Build and Query Indexes of Clinical Documents with Easy-to-Reuse Pipelines
Clinical Snapshot
PICO Framework
| P — Population | Electronic health records containing unstructured clinical text data |
| I — Intervention | medkit Seshat - an open-source Python pipeline for natural language processing of clinical documents |
| C — Comparator | Traditional one-off, study-specific text extraction methods |
| O — Outcomes | Creation of searchable indexes with entity recognition, OMOP vocabulary normalization, and reusable pipeline infrastructure |
Bottom Line
This software development paper presents medkit Seshat, an open-source pipeline for processing clinical text from electronic health records. The tool addresses a genuine need for reusable natural language processing infrastructure in healthcare informatics by providing entity recognition, OMOP vocabulary normalization, and searchable indexing capabilities. While the concept is sound and the open-source approach commendable, the abstract lacks crucial validation data including accuracy metrics, performance benchmarks, and clinical utility assessments. The pipeline's integration with standardized vocabularies is promising for interoperability, but real-world implementation would require local adaptation and thorough testing. Healthcare informaticians and researchers involved in clinical data extraction may find this tool useful, though careful evaluation of its performance in specific institutional contexts would be essential before deployment.
Key Findings
Effect Size: Not quantified
Primary Outcome: Functional open-source pipeline for clinical text processing and indexing
Nnt Or Sensitivity: Entity recognition and normalization accuracy not reported
Confidence Interval: Not provided
Clinical Application
High - open-source Python implementation with web interface Potentially valuable for Australian Digital Health initiatives, though integration with local terminologies (SNOMED CT-AU) and My Health Record system would require adaptation Healthcare institutions with electronic health records containing unstructured clinical text
Abstract
Electronic Health Records are a central source of healthcare data, containing structured data alongside unstructured clinical texts. The latter capture detailed reasoning, observations, treatment plans and clinical evolutions, which are crucial for phenotyping, and real-world evidence generation. Natural language processing enables the extraction, thus the subsequent use, of these crucial elements; however, these extractions remain one-off, study-specific efforts. This is detrimental as the extracted elements could be valuable for future research. We present medkit Seshat, an open-source Python pipeline that: (1) ingests free text, (2) recognizes relevant entities, (3) normalizes them with OMOP vocabularies, (4) builds an index that can either be searched by concept or by document. In addition, we share a flexible web UI to illustrate the interest of built indexes in terms of search, text analysis and export. Seshat aims at facilitating the reuse and adaptation of this prototypical pipeline to various purposes, with the main objective of enabling the secondary use of results of phenotyping campaigns.
References
- 1.Berthou, F., Vaillant, G., Rance, B., & Coulet, A. (2026). Build and Query Indexes of Clinical Documents with Easy-to-Reuse Pipelines. Studies in Health Technology and Informatics. https://doi.org/10.3233/SHTI260325
Related Research
Journal of medical Internet research
Advancing Human-Centered AI in Clinical Decision Support: Sociocognitive Human-in-the-Loop Study in HIV Care
2 Aug 2026
Neurological research
Federated deep learning model for epilepsy seizure detection using electroencephalogram (EEG) signal
2 Aug 2026
Neural networks : the official journal of the International Neural Network Society
MFBD: Model-free backdoor defense based on vision-language pre-trained models
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service