ObjectiveTo investigate the application of the novel inflammatory factor adsorption column CA280 combined with low-dose plasma exchange （LPE） in patients with acute-on-chronic liver failure （ACLF）. MethodsA prospective cohort study was designed， and a total of 93 ACLF patients who were admitted to The Ninth Hospital of Nanchang from June 2023 to January 2025 were enrolled and randomly divided into DPMAS+LPE group with 50 patients and CA280+LPE group with 43 patients. In addition to comprehensive medical treatment， the patients in the DPMAS+LPE group received DPMAS and LPE treatment， and those in the CA280+LPE group received CA280 and LPE treatment. The two groups were observed in terms of routine blood test results， liver function parameters， renal function markers， electrolytes， coagulation function parameters， cytokines， adverse events， and 28-day prognosis before surgery （baseline）， during surgery （DPMAS or CA280）， and after surgery （after sequential LPE treatment）. The paired t-test was used for comparison of normally distributed continuous data before and after treatment within each group， and the independent-samples t test was used for comparison between groups； the Wilcoxon signed-rank test was used for comparison of non-normally distributed continuous data before and after treatment within each group， and the Mann-Whitney U test was used for comparison between groups. The chi-square test or the Fisher’s exact test was used for comparison of categorical data between groups， and the Spearman test was used for correlation analysis. ResultsAfter CA280 treatment， the ACLF patients had significant reductions in the levels of cytokines （IL-6， IL-8， IL-10， TNF-α， and IFN-γ）， liver function parameters （ALT， AST， ALP， TBil， DBil， Alb， and glutathione reductase）， and the renal function marker urea nitrogen （all P<0.05）， and in terms of coagulation function parameters， there were significant increases in prothrombin time， activated partial thromboplastin time （APTT）， thrombin time， and international normalized ratio （INR） and significant reductions in prothrombin activity （PTA） and fibrinogen （FIB） （all P<0.05）. Compared with the DPMAS+LPE group， the CA280+LPE group showed better improvements in the serum cytokines IL-8 （Z=-2.63， P=0.009）， IL-10 （Z=-3.94， P<0.001）， and TNF-α （Z=-1.53， P=0.023）， and the two artificial liver support systems had a similar effect in improving liver function （ALT， AST， GGT， GR， TBil， and DBil） （all P >0.05）， but the CA280+LPE group showed a significantly greater reduction in Alb （Z=-2.08， P=0.037）. CA280+LPE was more effective in reducing uric acid （Z=-2.97， P=0.003）. Compared with DPMAS+LPE， CA280+LPE treatment resulted in a significant reduction in INR （Z=-4.01， P<0.001）， a significant increase in APTT （Z=-2.53， P=0.011）， and significant greater increases in PTA （Z=-6.28， P<0.001） and FIB （Z=-3.93， P<0.001）. There were no significant differences in the incidence rates of adverse reactions and the rate of improvement at discharge between the two groups （all P>0.05）. The Spearman correlation analysis showed that IL-6 was significantly correlated with WBC （r=0.22， P=0.042）， TBil （r=0.29， P=0.005）， and FIB （r=-0.33， P=0.003）； IL-8 was positively correlated with APTT （r=0.37， P<0.001） and INR （r=0.25， P=0.013）； TNF-α was significantly correlated with WBC （r=0.40， P<0.001） and TBil （r=0.34， P<0.001）. ConclusionCompared with DPMAS， CA280 combined with LPE can effectively clear proinflammatory cytokines and improve liver function in ACLF patients， but it has a certain impact on Alb and coagulation function. This regimen provides a new option for the individualized treatment of ACLF and can improve the short-term prognosis of patients， but further studies are needed to verify its long-term efficacy.

Objective:To explore the application of machine learning (ML) models based on radiomics and dosiomics to the assessment of hematologic toxicity (HT) in patients with locally advanced cervical cancer, and to preliminarily explore the comprehensive application of multi-omics features.Methods:A retrospective study was conducted on the clinical data, planning computed tomography (CT) images, and dose files of 205 patients with locally advanced cervical cancer who received concurrent chemoradiotherapy at the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, from January 2022 to June 2023. Patients were categorized according to the severity of HT. Radiomics and dosiomics features were extracted from the same regions of interest (ROIs), followed by feature selection utilizing a random forest algorithm. Then, radiomics, dosiomics, and hybrid models were established based on extreme gradient boosting (XGBoost). The classification performance of these models was assessed by calculating their sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).Results:The radiomics model yielded sensitivity, specificity, and AUC of 0.42, 0.86, and 0.78, respectively. The dosiomics model exhibited sensitivity, specificity, and AUC of 0.50, 0.90, and 0.74, respectively. In contrast, the hybrid model achieved sensitivity, specificity, and AUC of 0.50, 0.83, and 0.83, respectively. These findings suggest that the hybrid model possessed an enhanced classification capability compared to the individual radiomics and dosiomics models.Conclusions:It is feasible to use ML models based on radiomics and dosiomics to conduct the classification and prediction of HT in patients with locally advanced cervical cancer treated with concurrent chemoradiotherapy. Furthermore, integrating both radiomics features and dosiomics features can improve the classification performance of relevant prediction models, thus holding application potentials to optimize treatment strategies for patients with locally advanced cervical cancer.

Objective:To explore the application of machine learning (ML) models based on radiomics and dosiomics to the assessment of hematologic toxicity (HT) in patients with locally advanced cervical cancer, and to preliminarily explore the comprehensive application of multi-omics features.Methods:A retrospective study was conducted on the clinical data, planning computed tomography (CT) images, and dose files of 205 patients with locally advanced cervical cancer who received concurrent chemoradiotherapy at the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, from January 2022 to June 2023. Patients were categorized according to the severity of HT. Radiomics and dosiomics features were extracted from the same regions of interest (ROIs), followed by feature selection utilizing a random forest algorithm. Then, radiomics, dosiomics, and hybrid models were established based on extreme gradient boosting (XGBoost). The classification performance of these models was assessed by calculating their sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).Results:The radiomics model yielded sensitivity, specificity, and AUC of 0.42, 0.86, and 0.78, respectively. The dosiomics model exhibited sensitivity, specificity, and AUC of 0.50, 0.90, and 0.74, respectively. In contrast, the hybrid model achieved sensitivity, specificity, and AUC of 0.50, 0.83, and 0.83, respectively. These findings suggest that the hybrid model possessed an enhanced classification capability compared to the individual radiomics and dosiomics models.Conclusions:It is feasible to use ML models based on radiomics and dosiomics to conduct the classification and prediction of HT in patients with locally advanced cervical cancer treated with concurrent chemoradiotherapy. Furthermore, integrating both radiomics features and dosiomics features can improve the classification performance of relevant prediction models, thus holding application potentials to optimize treatment strategies for patients with locally advanced cervical cancer.