Jorge R Herskovic
Affiliation: Texas Medical Center
- Graph-based signal integration for high-throughput phenotypingJorge R Herskovic
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA
BMC Bioinformatics 13:S2. 2012..In this paper, we automatically construct a graphical knowledge model and then use it to phenotype breast cancer patients. We compare the performance of this approach to using MetaMap when labeling records...
- Optimized dual threshold entity resolution for electronic health record databases--training set size and active learningErel Joffe
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX
AMIA Annu Symp Proc 2013:721-30. 2013..Active learning achieved comparable results with 3,000 records. Automated optimization is effective and targeted sampling can reduce the required training set size. ..
- Deterministic binary vectors for efficient automated indexing of MEDLINE/PubMed abstractsManuel Wahle
The University of Texas Health Science Center at Houston, School of Biomedical Informatics, USA
AMIA Annu Symp Proc 2012:940-9. 2012..The increased capacity demonstrated by binary vectors has implications for information retrieval, and the elimination of the need to retain term vectors facilitates distributed implementations, enhancing the scalability of RI...
- Predicting biomedical document access as a function of past useJ Caleb Goodwin
School of Biomedical Informatics, The University of Texas Health Science Center, Houston, Texas 77030, USA
J Am Med Inform Assoc 19:473-8. 2012..To determine whether past access to biomedical documents can predict future document access...
- Expert guided natural language processing using one-class classificationErel Joffe
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Texas Department of Hematology and Bone Marrow Transplantation, Tel Aviv Medical Center, Tel Aviv Israel
J Am Med Inform Assoc 22:962-6. 2015..In this study, the authors combine expert-guided feature (text) selection with one-class classification for text processing...
- A benchmark comparison of deterministic and probabilistic methods for defining manual review datasets in duplicate records reconciliationErel Joffe
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, Texas, USA
J Am Med Inform Assoc 21:97-104. 2014..We compared the performance of common ER algorithms: using algorithmic optimization, rather than manual parameter tuning, and on two-threshold classification (match/manual review/non-match) as well as single-threshold (match/non-match)...
- SYFSA: a framework for systematic yet flexible systems analysisTodd R Johnson
The University of Texas School of Biomedical Informatics at Houston, 7000 Fannin Suite 600, Houston, TX 77030, USA
J Biomed Inform 46:665-75. 2013..We also describe several information-theoretic measures of flexibility that can be used to compare alternative designs, and to measure how efficiently a system supports a given task, the relative cognitive workload, and learnability. ..
- MEDRank: using graph-based concept ranking to index biomedical textsJorge R Herskovic
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, United States
Int J Med Inform 80:431-41. 2011..NLM indexers are assisted by a system called the Medical Text Indexer (MTI) that suggests candidate indexing terms...
- Automated medication reconciliation and complexity of care transitionsPamela A Bozzo Silva
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, TX, USA
AMIA Annu Symp Proc 2011:1252-60. 2011..Our study did not have sufficient statistical power to establish whether the kind of transition affects reconcilability. We conclude that automated reconciliation is possible and will help accomplish the NPSG...