Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Alpha-fetoprotein (AFP) (1)
- Cabozantinib (1)
- Hepatocellular carcinoma (HCC) (1)
- Indirect treatment comparison (ITC) (1)
- Matching-adjusted indirect comparison (MAIC) (1)
- Monoclonal antibody (mAb) (1)
- Ramucirumab (1)
- Tyrosine kinase inhibitor (TKI) (1)
- Vascular endothelial growth factor (VEGF) (1)
- machine learning (1)
Institute
- Biochemie und Chemie (1)
- Medizin (1)
Individual patient data (IPD) from the CELESTIAL trial (cabozantinib) and population-level data from the REACH-2 trial (ramucirumab) were used. To align with REACH-2, the CELESTIAL population was limited to patients who received first-line sorafenib only and had baseline serum AFP ≥ 400 ng/mL. The IPD from CELESTIAL were weighted to balance the distribution of 11 effect-modifying baseline characteristics with those of REACH-2. Overall survival (OS; primary endpoint) and progression-free survival (PFS) were compared for the CELESTIAL (matching-adjusted) and REACH-2 populations using weighted Kaplan-Meier (KM) curves and parametric (OS, Weibull; PFS, log-logistic) modeling. Rates of treatment-related adverse events (TRAEs) and TRAE-related discontinuations were also compared.
In this study, a portable electronic nose (E-nose) prototype is developed using metal oxide semiconductor (MOS) sensors to detect odors of different wines. Odor detection facilitates the distinction of wines with different properties, including areas of production, vintage years, fermentation processes, and varietals. Four popular machine learning algorithms—extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and backpropagation neural network (BPNN)—were used to build identification models for different classification tasks. Experimental results show that BPNN achieved the best performance, with accuracies of 94% and 92.5% in identifying production areas and varietals, respectively; and SVM achieved the best performance in identifying vintages and fermentation processes, with accuracies of 67.3% and 60.5%, respectively. Results demonstrate the effectiveness of the developed E-nose, which could be used to distinguish different wines based on their properties following selection of an optimal algorithm.
