Recommendations and Extraction of Clinical Variables of Pediatric Multiple Sclerosis Using Common Data Elements

Area of Science:

• Pediatric Neurology
• Health Informatics
• Data Science

Background:

• Pediatric multiple sclerosis (MS) requires specialized data management for effective research and care.
• Utilizing common data elements (CDEs) is crucial for standardizing information retrieval in complex pediatric conditions.
• The St. Louis Children's Hospital/Washington University (SLCH/WU) pediatrics data network offers a large dataset for such investigations.

Purpose of the Study:

• To assess the feasibility of using CDEs to identify pediatric patients with MS.
• To explore the utility of CDEs for pediatric MS symptom management research.
• To provide recommendations for improving CDE use in pediatric MS care.

Main Methods:

• Evaluation of the SLCH/WU pediatrics data network for CDE application.
• Development of algorithms using ICD codes and keywords to identify pediatric MS cases.
• Extraction of clinical data, including medications and diagnosis codes, from de-identified electronic health records.

Main Results:

• Successfully identified 466 pediatric patients with MS within the dataset.
• Noted a comorbidity of anxiety and depression in a subset of these patients.
• Demonstrated the capability to extract detailed clinical information relevant to MS progression.

Conclusions:

• The SLCH/WU pediatrics data network is a valuable resource for pediatric MS research due to its extensive and queryable data.
• Standardized CDEs are essential for quality improvement, research, and practice in pediatric MS.
• Leveraging big data analytics from this network can inform personalized interventions and decision-making for pediatric MS patients.