Related Experiment Video
Updated: Dec 10, 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
7.4K
Clinical information extraction for preterm birth risk prediction.
Lucas Sterckx1, Gilles Vandewiele1, Isabelle Dehaene2
1IDLab, Ghent University - imec, Technologiepark-Zwijnaarde 126, Ghent, Belgium.
Journal of Biomedical Informatics
|August 29, 2020
Summary
This study developed a pipeline to extract clinical information from unstructured medical notes for preterm birth prediction. This approach enhances clinical decision-making by integrating extracted data with electronic health records.
Area of Science:
- Medical Informatics
- Clinical Decision Support
- Natural Language Processing
Background:
- Unstructured clinical notes contain valuable patient data.
- Extracting this information can improve clinical decision-making.
- Preterm birth prediction is a critical area for intervention.
Purpose of the Study:
- To develop and evaluate a pipeline for clinical information extraction from medical notes.
- To identify clinical entities and attributes related to preterm birth.
- To assess the utility of extracted information for clinical decision support models.
Main Methods:
- Gathered and analyzed a large collection of medical notes from patients at risk of preterm delivery.
- Trained and evaluated information extraction components on an annotated dataset.
- Identified clinical entities (symptoms, events, procedures) and their attributes.
- Integrated extracted information with structured electronic health record data.
Main Results:
- Developed an effective pipeline for clinical information extraction from medical notes.
- Demonstrated that extracted clinical entities and attributes are highly informative.
- Showed that this information significantly improves the performance of predictive models for preterm delivery.
Conclusions:
- Leveraging unstructured medical notes through information extraction is feasible and beneficial.
- The developed pipeline has potential for enhancing clinical practice and decision support in preterm birth management.
- Combining unstructured and structured data improves predictive accuracy for clinical outcomes.
Related Concept Videos
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
302
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
302
01:52Regression Toward the Mean
6.7K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.7K