基于超声影像组学的乳腺癌预测模型的诊断性能研究

目的评估并比较基于不同机器学习算法建立的乳腺癌超声影像组学预测模型的诊断性能。 方法回顾性收集2017年1月至2019年4月就诊皖南医学院第一附属医院、有明确病理结果的乳腺肿块病例828例，以2018年8月31日为节点将其分为训练集（526例）和验证集（302例），提取肿块的超声影像组学特征并进行特征筛选，运用k最近邻（kNN）、逻辑回归（LR）、朴素贝叶斯（NB）、随机森林（RF）和支持向量机（SVM）5种机器学习算法分别建立预测模型，使用重复交叉验证方法做内部验证，计算比较各模型的敏感度、特异度、阳性预测值（PPV）和阴性预测值（NPV），并实施外部验证，绘制ROC曲线并比较ROC曲线下面积（AUC）以评价模型的鉴别诊断性能，绘制校准曲线评价模型校准度。 结果从提取的109个影像组学特征中筛选出19个特征建立了5种机器学习算法模型。在内部验证中，5种模型的敏感度、特异度、PPV、NPV比较，总体差异均有统计学意义（P均＜0.001）。LR模型的特异度、PPV、NPV中位数分别为0.769、0.816、0.778，3项指标均高于其他4种模型；敏感度中位数为0.824，高于kNN、RF和SVM模型。此外，SVM模型的特异度、PPV、NPV中位数分别为0.706、0.774、0.759，虽均低于LR模型，但均高于其他3种模型。在外部验证中，LR、SVM、RF、kNN和NB的AUC依次为0.890、0.832、0.821、0.746和0.703，其中LR与SVM的AUC差异有统计学意义（P=0.012）；此外，各模型在校准性能上表现并不一致，LR和SVM模型的校准曲线显示乳腺癌实际概率与预测概率之间的一致性较好。 结论以超声影像组学特征为基础，运用不同机器学习算法建立的乳腺癌超声预测模型，均表现出较高的诊断性能，其中LR模型表现最为突出；选择合适的机器学习算法有助于进一步提高预测模型的诊断性能，提供更加准确的量化预测结果。     

胃癌患者心理痛苦的研究进展

综述心理痛苦的概念与内涵，胃癌患者的心理痛苦水平、评估工具、影响因素及干预措施。提出需构建胃癌患者心理痛苦模型，实施针对性的护理措施以减轻胃癌患者心理痛苦水平，提高生活质量。     

Comparison of accuracy of intraocular lens power calculation for eyes with an axial length greater than 29.0 mm

International Ophthalmology - To evaluate and compare the accuracy of six different formulas (Emmetropia Verifying Optical version 2.0, Kane, SRK/T, Barrett Universal II, Haigis and Olsen) in...     

Effects of Angiotensin II Receptor Blockers on Ventricular Hypertrophy in Hypertrophic Cardiomyopathy: A Meta-Analysis of Randomized Controlled Trials

Cardiovascular Drugs and Therapy - Animal studies have suggested that angiotensin II receptor blockers (ARBs) can attenuate or reverse the progression of hypertrophic cardiomyopathy, while clinical...     

Proteomics analysis of lysine crotonylation and 2-hydroxyisobutyrylation reveals significant features of systemic lupus erythematosus

Introduction/objectives

To seek significant features of systemic lupus erythematosus (SLE) by utilizing bioinformatics analysis.

Method

Liquid chromatography-tandem mass spectrometry (LC–MS/MS) was used to quantify lysine crotonylation (Kcr) and lysine 2-hydroxyisobutyrylation (Khib) in peripheral blood mononuclear cells (PBMCs) of systemic lupus erythematosus (SLE) patients and normal controls.

Results

Seventy-six differentially modified proteins (DMPs) dually modified by Kcr and Khib were identified between SLE patients and healthy people. GO enrichment analysis prompted significant enrichment of seventy-six DMPs in MHC class II protein complex binding and leukocyte migration. KEGG pathways were enriched in antigen processing and presentation pathway and leukocyte transendothelial migration pathway. Six DMPs (CLTC, HSPA1B, HSPA8, HSP90AB1, HSPD1, and PDIA3) were identified in antigen processing and presentation pathway, of which HSPA8 was the core protein. Significant changes of Kcr and Khib in HSPA8 may increase ATP hydrolysis and promote antigen binding to MHC II molecule. In leukocyte transendothelial migration pathway, 7 DMPs (ACTN1, ACTN4, EZR, MSN, RAC1, RHOA, and VCL) were identified. MSN was the protein with the most modification sites in this pathway. In amino terminal ferm region of MSN, Kcr and Khib expression change may lead to the adhesion between leukocytes and endothelial cells, which was an important step of leukocyte migration.

Conclusion

Kcr and Khib may promote the antigen presentation and jointly regulate the tissue damage mediated by leukocyte migration in SLE patients, which may play key roles in the pathogenesis of SLE probably.

The China birth cohort study (CBCS)

European Journal of Epidemiology - The China birth cohort study (CBCS) is a prospective longitudinal, mega-cohort study and the first national-based birth cohort study, aiming to establish a birth...     

基于CiteSpace的结直肠癌患者生命质量研究

目的：通过中英文文献了解结直肠癌患者生命质量研究现状及发展趋势。方法：运用CiteSpace对中国知网（CNKI）、万方数据知识服务平台、中国生物医学文献数据库、Web of Science核心数据集、PubMed、Cochrane Library中收录的关于结直肠癌患者生命质量研究的中英文文献进行可视化分析。结果：检索得到中文文献1 285篇，英文文献871篇，中英文文献发文量均呈上升趋势，相关研究关注的重点主要是结直肠癌患者造口、抑郁、免疫、肠道功能、化疗及化疗药物，但机构之间、学者之间合作程度及研究类型等方面存在一定差异。结论：中文文献相关研究起步晚、发展快，但在研究质量与研究深度等方面与英文文献相比还有一定差距；国内学者之间、机构之间应加强合作，关心患者肠道功能、心理状况，提高患者体力活动水平，开展更多高质量研究。