Related Experiment Video
Updated: Feb 9, 2026

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
Can Text-Search Methods of Pathology Reports Accurately Identify Patients with Rectal Cancer in Large Administrative
Reilly P Musselman1, Deanna Rothwell2, Rebecca C Auer1
1Division of General Surgery, University of Ottawa, Ottawa, ON, Canada.
A text-search algorithm effectively identifies rectal cancer surgery patients in administrative data. Combining this with manual review ensures accuracy, especially with low initial probabilities.
Area of Science:
- Oncology
- Health Informatics
- Data Science
Background:
- Administrative datasets are valuable for clinical research but require robust patient identification methods.
- Accurate identification of rectal cancer surgical patients is crucial for epidemiological studies and healthcare management.
Purpose of the Study:
- To develop and validate a text-search algorithm for identifying rectal cancer surgical patients within administrative datasets.
- To assess the accuracy (sensitivity, specificity, PPV) of this text-search methodology.
Main Methods:
- A text-search algorithm was created and validated using pathology reports from known rectal cancer, colon cancer, and noncolorectal specimens.
- The algorithm was applied to a large administrative dataset (Ottawa Hospital Data Warehouse, 1996-2010).
- Manual chart review was performed to validate identified rectal cancer cases and calculate performance metrics.
Main Results:
- The text-search algorithm demonstrated high performance in derivation (100% sensitivity, 98.6% specificity) and application cohorts (100% sensitivity, 98.4% specificity).
- Out of 5588 initially identified reports, 1038 were confirmed as rectal cancer patients after manual review.
- The positive predictive value (PPV) of the algorithm was 18.6%.
Conclusions:
- Text-search methodology offers a feasible approach for identifying rectal cancer surgery patients in administrative data with high accuracy.
- Given the low positive predictive value observed, text-search methods necessitate integration with validation processes like manual chart review for reliable cohort identification.
Related Concept Videos
Data Reporting and Recording
Assessing Body Temperature - Rectal
Follow these steps for rectal temperature assessment:
Step 1: Perform hand hygiene and don clean gloves to prevent cross-infection.
Step 2: Position the patient in a side-lying position to better visualize the rectal...
Dosage Interval and Administration Route: Determination Methods
Types of Reports I: Hands-off Report
Following are the key components and categories of hand-off reports:
Purpose and Process:
Types of Reports II: Incident or Occurrence Report
Purposes:
In the healthcare industry, reports play a crucial role in documenting incidents within an agency. The primary objective of these reports is to ensure patient safety, uphold the...
Types of Reports III: Telephone and Verbal Reports
Here's an overview of each type:
Telephone Orders

