Related Experiment Video
Updated: Sep 18, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Quantitative Analysis of Diagnostic Reasoning Using Initial Electronic Medical Records
Shinya Takeuchi1, Yoshiyasu Okuhara2, Yutaka Hatakeyama2
1Department of Disaster and Emergency Medicine, Kochi Medical School, Kochi University, Nankoku 783-8505, Kochi, Japan.
Initial electronic medical records (EMRs) contain valuable linguistic cues for diagnostic reasoning. Text analysis of EMRs can reveal clinical reasoning patterns, aiding medical education and diagnostic support systems.
Area of Science:
- Clinical Informatics
- Medical Education
- Natural Language Processing
Background:
- Diagnostic reasoning is crucial but often automated and opaque.
- Limited quantitative studies assess clinical reasoning in electronic medical records (EMRs).
- Need to explore EMRs for insights into diagnostic processes.
Purpose of the Study:
- Investigate if initial EMRs hold diagnostic reasoning information.
- Assess text analysis and logistic regression for visualizing reasoning.
- Enhance understanding of clinical decision-making.
Main Methods:
- Retrospective analysis of EMRs (2008-2022) at Kochi University Hospital.
- Text analysis using Japanese NLP library (GiNZA).
- Logistic regression to link terms with final diagnoses in dizziness and headache cohorts.
Main Results:
- Identified 48 significant diagnostic terms in 248 dizziness cases.
- Identified 46 significant diagnostic terms in 616 headache cases.
- Term presence and expression (affirmative/negative) significantly correlated with diagnoses.
Conclusions:
- Initial EMRs contain quantifiable linguistic data reflecting diagnostic reasoning.
- Simple analytical methods can reveal reasoning patterns.
- Findings support medical education and explainable AI in diagnostics.
Related Concept Videos
Methods of Documentation VII: EMR
Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
Critical Thinking II
Patient-centered Care
Reasoning
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
Purpose of Health Records I
Here's a breakdown of how health records serve these purposes:

