Determination of TTT Diagrams of Ni-Al Binary Using Neural Networks

The heat treatment of a metal is a set of heating and cooling cycles that a metal undergoes to change its microstructure and, therefore, its properties. Temperature–time–transformation (TTT) diagrams are an essential tool for interpreting the resulting microstructures after heat treatments. The present work describes a novel proposal to predict TTT diagrams of the γ′ phase for the Ni-Al alloy using artificial neural networks (ANNs). The proposed methodology is composed of five stages: (1) database creation, (2) experimental design, (3) ANNs training, (4) ANNs validation, and (5) proposed models analysis. Two approaches were addressed, the first to predict only the nose point of the TTT diagrams and the second to predict the complete curve. Finally, the best models for each approach were merged to compose a more accurate hybrid model. The results show that the multilayer perceptron architecture is the most efficient and accurate compared to the simulated TTT diagrams. The prediction of the nose point and the complete curve showed an accuracy of 98.07% and 86.41%, respectively. The proposed final hybrid model achieves an accuracy of 96.59%.     

Analysis of Unconfined Compressive Strength of Rammed Earth Mixes Based on Artificial Neural Network and Statistical Analysis

Earth materials have been used in construction as safe, healthy and environmentally sustainable. It is often challenging to develop an optimum soil mix because of the significant variations in soil properties from one soil to another. The current study analyzed the soil properties, including the grain size distribution, Atterberg limits, compaction characteristics, etc., using multilinear regression (MLR) and artificial neural networks (ANN). Data collected from previous studies (i.e., 488 cases) for stabilized (with either cement or lime) and unstabilized soils were considered and analyzed. Missing data were estimated by correlations reported in previous studies. Then, different ANNs were designed (trained and validated) using Levenberg-Marquardt (L-M) algorithms. Using the MLR, several models were developed to estimate the compressive strength of both unstabilized and stabilized soils with a Pearson Coefficient of Correlation (R²) equal to 0.2227 and 0.766, respectively. On the other hand, developed ANNs gave a higher value for R² than MLR (with the highest value achieved at 0.9883). Thereafter, an experimental program was carried out to validate the results achieved in this study. Finally, a sensitivity analysis was carried out using the resulting networks to assess the effect of different soil properties on the unconfined compressive strength (UCS). Moreover, suitable recommendations for earth materials mixes were presented.     

单腔、双腔气管插管在微创食管癌根治术中近期效果

目的比较单腔气管插管和双腔气管插管在微创食管癌根治术中近期效果的差异。方法回顾性分析福建省立医院胸外科2014年1月~2015年12月接受微创Mckeown术的94例食管癌患者的临床资料。结果单腔插管组术中出血显著少于双腔插管组（205.6±62.1 mL vs 277.9±219.9 mL,P=0.028）,左喉返神经旁淋巴结清扫数（3.4±5.5 vs 1.2±2.5,P=0.043）和纵隔淋巴结清扫数（19.1±14.2 vs 13.7±9.2,P=0.037）显著多于双腔插管组。两组手术时间、右喉返神经旁淋巴结清扫数、淋巴结清扫总数、平均住院时间、平均住ICU时间及术后并发症的发生率的差异无统计学意义。结论单腔气管插管具有费用低、操作简单、术野显露好的特点,有助于纵隔淋巴结的清扫和减少术中出血,其近期效果优于双腔支气管插管。     

肿瘤新抗原预测方法研究进展

肿瘤新抗原是一类肿瘤特异性抗原,是潜在的肿瘤免疫治疗理想靶标。由于肿瘤新抗原产生及刺激T细胞应答的生理过程复杂,如何高效地发现与鉴定肿瘤新抗原仍是一个巨大的挑战。随着肿瘤免疫基因组学数据的积累和人工智能预测方法的深入研究,研究者能够借助人工智能新算法进行肿瘤新抗原预测方法的研究,为基于肿瘤新抗原的肿瘤免疫治疗奠定坚实的基础。本文围绕肿瘤新抗原胞内处理、抗原提呈和T细胞识别等生理过程系统综述了肿瘤新抗原预测方法的进展。     

Design of Multi-Stage Roll Die Forming Process for Drum Clutch with Artificial Neural Network

The multi-stage roll die forming (RDF) process is a plastic forming process that can manufacture a transmission part with a complex shape, such as a drum clutch, by using a die set with rotational rolls. However, it is difficult to satisfy dimensional accuracy because of spring-back and unfilling. The purpose of this study is to design a multi-stage RDF process for the manufacturing of a drum clutch to improve dimensional accuracy using an artificial neural network (ANN). Finite element (FE) simulation of the multi-stage RDF process is performed to predict the dimensional accuracy according to various clearances for each stage. Moreover, the ANN is used to determine the relationship between the clearance and dimensional accuracy of the drum clutch to reduce the number of FE simulation. The results of the FE simulation and ANN are used to determine the optimal clearance for each stage of the RDF process. Finally, the drum clutch is fabricated using the determined conditions. The experimental results are in good agreement with the results of FE simulation from the aspect of outer diameter, inner diameter, thickness of outer tooth, thickness of inner tooth, and face thickness of tooth.     

Electroejaculation and assisted reproductive technologies in the treatment of anejaculatory infertility

Objective: To determine the efficacy of electroejaculation in combination with assisted reproductive technology (ART).

Design: Case series.

Setting: University fertility program.

Patient(s): One hundred twenty-one consecutive couples seeking treatment of anejaculatory infertility.

Intervention(s): Electroejaculation with IUI, or gamete intrafallopian transfer or IVF.

Main Outcome Measure(s): Pregnancy and pregnancy outcome.

Result(s): Fifty-two couples became pregnant (43%), 39 by IUI alone (32.2%). Cycle fecundity for IUI was 8.7%. No difference in cycle fecundity was seen among ovarian stimulation protocols (clomiphene citrate, 7.6%, hMG, 13.2%, and natural cycle, 11.2%). Pregnancy was unlikely when the inseminated motile sperm count was <4 million. Female management protocol and etiology of anejaculation did not affect results. Patients undergoing IVF had higher cycle fecundity (37.2%) than did those undergoing IUI. The rates of spontaneous abortion and multiple gestations were 23% and 12%, respectively.

Conclusion(s): Electroejaculation with stepwise application of ART is effective in treating anejaculatory infertility. Intrauterine insemination with the least expensive monitoring protocol should be used for most couples, because use of more expensive monitoring did not improve results. It is cost-effective to bypass IUI and proceed directly to IVF in men who require anesthesia for electroejaculation and in those with a total inseminated motile sperm count < 4 million.     

白内障术后角膜病变治疗的新进展

白内障患者晶状体超声乳化术后的角膜水肿、干眼、角膜内皮功能失代偿致大泡性角膜病变等严重影响着患者满意度和视觉质量。长期以来,穿透性角膜移植是角膜内皮功能失代偿患者视力恢复的有效方法,但角膜供体缺乏及移植后角膜内皮细胞密度降低等问题仍然无法解决。近年来,角膜内皮移植、局部角膜后弹力层撕除、人工培养角膜内皮细胞植片的移植、Rho激酶抑制剂调节角膜内皮细胞增殖等方面的进展和新手段,为白内障术后角膜内皮功能失代偿患者的治疗带来新思路。     

几种常用烧伤敷料的物理特性实验研究

目的探讨几种烧伤敷料的物理特性,为烧伤创面外用材料的选择提供依据。方法分别对非脱脂纱布、脱脂纱布及人造皮膜等几种材料的通透性、对外界污染的屏障隔离作用、对烧伤创面的保护作用、敷料的黏性进行实验。结果在抵抗外界污染方面,非脱脂纱布的抵抗力是脱脂纱布的2倍;在隔离保护烧伤创面方面,15层脱脂纱布已能有效保护创面从而防止渗液外漏;人造皮膜的通透性是刃厚皮片的3.8倍;人造皮膜与创面的黏附力是脱脂纱布的1/2。结论以非脱脂纱布作为外层敷料优于脱脂纱布,5层非脱脂纱布即可达到隔离外界污染的作用;以15层脱脂纱布作为包扎烧伤创面的敷料,可达到有效保护创面的作用;人造皮膜作为内层敷料,有利于维持创面组织细胞复苏的内环境;人造皮膜与创面的黏性较小,有利于敷料的更换。     

The Emerging Hazard of AI‐Related Health Care Discrimination

Artificial intelligence holds great promise for improved health‐care outcomes. But it also poses substantial new hazards, including algorithmic discrimination. For example, an algorithm used to identify candidates for beneficial “high risk care management” programs routinely failed to select racial minorities. Furthermore, some algorithms deliberately adjust for race in ways that divert resources away from minority patients. To illustrate, algorithms have underestimated African Americans’ risks of kidney stones and death from heart failure. Algorithmic discrimination can violate Title VI of the Civil Rights Act and Section 1557 of the Affordable Care Act when it unjustifiably disadvantages underserved populations. This article urges that both legal and technical tools be deployed to promote AI fairness. Plaintiffs should be able to assert disparate impact claims in health‐care litigation, and Congress should enact an Algorithmic Accountability Act. In addition, fairness should be a key element in designing, implementing, validating, and employing AI.