Related Experiment Video
Updated: May 19, 2026
07:13
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Automatic detection of inconsistencies between free text and coded data in Sarcoma discharge letters
Ruty Rinott1, Michele Torresani, Rossella Bertulli
1IBM Haifa Research Labs, Haifa, Israel. rutyr@il.ibm.com
Studies in Health Technology and Informatics
|August 10, 2012
Summary
We developed a method to automatically detect inconsistencies in Electronic Health Records (EHR) by comparing free text to coded fields. This helps improve patient care by flagging potential data errors for review.
Area of Science:
- Medical Informatics
- Clinical Data Management
- Health Information Technology
Background:
- Data discordance in Electronic Health Records (EHR) can negatively impact patient care.
- Identifying inconsistencies, particularly within free text fields, is a significant challenge in healthcare data management.
Purpose of the Study:
- To develop and validate a method for automatically detecting inconsistencies between free text and coded data within EHR systems.
- To improve the accuracy and reliability of patient information stored in EHRs.
Main Methods:
- An ensemble of machine learning classifiers was trained using EHR data.
- Classifiers were used to predict coded field values based on information present in free text fields.
- Potential inconsistencies were identified when classifier predictions with high confidence differed from the clinician-entered codes.
Main Results:
- The method successfully identified potential inconsistencies between free text and coded fields in EHR data.
- Experimental results on discharge letters from sarcoma patients demonstrated the method's validity.
- A domain expert verified the identified potential inconsistencies, confirming the method's effectiveness.
Conclusions:
- Automatic detection of data discordance between free text and coded fields in EHRs is feasible.
- The proposed method offers a promising approach to enhance data quality and patient safety in healthcare.
- This technique can aid clinicians in identifying and rectifying potential errors in patient records.
Related Concept Videos
01:14SBAR II: Application of SBAR
SBAR is an effective communication tool used by healthcare professionals to communicate patient information accurately. SBAR stands for Situation, Background, Assessment, and Recommendation. For a better understanding, an example is given below.
SBAR Report from a Nurse to a Health Care Provider
S: "Hello, Dr. Smith. This is Jane, RN, from the Med Surg unit. I am calling to tell you about Ms. White in Room 210, who is experiencing increased pain and redness at her incision site. Her recent...
SBAR Report from a Nurse to a Health Care Provider
S: "Hello, Dr. Smith. This is Jane, RN, from the Med Surg unit. I am calling to tell you about Ms. White in Room 210, who is experiencing increased pain and redness at her incision site. Her recent...
01:18Methods of Documentation I: Source-Oriented Records
Source-oriented records, or SOR, are medical record-keeping organized by the data source. The SOR system was first developed in the mid-1900s to organize the growing patient data in hospitals and other healthcare facilities.
In an SOR, each discipline involved in patient care maintains a separate medical record section. This record-keeping method enables easy tracking of patient progress and ensures healthcare staff have access to up-to-date information.
Key Attributes include the following:
In an SOR, each discipline involved in patient care maintains a separate medical record section. This record-keeping method enables easy tracking of patient progress and ensures healthcare staff have access to up-to-date information.
Key Attributes include the following: