Using machine learning to aid treatment decision and risk assessment for severe three-vessel coronary artery disease

BACKGROUNDThree-vessel disease (TVD) with a SYNergy between PCI with TAXus and cardiac surgery (SYNTAX) score of ≥ 23 is one of the most severe types of coronary artery disease. We aimed to take advantage of machine learning to help in decision-making and prognostic evaluation in such patients.METHODSWe analyzed 3786 patients who had TVD with a SYNTAX score of ≥ 23, had no history of previous revascularization, and underwent either coronary artery bypass grafting (CABG) or percutaneous coronary intervention (PCI) after enrollment. The patients were randomly assigned to a training group and testing group. The C4.5 decision tree algorithm was applied in the training group, and all-cause death after a median follow-up of 6.6 years was regarded as the class label.RESULTSThe decision tree algorithm selected age and left ventricular end-diastolic diameter (LVEDD) as splitting features and divided the patients into three subgroups: subgroup 1 (age of ≤ 67 years and LVEDD of ≤ 53 mm), subgroup 2 (age of ≤ 67 years and LVEDD of > 53 mm), and subgroup 3 (age of > 67 years). PCI conferred a patient survival benefit over CABG in subgroup 2. There was no significant difference in the risk of all-cause death between PCI and CABG in subgroup 1 and subgroup 3 in both the training data and testing data. Among the total study population, the multivariable analysis revealed significant differences in the risk of all-cause death among patients in three subgroups.CONCLUSIONSThe combination of age and LVEDD identified by machine learning can contribute to decision-making and risk assessment of death in patients with severe TVD. The present results suggest that PCI is a better choice for young patients with severe TVD characterized by left ventricular dilation.

Coronary artery disease (CAD) is the leading cause of death and disability worldwide.^[1] Three-vessel disease (TVD) is the most severe form of CAD and is characterized by significant stenosis in all three major coronary arteries. The application of myocardial revascularization techniques, including coronary artery bypass grafting (CABG) and percutaneous coronary intervention (PCI), has significantly improved the clinical outcomes of patients with severe CAD. CABG has traditionally been the standard therapy for complex coronary lesions, including TVD.^[2] In recent years, with the advancements in PCI technology and the accumulation of operators’ experience, the incidence of periprocedural and long-term adverse events of PCI has substantially decreased, and PCI has been gradually applied in the treatment of TVD.^[3,4] Current guidelines recommend use of the SYNergy between PCI with TAXus and cardiac surgery (SYNTAX) score and diabetes status to guide the revascularization strategy for patients with TVD.^[5,6] Current practice guidelines do not recommend PCI for patients with TVD with a SYNTAX score of ≥ 23. However, using the SYNTAX score to guide clinical decision-making between PCI and CABG remains controversial, and its reasonability has been questioned since a newly published meta-analysis showed no significant association between the SYNTAX score and the comparative effectiveness of PCI and CABG.^[7] Moreover, the SYNTAX score is a quantitative indicator of the anatomical complexity of TVD and does not include clinical variables that may have significant effects on the patient’s prognosis. Whether some patients with specific clinical characteristics can obtain a comparable or even greater survival benefit from PCI than from CABG is unclear. Moreover, risk assessment for patients with TVD after revascularization therapy remain challenging.^[8–10]Machine learning has recently emerged as an important research method and has been successfully applied in many scientific fields, including clinical medicine.^[11–13] The decision tree algorithm, a common approach in machine learning, can handle non-linearity, heterogeneous effects, and high-dimensional features and partition a trial population into subgroups characterized by multiple simultaneous characteristics.^[14] In the present study involving a large cohort of patients with TVD with a SYNTAX score of ≥ 23, we employed a decision tree algorithm to generate specific subgroups, compared the long-term prognosis between patients who underwent PCI or CABG in each subgroup, and conducted a comparative analysis of the long-term prognosis between subgroups generated by machine learning. We evaluated whether machine learning can help in selecting the optimal revascularization method and assessing risk in patients with severe TVD.     

宝鸡市2000—2007年乙型肝炎流行病学特征和控制策略分析

目的了解宝鸡市乙型肝炎发病情况及流行病学特征，为制定控制策略和措施提供科学依据。方法采用描述流行病学方法，对2000-2007年宝鸡市乙型肝炎疫情资料进行统计分析。结果2000～2004年各年龄组发病率呈上升趋势，2005年起各年龄组发病率均有所下降，特别是14岁以下儿童发病率下降比较明显。农村发病明显高于城区。发病构成中农民所占比例最高，占乙型肝炎发病总数的51．85％，幼托儿童和散居儿童发病构成呈下降趋势。结论14岁以下儿童乙肝免疫防治策略已初见成效。应在加强新生儿及儿童乙型肝炎免疫接种工作的同时，加大对中青年及农村劳动人口乙型肝炎疫苗的免疫接种工作。     

2种不同弹力纤维染色方法对肿瘤侵犯判读结果的对比研究

目的 比较Victoria blue法(A组)和Verhoeff法(B组)弹力纤维染色在染色过程、染色时间、染色效果方面对肺癌胸膜侵犯和结直肠癌浆膜或静脉侵犯判读的差异。方法 A组、B组均分别纳入肺癌怀疑胸膜侵犯标本50例和结直肠癌怀疑浆膜或静脉侵犯标本20例,进行弹力纤维染色。对比2组染色过程、染色时间、染色效果;根据染色稳定性、清晰度、对比度等综合评价胸膜侵犯和浆膜或静脉侵犯情况,并对染色质量及判读准确性进行评分。结果 A组比B组操作简单,染色质量稳定,肿瘤细胞与脏层胸膜、浆膜或静脉的关系显示更清晰。A组判读评分高于B组,差异有统计学意义(P<0.05)。结论 Victoria blue法染色有助于准确评估肺癌的胸膜侵犯和结直肠癌浆膜或静脉的侵犯,提高判读准确性。     

扶正治癌调控肿瘤免疫研究

中医学重视人体正气在恶性肿瘤防治中的关键作用,强调"调和阴阳,以平为期",刘嘉湘教授创建"以人为本"、"顾护正气"为核心特征的"扶正治癌"学术体系,强调调控机体内在抵抗力(含免疫功能)以防治恶性肿瘤;肿瘤免疫治疗的疗效已经在泛癌种范围内得以确认,被认为是"最有可能治愈癌症"的疗法.从肿瘤免疫学角度深入研究人体"正气"的...     

儿童脑动静脉畸形出血早期诊断和显微外科治疗

目的 探讨儿童脑动静脉畸形(AVM)破裂出血急性期的诊断方法和显微外科治疗的时机与手术技术.方法 对2002年6月至2011年6月间收治的32例儿童AVM出血患者进行回顾性分析.除CTA和MRA检查外,本组行早期全脑DSA检查24例,另外入院时因出血量大发生脑疝者8例,立即行血肿清除术,其中3例病情稳定后再行DSA检查.明确诊断后根据Spetzler-Martin分级选择治疗方案.24例Spetzler-Martin分级Ⅰ～Ⅲ级AVM患者行急性期(3d内)显微外科治疗,其中栓塞后再手术2例.结果 8例急诊行显微手术血肿清除术者,术后死亡2例,镜下AVM完全切除2例,部分切除1例.病情稳定后行DSA检查证实AVM者3例,继而再行显微手术切除.24例急性期显微手术AVM切除者,术中显微镜下AVM血管团和颅内血肿完全清除.术后获DSA或CTA复查18例,均未见病灶残留.随访3-12个月.根据GOS评定:24例Sptetzler-Martin分级Ⅰ～Ⅲ级AVM患者恢复良好者21例,轻残2例,重残1例,无死亡病例.结论 DSA是儿童AVM出血早期诊断主要的检查手段.急性期显微手术可降低出血病死率和改善预后.     

迷走神经刺激术治疗药物难治性癫痫的初步研究

目的 探讨迷走神经刺激术治疗药物难治性癫痫的方法及效果. 方法 回顾性分析上海交通大学医学院附属仁济医院神经外科自2007年1月至2011年1月收治的14例药物难治性、全身性癫痫患者临床资料,其中脑炎后继发癫痫6例,外伤后继发癫痫3例,原因不明5例,所有患者均行左侧迷走神经刺激术治疗.术后3周内开机,初始刺激参数为:刺激电流0.25 mA,频率30 Hz,刺激时间30 s,间歇时间5 min,脉宽500 μs.刺激电流强度以0.25 mA为一调整单位逐渐递增,并综合其他参数调控以到达满意疗效. 结果 随访3月以上,14例患者术后发作频率平均减少63.6％,其中3例发作频率减少＜50％,11例发作频率减少≥50％,6例发作频率减少＞80％,2例发作停止.5例患者使用磁铁后发作控制得到改善. 结论 迷走神经刺激术是一种治疗药物难治性癫痫有效、安全的方法,对全身性癫痫发作患者同样有效.     

股胭动脉TASCⅡ-C、D级病变腔内治疗技术体会

目的:探讨经皮腔内血管成形术(PTA)结合支架植入术对股胭动脉TASCⅡ-C、D级病变的技术方法和治疗效果.方法:回顾性分析我院从2008年9月～2010年5月对股腘动脉硬化闭塞症TASC Ⅱ-C、D级病变的52例患者(60条肢体).采用顺行或逆行股动脉穿刺途径,通过常规技术或内膜下血管成形术(SIA)通过狭窄或闭塞性病变.进行球囊扩张成形,部分患者行支架植入,分析介入治疗技术、临床症状改善情况、并发症发生情况及随访情况.结果:56条肢体获得技术成功,成功率为93.3％(56/60),无围手术期死亡者,并发症发生率为6.67％(4/60),主要有导丝穿破血管壁及穿刺点血肿等,根据情况给予相应处理.术后第1周踝/肱指数(ABI)由术前的0.42士0.11增至术后7d的0.85士0.18(t=15.79 P ＜0.001).术后随访45例患者(51条肢体)6～22个月(平均10.7个月).术后6个月、12个月肢体一期通畅率分别为94.1％(48/51)和73.7％(28/38).术后l2个月肢体保全率和存活率分别为I00％(38/38)和89 5％(34/38).结论:血管腔内介入治疗TASCⅡ-C、D级股腘动脉硬化闭塞症的临床成功率高、并发症少、救肢率高,是安全有效的治疗方法,近期效果确切,其长期疗效尚须进一步观察.     

不同亚型髓母细胞瘤中增殖细胞核抗原的表达差异及意义

目的 探讨增殖细胞核抗原在不同病理类型髓母细胞瘤中的表达差异和临床意义.方法 对34例髓母细胞瘤(经典型61.8%,促硬纤维增生型38.2%)进行增殖细胞核抗原的免疫组化染色,测定不同类型髓母细胞瘤的增殖细胞核抗原指数.结果 经典型髓母细胞瘤的增殖细胞核抗原指数为(81.45±9.29)%,促硬纤维增生型髓母细胞瘤增殖细胞核抗原指数为(39.86±8.37)%,不同髓母细胞瘤亚型的增殖细胞核抗原指数值存在显著差异(P＜0.01).结论 增殖细胞核抗原的表达差异,为不同亚型髓母细胞瘤的生物行为学差异提供了病理学依据,增殖细胞核抗原指数可以作为髓母细胞瘤恶性程度及患者预后判断指标.     

曲美他嗪对急进高原新兵抗高原反应能力的作用

 目的 了解急进高原地区新战士生理生化指标的变化,评估曲美他嗪对急性高原反应的药物作用。方法 选取120名入高原服役新兵,随机分为曲美他嗪组和对照组。分别检测其高原反应性评分,心、肺功能,以及动脉血气及静脉血氧化应激指标。结果 与急进高原前指标比较,进入高原后战士的大部分心、肺功能、血气及氧化应激指标恶化(P<0.05);进入高原后与对照组比较,曲美他嗪组的心功能指数[(12.74±2.44 )vs (14.28±4.38)]、A-aDO₂、 H₂O₂和LA较低,pH、CAT和SOD较高(P<0.05)。结论 进入高原后,战士的心肺、酸碱平衡及抗氧化应激能力下降。曲美他嗪可明显提高战士的心功能,对酸碱平衡及抗氧化应激有一定益处,对呼吸功能则无明显作用。
     

保留幽门和迷走神经的胃部分切除手术对早期胃癌的疗效观察

目的 探讨保留幽门和迷走神经的胃部分切除手术（PPG）对早期胃癌的疗效.方法 回顾性分析1995年8月至2005年12月对52例早期胃癌患者行保留幽门和迷走神经的胃部分切除术（PPG组）的临床资料和随访结果;并与同期行远端胃切除术伴淋巴结清除的159例早期胃癌患者（对照组）的临床资料进行比较.结果 PPG组早期胃癌的淋巴结转移率为9.6%,对照组淋巴结转移率为17.0%;两组比较,差异无统计学意义（P＞0.05）.PPG组淋巴结清除范围D1为25%,D1＋α（α=No.7）为25%,D1＋β（β=No.8a和No.9）为34.6%,D2为15.3%;对照组121例（76.1%）D2以下,33例（20.7%）D2,5例（3.1%）D3;两组比较,差异无统计学意义（P＞0.05）.术后累计5年生存率PPG组为92.3%,对照组93.1%,两组差异无统计学意义（P=0.881）.其中淋巴结不同清除程度的累计5年生存率PPG组：D1为100%,D1＋α为92.3%,D1＋β为88.9%,D2为87.5%;对照组：D1为92.3%,D1＋α为93.3%,D1＋β为91.7%,D2为93.9%;两组比较,差异无统计学意义（P＞0.05）.PPG组术后的复发率为5.7%,对照组则为5.6%,两组差异无统计学意义（P＞0.05）.结论 PPG对于早期胃癌的治疗是有效的.