Related Experiment Video
Updated: Jul 5, 2025
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.1K
Elucidating Discrepancy in Explanations of Predictive Models Developed Using EMR
Aida Brankovic1, Wenjie Huang2, David Cook1,3
1CSIRO Australian e-Health Research Centre, Brisbane, QLD 4029, Australia.
Studies in Health Technology and Informatics
|January 25, 2024
Summary
Explainable AI (XAI) methods show limited agreement with expert clinical knowledge in Electronic Medical Records (EMR) decision support. Addressing discrepancies is crucial for trustworthy clinical AI adoption.
Area of Science:
- Artificial Intelligence in Medicine
- Clinical Decision Support Systems
- Machine Learning Interpretability
Background:
- Machine learning (ML) adoption in healthcare is limited by a lack of transparency and explainability.
- Explainable artificial intelligence (XAI) offers potential solutions, but its alignment with clinical expertise is under-researched.
Purpose of the Study:
- To evaluate the concordance between state-of-the-art XAI methods and expert clinical knowledge.
- To analyze discrepancies between XAI explanations and clinical insights in Electronic Medical Records (EMR) based decision support algorithms.
- To identify factors crucial for developing trustworthy XAI in clinical settings.
Main Methods:
- Application of current XAI techniques to ML algorithms used in EMR data.
- Analysis of agreement between XAI outputs and expert clinical judgment.
- Discussion of clinical and technical factors contributing to observed discrepancies.
Main Results:
- Identified significant discrepancies between XAI-generated explanations and expert clinical knowledge.
- Highlighted the need for a deeper understanding of the causes of these differences.
- Underscored the importance of clinical validation for XAI methods.
Conclusions:
- Current XAI methods may not fully align with clinical reasoning, posing a challenge for trustworthy adoption.
- Addressing the gap between technical explainability and clinical expertise is essential for reliable clinical decision support.
- Future research should focus on developing XAI solutions that are both technically sound and clinically relevant.
Related Concept Videos
01:30Methods of Documentation VII: EMR
836
Electronic Medical Records (EMRs) primarily center around electronically documenting patients' health information within a single healthcare organization or practice. They contain essential clinical data related to a patient's medical history, diagnoses, medications, treatment plans, lab results, and other pertinent information relevant to the specific encounter or episode of care. EMRs are designed to streamline documentation and workflow processes within individual healthcare...
836
01:10Documentation of Nursing Diagnosis
1.3K
The nurse documents nursing diagnoses and enters them into the patient record. The identified patient's nursing diagnosis is either written out with a plan of care or entered into the electronic health record.
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...
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...
1.3K
01:27Confounding in Epidemiological Studies
170
Confounding in statistical epidemiology represents a pivotal challenge, referring to the distortion in the perceived relationship between an exposure and an outcome due to the presence of a third variable, known as a confounder. This variable is associated with both the exposure and the outcome but is not a direct link in their causal chain. Its presence can lead to erroneous interpretations of the exposure's effect, either exaggerating or underestimating the true association. This...
170
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
43
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
43
01:15Methods of Documentation VI: Case Management Model
573
The case management model is a multidisciplinary approach that involves healthcare professionals from diverse disciplines, such as physicians, nurses, therapists, social workers, and pharmacists, working collaboratively to address the various needs of patients. Each healthcare professional brings unique expertise and perspectives, contributing to a more comprehensive understanding of the patient's condition and tailoring treatment plans accordingly.
For example, a patient with a chronic...
For example, a patient with a chronic...
573
01:29Bias in Epidemiological Studies
271
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
271