Predicting coronary heart disease in Chinese diabetics using machine learning.

Diabetes, a common chronic disease worldwide, can induce vascular complications, such as coronary heart disease (CHD), which is also one of the main causes of human death. It is of great significance to study the factors of diabetic patients complicated with CHD for understanding the occurrence of diabetes/CHD comorbidity. In this study, by analyzing the risk of CHD in more than 300,000 diabetes patients in southwest China, an artificial intelligence (AI) model was proposed to predict the risk of diabetes/CHD comorbidity. Firstly, we statistically analyzed the distribution of four types of features (basic demographic information, laboratory indicators, medical examination, and questionnaire) in comorbidities, and evaluated the predictive performance of three traditional machine learning methods (eXtreme Gradient Boosting, Random Forest, and Logistic regression). In addition, we have identified nine important features, including age, WHtR, BMI, stroke, smoking, chronic lung disease, drinking and MSP. Finally, the model produced an area under the receiver operating characteristic curve (AUC) of 0.701 on the test samples. These findings can provide personalized guidance for early CHD warning for diabetic populations.

[A method of screening the antitumor lead compounds based on the dynamic bio-response profile of cells].

The study is to report the establishment of a method of screening the antitumor compounds based on the dynamic bio-response profile of cells to make up for the shortages of conventional end-point tests such as tedious operation and low sensitivity. Based on the principle of electric impedance of cells, the real-time cell electronic sensing (RT-CES) system was used to monitor the effect of epirubicin (EPI), cisplatinum (DDP) and carboplatin (CBP) on the growth of HepG2 cells, with the cell index (CI), half maximal inhibitory concentration (IC50) and detachment curve as evaluation indexes. Meanwhile, cell counting kit-8 (CCK-8) and microscopy were applied for verification. The results showed that CI curve could sensitively real-time profile the inhibitory effect of model drugs on HepG2 cells. The IC50 of EPI, DDP and CBP were 0.53 +/- 0.04, 9.79 +/- 0.26 and 597.00 +/- 3.79 microg x mL(-1), respectively. What's more, the significant differences of detachment curves of the three drugs indicated that their functional mechanisms might be different, this is consistent with the literature. The RT-CES system with non-invasive, label-free and real-time characteristics could be used to monitor the bio-response profile of the three drugs to HepG2 cells, allowing to qualitatively and quantitatively distinguish the antitumor activities of the three drugs, and could be a complementary method for the present screening of antitumor compounds.

Clinical and pathological study of 328 cases of actinic keratosis in eastern chinese patients.

BACKGROUND: Actinic keratosis (AK) is prevalent and has been widely studied in fair-skinned populations. However, this is not the case in eastern countries. AK in Asians has not been so thoroughly investigated. OBJECTIVES: To analyse the clinical and pathological features of a relatively large number of cases of AK diagnosed in older Chinese patients. METHODS: Case histories of 328 patients with pathologically diagnosed AK were analysed retrospectively. Their demographic, clinical, pathological and treatment data were collected for analysis of associated factors. RESULTS: Lesions were usually distributed on the face, especially the cheeks and temples. The most frequent pathological type was hypertrophic. Only 34% of the cases had been diagnosed correctly as AK before biopsy; many were mistaken for seborrhoeic keratosis. CONCLUSIONS: Most patients were elderly females and there was a higher incidence of lesions on the face, and a lower incidence on the extremities and trunk; this finding contrasts with previous investigations in fair-skinned people.