Urine fluorescence spectroscopy combined with machine learning for screening of hepatocellular carcinoma and liver cirrhosis

Influence of vitamins and food on the fluorescence spectrum of human urine

OBJECTIVES

Fluorescence spectroscopy of human urine is a method with the potential to gain importance as a diagnostic tool in the medical field, e.g., for measuring Coproporphyrin III (CPIII) as an indicator of cancer and acute types of porphyria. Food can change human urine's color, which could influence the urine fluorescence spectrum and the detection of CPIII in urine. To determine if there is a noticeable influence on the urine fluorescence spectrum or on the detection of CPIII in urine, 16 vitamin supplements, and three food items were tested. Such investigation may also prevent false interpretation of measured data.

METHODS

Urine samples were collected before and after (overnight, ca. 8 h) intake of each test substance. Samples were investigated by fluorescence spectrum analysis. At excitation wavelengths from 300 to 500 nm and emission wavelengths from 400 to 700 nm excitation-emission-matrices were measured. Data obtained from urine before intake were compared to the data from overnight urine. Furthermore, the investigation of any interference with the CPIII concentration was performed at an excitation wavelength of 407 ± 3 nm and emission wavelengths of 490-800 nm.

RESULTS

Only vitamin B2, but none of the other tested substances, showed noticeable influence on the urine fluorescence spectrum. None of the tested substances showed noticeable interference with the recovery rate of CPIII.

CONCLUSIONS

The correct interpretation of measured data by fluorescence spectroscopy is possible with the exception if vitamin B2 supplementation was performed; thus, the consumption of vitamin B2 supplements before fluorescence testing of the patient's urine should be avoided and/or must be requested. CPIII concentrations could reliably be measured in all cases.

Development status of novel spectral imaging techniques and application to traditional Chinese medicine

Traditional Chinese medicine (TCM) is a treasure of the Chinese nation, providing effective solutions to current medical requisites. Various spectral techniques are undergoing continuous development and provide new and reliable means for evaluating the efficacy and quality of TCM. Because spectral techniques are noninvasive, convenient, and sensitive, they have been widely applied to in vitro and in vivo TCM evaluation systems. In this paper, previous achievements and current progress in the research on spectral technologies (including fluorescence spectroscopy, photoacoustic imaging, infrared thermal imaging, laser-induced breakdown spectroscopy, hyperspectral imaging, and surface enhanced Raman spectroscopy) are discussed. The advantages and disadvantages of each technology are also presented. Moreover, the future applications of spectral imaging to identify the origins, components, and pesticide residues of TCM in vitro are elucidated. Subsequently, the evaluation of the efficacy of TCM in vivo is presented. Identifying future applications of spectral imaging is anticipated to promote medical research as well as scientific and technological explorations.

Rapid detection of cholecystitis by serum fluorescence spectroscopy combined with machine learning

While cholecystitis is a critical public health problem, the conventional diagnostic methods for its detection are time consuming, expensive and insufficiently sensitive. This study examined the possibility of using serum fluorescence spectroscopy and machine learning for the rapid and accurate identification of patients with cholecystitis. Significant differences were observed between the fluorescence spectral intensities of the serum of cholecystitis patients (n = 74) serum and those of healthy subjects (n = 71) at 455, 480, 485, 515, 625 and 690 nm. The ratios of characteristic fluorescence spectral peak intensities were first calculated, and principal component analysis (PCA)-linear discriminant analysis (LDA) and PCA-support vector machine (SVM) classification models were then constructed using the ratios as variables. Compared with the PCA-LDA model, the PCA-SVM model displayed better diagnostic performance in differentiating cholecystitis patients from healthy subjects, with an overall accuracy of 96.55%. This exploratory study showed that serum fluorescence spectroscopy combined with the PCA-SVM algorithm has significant potential for the development of a rapid cholecystitis screening method.