Optical screening of hepatitis-B infected blood sera using optical technique and neural network classifier

Utilizing machine learning algorithms for precise discrimination of glycosuria in fluorescence spectroscopic data

Fluorescence spectroscopy coupled with a random forest machine learning algorithm offers a promising non-invasive approach for diagnosing glycosuria, a condition characterized by excess sugar in the urine of diabetic patients. This study investigated the ability of this method to differentiate between diabetic and healthy control urine samples. Fluorescent spectra were captured from urine samples using a Xenon arc lamp emitting light within the 200 to 950 nm wavelength range, with consistent fluorescence emission observed at 450 nm under an excitation wavelength of 370 nm. Healthy control samples were also analyzed within the same spectral range for comparison. To distinguish spectral differences between healthy and infected samples, the random forest (RF) and K-Nearest Neighbors (KNN) machine learning algorithms have been employed. These algorithms automatically recognize spectral patterns associated with diabetes, enabling the prediction of unknown classifications based on established samples. Principal component analysis (PCA) was utilized for dimensionality reduction before feeding the data to RF and KNN for classification. The model's classification performance was evaluated using 10-fold cross-validation, resulting in the proposed RF-based model achieving accuracy of 96 %, specificity of 100 %, sensitivity of 93 %, and precision of 100 %. These results suggest that the proposed method holds promise for a more convenient and potentially more accurate method for diagnosing glycosuria in diabetic patients.

Raman spectroscopy combined with machine learning and chemometrics analyses as a tool for identification atherosclerotic carotid stenosis from serum

Atherosclerosis carotid stenosis (ACS) is one of the main causes of stroke. Unfortunately, the highest number of people go to the doctor with an advanced disease or as a result of a stroke, because carotid atherosclerosis does not cause obvious symptoms. Therefore, it is important to find a diagnostic method to detect the disease during routine tests (using blood or serum). Consequently, in this article, Raman spectroscopy was tested as a potential diagnostic method. Indeed, Raman spectra of serum collected from ACS and control patients showed decrease of Raman peak around 1520 cm-1 and increase of peak around 3050 cm-1 in people with ACS. Moreover in people with ACS shift of peaks originating from amides II, I and lipids vibrations were noticed in comparison with control group. Interestingly, decision tree algorithm showed that peaks at 1656 cm-1 and 2957 cm-1 could be a spectroscopy markers of atherosclerotic carotid stenosis. Continuing, Principal Component Analysis (PCA) clearly showed distinguishing between serum collected from ACS and control patients, while machine learning algorithms showed high value of accuracy, sensitivity and selectivity (more than 90 %). Finally, value of area under the curve of Receiver Operating Characteristic (AUC-ROC) showed value of 0.81 for Raman range between 800 cm-1 and 1800 cm-1 and 0.86 for 2800 cm-1-3000 cm-1 range. Obtained results clearly showed possibility of Raman spectroscopy in detection of ACS from serum.

Rapid diagnosis of diabetes based on ResNet and Raman spectroscopy

Diabetes mellitus is a global public health problem, and the epidemic situation in China is particularly serious. The prevalence of the disease has been increasing in recent years, and the number of patients is the highest in the world. Diabetes has become another chronic non-communicable disease that seriously endangers the health of our people after cardiovascular and cerebrovascular diseases and tumors. In this study, urine sample data were collected from 37 diabetic patients and 37 healthy volunteers using Raman spectroscopy. The collected data were preprocessed using an adaptive iterative reweighted penalized least squares (airPLS) algorithm and a polynomial Savitzky-Golay smoothing algorithm. After extracting features using principal component analysis (PCA) dimensionality reduction algorithm, ResNet, support vector machine (SVM) and linear discriminant analysis (LDA) classification models were selected to classify and identify diabetic patients and healthy controls. The results show that ResNet has the best discrimination effect, and the average accuracy, recall and F1-score can reach 84.28%, 86.20% and 84.02% respectively after five cross-validations, and the area under the subject working characteristic (ROC) curve is 0.93. The experimental results show that the model established in this paper is simple to operate, highly accurate and has good reference value for rapid screening of diabetes.

Pattern Recognition for Human Diseases Classification in Spectral Analysis

Pattern recognition is a multidisciplinary area that received more scientific attraction during this period of rapid technological innovation. Today, many real issues and scenarios require pattern recognition to aid in the faster resolution of complicated problems, particularly those that cannot be solved using traditional human heuristics. One common problem in pattern recognition is dealing with multidimensional data, which is prominent in studies involving spectral data such as ultraviolet-visible (UV/Vis), infrared (IR), and Raman spectroscopy data. UV/Vis, IR, and Raman spectroscopy are well-known spectroscopic methods that are used to determine the atomic or molecular structure of a sample in various fields. Typically, pattern recognition consists of two components: exploratory data analysis and classification method. Exploratory data analysis is an approach that involves detecting anomalies in data, extracting essential variables, and revealing the data’s underlying structure. On the other hand, classification methods are techniques or algorithms used to group samples into a predetermined category. This article discusses the fundamental assumptions, benefits, and limitations of some well-known pattern recognition algorithms including Principal Component Analysis (PCA), Kernel PCA, Successive Projection Algorithm (SPA), Genetic Algorithm (GA), Partial Least Square Regression (PLS-R), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Partial Least Square-Discriminant Analysis (PLS-DA) and Artificial Neural Network (ANN). The use of UV/Vis, IR, and Raman spectroscopy for disease classification is also highlighted. To conclude, many pattern recognition algorithms have the potential to overcome each of their distinct limits, and there is also the option of combining all of these algorithms to create an ensemble of methods.

Role of plasmonics in detection of deadliest viruses: a review

Viruses have threatened animal and human lives since a long time ago all over the world. Some of these tiny particles have caused disastrous pandemics that killed a large number of people with subsequent economic downturns. In addition, the quarantine situation itself encounters the challenges like the deficiency in the online educational system, psychiatric problems and poor international relations. Although viruses have a rather simple protein structure, they have structural heterogeneity with a high tendency to mutation that impedes their study. On top of the breadth of such worldwide worrying issues, there are profound scientific gaps, and several unanswered questions, like lack of vaccines or antivirals to combat these pathogens. Various detection techniques like the nucleic acid test, immunoassay, and microscopy have been developed; however, there is a tradeoff between their advantages and disadvantages like safety in sample collecting, invasiveness, sensitivity, response time, etc. One of the highly resolved techniques that can provide early-stage detection with fast experiment duration is plasmonics. This optical technique has the capability to detect viral proteins and genomes at the early stage via highly sensitive interaction between the biological target and the plasmonic chip. The efficiency of this technique could be proved using commercialized techniques like reverse transcription polymerase chain reaction (RT-PCR) and enzyme-linked immunosorbent assay (ELISA) techniques. In this study, we aim to review the role of plasmonic technique in the detection of 11 deadliest viruses besides 2 common genital viruses for the human being. This is a rapidly moving topic of research, and a review article that encompasses the current findings may be useful for guiding strategies to deal with the pandemics. By investigating the potential aspects of this technique, we hope that this study could open new avenues toward the application of point-of-care techniques for virus detection at early stage that may inhibit the progressively hygienic threats.

Applicability of Raman spectroscopy on porcine parvovirus and porcine circovirus type 2 detection

Porcine parvovirus (PPV) is one of the major infectious causes of reproductive failure of swine. This disease is characterized by embryonic and fetal infection and death, responsible for important economic losses. PPV is also implicated as a trigger in the development of post-weaning multisystemic wasting syndrome (PMWS) caused by Porcine circovirus type 2 (PCV2). Their detection is PCR-based, which is quite sensitive and specific, but laborious, costly and time-demanding. Therefore, this study aimed to assess Raman spectroscopy (RS) as a diagnostic tool for PPV and PCV2 due to its label-free properties and unique ability to search and identify molecular fingerprints. Briefly, swine testis (ST) cells were inoculated with PPV or PCV2 and in vitro cultured (37 °C, 5% CO₂) for four days. Fixed cells were then submitted to RS investigation using a 633 nm laser. A total of 225 spectra centered at 1300 cm^-1 was obtained for each sample (5 spectra/cell; 15 cells/replicate; 3 replicates) of PPV-, PCV2-infected and uninfected (control) ST cells. Clear statistical discrimination between samples from both virus-infected cells was achieved with a Principal Component - Linear Discriminant Analysis (PCA-LDA) model, reaching sensitivity rates from 95.55% to 97.77%, respectively to PCV2- and PPV-infected cells. These results were then submitted to a Leave-One-Out (LOO) validation algorithm resulting in 99.97% of accuracy. Extensive band assignment was analyzed and compiled for better understanding of PPV and PCV2 virus-cell interaction, demonstrating that specific protein, lipids and DNA/RNA bands are the most important assignments related to discrimination of virus-infected from uninfected cells. In conclusion, these results represent promising bases for RS application on PCV2 and PPV detection for future diagnostic applications.

Machine assisted classification of chicken, beef and mutton tissues using optical polarimetry and Bagging model

Optical polarimetry has been used to characterize muscle tissue samples of chicken, beef and mutton, exhibiting statistically significant (p <  0.01) differences in total depolarization and retardance of three tissue groups. Herein, the total depolarization and retardance were utilized to differentiate and classify the three tissue groups. Specifically, the Bagging classification algorithm was employed for this multi-class differentiation. The performance of the optical polarimetry in tandem with the Bagging model for machine-assisted classification of the three tissue groups was assessed in terms of a comprehensive set of evaluation metrics. The Bagging model correctly classified 47/48, 19/20 and 15/18, whereas the sensitivity (Sn = 97.9 %, 82.6 %, 100 %), specificity (Sp = 97.4 %, 98.4 %, 95.8 %), positive predictive values (PPV = 0.97, 0.95, 0.83) and negative predictive values (NPV = 0.97, 0.94, 1.0) were calculated for the chicken, beef and mutton tissue samples, respectively. This automatic classification of the three tissue samples indicates a novel application of the optical polarimetry in the meat industry.