Recognition of chronic renal failure based on Raman spectroscopy and convolutional neural network

Analysis of the application effect of the Clark comfortable nursing approach in hemodialysis patients with end stage renal failure

OBJECTIVE

This study observed the effects of the Clark comfortable nursing approach on self-care ability, self-burden, treatment adherence, quality of life, and complications in hemodialysis patients with end stage renal failure (ESRF).

METHODS

Eighty-two patients with ESRF receiving hemodialysis treatment were included and allocated into control and intervention groups. The control group received conventional nursing care, while the intervention group received the Clark comfortable nursing approach. The self-care ability, self-burden, treatment adherence, quality of life scores before and after the nursing intervention, and the occurrence of complications in both groups were compared.

RESULTS

After the intervention, the intervention group showed higher scores in each dimension and the total score of the Exercise of Self-Care Agency Scale compared to the control group. Both groups exhibited improvements in various scores and total scores; however, the intervention group had lower scores overall than the control group. Additionally, the intervention group had higher scores in diet, water intake, medication, and dialysis regimen. Additionally, both groups had significantly higher scores in all dimensions of the quality-of-life scale post-intervention, with the intervention group demonstrating markedly higher scores in all dimensions. The total incidence of complications in the intervention group was 9.76%, which was lower than the 29.27% observed in the control group.

CONCLUSION

The Clark comfortable nursing approach applied to hemodialysis patients with ESRF can enhance self-care ability, improve quality of life, increase treatment adherence, and reduce the incidence of hemodialysis-related complications. This model is worthy of clinical promotion.

Comparative study of Raman spectroscopy techniques in blood plasma-based clinical diagnostics: A demonstration on Alzheimer's disease

Nowadays, there are still many diseases with limited or no reliable methods of early diagnosis. A popular approach in clinical diagnostic research is Raman spectroscopy, as a relatively simple, cost-effective, and high-throughput method for searching for disease-specific alterations in the composition of blood plasma. However, the high variability of the experimental designs, targeted diseases, or statistical processing in the individual studies makes it challenging to compare and compile the results to critically assess the applicability of Raman spectroscopy in real clinical practice. This study aimed to compare data from a single series of blood plasma samples of patients with Alzheimer's disease and non-demented elderly controls obtained by four different techniques/experimental setups - Raman spectroscopy with excitation at 532 and 785 nm, Raman optical activity, and surface-enhanced Raman scattering spectroscopy. The obtained results showed that the spectra from each Raman spectroscopy technique contain different information about biomolecules of blood plasma or their conformation and may, therefore, offer diverse points of view on underlying biochemical processes of the disease. The classification models based on the datasets generated by the three non-chiroptical variants of Raman spectroscopy exhibited comparable diagnostic performance, all reaching an accuracy close to or equal to 80%. Raman optical activity achieved only 60% classification accuracy, suggesting its limited applicability in the specific case of Alzheimer's disease diagnostics. The described differences in the outputs of the four utilized techniques/setups of Raman spectroscopy imply that their choice may crucially affect the acquired results and thus should be approached carefully concerning the specific purpose.

Application of serum Raman spectroscopy combined with classification model for rapid breast cancer screening

Introduction

This study aimed to evaluate the feasibility of using general Raman spectroscopy as a method to screen for breast cancer. The objective was to develop a machine learning model that utilizes Raman spectroscopy to detect serum samples from breast cancer patients, benign cases, and healthy subjects, with puncture biopsy as the gold standard for comparison. The goal was to explore the value of Raman spectroscopy in the differential diagnosis of breast cancer, benign lesions, and healthy individuals.

Methods

In this study, blood serum samples were collected from a total of 333 participants. Among them, there were 129 cases of tumors (pathologically diagnosed as breast cancer and labeled as cancer), 91 cases of benign lesions (pathologically diagnosed as benign and labeled as benign), and 113 cases of healthy controls (labeled as normal). Raman spectra of the serum samples from each group were collected. To classify the normal, benign, and cancer sample groups, principal component analysis (PCA) combined with support vector machine (SVM) was used. The SVM model was evaluated using a cross-validation method.

Results

The results of the study revealed significant differences in the mean Raman spectra of the serum samples between the normal and tumor/benign groups. Although the mean Raman spectra showed slight variations between the cancer and benign groups, the SVM model achieved a remarkable prediction accuracy of up to 98% for classifying cancer, benign, and normal groups.

Discussion

In conclusion, this exploratory study has demonstrated the tremendous potential of general Raman spectroscopy as a clinical adjunctive diagnostic and rapid screening tool for breast cancer.

Study on the mechanism of Shenkang injection in the treatment of chronic renal failure based on the strategy of "Network pharmacology-Molecular docking-Key target validation"

OBJECTIVE

To explore the potential mechanism of Shenkang injection (SKI) in the treatment of chronic renal failure based on network pharmacology and molecular docking technology, and to verify the core targets and key pathways by using the renal failure model.

METHODS

The active components and targets of Shenkang injection were retrieved by TCMSP database, and the disease related targets were obtained by OMIM, GeneCards and other databases. Then, the intersection was obtained, and were imported into String database for PPI analysis. After further screening of core targets, GO and KEGG analysis were performed. Autodock software was used to predict the molecular docking and binding ability of the selected active ingredients and core targets. Chronic renal failure (CRF) model was established by adenine induction in rats, and the pathological observation of renal tissues was conducted. Meanwhile, the effects of Shenkang injection and its active components on core targets and pathways of renal tissues were verified.

RESULTS

The results of network pharmacology showed that the main components of Shenkang injection might be hydroxysafflor yellow A (HSYA)、tanshinol、rheum emodin、Astragaloside IV. Through enrichment analysis of core targets, it was found that Shenkang injection may play an anti-chronic renal failure effect through PI3K-Akt signaling pathway. Molecular docking results showed that the above pharmacodynamic components had strong binding ability with the target proteins PI3K and Akt. The results of animal experiments showed that renal function indexes of Shenkang injection group and pharmacodynamic component group were significantly improved compared with model group. HE staining results showed that the pathological status of the kidney was significantly improved in SKI and pharmacodynamic component treatment groups. Immunohistochemical results showed that the renal fibrosis status was significantly reduced in SKI and pharmacodynamic component treatment groups. q-RTPCR and WB results showed that the expression levels of PI3K and Akt were significantly decreased in the treatment groups (P< 0.05).

CONCLUSIONS

Shenkang injection may inhibit PI3K-Akt signaling pathway to play an anti-chronic renal failure role through the pharmacodynamic component hydroxysafflor yellow A (HSYA), tanshinol, rheum emodin, Astragaloside IV.

Raman spectroscopy in chronic heart failure diagnosis based on human skin analysis

This work aims at studying Raman spectroscopy in combination with chemometrics as an alternative fast noninvasive method to detect chronic heart failure (CHF) cases. Optical analysis is focused on the changes in the spectral features associated with the biochemical composition changes of skin tissues. A portable spectroscopy setup with the 785 nm excitation wavelength was used to record skin Raman features. In this in vivo study, 127 patients and 57 healthy volunteers were involved in measuring skin spectral features by Raman spectroscopy. The spectral data were analyzed with a projection on the latent structures and discriminant analysis. 202 skin spectra of patients with CHF and 90 skin spectra of healthy volunteers were classified with 0.888 ROC AUC for the 10-fold cross validated algorithm. To identify CHF cases, the performance of the proposed classifier was verified by means of a new test set that is equal to 0.917 ROC AUC.

Raman spectroscopy and FTIR spectroscopy fusion technology combined with deep learning: A novel cancer prediction method

According to the limited molecular information reflected by single spectroscopy, and the complementarity of FTIR spectroscopy and Raman spectroscopy, we propose a novel diagnostic technology combining multispectral fusion and deep learning. We used serum samples from 45 healthy controls, 44 non-small cell lung cancer (NSCLC), 38 glioma and 37 esophageal cancer patients, and the Raman spectra and FTIR spectra were collected respectively. Then we performed low-level fusion and feature fusion on the spectral, and used SVM, Convolutional Neural Network-Long-Short Term Memory (CNN-LSTM) and the multi-scale convolutional fusion neural network (MFCNN). The accuracy of low-level fusion and feature fusion models are improved by about 10% compared with single spectral models.

Serum Raman spectroscopy combined with multiple classification models for rapid diagnosis of breast cancer

Breast cancer is a malignant tumor with the highest incidence rate in women. Current diagnostic methods are time-consuming, costly, and dependent on physician experience. In this study, we used serum Raman spectroscopy combined with multiple classification algorithms to implement an auxiliary diagnosis method for breast cancer, which will help in the early diagnosis of breast cancer patients. We analyzed the serum Raman spectra of 171 invasive ductal carcinoma (IDC) and 100 healthy volunteers; The analysis showed differences in nucleic acids, carotenoids, amino acids, and lipid concentrations in their blood. These differences provide a theoretical basis for this experiment. First, we used adaptive iteratively reweighted penalized least squares (airPLS) and Savitzky-Golay (SG) for baseline correction and smoothing denoising to remove the effect of noise on the experiment. Then, the Principal component analysis (PCA) algorithm was used to extract features. Finally, we built four classification models: support vector machine (SVM), decision tree (DT), linear discriminant analysis (LDA), and Neural Network Language Model (NNLM). The LDA, SVM, and NNLM achieve 100% accuracy. As supplementary, we added the classification experiment of the raw data. By comparing the experimental results of the two groups, We concluded that the NNLM was the best model. The results show the reliability of the combination of serum Raman spectroscopy and classification models under large sample conditions.

Rapid and sensitive detection of esophageal cancer by FTIR spectroscopy of serum and plasma

Fourier transform infrared (FTIR) spectroscopy, as a platform technology for cancer detection, must be up to the challenge of clinical transformation. To this end, detection of esophageal squamous cell carcinoma (ESCC) was hereby explored using serum and plasma scrape-coated on barium fluoride (BaF₂) disk by transmission FTIR method, and the classification model was built using six multivariate statistical analyses, including support vector machine (SVM), principal component linear discriminant analysis (PC-LDA), decision tree (DT), k-nearest neighbor (KNN) classification, ensemble algorithms (EA) and partial least squares for discriminant analysis (PLS-DA). All statistical analyses methods demonstrated that late-stage cancer could be well classified from healthy people employing either serum or plasma with different anticoagulants. Resulting PC-LDA model differentiated late-stage cancer from normal group with an accuracy of 99.26%, a sensitivity of 98.53%, and a specificity of 100%. The accuracy and sensitivity reached 97.08% and 91.43%, respectively for early-stage cancer discrimination from normal group. This pilot exploration demonstrated that transmission FTIR provided a rapid, cost effective and sensitive method for ESCC diagnosis using either serum or plasma.

Application of machine and deep learning algorithms in optical microscopic detection of Plasmodium: A malaria diagnostic tool for the future

Machine and deep learning techniques are prevalent in the medical discipline due to their high level of accuracy in disease diagnosis. One such disease is malaria caused by Plasmodium falciparum and transmitted by the female anopheles mosquito. According to the World Health Organisation (WHO), millions of people are infected annually, leading to inevitable deaths in the infected population. Statistical records show that early detection of malaria parasites could prevent deaths and machine learning (ML) has proved helpful in the early detection of malarial parasites. Human error is identified to be a major cause of inaccurate diagnostics in the traditional microscopy malaria diagnosis method. Therefore, the method would be more reliable if human expert dependency is restricted or entirely removed, and thus, the motivation of this paper. This study presents a systematic review to understand the prevalent machine learning algorithms applied to a low-cost, portable optical microscope in the automation of blood film interpretation for malaria parasite detection. Peer-reviewed papers were downloaded from selected reputable databases eg. Elsevier, IEEExplore, Pubmed, Scopus, Web of Science, etc. The extant literature suggests that convolutional neural network (CNN) and its variants (deep learning) account for 41.9% of the microscopy malaria diagnosis using machine learning with a prediction accuracy of 99.23%. Thus, the findings suggest that early detection of the malaria parasite has improved through the application of CNN and other ML algorithms on microscopic malaria parasite detection.

Culture-Independent Raman Spectroscopic Identification of Bacterial Pathogens from Clinical Samples Using Deep Transfer Learning

The rapid identification of bacterial pathogens in clinical samples like blood, urine, pus, and sputum is the need of the hour. Conventional bacterial identification methods like culturing and nucleic acid-based amplification have limitations like poor sensitivity, high cost, slow turnaround time, etc. Raman spectroscopy, a label-free and noninvasive technique, has overcome these drawbacks by providing rapid biochemical signatures from a single bacterium. Raman spectroscopy combined with chemometric methods has been used effectively to identify pathogens. However, a robust approach is needed to utilize Raman features for accurate classification while dealing with complex data sets such as spectra obtained from clinical isolates, showing high sample-to-sample heterogeneity. In this study, we have used Raman spectroscopy-based identification of pathogens from clinical isolates using a deep transfer learning approach at the single-cell level resolution. We have used the data-augmentation method to increase the volume of spectra needed for deep-learning analysis. Our ResNet model could specifically extract the spectral features of eight different pathogenic bacterial species with a 99.99% classification accuracy. The robustness of our model was validated on a set of blinded data sets, a mix of cultured and noncultured bacterial isolates of various origins and types. Our proposed ResNet model efficiently identified the pathogens from the blinded data set with high accuracy, providing a robust and rapid bacterial identification platform for clinical microbiology.

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.

Raman spectroscopy combined with machine learning algorithms to detect adulterated Suichang native honey

Zhejiang Suichang native honey, which is included in the list of China’s National Geographical Indication Agricultural Products Protection Project, is very popular. This study proposes a method of Raman spectroscopy combined with machine learning algorithms to accurately detect low-concentration adulterated Suichang native honey. In this study, the native honey collected by local beekeepers in Suichang was selected for adulteration detection. The spectral data was compressed by Savitzky–Golay smoothing and partial least squares (PLS) in sequence. The PLS features taken for further analysis were selected according to the contribution rate. In this study, three classification modeling methods including support vector machine, probabilistic neural network and convolutional neural network were adopted to correctly classify pure and adulterated honey samples. The total accuracy was 100%, 100% and 99.75% respectively. The research result shows that Raman spectroscopy combined with machine learning algorithms has great potential in accurately detecting adulteration of low-concentration honey.

Controllable Fabrication of Molecularly Imprinted Microspheres with Nanoporous and Multilayered Structure for Dialysate Regeneration

Adsorption of urea from dialysate is essential for wearable artificial kidneys (WRK). Molecularly imprinted microspheres with nanoporous and multilayered structures are prepared based on liquid–liquid phase separation (LLPS), which can selectively adsorb urea. In addition, we combine the microspheres with a designed polydimethylsiloxane (PDMS) chip to propose an efficient urea adsorption platform. In this work, we propose a formulation of LLPS including Tripropylene glycol diacrylate (TPGDA), ethanol, and acrylic acid (30% v/v), to prepare urea molecularly imprinted microspheres in a simple and highly controllable method. These microspheres have urea molecular imprinting sites on the surface and inside, allowing selective adsorption of urea and preservation of other essential constituents. Previous static studies on urea adsorption have not considered the combination between urea adsorbent and WRK. Therefore, we design the platform embedded with urea molecular imprinted microspheres, which can disturb the fluid motion and improve the efficiency of urea adsorption. These advantages enable the urea absorption platform to be highly promising for dialysate regeneration in WRK.

Detection of tumour infiltrating lymphocytes in CD3 and CD8 stained histopathological images using a two-phase deep CNN

BACKGROUND

Immuno-score, a prognostic measure for cancer, employed in determining tumor grade and type, is generated by counting the number of Tumour-Infiltrating Lymphocytes (TILs) in CD3 and CD8 stained histopathological tissue samples. Significant stain variations and heterogeneity in lymphocytes' spatial distribution and density make automated counting of TILs' a challenging task.

METHODS

This work addresses the aforementioned challenges by developing a pipeline "Two-Phase Deep Convolutional Neural Network based Lymphocyte Counter (TDC-LC)" to detect lymphocytes in CD3 and CD8 stained histology images. The proposed pipeline sequentially works by removing hard negative examples (artifacts) in the first phase using a custom CNN "LSATM-Net" that exploits the idea of a split, asymmetric transform, and merge. Whereas, in the second phase, instance segmentation is performed to detect and generate a lymphocyte count against the remaining samples. Furthermore, the effectiveness of the proposed pipeline is measured by comparing it with the state-of-the-art single- and two-stage detectors. The inference code is available at GitHub Repository https://github.com/m-mohsin-zafar/tdc-lc.

RESULTS

The empirical evaluation on samples from LYSTO dataset shows that the proposed LSTAM-Net can learn variations in the images and precisely remove the hard negative stain artifacts with an F-score of 0.74. The detection analysis shows that the proposed TDC-LC outperforms the existing models in identifying and counting lymphocytes with high Recall (0.87) and F-score (0.89). Moreover, the commendable performance of the proposed TDC-LC in different organs suggests a good generalization.

CONCLUSION

The promising performance of the proposed pipeline suggests that it can serve as an automated system for detecting and counting lymphocytes from patches of tissue samples thereby reducing the burden on pathologists.