Serum Raman spectroscopy combined with multiple algorithms for diagnosing thyroid dysfunction and chronic renal failure

In this study, 60 samples taken from patients with thyroid dysfunction, 40 samples taken from patients with chronic renal failure (CRF) and 60 samples taken from healthy people were classified. We used partial least squares (PLS) to extract features to reduce the dimension of the spectral data to discriminate among the different samples. The Decision Trees (DT), Extreme Learning Machine (ELM), Probabilistic Neural Network (PNN), Back Propagation Neural Network (BPNN) and Learning Vector Quantization (LVQ) algorithms were used to build classification models and compare the results. The PLS-PNN algorithm distinguished between patients with thyroid dysfunction and patients with chronic renal failure with up to a 96.67 % accuracy rate, the PLS-BP algorithm distinguished between patients with chronic renal failure and healthy people with up to a 98.33 % accuracy rate, and the PLS-PNN algorithm and the PLS-DT algorithm distinguished between healthy people and patients with chronic renal failure with up to a 100 % accuracy rate. The results showed that serum Raman spectroscopy can be used in conjunction with classification algorithms to rapidly and accurately diagnose and distinguish between thyroid dysfunction and chronic renal failure.

Automated summary

This study collected samples from patients with thyroid dysfunction, chronic renal failure, and healthy individuals. By using PLS and various classification algorithms, it was found that serum Raman spectroscopy combined with classification algorithms can rapidly and accurately diagnose and distinguish between thyroid dysfunction and chronic renal failure.