Удалил старую таблицу с резульатами

report.tex

@@ -274,46 +274,6 @@
         \end{tikzpicture}
     }]{results_table/results.pdf}
 
-    \newpage
-
-    \begin{table}[h!]
-        \centering
-        \caption{Results obtained in research papers.}
-        \footnotesize
-        \begin{tabularx}{\textwidth}{|X|X|X|X|}
-        \hline
-        \textbf{Article} & \textbf{Key results} & \textbf{Best algorithms} & \textbf{Metrics} \\
-        \hline
-        Classification of paclitaxel-resistant ovarian cancer cells using holographic flow cytometry through interpretable machine learning~\cite{paclitaxel} & Demonstrated that morphological changes in epithelial ovarian cancer (EOC) cells correlate with drug sensitivity, highlighting the potential for monitoring drug resistance.
-        & Support vector machine (SVM) and neural network (NN) & Accuracy of 94.5\% for SVM and 93.4\% for NN \\
-        \hline
-        Heterogeneity of computational pathomic signature predicts drug resistance and intra-tumor heterogeneity of ovarian cancer~\cite{heterogeneity} & Demonstrated a strong correlation between intra-tumor heterogeneity (ITH) and drug resistance in epithelial ovarian cancer (EOC) cells & Least absolute shrinkage and selection operator (LASSO) regression & Area under curve (AUC) of 0.601, 0.594, and 0.589 for 1, 3, and 5 years survival time accordingly \\
-        \hline
-        Mitochondria-related chemoradiotherapy resistance genes-based machine learning model associated with immune cell infiltration on the prognosis of esophageal cancer and its value in pan-cancer~\cite{mitochondria} & Proposed a model  that incorporates mitochondria-related chemoradiotherapy resistance (MRCRTR) genes. Identified six mitochondria-related genes that affect CRT and the prognosis of esophageal cancer. & Neural network (NN) and least absolute shrinkage and selection operator (LASSO) regression & Root mean squared error (RMSE) of 0.001 for NN and 0.003 for LASSO \\
-        \hline
-        Molecular separation-assisted label-free SERS combined with machine learning for nasopharyngeal cancer screening and radiotherapy resistance prediction~\cite{sers} & Developed a novel approach using label-free surface-enhanced Raman spectroscopy (SERS) to profile molecular patterns in the blood of nasopharyngeal cancer (NPC) patients, distinguishing those with radiotherapy sensitivity from those with resistance & Principal component analysis and linear discriminant analysis (PCA-LDA) & Accuracy of 96.7\% for identifying radiotherapy resistance subjects from sensitivity ones and 100\% for identifying the nasopharyngeal cancer (NPC) subjects from healthy ones \\
-        \hline
-        \end{tabularx}
-    \end{table}
-
-    \newpage
-    \addtocounter{table}{-1}
-    \begin{table}[h!]
-        \centering
-        \caption{Results obtained in research papers (continued).}
-        \footnotesize
-        \begin{tabularx}{\textwidth}{|X|X|X|X|}
-        \hline
-        \textbf{Article} & \textbf{Key results} & \textbf{Best algorithms} & \textbf{Metrics} \\
-        \hline
-        A Predictive Model for Initial Platinum-Based Chemotherapy Efficacy in Patients with Postoperative Epithelial Ovarian Cancer Using Tissue-Derived Small Extracellular Vesicles~\cite{platinum} & Found that three immune-related proteins—CCR1, IGHV3-35, and CD72—along with the presence of postoperative residual tumors, are strong predictors of platinum resistance in EOC patients. Proposed a model that can predict the efficacy of initial platinum-based chemotherapy & Least absolute shrinkage and selection operator (LASSO) regression and logistic regression (LR) & Area under curve (AUC) of 0.864 \\
-        \hline
-        Identifying genes associated with resistance to KRAS G12C inhibitors via machine learning methods~\cite{kras} & Identified some top-ranked genes, including H2AFZ, CKS1B, TUBA1B, RRM2, and BIRC5, associated with cancer progression and drug resistance. Have built efficient classifiers as the byproduct & Categorical boosting (CATB) for feature selection and support vector machine (SVM) for classification & Accuracy of 93.1\% and F1-score of 0.938 \\
-        \hline
-        Turning to immunosuppressive tumors: Deciphering the immunosenescence-related microenvironment and prognostic characteristics in pancreatic cancer, in which GLUT1 contributes to gemcitabine resistance~\cite{glut} & Identified that IMSP1 and IMSP2 phenotypes influence pancreatic cancer prognosis and treatment response. Found that high MLIRS scores are linked to lower immune infiltration, while low scores indicate better drug sensitivity. Highlighted GLUT1 as a key factor driving tumor proliferation, migration, and chemotherapy resistance & Stepwise Cox combined with generalized boosted regression modeling (GBM) & Area under the curve (AUC) of 0.91 \\
-        \hline
-        \end{tabularx}
-    \end{table}
 
     % \section*{Conclusion}
     % \addcontentsline{toc}{section}{Conclusion}