Validation of electronic health record phenotyping of bipolar disorder cases and controls.
Validation of electronic health record phenotyping of bipolar disorder cases and controls.
复制标题
DOI：
10.1176/appi.ajp.2014.14030423
复制
发表时间：
2015-04
期刊：
影响因子：
--
通讯作者：
International Cohort Collection for Bipolar Disorder Consortium
中科院分区：
文献类型：
--
作者：
Castro VM;Minnier J;Murphy SN;Kohane I;Churchill SE;Gainer V;Cai T;Hoffnagle AG;Dai Y;Block S;Weill SR;Nadal-Vicens M;Pollastri AR;Rosenquist JN;Goryachev S;Ongur D;Sklar P;Perlis RH;Smoller JW;International Cohort Collection for Bipolar Disorder Consortium
验证电子健康记录（EHRs）在双相情感障碍（BD）和对照诊断中的应用。电子病历数据来自20多年来420多万患者的医疗保健系统。由经验丰富的临床医生进行图表审查，以识别与双相障碍诊断一致或不一致的文本特征和编码数据。使用自然语言处理（NLP）训练具有95%特异性的诊断算法，用于对双相障碍进行分类。过滤后的编码数据用于导出三个额外的病例分类规则和一个用于对照组的分类规则。基于EHR的BD和亚表型诊断的阳性预测值（PPV）是通过对190例患者样本进行EHR盲诊断的训练有素的临床医生直接半结构化访谈诊断来计算的。nlp定义BD的PPV为0.85。基于严格过滤的编码分类实现了0.79的PPV，但基于不太严格标准的BD分类表现不佳。在直接访谈中，没有ehr分类的对照组被诊断为BD （PPV = 1.0）。对于大多数亚表型，ppv超过0.80。以ehr为基础的分类被用于累积4500例BD病例和5000例对照进行遗传分析。与金标准的诊断访谈相比，半自动化的电子病历挖掘可用于确定BD病例和对照，具有高特异性和预测性。电子病历为遗传和临床研究提供了高通量表型分析的强大资源。
To validate the use of electronic health records (EHRs) for the diagnosis of bipolar disorder (BD) and controls. EHR data were obtained from a healthcare system of more than 4.2 million patients spanning more than 20 years. Chart review by experienced clinicians was used to identify text features and coded data consistent or inconsistent with a diagnosis of BD. Natural language processing (NLP) was used to train a diagnostic algorithm with 95% specificity for classifying BD. Filtered coded data were used to derive three additional classification rules for cases and one for controls. The positive predictive value (PPV) of EHR-based BD and subphenotype diagnoses was calculated against direct semi-structured interview diagnoses by trained clinicians blind to EHR diagnosis in a sample of 190 patients. The PPV of NLP-defined BD was 0.85. A coded classification based on strict filtering achieved a PPV of 0.79, but BD classifications based on less stringent criteria performed less well. None of the EHR-classified controls was given a diagnosis of BD on direct interview (PPV = 1.0). For most subphenotypes, PPVs exceeded 0.80. The EHR-based classifications were used to accrue 4500 BD cases and 5000 controls for genetic analyses. Semi-automated mining of EHRs can be used to ascertain BD cases and controls with high specificity and predictive value compared to a gold-standard diagnostic interview. EHRs provide a powerful resource for high-throughput phenotyping for genetic and clinical research.
登录
查看更多内容
影响因子：
--
作者：
Simpson, SG;McMahon, FJ;DePaulo, JR
通讯作者：
DePaulo, JR
影响因子：
30.8
作者：
Ripke, Stephan;O'Dushlaine, Colm;Chambert, Kimberly;Moran, Jennifer L.;Kaehler, Anna K.;Akterin, Susanne;Bergen, Sarah E.;Collins, Ann L.;Crowley, James J.;Fromer, Menachem;Kim, Yunjung;Lee, Sang Hong;Magnusson, Patrik K. E.;Sanchez, Nick;Stahl, Eli A.;Williams, Stephanie;Wray, Naomi R.;Xia, Kai;Bettella, Francesco;Borglum, Anders D.;Bulik-Sullivan, Brendan K.;Cormican, Paul;Craddock, Nick;de Leeuw, Christiaan;Durmishi, Naser;Gill, Michael;Golimbet, Vera;Hamshere, Marian L.;Holmans, Peter;Hougaard, David M.;Kendler, Kenneth S.;Lin, Kuang;Morris, Derek W.;Mors, Ole;Mortensen, Preben B.;Neale, Benjamin M.;O'Neill, Francis A.;Owen, Michael J.;Milovancevic, Milica Pejovic;Posthuma, Danielle;Powell, John;Richards, Alexander L.;Riley, Brien P.;Ruderfer, Douglas;Rujescu, Dan;Sigurdsson, Engilbert;Silagadze, Teimuraz;Smit, August B.;Stefansson, Hreinn;Steinberg, Stacy;Suvisaari, Jaana;Tosato, Sarah;Verhage, Matthijs;Walters, James T.;Bramon, Elvira;Corvin, Aiden P.;O'Donovan, Michael C.;Stefansson, Kari;Scolnick, Edward;Purcell, Shaun;McCarroll, Steven A.;Sklar, Pamela;Hultman, Christina M.;Sullivan, Patrick F.
通讯作者：
Sullivan, Patrick F.
影响因子：
30.8
作者：
Zeggini, Eleftheria;Scott, Laura J.;Saxena, Richa;Voight, Benjamin F.;Marchini, Jonathan L.;Hu, Tianle;de Bakker, Paul I. W.;Abecasis, Goncalo R.;Almgren, Peter;Andersen, Gitte;Ardlie, Kristin;Bostroem, Kristina Bengtsson;Bergman, Richard N.;Bonnycastle, Lori L.;Borch-Johnsen, Knut;Burtt, Noel P.;Chen, Hong;Chines, Peter S.;Daly, Mark J.;Deodhar, Parimal;Ding, Chia-Jen;Doney, Alex S. F.;Duren, William L.;Elliott, Katherine S.;Erdos, Michael R.;Frayling, Timothy M.;Freathy, Rachel M.;Gianniny, Lauren;Grallert, Harald;Grarup, Niels;Groves, Christopher J.;Guiducci, Candace;Hansen, Torben;Herder, Christian;Hitman, Graham A.;Hughes, Thomas E.;Isomaa, Bo;Jackson, Anne U.;Jorgensen, Torben;Kong, Augustine;Kubalanza, Kari;Kuruvilla, Finny G.;Kuusisto, Johanna;Langenberg, Claudia;Lango, Hana;Lauritzen, Torsten;Li, Yun;Lindgren, Cecilia M.;Lyssenko, Valeriya;Marvelle, Amanda F.;Meisinger, Christa;Midthjell, Kristian;Mohlke, Karen L.;Morken, Mario A.;Morris, Andrew D.;Narisu, Narisu;Nilsson, Peter;Owen, Katharine R.;Palmer, Colin N. A.;Payne, Felicity;Perry, John R. B.;Pettersen, Elin;Platou, Carl;Prokopenko, Inga;Qi, Lu;Qin, Li;Rayner, Nigel W.;Rees, Matthew;Roix, Jeffrey J.;Sandbaek, Anelli;Shields, Beverley;Sjogren, Marketa;Steinthorsdottir, Valgerdur;Stringham, Heather M.;Swift, Amy J.;Thorleifsson, Gudmar;Thorsteinsdottir, Unnur;Timpson, Nicholas J.;Tuomi, Tiinamaija;Tuomilehto, Jaakko;Walker, Mark;Watanabe, Richard M.;Weedon, Michael N.;Willer, Cristen J.;Illig, Thomas;Hveem, Kristian;Hu, Frank B.;Laakso, Markku;Stefansson, Kari;Pedersen, Oluf;Wareham, Nicholas J.;Barroso, Ines;Hattersley, Andrew T.;Collins, Francis S.;Groop, Leif;McCarthy, Mark I.;Boehnke, Michael;Altshuler, David
通讯作者：
Altshuler, David
影响因子：
2.9
作者：
Castro VM;Gallagher PJ;Clements CC;Murphy SN;Gainer VS;Fava M;Weilburg JB;Churchill SE;Kohane IS;Iosifescu DV;Smoller JW;Perlis RH
通讯作者：
Perlis RH
影响因子：
17.7
作者：
Regier, Darrel A.;Narrow, William E.;Kupfer, David J.
通讯作者：
Kupfer, David J.