Related Experiment Video
Updated: Aug 3, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Annotation of Trauma-related Linguistic Features in Psychiatric Electronic Health Records for Machine Learning
Eben Holderness1, Bruce Atwood2, Marc Verhagen1
1Brandeis University.
Researchers created a gold standard dataset from psychiatric electronic health records (EHRs) to train machine learning models. This dataset helps identify trauma indicators in unseen patient records, improving mental healthcare.
Area of Science:
- Clinical Informatics
- Natural Language Processing
- Machine Learning
Background:
- Psychiatric electronic health records (EHRs) are complex and unstructured, posing challenges for machine learning (ML) applications.
- Identifying traumatic events within these records is crucial for understanding patient conditions like psychotic disorders and posttraumatic stress disorder (PTSD).
Conclusions:
- The developed gold standard dataset and annotation scheme are suitable for training ML models to identify trauma indicators in psychiatric EHRs.
- This work facilitates the advancement of ML applications in mental healthcare by providing a valuable, annotated data resource.
- The findings support the use of ML for extracting critical clinical information from complex EHR data.
More Related Videos
05:51Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
Published on: May 15, 2016
09:55Use of a Psychophysiological Script-driven Imagery Experiment to Study Trauma-related Dissociation in Borderline Personality Disorder
Published on: March 8, 2018