基于集成神经网络的类风湿关节炎中医证候分类研究

目的 针对基于AI技术的类风湿关节炎（RA）中医证候多标签分类中存在标签关联性差、泛化性能低等问题,提出构建一种集成神经网络模型来实现RA中医证候分类,并探究其中的特征重要性和风险因素,为RA的诊断和治疗提供参考。方法 本文提出一种集成神经网络模型实现RA中医证候分类。该模型采用一种基于多层神经网络的基分类器提取临床RA多标签样本的深层特征,增强RA特征区分度,根据协方差理论衡量标签相关性,调节分类器链的输入空间,减少RA错误信息传播和冗余度,采用集成学习方法减小分类器链中不合理标签序列对RA特征分类的影响。结果 该模型在10折交叉验证性能参数中表现出优秀的性能,其中汉明损失、1-错误率、准确率和F1值分别为0.0036、0.0248、97.52%、99.18%。与其他常用多标签分类器相比,该模型的性能更为优秀具有更好的分类性能。此外,本文分析了RA中医证候特征重要性,并挖掘了潜在的风险因素。结论 基于集成神经网络模型的RA中医证候分类器具有较高的分类精度和效率,对于RA的临床诊断和治疗具有重要参考价值。     

Agar Biopolymer Films for Biodegradable Packaging: A Reference Dataset for Exploring the Limits of Mechanical Performance

This article focuses on agar biopolymer films that offer promise for developing biodegradable packaging, an important solution for reducing plastics pollution. At present there is a lack of data on the mechanical performance of agar biopolymer films using a simple plasticizer. This study takes a Design of Experiments approach to analyze how agar-glycerin biopolymer films perform across a range of ingredients concentrations in terms of their strength, elasticity, and ductility. Our results demonstrate that by systematically varying the quantity of agar and glycerin, tensile properties can be achieved that are comparable to agar-based materials with more complex formulations. Not only does our study significantly broaden the amount of data available on the range of mechanical performance that can be achieved with simple agar biopolymer films, but the data can also be used to guide further optimization efforts that start with a basic formulation that performs well on certain property dimensions. We also find that select formulations have similar tensile properties to thermoplastic starch (TPS), acrylonitrile butadiene styrene (ABS), and polypropylene (PP), indicating potential suitability for select packaging applications. We use our experimental dataset to train a neural network regression model that predicts the Young’s modulus, ultimate tensile strength, and elongation at break of agar biopolymer films given their composition. Our findings support the development of further data-driven design and fabrication workflows.     

Does my high blood pressure improve your survival? Overall and subgroup learning curves in health

Learning curves in health are of interest for a wide range of medical disciplines, healthcare providers, and policy makers. In this paper, we distinguish between three types of learning when identifying overall learning curves: economies of scale, learning from cumulative experience, and human capital depreciation. In addition, we approach the question of how treating more patients with specific characteristics predicts provider performance. To soften collinearity problems, we explore the use of least absolute shrinkage and selection operator regression as a variable selection method and Theil–Goldberger mixed estimation to augment the available information. We use data from the Belgian Transcatheter Aorta Valve Implantation (TAVI) registry, containing information on the first 860 TAVI procedures in Belgium. We find that treating an additional TAVI patient is associated with an increase in the probability of 2‐year survival by about 0.16%‐points. For adverse events like renal failure and stroke, we find that an extra day between procedures is associated with an increase in the probability for these events by 0.12%‐points and 0.07%‐points, respectively. Furthermore, we find evidence for positive learning effects from physicians' experience with defibrillation, treating patients with hypertension, and the use of certain types of replacement valves during the TAVI procedure.     

Applicability Assessment of Different Materials for Standards Ensuring Comparability of Optical and Tactile Coordinate Measurements

Multisensor CMMs are systems with an established position on the market, but their popularity still grows, as they provide access to the advantages offered by tactile and contactless measurement methods. Yet there are still questions of the comparability of results obtained using the optical and tactile operation modes of multisensor system. This phenomenon can be assessed by measuring appropriate gauges, most often reference rings or spheres. Due to the completely different nature of probing processes for tactile and contactless measurements, the material from which reference object is made may significantly affect measurement results. In order to assess the influence of this factor on measurement accuracy, three reference spheres made from different materials were measured on optical multisensor CMMs. Measurements involved tactile measurements as well as optical measurements made using different probing systems: a video probe and white light sensor. Results obtained from performed experiments show large differences depending on the material used for spherical standard production. On the basis of obtained results, it can be stated that the best material for a reference object that can be used for comparability tests of tactile and optical measurements is a composite of alumina with at least one oxidic additive.     

Machine Learning Approaches for Monitoring of Tool Wear during Grey Cast-Iron Turning

The dynamic development of new technologies enables the optimal computer technique choice to improve the required quality in today’s manufacturing industries. One of the methods of improving the determining process is machine learning. This paper compares different intelligent system methods to identify the tool wear during the turning of gray cast-iron EN-GJL-250 using carbide cutting inserts. During these studies, the experimental investigation was conducted with three various cutting speeds vc (216, 314, and 433 m/min) and the exact value of depth of cut a_p and federate f. Furthermore, based on the vibration acceleration signals, appropriate measures were developed that were correlated with the tool condition. In this work, machine learning methods were used to predict tool condition; therefore, two tool classes were proposed, namely usable and unsuitable, and tool corner wear VBc = 0.3 mm was assumed as a wear criterium. The diagnostic measures based on acceleration vibration signals were selected as input to the models. Additionally, the assessment of significant features in the division into usable and unsuitable class was caried out. Finally, this study evaluated chosen methods (classification and regression tree, induced fuzzy rules, and artificial neural network) and selected the most effective model.     

Application of Machine Learning Approaches to Predict Postnatal Growth Failure in Very Low Birth Weight Infants

PurposeThe aims of the study were to develop and evaluate a machine learning model with which to predict postnatal growth failure (PGF) among very low birth weight (VLBW) infants.Materials and MethodsOf 10425 VLBW infants registered in the Korean Neonatal Network between 2013 and 2017, 7954 infants were included. PGF was defined as a decrease in Z score >1.28 at discharge, compared to that at birth. Six metrics [area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity, specificity, and F1 score] were obtained at five time points (at birth, 7 days, 14 days, 28 days after birth, and at discharge). Machine learning models were built using four different techniques [extreme gradient boosting (XGB), random forest, support vector machine, and convolutional neural network] to compare against the conventional multiple logistic regression (MLR) model.ResultsThe XGB algorithm showed the best performance with all six metrics across the board. When compared with MLR, XGB showed a significantly higher AUROC (p=0.03) for Day 7, which was the primary performance metric. Using optimal cut-off points, for Day 7, XGB still showed better performances in terms of AUROC (0.74), accuracy (0.68), and F1 score (0.67). AUROC values seemed to increase slightly from birth to 7 days after birth with significance, almost reaching a plateau after 7 days after birth.ConclusionWe have shown the possibility of predicting PGF through machine learning algorithms, especially XGB. Such models may help neonatologists in the early diagnosis of high-risk infants for PGF for early intervention.     

Machine Learning Model for Classifying the Results of Fetal Cardiotocography Conducted in High-Risk Pregnancies

PurposeFetal well-being is usually assessed via fetal heart rate (FHR) monitoring during the antepartum period. However, the interpretation of FHR is a complex and subjective process with low reliability. This study developed a machine learning model that can classify fetal cardiotocography results as normal or abnormal.Materials and MethodsIn total, 17492 fetal cardiotocography results were obtained from Ajou University Hospital and 100 fetal cardiotocography results from Czech Technical University and University Hospital in Brno. Board-certified physicians then reviewed the fetal cardiotocography results and labeled 1456 of them as gold-standard; these results were used to train and validate the model. The remaining results were used to validate the clinical effectiveness of the model with the actual outcome.ResultsIn a test dataset, our model achieved an area under the receiver operating characteristic curve (AUROC) of 0.89 and area under the precision-recall curve (AUPRC) of 0.73 in an internal validation dataset. An average AUROC of 0.73 and average AUPRC of 0.40 were achieved in the external validation dataset. Fetus abnormality score, as calculated from the continuous fetal cardiotocography results, was significantly associated with actual clinical outcomes [intrauterine growth restriction: odds ratio, 3.626 (p=0.031); Apgar score 1 min: odds ratio, 9.523 (p<0.001), Apgar score 5 min: odds ratio, 11.49 (p=0.001), and fetal distress: odds ratio, 23.09 (p<0.001)].ConclusionThe machine learning model developed in this study showed precision in classifying FHR signals. This suggests that the model can be applied to medical devices as a screening tool for monitoring fetal status.     

Ferroptosis‐based molecular prognostic model for adrenocortical carcinoma based on least absolute shrinkage and selection operator regression

BackgroundThis study aimed to find ferroptosis‐related genes linked to clinical outcomes of adrenocortical carcinoma (ACC) and assess the prognostic value of the model.MethodsWe downloaded the mRNA sequencing data and patient clinical data of 78 ACC patients from the TCGA data portal. Candidate ferroptosis‐related genes were screened by univariate regression analysis, machine‐learning least absolute shrinkage, and selection operator (LASSO). A ferroptosis‐related gene‐based prognostic model was constructed. The effectiveness of the prediction model was accessed by KM and ROC analysis. External validation was done using the {"type":"entrez-geo","attrs":{"text":"GSE19750","term_id":"19750"}}GSE19750 cohort. A nomogram was generated. The prognostic accuracy was measured and compared with conventional staging systems (TNM stage). Functional analysis was conducted to identify biological characterization of survival‐associated ferroptosis‐related genes.ResultsSeventy genes were identified as survival‐associated ferroptosis‐related genes. The prognostic model was constructed with 17 ferroptosis‐related genes including STMN1, RRM2, HELLS, FANCD2, AURKA, GABARAPL2, SLC7A11, KRAS, ACSL4, MAPK3, HMGB1, CXCL2, ATG7, DDIT4, NOX1, PLIN4, and STEAP3. A RiskScore was calculated for each patient. KM curve indicated good prognostic performance. The AUC of the ROC curve for predicting 1‐, 3‐, and 5‐ year(s) survival time was 0.975, 0.913, and 0.915 respectively. The nomogram prognostic evaluation model showed better predictive ability than conventional staging systems.ConclusionWe constructed a prognosis model of ACC based on ferroptosis‐related genes with better predictive value than the conventional staging system. These efforts provided candidate targets for revealing the molecular basis of ACC, as well as novel targets for drug development.     

上海市浦东新区自动售水机卫生状况及影响因素分析

[目的]了解自动售水机选址与外表卫生状况,为改善自动售水机卫生现状提出建议。[方法]以上海市浦东新区辖区内所有的自动售水机为对象,随机抽取236台对其选址、遮雨棚设置、机器外表整洁及完整与否、出水口防护门、出水管口及取水凹口周壁等内容开展卫生学调查。[结果]调查结果表明,17．37％的自动售水机设置点周围10m范围内存在污染源;11．44％的自动售水机设置点周围地面排水不畅,有积水;2．54％的自动售水机未安装防护门和8．47％的自动售水机防护门已损坏不能正常使用;30．93％的自动售水机器外表存在各种污迹,同时有2．12％的受调查机器外壳已破损;受调查自动售水机的出水管口、取水凹口顶壁、内侧壁的细菌总数、霉菌、大肠菌群的检出率分别为78．81％、39．41％、48．30％;75．85％、81．78％、90．68％和21．19％、5．93％、15．25％。同时,保持自动售水机周边环境整洁、设置取水凹口防护门并保持正常运作、出水管外套有套管对减少或减轻上述部位的污染有着显著的意义。[结论]自动售水机经营单位应加强设备管理,注意维护设备的外表整洁,定期对取水凹口周壁、出水管口进行清洗、消毒;同时,要注意保持设备周边环境的整洁,并应在设备上加装取水凹口防护门、出水管套管等装置,维护其正常运作和洁净。     

停课不停学背景下对机能学实验虚拟实验平台建设的思考

北京中医药大学积极响应教育部"停课不停学"的要求,借助机能学实验虚拟实验平台切实保障机能学实验教学工作的顺利开展。此文通过对"停课不停学"背景下的机能学实验课程以及机能学实验虚拟实验平台进行系统思考,并且结合问卷调查、教师走访、纵向比较等方法,分析"停课不停学"背景下机能学实验虚拟实验平台的使用效果和不足之处,旨在为虚拟实验"金"平台的建设提供参考和思路。