ABSTRACT
Objective: The Eastern Cooperative Oncology Group performance status (ECOG PS) is a widely recognized measure used to assess the functional abilities of cancer patients and predict their prognosis. It plays a crucial role in guiding treatment decisions made by physicians. This study aimed to build a stacking ensemble-based prognosis predictor model for predicting the ECOG PS of a liver cancer patient undergoing treatment. Methods: We used Light Gradient Boosting Machine (LightGBM) as the meta-model, and five base models, including Random Forest (RF), Extra Trees (ET), AdaBoost (Ada), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost). After preprocessing the data and applying feature selection method, the stacking ensemble model was trained using 1622 liver cancer patients' data and 46 variables. We also integrated the stacking ensemble model with a LIME-based explainable model to obtain model prediction explainability. Results: According to the research, the best combination of the stacking ensemble model is ET + XGBoost + RF + GBM + Ada + LightGBM and achieved a ROC AUC of 0.9826 on the training set and 0.9675 on the test set. Conclusions: This explainable stacking ensemble model can become a helpful tool for objectively predicting ECOG PS in liver cancer patients and aiding healthcare practitioners to adapt their treatment approach more effectively.
ABSTRACT
The thermal behavior of ash components in two bituminous coal samples [Upper Freeport (the "UF") and Illinois #6 (the "IL")] was investigated under air and argon atmospheres in the temperature range of 800-1200 °C using thermal gravimetric-differential thermal analysis, X-ray diffraction transmission electron microscopy (TEM), and TEM-energy dispersive X-ray spectrometry measurements. The UF treated under air formed the needle-like crystals which were assumed to be mullite-related substances formed by transformation of andalusite, because the crystals are mainly composed of SiO2 and Al2O3. In contrast to the UF, the IL did not generate such crystals; however, when the IL was treated under air after carbonization under Ar, crystals appeared. The composition of the UF with an Al/Si ratio higher than that of the IL favored the formation of mullite-related substances, while the presence of lime in the IL inhibited the formation of mullite-related substances. Oldhamite was formed by the reaction of lime with sulfur at the carbonization of the IL under Ar and remained even at the successive air treatment. As lime was consumed, the formation of mullite-related substances was ceased to be inhibited under air after Ar treatment.
ABSTRACT
Atmospheric pollution has become a major problem for modern societies owing to its fatal effects on both human health and ecosystems. We studied the relationships of nitrogen dioxide atmospheric pollution and metal trace elements contained in atmospheric particles which were accumulated in bryophytes to microbial communities of bryophytes at three differently polluted sites in France (rural, urban, and industrial) over an 8-month period. The analysis of bryophytes showed an accumulation of Cr and Fe at the rural site; Cr, Fe, Zn, Cu, Al, and Pb at the urban site; and Fe, Cr, Pb, Al, Sr, Cu, and Zn at the industrial site. During this study, the structure of the microbial communities which is characterized by biomasses of microbial groups evolved differently according to the site. Microalgae, bacteria, rotifers, and testate amoebae biomasses were significantly higher in the rural site. Cyanobacteria biomass was significantly higher at the industrial site. Fungal and ciliate biomasses were significantly higher at the urban and industrial sites for the winter period and higher at the rural site for the spring period. The redundancy analysis showed that the physico-chemical variables ([NO(2)], relative humidity, temperature, and site) and the trace elements which were accumulated in bryophytes ([Cu], [Sr], [Pb]) explained 69.3% of the variance in the microbial community data. Moreover, our results suggest that microbial communities are potential biomonitors of atmospheric pollution. Further research is needed to understand the causal relationship underlined by the observed patterns.
