Response to Maojo and Kulikowski.
Author(s): Friedman, Charles P
DOI: 10.1136/amiajnl-2013-002120
Author(s): Friedman, Charles P
DOI: 10.1136/amiajnl-2013-002120
We define and validate an architecture for systems that identify patient cohorts for clinical trials from multiple heterogeneous data sources. This architecture has an explicit query model capable of supporting temporal reasoning and expressing eligibility criteria independently of the representation of the data used to evaluate them.
Author(s): Bache, Richard, Miles, Simon, Taweel, Adel
DOI: 10.1136/amiajnl-2013-001858
This study compares the yield and characteristics of diabetes cohorts identified using heterogeneous phenotype definitions.
Author(s): Richesson, Rachel L, Rusincovitch, Shelley A, Wixted, Douglas, Batch, Bryan C, Feinglos, Mark N, Miranda, Marie Lynn, Hammond, W Ed, Califf, Robert M, Spratt, Susan E
DOI: 10.1136/amiajnl-2013-001952
To study the relation between electronic health record (EHR) variables and healthcare process events.
Author(s): Hripcsak, George, Albers, David J
DOI: 10.1136/amiajnl-2013-001922
Celiac disease (CD) is a lifelong immune-mediated disease with excess mortality. Early diagnosis is important to minimize disease symptoms, complications, and consumption of healthcare resources. Most patients remain undiagnosed. We developed two electronic medical record (EMR)-based algorithms to identify patients at high risk of CD and in need of CD screening.
Author(s): Ludvigsson, Jonas F, Pathak, Jyotishman, Murphy, Sean, Durski, Matthew, Kirsch, Phillip S, Chute, Christophe G, Ryu, Euijung, Murray, Joseph A
DOI: 10.1136/amiajnl-2013-001924
To develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR).
Author(s): Warner, Jeremy L, Zollanvari, Amin, Ding, Quan, Zhang, Peijin, Snyder, Graham M, Alterovitz, Gil
DOI: 10.1136/amiajnl-2013-001861
Author(s): Maojo, Victor, Kulikowski, Casimir A
DOI: 10.1136/amiajnl-2013-001807
Generalizable, high-throughput phenotyping methods based on supervised machine learning (ML) algorithms could significantly accelerate the use of electronic health records data for clinical and translational research. However, they often require large numbers of annotated samples, which are costly and time-consuming to review. We investigated the use of active learning (AL) in ML-based phenotyping algorithms.
Author(s): Chen, Yukun, Carroll, Robert J, Hinz, Eugenia R McPeek, Shah, Anushi, Eyler, Anne E, Denny, Joshua C, Xu, Hua
DOI: 10.1136/amiajnl-2013-001945
To describe a collaborative approach for developing an electronic health record (EHR) phenotyping algorithm for drug-induced liver injury (DILI).
Author(s): Overby, Casey Lynnette, Pathak, Jyotishman, Gottesman, Omri, Haerian, Krystl, Perotte, Adler, Murphy, Sean, Bruce, Kevin, Johnson, Stephanie, Talwalkar, Jayant, Shen, Yufeng, Ellis, Steve, Kullo, Iftikhar, Chute, Christopher, Friedman, Carol, Bottinger, Erwin, Hripcsak, George, Weng, Chunhua
DOI: 10.1136/amiajnl-2013-001930
To construct and validate billing code algorithms for identifying patients with peripheral arterial disease (PAD).
Author(s): Fan, Jin, Arruda-Olson, Adelaide M, Leibson, Cynthia L, Smith, Carin, Liu, Guanghui, Bailey, Kent R, Kullo, Iftikhar J
DOI: 10.1136/amiajnl-2013-001827