Chemometrics analysis for the detection of dental caries via UV absorption spectroscopy

Artificial neural network and convolutional neural network for prediction of dental caries

Dental caries has high prevalence among kids and adults thus it has become one of the global health concerns. The current modern dentistry focused on the preventives measures to reduce the number of dental caries cases. The employment of machine learning coupled with UV spectroscopy plays a crucial role to detect the early stage of caries. Artificial neural network with hyperparameter tuning was employed to train spectral data for the classification based on the International Caries Detection and Assesment System (ICDAS). Spectra preprocessing namely mean center (MC), autoscale (AS) and Savitzky Golay smoothing (SG) were applied on the data for spectra correction. The best performance of ANN model obtained has accuracy of 0.85 with precision of 1.00. Convolutional neural network (CNN) combined with Savitzky Golay smoothing performed on the spectral data has accuracy, precision, sensitivity and specificity for validation data of 1.00 respectively. The result obtained shows that the application of ANN and CNN capable to produce robust model to be used as an early screening of dental caries.

A UV-Vis spectroscopic detection method for cobalt ions in zinc sulfate solution based on discrete wavelet transform and extreme gradient boosting

Zinc is a crucial strategic metal resource. The concentration of cobalt ions in zinc refining solution significantly impacts the efficiency of zinc electrolysis production. The traditional method of detecting cobalt ions in zinc solution is time-consuming, labor-intensive and ineffective. However, optical detection offers the advantage of high efficiency and low cost, making it a potential replacement for the traditional method. In this study, the spectral curve of cobalt ions in zinc solution is detected by ultraviolet-visible (UV-Vis) spectrophotometry. Additionally, we propose a model for the concentration-absorbance relationship of cobalt ions in zinc solution based on discrete wavelet transform and extreme gradient boosting (DWT-XGBoost) algorithms. First, the spectral curve's information region is denoised by using Savitzky-Golay (S-G) smoothing. Then, the denoised spectra is utilized to extract features through discrete wavelet transform and principal component analysis. These features are used as inputs to the XGBoost model to establish prediction models for low and high cobalt ions in zinc solution. Bayesian optimization is implemented to adjust the model's hyperparameters, including learning rate, feature sampling ratio, to enhance the prediction performance. Finally, applying the model to zinc solution samples from a zinc smelter and compared with other state-of-the-art algorithms, the DWT-XGBoost algorithm exhibits the lowest RMSE, MAE and MAPE, with values of 0.034 mg/L, 0.025 mg/L, 6.983 % for low cobalt and with values of 0.231 mg/L, 0.067 mg/L and 0.472 % for high cobalt. The experimental results demonstrate that the DWT-XGBoost model exhibits significantly superior prediction performance.

Host-Guest Mechanism via Induced Fit Fullerene Complexation in Porphin Receptor to Probe Salivary Alpha-Amylase in Dental Caries for Clinical Applications

Salivary α-amylase is the most abundant protein of human saliva that potentially binds to streptococcus and other bacteria via specific surface-exposed α-amylase-binding proteins and plays a significant role in caries development. The detection of α-amylase in saliva can be used as a bioindicator of caries development. Herein, a facile strategy has been applied, tailoring the photochemical properties of 5,10,15,20-tetrakis(4-hydroxyphenyl)-21H,23H-porphine (TPPOH) and the fullerene C60 complex. The fluorescence emission of TPPOH is quenched by starch-coated fullerene C60 via charge-transfer effects, as determined by UV absorption and fluorescence spectroscopic studies. The starch-coated C60 has been thoroughly characterized via Fourier transform infrared (FTIR) spectroscopy, X-ray diffraction (XRD), field emission scanning electron microscopy (FE-SEM), optical microscopy, thermal gravimetric analysis (TGA), static water contact angle measurements, and zeta potential measurements. The analytical response of the assay showed a linear fluorescent response in α-amylase concentrations ranging from 0.001-0.1 Units/mL, with an LOD of 0.001 Units/mL. The applicability of the method was tested using artificial saliva with quantitative recoveries in the range 95-100%. The practicability of the procedure was verified by inspecting saliva samples of real clinical samples covering all age groups. We believe that the proposed method can serve as an alternative analytical method for caries detection and risk assessment that would also minimize the cost of professional preventive measures and treatments.

Screening and optimization of a water-soluble near-infrared fluorescent probe for drug-induced liver injury monitoring

Peroxynitrite (ONOO-) is a potential biomarker of drug-induced liver injury (DILI) and is involved in the process of DILI. Therefore, developing a reliable detection method for ONOO- will greatly contribute to ensuring drug safety and improving treatment efficiency. Here, based on the previous work, two kinds of NIR fluorescence probes PN and SPN were developed with phenyl-hydrazine as the ONOO- recognition group, which based on two fluorophores RN and SRN that are stable to ONOO-. A sensitive NIR probe SPN with good water solubility, low detection limit and good biocompatibility was selected through in vitro spectral property screening. Further experimental results show that there is a good linear relationship between the response intensity of probe SPN to ONOO- and the concentration of ONOO-, and the detection limit can reach 19.7 nM. At the cellular level, probe SPN can achieve a good and specific response to endogenous and exogenous ONOO-. Also, the probe SPN can be used for imaging and detection of DILI in zebrafish level and small animal level, indicating that probe SPN can be used as a powerful tool for diagnosis of DILI and efficacy evaluation of therapeutic drugs.

A conventional and chemometric analytical approach to solving urea determination with accuracy and precision

Urea is an essential molecule usually detected using spectroscopy, particularly ultraviolet and visible spectroscopy (UV-vis). However, its detection represents a not always fully acknowledged issue. Its concentration dependency has raised questions about the reliability of the UV-vis results. Derivatization reactions, common alternatives to achieve accuracy and precision with UV-vis measurements, still represent an additional step in the measurement process. Besides the problems mentioned earlier, urea forms complex mixtures in aqueous mediums. Therefore, this work proposes to investigate the accuracy and precision of urea determination by UV-vis spectroscopy in the pure form and derivatized with para-dimethylaminobenzaldehyde. The results show that UV-vis spectroscopy could not quantify urea in both forms with precision and accuracy. On the other hand, when applying multivariate curve resolution with alternating least squares (MCR-ALS) to the UV-vis data, the pure urea analytical signal is mathematically separated. Then, those parameters of merit were successfully achieved.

Analysis and comparison of machine learning methods for blood identification using single-cell laser tweezer Raman spectroscopy

Raman spectroscopy, a "fingerprint" spectrum of substances, can be used to characterize various biological and chemical samples. To allow for blood classification using single-cell Raman spectroscopy, several machine learning algorithms were implemented and compared. A single-cell laser optical tweezer Raman spectroscopy system was established to obtain the Raman spectra of red blood cells. The Boruta algorithm extracted the spectral feature frequency shift, reduced the spectral dimension, and determined the essential features that affect classification. Next, seven machine learning classification models are analyzed and compared based on the classification accuracy, precision, and recall indicators. The results show that support vector machines and artificial neural networks are the two most appropriate machine learning algorithms for single-cell Raman spectrum blood classification, and this finding provides essential guidance for future research studies.