[Machine learning algorithms for identifying autism spectrum disorder through eye-tracking in different intention videos]. / ä¸åŒæ„å›¾åœºæ™¯çœ¼åŠ¨æ³¨è§†æ¨¡å¼æœºå™¨å­¦ä¹ ç®—æ³•è¯†åˆ«å­¤ç‹¬ç—‡è°±ç³»éšœç¢çš„ç ”ç©¶.

OBJECTIVES: To investigate the differences in visual perception between children with autism spectrum disorder (ASD) and typically developing (TD) children when watching different intention videos, and to explore the feasibility of machine learning algorithms in objectively distinguishing between ASD children and TD children. METHODS: A total of 58 children with ASD and 50 TD children were enrolled and were asked to watch the videos containing joint intention and non-joint intention, and the gaze duration and frequency in different areas of interest were used as original indicators to construct classifier-based models. The models were evaluated in terms of the indicators such as accuracy, sensitivity, and specificity. RESULTS: When using eight common classifiers, including support vector machine, linear discriminant analysis, decision tree, random forest, and K-nearest neighbors (with K values of 1, 3, 5, and 7), based on the original feature indicators, the highest classification accuracy achieved was 81.90%. A feature reconstruction approach with a decision tree classifier was used to further improve the accuracy of classification, and then the model showed the accuracy of 91.43%, the specificity of 89.80%, and the sensitivity of 92.86%, with an area under the receiver operating characteristic curve of 0.909 (P<0.001). CONCLUSIONS: The machine learning model based on eye-tracking data can accurately distinguish ASD children from TD children, which provides a scientific basis for developing rapid and objective ASD screening tools.

Main Risk Factors Related to Activities of Daily Living in Non-Dialysis Patients with Chronic Kidney Disease Stage 3-5: A Case-Control Study.

INTRODUCTION: Elderly people are at increased risk of falls, disability and death due to reduced functional reserve, decline in multiple systems functions, which affects their activities of daily living (ADL) and eventually develop into frailty. The ADL assessment is conducive to early detection to avoid further serious situations. Previous studies on patients' activities of daily living with chronic kidney disease (CKD) are mainly focused on dialysis patients. Little information is available on non-dialysis patients. PATIENTS AND METHODS: A total of 303 elderly patients with CKD stage 3-5 who were admitted to our hospital were selected. ADL evaluation was performed on patients at admission, with Barthel index (BI) as the evaluation tool. They were divided into two groups based on BI (≥60 and <60). Demographic information, lifestyle and clinical profile were collected. The risk factors related to ADL were analyzed by univariate and multivariate models. RESULTS: The data of 303 patients enrolled in this study were analyzed. The average age of patients was 84.48± 7.14 years and 62.05% were male. There were 88 patients (29.04%) in BI <60 group and 215 patients (70.96%) in the BI ≥60 group. The average age of subjects in the two groups was 87.47 ± 5.85 years and 83.26± 7.28 years, respectively. On univariate analysis, ADL impairment was associated with many factors, such as age, body mass index, blood lipid, heart rate, smoking history, Charlson comorbidity index (CCI), hemoglobin, serum albumin, BNP, eGFR, etc. Multivariate logistic regression showed that age (OR 1.08, 95% CI 1.00-1.17, P=0.0390), Charlson comorbidity index (OR 4.75, 95% CI 1.17-19.30, P=0.0295), and serum albumin (OR 0.80, 95% CI 0.70-0.92, P=0.0012) were the independent risk factors of ADL impairment. CONCLUSION: Decline of ADL in CKD patients was independently correlated with age, Charlson comorbidity index and serum albumin. ADL and its influential factors in the elderly CKD patients deserve further attention.

[Simultaneous determination of four anthraquinones in Polygonum multiflorum by QAMS].

A simple, specific and selective quantitative analysis of multi-components by single marker(QAMS) method for simultaneous determination of anthraquinones and anthraquinone glycosides in Polygonum multiflorum was developed. Four main anthraquinones and its glycosides, emodin, emodin-8-O-ß-D-glucoside, physcion and physcion-8-O-ß-D-glucoside were selected as analytes to evaluate the quality of P. multiflorum. Emodin was used as the internal standard, and the relative correction factors(RCFs) between emodin and the other three anthraquinones were calculated. Comparison of the contents of the four components in 30 batches of P. multiflorum from different regions and 12 batches decoction pieces from different manufacturers by QAMS and external standard method(ESM) showed that there was no significant difference between QAMS and ESM for quantification of the four main components by using relative error results, and the QAMS method was accurate and reliable, and had a good repeatability. In addition, compared with the results calculated by the difference method between total anthraquinone and free anthraquinone in the content determination of P. multiflorum in Chinese Pharmacopoeia, the results of direct determination combined anthraquinone by QAMS were very close to that by measured the external standard method. Therefore, simultaneous quantification of four main anthraquinones by using QAMS is suitable to evaluate the quality of P. multiflorum. Then the optimized assay method of the combined anthraquinone contents showed simple and feasible, which could be replaced and improved the quantification method of the combined anthraquinone in the current Chinese Pharmacopeia.