Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Dec 7:8:580489.
doi: 10.3389/fchem.2020.580489. eCollection 2020.

Early Diagnosis of Type 2 Diabetes Based on Near-Infrared Spectroscopy Combined With Machine Learning and Aquaphotomics

Yuanpeng Li  1   2 , Liu Guo  3 , Li Li  4 , Chuanmei Yang  1 , Peiwen Guang  5 , Furong Huang  5 , Zhenqiang Chen  5 , Lihu Wang  1 , Junhui Hu  1
Affiliations

Early Diagnosis of Type 2 Diabetes Based on Near-Infrared Spectroscopy Combined With Machine Learning and Aquaphotomics

Yuanpeng Li et al. Front Chem. .

Abstract

Early diagnosis is important to reduce the incidence and mortality rate of diabetes. The feasibility of early diagnosis of diabetes was studied via near-infrared spectra (NIRS) combined with a support vector machine (SVM) and aquaphotomics. Firstly, the NIRS of entire blood samples from the population of healthy, pre-diabetic, and diabetic patients were obtained. The spectral data of the entire spectra in the visible and near-infrared region (400-2,500 nm) were used as the research object of the qualitative analysis. Secondly, several preprocessing steps including multiple scattering correction, variable standardization, and first derivative and second derivative steps were performed and the best pretreatment method was selected. Finally, for the early diagnosis of diabetes, models were established using SVM. The first overtone of water (1,300-1,600 nm) was used as the research object for an aquaphotomics model, and the aquagram of the healthy group, pre-diabetes, and diabetes groups were drawn using 12 water absorption patterns for the early diagnosis of diabetes. The results of SVM showed that the highest accuracy was 97.22% and the specificity and sensitivity were 95.65 and 100%, respectively when the pretreatment method of the first derivative was used, and the best model parameters were c = 18.76 and g = 0.008583.The results of the aquaphotomics model showed clear differences in the 1,400-1,500 nm region, and the number of hydrogen bonds in water species (1,408, 1,416, 1,462, and 1,522 nm) was evidently correlated with the occurrence and development of diabetes. The number of hydrogen bonds was the smallest in the healthy group and the largest in the diabetes group. The suggested reason is that the water matrix of blood changes with the worsening of blood glucose metabolic dysfunction. The number of hydrogen bonds could be used as biomarkers for the early diagnosis of diabetes. The result show that it is effective and feasible to establish an accurate and rapid early diagnosis model of diabetes via NIRS combined with SVM and aquaphotomics.

Keywords: aquaphotomics; early diagnosis; near-infrared spectroscopy(NIR); support vector machine (SVM); type 2 diabetes.

PubMed Disclaimer

Conflict of interest statement

LG was employed by the company Guangdong Hongke Agricultural Machinery Research & Development Co., Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
NIR spectra of the blood samples: (A) raw and (B) average spectra.
Figure 2
Figure 2
Optimization result map for healthy, pre-diabetic, and type 2 diabetic samples: (A,B) optimization result map for GS; (C) optimization result map for GA; and (D) optimization result map for PSO.
Figure 3
Figure 3
Graphs for the estimated class values (y axis) vs. the number of samples (x axis). (A) Training set. (B) Prediction set.
Figure 4
Figure 4
Average spectra of the blood samples in the 1,300–1,600 nm region: (A) raw spectra; (B) difference spectra of pre-diabetes and type 2 diabetes.
Figure 5
Figure 5
PCA results of NIR spectra (1,300–1,600 nm) collected from all samples. (A) PCA 3D score plot. (B) PCA loading plot.
Figure 6
Figure 6
Second derivative spectra and aquagram: (A) average and difference spectra in the 1,300–1,600 nm region; (B) aquagram of healthy, pre-diabetes, and type 2 diabetes samples in 12 fingerprint regions of water.
Figure 7
Figure 7
Hydrogen bond interaction: (A) schematic diagram of hydrogen bonding between water molecules; (B) replacement effect of glucose on water in blood glucose.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Abdi H., Williams L. J. (2010). Principal component analysis. Wiley Interdiscip. Rev. Comput. Stat. 2, 433–459. 10.1002/wics.101 - DOI
    1. Afara I. O., Sarin J. K., Ojanen S., Finnilä M. A., Herzog W., Saarakkala S., et al. . (2020). Machine learning classification of articular cartilage integrity using near infrared spectroscopy. Cell. Mol. Bioeng. 13, 219–228. 10.1007/s12195-020-00612-5 - DOI - PMC - PubMed
    1. Aljarah I., Ala M. A. Z., Faris H., Hassonah M. A., Mirjalili S., et al. (2018). Simultaneous feature selection and support vector machine optimization using the grasshopper optimization algorithm. Cogn. Comput. 10, 478–495. 10.1007/s12559-017-9542-9 - DOI
    1. American Diabetes Association (2012). Diagnosis and classification of diabetes mellitus. Diabetes Care 33, S64–S71. 10.2337/dc12-s064 - DOI - PMC - PubMed
    1. Arai K., Shikata T. (2019). Molecular motions, structure and hydration behaviour of glucose oligomers in aqueous solution. Phys. Chem. Chem. Phys. 21:25379. 10.1039/C9CP05214C - DOI - PubMed