Building an ensemble learning model for gastric cancer cell line classification via rapid raman spectroscopy

Stable SERS Detection of Lactobacillus fermentum Using Optical Tweezers in a Microfluidic Environment

“…Machine learning algorithms such as SVM (Support Vector Machine), LDA (Latent Dirichlet Allocation), KNN (K-Nearest Neighbor), XGBoost (eXtreme Gradient Boosting), Random Forest, and Decision Trees play a crucial role in the identification of Raman spectral data. Among many machine learning algorithms, the SVM algorithm is more advantageous for data analysis of small-scale data − and has a wide range of applications in biological Raman spectroscopy data analysis. , In recent years, the XGBoost algorithm has shown good performance in the process of biological Raman spectral analysis because of its fast data processing speed and strong data robustness. , In this work, SVM and XGBoost were chosen to process the obtained bacterial SERS spectral data. The Raman spectral data were divided into microtraining and test sets in a 4:1 ratio.…”

“…44,45 In recent years, the XGBoost algorithm has shown good performance in the process of biological Raman spectral analysis because of its fast data processing speed and strong data robustness. 46,47 In this work, SVM and XGBoost were chosen to process the obtained bacterial SERS spectral data. The Raman spectral data were divided into microtraining and test sets in a 4:1 ratio.…”

Evaluation of Raman spectroscopy combined with the gated recurrent unit serum detection method in early screening of gastrointestinal cancer

“…Recent years have seen successful applications of Raman spectroscopy in the diagnosis of malignant tumors located in diverse parts of the human body, including breast cancer, brain cancer, cervical cancer, gastric cancer, etc . 8–13…”

“…Recent years have seen successful applications of Raman spectroscopy in the diagnosis of malignant tumors located in diverse parts of the human body, including breast cancer, brain cancer, cervical cancer, gastric cancer, etc. [8][9][10][11][12][13] Numerous studies have utilized Raman spectroscopy to diagnose gastric cancer based on blood, tissue, cell line, and other samples. Such studies have successfully distinguished between cancer and normal samples while also identifying different stages of gastric cancer.…”

“…Such studies have successfully distinguished between cancer and normal samples while also identifying different stages of gastric cancer. 7,12,[14][15][16] However, these studies generally involved a limited sample size and did not consider the varying degrees of cancer cell differentiation. Furthermore, the analysis of Raman spectra in these studies mostly relied on traditional machine learning methods such as PCA and linear discriminant analysis (LDA) that yielded positive results.…”