A hybrid ensemble learning merging approach for enhancing the super drought computation over Lake Victoria Basin.

This study introduces a novel Hybrid Ensemble Machine-Learning (HEML) algorithm to merge long-term satellite-based reanalysis precipitation products (SRPPs), enabling the estimation of super drought events in the Lake Victoria Basin (LVB) during the period of 1984 to 2019. This study considers three widely used Machine learning (ML) models, including RF (Random Forest), GBM (Gradient Boosting Machine), and KNN (k-nearest Neighbors), for the emerging HEML approach. The three SRPPs, including CHIRPS (Climate Hazards Group Infra-Red Precipitation with Station), ERA5-Land, and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network-Climate Data Record), were used to merge for developing new precipitation estimates from HEML model. Additionally, classification and regression models were employed as base learners in developing this algorithm. The newly developed HEML datasets were compared with other ML and SRPP products for super-drought monitoring. The Standardized precipitation evapotranspiration index (SPEI) was used to estimate super drought characteristics, including Drought frequency (DF), Drought Duration (DD), and Drought Intensity (DI) from machine learning and SRPPs products in LVB and compared with RG observation. The results revealed that the HEML algorithm shows excellent performance (CC = 0.93) compared to the single ML merging method and SRPPs against observation. Furthermore, the HEML merging product adeptly captures the spatiotemporal patterns of super drought characteristics during both training (1984-2009) and testing (2010-2019) periods. This research offers crucial insights for near-real-time drought monitoring, water resource management, and informed policy decisions.

Construction of an enhanced computed tomography radiomics model for non-invasively predicting granzyme A in head and neck squamous cell carcinoma by machine learning.

PURPOSE: Classical prognostic indicators of head and neck squamous cell carcinoma (HNSCC) can no longer meet the clinical needs of precision medicine. This study aimed to establish a radiomics model to predict Granzyme A (GZMA) expression in patients with HNSCC. METHODS: We downloaded transcriptomic data of HNSCC patients from The Cancer Genome Atlas for prognosis analysis and then used corresponding enhanced computed tomography (CT) images from The Cancer Imaging Archive for feature extraction and model construction. We explored the influence of differences in GZMA expression on signaling pathways and analyzed the potential molecular mechanism and its relationship with immune cell infiltration. Subsequently, non-invasive CT radiomics models were established to predict the expression of GZMA mRNA and evaluate the correlation with the radiomics-score (Rad-score), related genes, and prognosis. RESULTS: We found that GZMA was highly expressed in tumor tissues, and high GZMA expression was a protective factor for overall survival. The degree of B and T lymphocyte and natural killer cell infiltration was significantly correlated with GZMA expression. The receiver operating characteristic curve showed that the Relief GBM and RFE_GBM radiomics models had good predictive ability, and there were significant differences in the Rad-score distribution between the high- and low-GZMA-expression groups. CONCLUSIONS: GZMA expression can significantly affect the prognosis of patients with HNSCC. Enhanced CT radiomics models can effectively predict the expression of GZMA mRNA.

Constructing a predictive risk score for the needs of coronary care unit care in patients with ST-segment elevation myocardial infarction / 中国医师进修杂志

Objective:To construct a risk prediction score for the needs of coronary care unit (CCU) care in stable condition acute ST-segment elevation myocardial infarction (STEMI) patients who receive percutaneous coronary intervention (PCI) treatment.Methods:The clinical data of 805 STEMI patients who accepted PCI in the First Hospital of Jilin University from November 2017 to October 2018 were retrospectively analyzed. Among the patients, 654 patients from November 2017 to July 2018 were served as the modeling group, the patients with needs of CCU had 125 cases, and the patients without needs of CCU had 529 cases; 151 patients from August 2018 to October 2018 were served as the validation group, the patients with needs of CCU had 28 cases, and the patients without needs of CCU had 123 cases. Binary Logistic regression analysis was used to establish the risk prediction model and determine the score standards. The critical value was determined according to the best Youden index of receiver operating characteristic (ROC) curve.Results:Among 805 patients with STEMI, 153 cases (19.01%) had the needs of CCU, and the most common reason was pump failure (heart failure and cardiogenic shock, 113 cases). In the modeling group, age (60 to 74 years old, OR = 1.513, 95% CI 0.945 to 2.424, P = 0.085; ≥75 years old, OR = 2.740, 95% CI 1.371 to 5.478, P = 0.004), total ischemic time>4 h ( OR = 1.701, 95% CI 1.022 to 2.831, P = 0.041), admission shock index ≥0.8 ( OR = 1.910, 95% CI 1.178 to 3.099, P = 0.009), multi-vessel disease ( OR = 2.090, 95% CI 1.272 to 3.432, P = 0.004), preoperative diseased vessels thrombolysis in myocardial ischemia (TIMI) blood flow grade 0 ( OR = 2.099, 95% CI 1.313 to 3.353, P = 0.002), acute anterior myocardial infarction ( OR = 3.696, 95% CI 2.347 to 5.819, P<0.001) and previous history of stroke ( OR = 3.927, 95% CI 2.057 to 7.500, P<0.001) were independent risk factors for CCU needs in STEMI patients undergoing PCI. The scoring criteria were as followings: age<60 years old was given 0 score, 60 to 74 years old 1 score, ≥75 years old 2 score; total ischemic time>4 h in 1 score, admission shock index ≥0.8 2 scores, multi-vessel disease 2 scores, preoperative diseased vessels TIMI blood flow grade 0 2 scores, acute anterior myocardial infarction 3 scores, previous history of stroke 3 scores, and the total score was 15 scores. The patients with 0 to 6 scores were low-risk, and the patients with 7 to 15 scores were high-risk. ROC curve analysis result showed that, in modeling group, the area under curve (AUC) of risk prediction score for predicting the needs of CCU in STEMI patients was 0.740 (95% CI 0.692 to 0.788, P = 0.580); in validation group, the AUC of risk prediction score for predicting the needs of CCU in STEMI patients was 0.755 (95% CI 0.658 to 0.853, P = 0.755). Conclusions:A predictive risk score based on seven risk factors such as age, total ischemic time, admission shock index, multi-vessel disease, preoperative diseased vessels TIMI blood flow grade, acute anterior myocardial infarction and previous history of stroke is constructed in order to predict the needs of CCU in STEMI patients with stable condition who receive PCI treatment. It can be used to help doctors to identify high-risk patients before the admission to CCU, thus providing simple and practical clinical tool for rational allocation of limited CCU resources.

Modern research on detection technology of exogenous pollutants in Chinese materia medica / 中草药

The residues of exogenous pollutants in Chinese materia medica (CMM) have become an important cause of adverse reactions of CMM, including agricultural/veterinary drug residues, heavy metal contamination, mycotoxin residues, pathogenic microbial contamination and other organic pollutant residues according to their sources. This paper reviews the modern research on inspection objects and detection methods of main exogenous pollutants in CMM, with view to providing reference and basis for supplementing, perfecting and improving the quality and safety system of CMM.

Ethanol decreases radiosensitivity of human breast cancer MCF-7 cells / 中华放射医学与防护杂志

Objective To investigate the effect of ethanol on radiosensitivity of human breast cancer MCF-7 cells.Methods Human breast cancer MCF-7 cells were divided into four groups including control group,ethanol treatment group,X-ray exposed group,and ethanol combined with X-ray group.Clonogenic assay was used to determine cell survival.Flow cytometry was employed to analyze cell cycle progression.Annexin V-FITC kit was used to determine cell apoptosis induction.Results Ethanol(50 and 100 mmol/L,50 h)had no influence on MCF-7 cell growth( t =0.82,1.15,P ＞0.05 ).The radiosensitivity of MCF-7 cells was reduced when the cells were pretreated with 50 mmol/L ethanol (t =4.15,P ＜0.05)and 100 mmol/L ethanol ( t =10.28,P ＜ 0.05 ) for 2 h. Compared with irradiation with X-ray alone,ethanol treatment decreased G2/M phase arrest(t =7.18,P ＜0.05) and sub-G1population(an indicator of apoptosis induction) ( t =5.39,P ＜ 0.05).A decrease of advanced and early apoptosis in the cells pretreated with ethanol was also confirmed by Annexin V-FITC apoptosis assay( t =4.86,7.59,P ＜ 0.05 ).Conclusions Ethanol causes radioresistance in human breast cancer MCF-7 cells,where the decreases of radiation-induced G2/M phase arrest and apoptosis may be involved.