Application of random forests methods to diabetic retinopathy classification analyses.
Application of random forests methods to diabetic retinopathy classification analyses.
复制标题
DOI：
10.1371/journal.pone.0098587
复制
发表时间：
2014
期刊：
影响因子：
3.7
通讯作者：
Ambrosius WT
中科院分区：
文献类型：
--
作者：
Casanova R;Saldana S;Chew EY;Danis RP;Greven CM;Ambrosius WT
糖尿病视网膜病变（DR）是美国和全世界失明的主要原因之一。 DR 是一种无声的疾病，可能会被忽视，直到发现时已为时已晚，无法进行有效治疗。因此，早期发现可以提高治疗干预的机会，从而减轻其影响。使用来自 3443 名 ACCORD-Eye 研究参与者的分级眼底摄影和系统数据来估计随机森林 (RF) 和逻辑回归分类器。我们研究了样本大小对分类器性能的影响，以及使用 RF 生成的类条件概率作为描述 DR 风险的指标的可能性。不同重要性的 RF 度量用于检测影响分类性能的因素。在区分有或没有 DR 的参与者时，两种类型的数据都提供了信息。基于 RF 的模型比基于逻辑回归的模型产生更高的分类精度。结合这两种类型的数据并没有提高准确性，但确实增加了对随后在四年的随访期间发生或未发生 DR 事件的健康参与者的统计歧视。 RF变量重要性标准显示，双眼微动脉瘤计数似乎在分级眼底变量的区分中发挥最重要的作用，而药物数量和糖尿病持续时间是系统变量中最相关的。我们将RF方法引入到基于眼底摄影数据的DR分类分析中。此外，我们提出了一种基于分级眼底摄影和系统数据得出的指标的 DR 风险评估方法。我们的结果表明，射频方法可能是诊断 DR 并评估其进展的宝贵工具。
Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects. Graded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance. Both types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables. We have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression.
登录
查看更多内容
DOI：
10.1056/nejmoa1001288
发表时间：
2010-07-15
期刊：
The New England journal of medicine
影响因子：
--
作者：
ACCORD Study Group;ACCORD Eye Study Group;Chew EY;Ambrosius WT;Davis MD;Danis RP;Gangaputra S;Greven CM;Hubbard L;Esser BA;Lovato JF;Perdue LH;Goff DC Jr;Cushman WC;Ginsberg HN;Elam MB;Genuth S;Gerstein HC;Schubart U;Fine LJ
通讯作者：
Fine LJ
DOI：
10.1590/s0004-27302008000300003
发表时间：
2008-04-01
期刊：
Arquivos Brasileiros de Endocrinologia & Metabologia
影响因子：
--
作者：
Esteves, Jorge;Laranjeira, Andréia F.;Canani, Luís H.
通讯作者：
Canani, Luís H.
影响因子：
5.8
作者：
Lanckriet, GRG;De Bie, T;Noble, WS
通讯作者：
Noble, WS
DOI：
10.1056/nejmoa1001282
发表时间：
2010-04-29
期刊：
The New England journal of medicine
影响因子：
--
作者：
ACCORD Study Group;Ginsberg HN;Elam MB;Lovato LC;Crouse JR 3rd;Leiter LA;Linz P;Friedewald WT;Buse JB;Gerstein HC;Probstfield J;Grimm RH;Ismail-Beigi F;Bigger JT;Goff DC Jr;Cushman WC;Simons-Morton DG;Byington RP
通讯作者：
Byington RP
影响因子：
3.5
作者：
Casanova R;Whitlow CT;Wagner B;Williamson J;Shumaker SA;Maldjian JA;Espeland MA
通讯作者：
Espeland MA