Combined methods of optical spectroscopy and artificial intelligence in the assessment of experimentally induced non-alcoholic fatty liver.

BACKGROUND AND OBJECTIVE: Due to the existing prevalence of nonalcoholic fatty liver disease (NAFLD) and its relation to the epidemic of obesity in the general population, it is imperative to develop detection and evaluation methods of the early stages of the disease with improved efficacy over the current diagnostic approaches. We aimed to obtain an improved diagnosis, combining methods of optical spectroscopy -diffuse reflectance and fluorescence- with statistical data analysis applied to detect early stages of NAFLD. METHODS: Statistical analysis scheme based on quadratic discriminant analysis followed by canonical discriminant analysis were applied to the diffuse reflectance data combined with endogenous fluorescence spectral data excited at one of these wavelengths: 330, 365, 385, 405 or 415 nm. The statistical scheme was also applied to the combinations of fluorescence spectrum (405 nm) with each one of the other fluorescence spectra. Details of the developed software, including the application of machine learning algorithms to the combination of spectral data followed by classification statistical schemes, are discussed. RESULTS: Steatosis progression was differentiated with little classification error (≤1.3%) by using diffuse reflectance and endogenous fluorescence at different wavelengths. Similar results were obtained using fluorescence at 405 nm and one of the other fluorescence spectra (classification error ≤1.0%). Adding the corresponding areas under the curves to the above combinations of spectra diminished errors to 0.6% and 0.3% or less, respectively. The best results for the compounded reflectance-plus-fluorescence spectra were obtained with fluorescence spectra excited at 415 nm with a total classification error of 0.2%; for the combination of the 405nm-excited fluorescence spectrum with another fluorescence spectrum, the best results were achieved for 385 nm, for which total relative classification error amounted 0.4%. The consideration of the area under the spectral curves further improved both classifiers, reducing the error to 0.0% in both cases. CONCLUSION: Spectrometric techniques combined with statistical processing are a promising tool to improve steatosis classification through a label free approach. However, statistical schemes here applied, might result complex for the everyday medical practice, the designed software including machine learning algorithms is able to render automatic classification of samples according to their steatosis grade with low error.

In vivo assessment of liver fibrosis using diffuse reflectance and fluorescence spectroscopy: a proof of concept.

A novel application of diffuse reflectance and fluorescence spectroscopy in the assessment of liver fibrosis is here reported. To induce different stages of liver fibrosis, a sufficient number of male Wistar rats were differentially exposed to chronic administration with carbon tetrachloride. Then, diffuse reflectance and fluorescence spectra were in vivo measured from the liver surface of each animal by a minimal invasive laparoscopic procedure. The liver fibrosis degree was conventionally determined by means of histological examination using the Mason's Trichrome stain, accompanied by hepatic expression of α-sma, and evaluation of the ALT/AST serum levels. The liver from rats exhibiting higher grades of fibrosis showed a significant increase in diffuse reflectance and fluorescence intensity when compared with control animals. At 365 nm, the diffuse reflectance spectrum exhibited an increase of 4 and 3-fold in mild and advanced fibrotic rats, respectively, when compared to the control group. Similarly, the fluorescence emission at 493 nm was 2-fold higher in fibrotic animals than in controls. By using fluorescence intensity, discrimination algorithms indicated 73% sensitivity and 94% specificity for recognition of hepatic fibrosis, while for diffuse reflectance, these values increased up to 85% and 100%, respectively. Taking into consideration there is a special need for developing new diagnostic approaches focused on detecting different stages of liver fibrosis with minimal invasiveness, these results suggest that diffuse reflectance and fluorescence spectroscopy could be worthy of further exploration in patients with liver disease.

Helicobacter pylori infection in pregnant women from a U.S.-Mexico border population.

Helicobacter pylori infection causes chronic digestive diseases that disproportionately affect Hispanics and other immigrant groups in the United States. Information on the epidemiology of H. pylori infection in pregnant women who reside along the U.S.-Mexico border is critical to understanding the dynamics of current H. pylori transmission patterns within families along the border. We describe the epidemiology of H. pylori infection in pregnant women recruited from Women, Infants, and Children (WIC) clinics in El Paso, Texas, and Mexican Social Security Institute maternal-child clinics in Ciudad Juarez, Mexico, from April 1998 to October 2000. We interviewed participants regarding environmental factors and tested their serum for IgG antibodies. We used logistic regression to estimate associations between environmental exposures and the odds of H. pylori prevalence. Definitive serological tests were available from 751 women. Seroprevalence was 74% in Juarez women and 56% in El Paso women. Prevalence increased with age, crowding, poor sanitation, and residence in Mexico, decreased with education, and was not associated with the woman's number of living children. In the U.S.-Mexico border region, women of reproductive age have a high prevalence of H. pylori infection, apparently related to poor socioeconomic conditions.