Near-infrared spectroscopic measurements of blood analytes using multi-layer perceptron neural networks

Abstract

Near-infrared (NIR) spectroscopy is being applied to the solution of problems in many areas of biomedical and pharmaceutical research. In this paper we investigate the use of NIR spectroscopy as an analytical tool to quantify concentrations of urea, creatinine, glucose and oxyhemoglobin (HbO2). Measurements have been made in vitro with a portable spectrometer developed in our labs that consists of a two beam interferometer operating in the range of 800-2300 nm. For the data analysis a pattern recognition philosophy was used with a preprocessing stage and a multi-layer perceptron (MLP) neural network for the measurement stage. Results show that the interferogram signatures of the above compounds are sufficiently strong in that spectral range. Measurements of three different concentrations were possible with mean squared error (MSE) of the order of 10(-6).

Competitive/collaborative neural computing system for medical diagnosis in pancreatic cancer detection

“…Although the use of neural computing techniques in the medical imaging field is now very widespread (Kalamatianos et al ., 2006; Chen et al ., 2007; García‐Orellana et al ., 2007; dos Santos et al ., 2007; Song et al ., 2007; Maglogiannis et al ., 2008; Übeyli, 2008), each diagnosis system contains one NN only. Unfortunately, the use of just one NN per system does not fully emphasize the NN computational power, which requires more NNs working together to provide a better solution than a stand‐alone one.…”