Minireview: Advances in Spectral-Based Machine Deep Learning Algorithms for Thyroid Function Diagnosis

Abstract

The thyroid gland is the largest endocrine organ in the body, and when it behaves abnormally, patient health may suffer. The development of thyroid diagnostic techniques is reviewed considering direct and indirect techniques. Combining spectroscopic approaches with machine deep learning represents a promising diagnostic tool due to its low cost, speed, and good precision. The machine deep learning models for spectral profiling and the evaluation methods are used to test the performance on the bases of precision, sensitivity, specificity, subject operating characteristic (ROC) curve, and F1-score. The analysis of the spectra with machine deep learning models has significant potential for disease diagnosis.

Keywords:

• Infrared spectroscopy
• machine learning
• principal component analysis (PCA)
• Raman spectroscopy
• terahertz spectroscopy
• thyroid function diagnosis

Disclosure statement

All authors declare that there are no potential conflicts of interest related to this study.

Additional information

Funding

This work was supported by the Natural Science Foundation of Xinjiang (2022D01C67), Tianchi Doctoral Program of Xinjiang Uygur Autonomous Region (TCBS202049), the Scientific Research Program of Colleges and Universities of Xinjiang (XJEDU2021Y007), and the Doctoral Initiation Fund of Xinjiang University (BS620320019).