Deep Phenotyping and Prediction of Long-term Cardiovascular Disease: Optimized by Machine Learning

BackgroundPrediction of cardiovascular disease (CVD) is important in clinical practice. Machine learning (ML) may offer an improved alternative to current CVD risk stratification in individual patients. We aim to identify important predictors and compare ML models with traditional models according to their prediction performance in a large long-term follow-up cohort.MethodsThe Atherosclerosis Risk in Communities (ARIC) study was designed to study the progression of subclinical disease to cardiovascular events over a 25-year follow-up period. All phenotypic variables at visit 1 were obtained. All-cause death, CVD, and coronary heart disease were the outcomes for analysis. The ML framework involved variable selection using the random survival forest (RSF) method, model building, and 5-fold cross-validation. Model performance was evaluated by discrimination using the Harrell concordance index (C-index), accuracy using the Brier score (BS), and interpretability using the number of variables in the model.ResultsOf the 14,842 participants in ARIC, the average age was 54.2 years, with 45.2% male and 26.2% Black participants. Thirty-eight unique variables were selected in the RSF top 20 importance ranking of all 6 outcomes. Aging, hypertension, glucose metabolism, renal function, coagulation, adiposity, and sodium retention dominated the predictions of all outcomes. The ML models outperformed the regression models and established risk scores with a higher C-index, lower BS, and varied interpretability.ConclusionsThe ML framework is useful for identifying important predictors of CVD and for developing models with robust performance compared with existing risk models.     

电阻抗断层成像技术在儿科呼吸系统疾病诊治中的应用

电阻抗断层成像技术(electrical impedance tomography,EIT)作为一项新兴的功能性成像技术,具有无损伤、便携、图像监护等突出特点。肺功能成像是目前EIT最主要的应用领域,可以实现实时动态监测肺通气及血流灌注。本文对肺EIT在儿童呼吸系统疾病及其诊疗过程中的应用基础及临床研究进展进行总结,为未来EIT技术在儿科临床急救领域的推广应用提供帮助。     

Next-generation sequencing through multigene panel testing for the diagnosis of hereditary epidermolysis bullosa in Chinese population

Epidermolysis bullosa (EB) is a heritable blistering disorder. We performed a next-generation sequencing-based multigene panel test and successfully predicted 100% of the EB types, including, 36 EB simplex (EBS), 13 junctional EB (JEB), 86 dystrophic EB (DEB), and 3 Kindler EB. Chinese JEB and recessive DEB (RDEB) patients have relatively mild phenotypes; for severe type separately accounts for 45.5% and 23.8%, respectively. We identified 96 novel and 49 recurrent pathogenic variants in 11 genes, although we failed to detect the second mutation in one JEB and five RDEB patients. We identified one novel p.E475K mosaic mutation in the clinically normal mother of one out of 13 EBS patients with KRT5 mutations, one recurrent p.G2034R mosaic mutation, and one novel p.G2043R mosaic mutation in the clinically normal relatives of two out of 19 dominant DEB patients. This study shows that next-generation technology could be an effective tool in diagnosing EB.     

甲胎蛋白阴性肝癌的临床特点分析

目的:分析甲胎蛋白(alphafetoprotein,AFP)阴性肝癌的临床特点。方法:对11年间(1994-2004年)76例AFP阴性肝癌患者和2年间(2002-2003年)102例AFP阳性肝癌患者在性别、临床表现、合并疾病[乙型肝炎和(或)肝硬化]、Child-Pugh分级和γ-谷氨酰转移酶(γ-glutamyltransferase,γGT)方面进行对比分析。结果:AFP阴性肝癌患者消瘦乏力、腹痛、腹部肿块的症状少于AFP阳性肝癌患者(分别为55.3%vs82.4%、56.6%vs75.5%、13.2%vs45.1%,均P<0.05),合并乙型肝炎较AFP阳性肝癌少(68.4%vs93.1%,P<0.05),Child-Pugh分级中A级显著多于AFP阳性肝癌(56.6%vs32.4%,P<0.05),而C级显著少于AFP阳性肝癌(2.6%vs16.7%,P<0.05);AFP阴性肝癌患者中γGT异常者的比例少于AFP阳性肝癌(64.5%vs84.3%,P<0.05)。两组患者在黄疸、腹水、肝硬化和Child-Pugh分级中B级方面差异无显著性。结论:AFP阴性肝癌患者临床表现较轻且缺乏特异性,诊断...     

原发性肾上腺皮质癌的诊治分析

目的总结和提高原发性肾上腺皮质癌的诊治水平。方法回顾分析16例肾上腺皮质癌患者的临床资料。根据其临床症状、内分泌功能测定、影像学特点做出诊断，手术治疗并随访。结果16例患者中，内分泌功能紊乱者8例，以库欣征、性征异常、醛固酮增多症为主。超声、CT、MRI测定肿瘤直径为4．8～19．5cm，平均7．8cm。3例有远处转移。行根治性切除术13例，侵及同侧肾脏者做肾和肾上腙切除术2例，肾上腺肿瘤并腔静脉癌栓切除2例，腔静脉部分切除1例。病理结果：Ⅰ其耳2例，Ⅱ期8例，Ⅲ期3例，Ⅳ期3例。随访3-62个月，手术2年以上的11例患者中有6例仍存活，但1例肺转移，1例骨转移；死亡5例，平均存活26个月。结论肾上腺皮质癌患者预后差。影像学检查结合临床症状是早期诊断的关键，根治性手术是惟一有效的治疗方法。     

激活素A对人肝星状细胞系LI 90细胞增殖的影响

目的：检测激活素（ACT）A对肝星状细胞（HSC）系LI90细胞增殖的影响。方法：采用基因重组人ACT A（0．025－250ng/ml）、转化生长因子－β1（TGF－β1）、镦泡抑素（FS）处理体外培养的人HSC系LI90，采用四唑盐比色法（MTT法）检测其对细胞增殖的影响。结果：ACT A浓度在0.025-250ng/ml范围内，均可刺激LI90细胞增殖，0.025-25ng/ml浓度范围内的ACT A作用轻微，而250ng/ml的ACT A作用明显增强（P＜0．01）；相反，TGF－β1（2．5ng/ml）对LI90细胞增殖无明显影响；0．315ng/ml FS与浓度为0.25ng/ml的ACT A共同孵育可阻断ACT A促进LI90增殖的活性（P＜0．05），而0．315ng/ml FS单独作用对LI 90细胞生长明显影响。结论：ACT可促进HSC增殖，在肝纤维化发病机制中发挥重要作用。