Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases - PubMed (original) (raw)

Comparative Study

Epub 2011 Oct 22.

Affiliations

Comparative Study

Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases

Hua Xu et al. AMIA Annu Symp Proc. 2011.

Abstract

Identification of a cohort of patients with specific diseases is an important step for clinical research that is based on electronic health records (EHRs). Informatics approaches combining structured EHR data, such as billing records, with narrative text data have demonstrated utility for such tasks. This paper describes an algorithm combining machine learning and natural language processing to detect patients with colorectal cancer (CRC) from entire EHRs at Vanderbilt University Hospital. We developed a general case detection method that consists of two steps: 1) extraction of positive CRC concepts from all clinical notes (document-level concept identification); and 2) determination of CRC cases using aggregated information from both clinical narratives and structured billing data (patient-level case determination). For each step, we compared performance of rule-based and machine-learning-based approaches. Using a manually reviewed data set containing 300 possible CRC patients (150 for training and 150 for testing), we showed that our method achieved F-measures of 0.996 for document level concept identification, and 0.93 for patient level case detection.

PubMed Disclaimer

Figures

Figure 1.

Figure 1.

Overview of the 2-step case detection method from EHR.

Figure 2.

Figure 2.

The workflow of creation of the gold standard data set containing 300 patients with labels indicating their CRC status (Yes or No).

Figure 3.

Figure 3.

Distribution of CRC concepts among different types of notes, including DS – discharge summaries, CC – clinical communications, FORM – clinical forms, RAD – radiology notes, PATH – pathology notes, PL – patient summary lists, and OTHER – Other clinical notes (History & Physicals, clinic notes, progress notes).

References

    1. eMERGE Network. https://www.mc.vanderbilt.edu/victr/dcc/projects/acc/index.php/Main_Page.
    1. Sager N, et al. The analysis and processing of clinical narrative. MedInfo. 1986
    1. Sager N, Friedman C, Lyman M. Medical language processing: computer management of narrative data. Reading, MA: Addison-Wesley; 1987.
    1. Hripcsak G, et al. Unlocking clinical data from narrative reports: a study of natural language processing. Ann Intern Med. 1995;122(9):681–8. -PubMed
    1. Friedman C, et al. A general natural-language text processor for clinical radiology. J Am Med Inform Assoc. 1994;1(2):161–74. -PMC -PubMed

Publication types

MeSH terms

Grants and funding

LinkOut - more resources