 Barrett's specimens, determined to be "fuzzy" using the Barrett's versus cancer (B versus C) classifier, were submitted to the other two classifiers (Barrett's versus normal [B versus N] and normal versus cancer [N versus C], respectively). The 4 Barrett's specimens were assigned to Barrett's by the N versus B classifier and to normal (n = 2) or cancer (n = 2) classes by the N versus C classifier. The 7 cancer specimens were crisply assigned to the cancer class (N versus C), or for the B versus N classifier, to the Barrett's class (ie, more similar to Barrett's than to normal tissue). Visual inspection of the spectra from histologically identified Barrett's epithelium showed a gradation from normal to carcinoma. CONCLUSIONS: Proton magnetic resonance spectroscopy of esophageal biopsies combined with a statistical classification strategy data analysis provides a robust diagnosis with a high degree of accuracy for discriminating normal epithelium from esophageal adenocarcinoma and Barrett's esophagus. Different spectral categories of Barrett's epithelium were identified both by visual inspection and by statistical classification strategy, possibly reflecting the risk of future malignant transformation.

Pathology of hepatocellular carcinoma and its precursors using proton magnetic resonance spectroscopy and a statistical classification strategy.

AIM: Apply the statistical classification strategy (SCS) to magnetic resonance spectroscopy (MRS) data from liver biopsies and test its potential to discriminate between normal liver, cirrhotic nodules and nodules of hepatocellular carcinoma with a high degree of accuracy. METHODS: Liver tissue specimens from 54 patients undergoing either partial (hemi) or total hepatectomy were analysed by one-dimensional proton MRS at 8.5 Tesla. Histologically, these specimens were confirmed as normal (n=31), cirrhotic (n=59), and hepatocellular carcinoma (HCC, n=32). Diagnostic correlation was performed between the MR spectra and histopathology. An SCS was applied consisting of pre-processing MR magnitude spectra to identify spectral regions of maximal discriminatory value, and cross-validated linear discriminant analysis. RESULTS: SCS applied to MRS data distinguished normal liver tissue from HCC with an accuracy of 100%. Normal liver tissue was distinguished from cirrhotic liver with an accuracy of 92% and cirrhotic liver was distinguished from HCC with an accuracy of 98%. CONCLUSIONS: SCS applied to proton MRS of liver biopsies provides a robust method to distinguish, with a high degree of accuracy, HCC from both cirrhotic and normal liver.

An ex vivo study exploring the diagnostic potential of 1H magnetic resonance spectroscopy in squamous cell carcinoma of the head and neck region.

BACKGROUND: Definitive diagnosis of head and neck cancer is generally made by histopathologic evaluation. Management and prognosis largely depend on accurate and timely diagnosis. We have explored the use of (1)H magnetic resonance spectroscopy in search of a better or complementary diagnostic technique. METHODS: Tumor and adjacent normal tissue specimens (n = 135) from untreated head and neck cancer patients (n = 40) were obtained and subjected to spectroscopic evaluation followed by histopathologic analysis. Data were partitioned into training and test sets and subjected to multivariate analysis. RESULTS: The resonances from taurine, choline, glutamic acid, lactic acid, and lipid were found to have diagnostic potential by our optimal region selection algorithm. Multivariate analysis of the spectral data differentiated between normal and malignant tissues, with an overall accuracy of 92.6% (training set, 97.3%; test set, 87.3%), an overall sensitivity of 93% (test set, 90%), and an overall specificity of 92% (test set, 82.6%). CONCLUSIONS: (1)H magnetic resonance spectroscopy combined with multivariate methods of analysis can distinguish between normal and malignant squamous cell tissue, and this may lead to the development of an objective and noninvasive diagnostic procedure.

Statistical classification strategy for proton magnetic resonance spectra of soft tissue sarcoma: an exploratory study with potential clinical utility.

PURPOSE: Histological grading is currently one of the best predictors of tumor behavior and outcome in soft tissue sarcoma. However, occasionally there is significant disagreement even among expert pathologists. An alternative method that gives more reliable and non-subjective diagnostic information is needed. The potential use of proton magnetic resonance spectroscopy in combination with an appropriate statistical classification strategy was tested here in differentiating normal mesenchymal tissue from soft tissue sarcoma. METHODS: Fifty-four normal and soft tissue sarcoma specimens of various histological types were obtained from 15 patients. One-dimensional proton magnetic resonance spectra were acquired at 360 MHz. Spectral data were analyzed by using both the conventional peak area ratios and a specific statistical classification strategy. RESULTS: The statistical classification strategy gave much better results than the conventional analysis. The overall classification accuracy (based on the histopathology of the MRS specimens) in differentiating normal mesenchymal from soft tissue sarcoma was 93%, with a sensitivity of 100% and specificity of 88%.The results in the test set were 83, 92 and 76%, respectively. Our optimal region selection algorithm identified six spectral regions with discriminating potential, including those assigned to choline, creatine, glutamine, glutamic acid and lipid. CONCLUSION: Proton magnetic resonance spectroscopy combined with a statistical classification strategy gave good results in differentiating normal mesenchymal tissue from soft tissue sarcoma specimens ex vivo. Such an approach may also differentiate benign tumors from malignant ones and this will be explored in future studies.