Elevated expression of ANAPC1 in lung squamous cell carcinoma: clinical implications and mechanisms

Future Science OA, Journal Year: 2025, Volume and Issue: 11(1)

Published: March 26, 2025

Aim To investigate the comprehensive expression levels and possible molecular mechanisms of Anaphase Promoting Complex Subunit 1 (ANAPC1) in lung squamous cell carcinoma (LUSC).

Language: Английский

---

Early prediction of neoadjuvant therapy response in breast cancer using MRI-based neural networks: data from the ACRIN 6698 trial and a prospective Chinese cohort

Breast Cancer Research, Journal Year: 2025, Volume and Issue: 27(1)

Published: April 3, 2025

Early prediction of treatment response to neoadjuvant therapy (NAT) in breast cancer patients can facilitate timely adjustment regimens. We aimed develop and validate a MRI-based enhanced self-attention network (MESN) for predicting pathological complete (pCR) based on longitudinal images at the early stage NAT. Two imaging datasets were utilized: subset from ACRIN 6698 trial (dataset A, n = 227) prospective collection Chinese hospital B, 245). These divided into three cohorts: an training cohort (n 153) dataset test 74) external 245) B. The proposed MESN allowed integration multiple timepoint features extraction dynamic information MR before after early-NAT. also constructed Pre model pre-NAT MRI features. Clinicopathological characteristics added these image-based models create integrated (MESN-C Pre-C), their performance was evaluated compared. MESN-C yielded area under receiver operating characteristic curve (AUC) values 0.944 (95% CI: 0.906 - 0.973), 0.903 (95%CI: 0.815 0.965), 0.861 0.811 0.906) training, cohorts, respectively, which significantly higher than those clinical (AUC: 0.720 [95%CI: 0.587 0.842], 0.738 0.669 0.796] two respectively; p < 0.05) Pre-C 0.697 0.554 0.819], 0.726 0.666 0.797] 0.05). High AUCs maintained standard (AUC 0.853 0.676 1.000]) experimental 0.905 0.817 0.993]) subcohorts, interracial subcohort 0.906]). Moreover, increased positive predictive value 48.6 71.3% compared with model, high negative (80.4-86.7%). using multiparametric short-term achieved favorable pCR, could regimens, increasing rates pCR avoiding toxic effects. Trial registration https://www.chictr.org.cn/ . ChiCTR2000038578, registered September 24, 2020.

Language: Английский

---

Targets and promising adjuvants for improving breast tumor response to radiotherapy

Bioorganic Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 108582 - 108582

Published: May 1, 2025

Language: Английский

---

A PET-CT radiomics model for immunotherapy response and prognosis prediction in patients with metastatic colorectal cancer

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15

Published: May 23, 2025

Background In recent years, radiomics, as a non-invasive method, has shown potential in predicting tumor response and prognosis by analyzing medical image data to extract high-dimensional features reveal the heterogeneity of microenvironment (TME). Objective The aim this study was construct validate radiomic model based on PET/CT images for immunotherapy mCRC patients. Methods This included patients from multiple cohorts, including training set (n=105), an internal validation (n=60), TME phenotype cohort (n=42), (n=99). High-dimensional were extracted using deep neural network (DNN), RNA-Seq used screen associated with phenotypes score (Rad-Score). At same time, combined immune scores (IHC staining results CD3 CD8) clinical features, joint prediction developed assess overall survival (OS) progression-free (PFS). predictive performance evaluated area under receiver operating characteristic curve (AUC), calibration decision analysis (DCA). Results A radiomics signature predict constructed verified it set, AUC 0.855 0.844 respectively. external cohort, can differentiate either immunopotentiation or immunosuppression (AUC=0.814). (AUC=0.784). nomograms OS PFS, 0.860 0.875 (DCA) confirmed utility nomograms. Conclusion study, successfully constructed, which effectively combines showing high accuracy application value. future, reliability generalization ability need be further larger prospective studies promote its practice.

Language: Английский

---

Exploring the Incremental Value of Aorta Enhancement Normalization Method in Evaluating Renal Cell Carcinoma Histological Subtypes: A Multi-center Large Cohort Study

Academic Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

---

Breast cancer prediction modeling based on SHAP interpretability analysis and XGBoost algorithm

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Purpose To compare the predictive effectiveness and risk factor screening of extreme gradient ascent (XGBoost) model four commonly used machine learning models for breast cancer diagnosis, to interpret results by SHAP interpretability analysis. Materials methods Breast tumor data from UCI public database were screen characteristic factors using heat map correlation coefficient matrix, five algorithms, XGBoost, Random Forest, K-Nearest Neighbors, Decision Tree, Support Vector Machines, compared precision, recall, F1 value, accuracy. The ROC curves plotted, confusion matrix was classify prediction results, resulting in best-performing model, XGBoost. XGBoost decision tree random forest derive order importance feature factors, an analysis performed through important affecting occurrence cancer. Results curve showed that accuracy test set 97.4%, 91.2%, 95.6%, neighborhood algorithm 94.7%, support vector 92.1%. plot also gives 97.3% 89.5% 95.6% 94.7% proximity 92.1% model. scores three models, first is radius-worst. interpretable main drivers high patients radius-worst,concave points-worst,concavity-worst.Also radius-worst interacted with concave points-worst. Conclusions more accurate traditional occurrence, its interaction points-worst exists.

Language: Английский

---

Comprehensive Analysis of Angiogenesis and Ferroptosis Genes for Predicting the Survival Outcome and Immunotherapy Response of Hepatocellular Carcinoma

Journal of Hepatocellular Carcinoma, Journal Year: 2024, Volume and Issue: Volume 11, P. 1845 - 1859

Published: Sept. 1, 2024

Angiogenesis and ferroptosis are both linked to hepatocellular carcinoma (HCC) development, recurrence, medication resistance. As a result, thorough examination of the link between genes associated with angiogenesis immunotherapy efficacy is required improve dismal prognosis HCC patients.

Language: Английский

---

Nomogram for Predicting Survival Post-Immune Therapy in Cholangiocarcinoma Based on Inflammatory Biomarkers

Cancer Control, Journal Year: 2024, Volume and Issue: 31

Published: Jan. 1, 2024

Background Immune therapy, especially involving PD-1/PD-L1 inhibitors, has shown promise as a therapeutic option for cholangiocarcinoma. However, limited studies have evaluated survival outcomes in cholangiocarcinoma patients treated with immune therapy. This study aims to develop predictive model evaluate the benefits of therapy Methods retrospective analysis included 120 from Shulan (Hangzhou) Hospital. Univariate and multivariate Cox regression analyses were conducted identify factors associated following A was constructed validated using calibration curves (CC), decision curve (DCA), concordance index (C-index), receiver operating characteristic (ROC) curves. Results identified several potential predictors post-immune cholangiocarcinoma: treatment cycle (<6 vs ≥ 6 months, 95% CI: 0.119-0.586, P = 0.001), neutrophil-to-lymphocyte ratio (NLR <3.08 3.08, 1.864-9.624, carcinoembryonic antigen (CEA <4.13 4.13, 1.175-5.321, 0.017), presence bone metastasis (95% 1.306-6.848, 0.010). The nomogram achieved good accuracy C-index 0.811. CC indicated strong between predicted observed outcomes. Multi-timepoint ROC at 1, 2, 3 years model’s performance (1-year AUC: 0.906, 2-year 0.832, 3-year 0.822). multi-timepoint DCA also demonstrated higher net benefit compared extreme Conclusion model, incorporating key risk demonstrates robust outcomes, offering improved clinical decision-making.

Language: Английский

---

Machine Learning-Based Cell Death Marker for Predicting Prognosis and Identifying Tumor Immune Microenvironment in Prostate Cancer

Heliyon, Journal Year: 2024, Volume and Issue: unknown, P. e37554 - e37554

Published: Sept. 1, 2024

Language: Английский

---

Interpretable Machine Learning Algorithms Identify Inetetamab‐Mediated Metabolic Signatures and Biomarkers in Treating Breast Cancer

Journal of Clinical Laboratory Analysis, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 21, 2024

ABSTRACT Background HER2‐positive breast cancer (BC), a highly aggressive malignancy, has been treated with the targeted therapy inetetamab for metastatic cases. Inetetamab (Cipterbin) is recently approved BC, significantly prolonging patients' survival. Currently, there no established biomarker to reliably predict or assess therapeutic efficacy of in BC patients. Methods This study harnesses power metabolomics and machine learning uncover biomarkers therapy. A total 23 plasma samples from inetetamab‐treated patients were collected stratified into responders nonresponders. Ultra‐high‐performance liquid chromatography‐quadrupole time‐of‐flight mass spectrometry was utilized analyze metabolites blood samples. combination univariate multivariate statistical analyses employed identify these metabolites, their biological functions then ascertained by Gene Ontology (GO) Kyoto Encyclopedia Genes Genomes (KEGG) enrichment analysis. Finally, algorithms screen responsive all differentially expressed metabolites. Results Our finding revealed 6889 unique that detected. Pathways like retinol metabolism, fatty acid biosynthesis, steroid hormone biosynthesis enriched Notably, two key associated response identified: FAPy‐adenine 2‐Pyrocatechuic acid. There some negative correlation between progress‐free survival (PFS) kurtosis content. Conclusions In summary, identification significant differential holds promise as potential evaluating predicting treatment outcomes ultimately contributing diagnosis disease discovery prognostic markers.

Language: Английский

---