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 evaluate the relationship between nuclear receptor subfamily 1 group D member 1 (Rev-erbα) and ferroptosis in cardiomyocytes subjected to high-fat/high-glucose (HFHG) and hypoxia-reoxygenation (H/R) injury.Methods:H9c2 cardiomyocytes were cultured under normal conditions. The cells were divided into 4 groups ( n=13 each) using a random number table method: control group (C group), H/R group, HFHG group and HFHG+ H/R1 group. The cells were divided into 3 groups ( n=17 each) using a random number table method: HFHG+ H/R2 group, negative control siRNA + HFHG + H/R group (si-NC+ HFHG+ H/R group), and Rev-erbα gene knockdown + HFHG + H/R group (si-Rev-erbα+ HFHG+ H/R group). The cardiomyocyte model of HFHG combined with H/R injury was established by incubating cells with HFHG medium for 12 h, followed by 6 h of hypoxia and 2 h of reoxygenation. Rev-erbα gene was knocked down using siRNA technology. Cell viability was assessed using CCK-8 and Calcein AM/PI live-dead cell double staining kits. The expression of Rev-erbα, acyl-CoA synthetase long-chain family member 4 (ACSL4), and nuclear receptor coactivator 4 (NCOA4) was detected by Western blot. The levels of lipid peroxide (LPO) were measured by flow cytometry. Results:Compared with C group, the cell viability was significantly decreased, and the expression of Rev-erbα, ACSL4 and NCOA4 was up-regulated in HFHG, H/R and HFHG+ H/R1 groups( P<0.05). Compared with HFHG group or H/R group, the cell viability was significantly decreased, and the expression of Rev-erbα, ACSL4 and NCOA4 was up-regulated in HFHG+ H/R1 group ( P<0.05).There were no significant differences in the cell viability, levels of LPO, or expression of Rev-erbα, ACSL4 and NCOA4 between HFHG+ H/R2 group and si-NC+ HFHG+ H/R group ( P>0.05). Compared with HFHG+ H/R2 group, the cell viability was significantly increased, the levels of LPO were decreased, and the expression of Rev-erbα, ACSL4 and NCOA4 was down-regulated in si-Rev-erbα+ HFHG+ H/R group ( P<0.05). Conclusions:Rev-erbα participates in the process of HFHG and H/R injury to cardiomyocytes by negatively regulating ferroptosis.

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 evaluate the relationship between nuclear receptor subfamily 1 group D member 1 (Rev-erbα) and ferroptosis in cardiomyocytes subjected to high-fat/high-glucose (HFHG) and hypoxia-reoxygenation (H/R) injury.Methods:H9c2 cardiomyocytes were cultured under normal conditions. The cells were divided into 4 groups ( n=13 each) using a random number table method: control group (C group), H/R group, HFHG group and HFHG+ H/R1 group. The cells were divided into 3 groups ( n=17 each) using a random number table method: HFHG+ H/R2 group, negative control siRNA + HFHG + H/R group (si-NC+ HFHG+ H/R group), and Rev-erbα gene knockdown + HFHG + H/R group (si-Rev-erbα+ HFHG+ H/R group). The cardiomyocyte model of HFHG combined with H/R injury was established by incubating cells with HFHG medium for 12 h, followed by 6 h of hypoxia and 2 h of reoxygenation. Rev-erbα gene was knocked down using siRNA technology. Cell viability was assessed using CCK-8 and Calcein AM/PI live-dead cell double staining kits. The expression of Rev-erbα, acyl-CoA synthetase long-chain family member 4 (ACSL4), and nuclear receptor coactivator 4 (NCOA4) was detected by Western blot. The levels of lipid peroxide (LPO) were measured by flow cytometry. Results:Compared with C group, the cell viability was significantly decreased, and the expression of Rev-erbα, ACSL4 and NCOA4 was up-regulated in HFHG, H/R and HFHG+ H/R1 groups( P<0.05). Compared with HFHG group or H/R group, the cell viability was significantly decreased, and the expression of Rev-erbα, ACSL4 and NCOA4 was up-regulated in HFHG+ H/R1 group ( P<0.05).There were no significant differences in the cell viability, levels of LPO, or expression of Rev-erbα, ACSL4 and NCOA4 between HFHG+ H/R2 group and si-NC+ HFHG+ H/R group ( P>0.05). Compared with HFHG+ H/R2 group, the cell viability was significantly increased, the levels of LPO were decreased, and the expression of Rev-erbα, ACSL4 and NCOA4 was down-regulated in si-Rev-erbα+ HFHG+ H/R group ( P<0.05). Conclusions:Rev-erbα participates in the process of HFHG and H/R injury to cardiomyocytes by negatively regulating ferroptosis.

Objective:This study aims to analyze of the quality of diagnosis and treatment data of community medical institutions on the national health information platform in a district of Beijing from the perspective of scientific research informatization, to provide experience and reference for promoting the informatization construction of primary medical units and tapping the scientific research potential of the regional data platform.Methods:Based on the data backup database of the national health information platform in the region, the data quality was analyzed and evaluated mainly in three dimensions: integrity, integration, and consistency.Results:Through the construction of the national health information platform, the district successfully achieved the effective collection of diagnosis and treatment data from community medical institutions, covering the main data such as patients′ basic information, visit information, test information, prescription information, etc. However, the data collected so far were still insufficient in terms of data integration and consistency.Conclusions:A regional medical data center is suggested to construct to break down the barriers between data systems, conduct pre-structuring of diagnosis and treatment data, improve data integration and consistency, and at the same time, carry out effective scientific research prospective design to promote the effective transformation of clinical data to scientific research data.