The long-term objective of this research is to increase the clinical trial enrollment of US patients via a semi- automated, Natural Language Processing (NLP) based, interactive and patient-centered informatics application. The study design is prospective observational study. Scope is limited to cancer patients. There are three specific aims for this project.
The first aim i s to identify concepts that overlap between the electronic medical record's (EMR) clinical notes and the free text of clinical trial announcements. The PI will use the concepts to develop mapping frames that connect concepts in the text of trial announcements to those found in clinical notes in the medical record. When he has the mapping frames he will build the NLP module for the application. In the software development work he will utilize as many publicly available software components as possible. He will experiment with UIMA, GATE, MetaMap, Stanford Parser, NegEx algorithm and others. The PI will develop the tool around the National Library of Medicine's Unified Medical Language System knowledgebase. He will use Java for programming.
The second aim i s to create an algorithm that automatically generates questions to request information directly from the patient if the information is not available or accessible in the records.
The third aim i s to evaluate the in-vitro, laboratory performance of the application. For performance evaluation purposes the PI will recruit cancer care specialists to generate the gold standard lists of eligible clinical trials for study patients. He will publicly release the developed code at the end of the grant period. This K99/R00 project will serve the foundation for future R01 grant applications. The PI is fully committed to become faculty in the Clinical Research Informatics domain with a specialization in biomedical NLP. The support of the K99/R00 grant will enable him to acquire substantial formal training in Computational Linguistics while contributing to the body of knowledge of the Clinical Research Informatics field. The five-year grant support will ensure success in his endeavor. The proposed work is highly significant because the dismal clinical trial accrual rates (2-4 % nationally) hampers timely development of new drugs. In addition, studies show that physicians have statistically significant bias against elderly and minority patients to invite participation in clinical trials. The proposed project is synergistic with physician-centered efforts but the goal is to provide individualized, EMR based clinical trial recommendations directly to the patients. The results of this research will empower the patients and elevate their role in the decision making process.

Public Health Relevance

The long-term objective of this research is to increase the clinical trial enrollment of US patients via a semi- automated, Natural Language Processing (NLP) based, interactive and patient-centered informatics application. The proposed work is highly significant because the dismal clinical trial accrual rates (2-4 % nationally) hampers timely development of new drugs. In addition, studies show that physicians have statistically significant bias against elderly and minority patients to invite participation in clinical trials. The proposed project is synergistic with physician-centered efforts but the goal is to provide individualized, electronic medical record based clinical trial recommendations directly to the patients. The results of this research will empower patients and elevate their role in the decision making process.

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
Research Transition Award (R00)
Project #
5R00LM010227-05
Application #
8331381
Study Section
Special Emphasis Panel (ZLM1-ZH-C (01))
Program Officer
Sim, Hua-Chuan
Project Start
2010-10-02
Project End
2013-09-29
Budget Start
2012-09-30
Budget End
2013-09-29
Support Year
5
Fiscal Year
2012
Total Cost
$238,944
Indirect Cost
$82,772
Name
Cincinnati Children's Hospital Medical Center
Department
Type
DUNS #
071284913
City
Cincinnati
State
OH
Country
United States
Zip Code
45229
Lingren, Todd; Deleger, Louise; Molnar, Katalin et al. (2014) Evaluating the impact of pre-annotation on annotation speed and potential bias: natural language processing gold standard development for clinical named entity recognition in clinical trial announcements. J Am Med Inform Assoc 21:406-13
Li, Qi; Melton, Kristin; Lingren, Todd et al. (2014) Phenotyping for patient safety: algorithm development for electronic health record based automated adverse event and medical error detection in neonatal intensive care. J Am Med Inform Assoc 21:776-84
Zhai, Haijun; Brady, Patrick; Li, Qi et al. (2014) Developing and evaluating a machine learning based algorithm to predict the need of pediatric intensive care unit transfer for newly hospitalized children. Resuscitation 85:1065-71
Deleger, Louise; Lingren, Todd; Ni, Yizhao et al. (2014) Preparing an annotated gold standard corpus to share with extramural investigators for de-identification research. J Biomed Inform 50:173-83
Li, Qi; Deleger, Louise; Lingren, Todd et al. (2013) Mining FDA drug labels for medical conditions. BMC Med Inform Decis Mak 13:53
Deleger, Louise; Molnar, Katalin; Savova, Guergana et al. (2013) Large-scale evaluation of automated clinical note de-identification and its impact on information extraction. J Am Med Inform Assoc 20:84-94
Zhai, Haijun; Lingren, Todd; Deleger, Louise et al. (2013) Web 2.0-based crowdsourcing for high-quality gold standard development in clinical natural language processing. J Med Internet Res 15:e73
Li, Qi; Zhai, Haijun; Deleger, Louise et al. (2013) A sequence labeling approach to link medications and their attributes in clinical notes and clinical trial announcements for information extraction. J Am Med Inform Assoc 20:915-21
Wu, Cuijun; Xia, Fei; Deleger, Louise et al. (2011) Statistical machine translation for biomedical text: are we there yet? AMIA Annu Symp Proc 2011:1290-9
Uzuner, Ozlem; Solti, Imre; Xia, Fei et al. (2010) Community annotation experiment for ground truth generation for the i2b2 medication challenge. J Am Med Inform Assoc 17:519-23

Showing the most recent 10 out of 14 publications