nttmuClinical.NET is a set of C# library developed for processing discharge summaries. nttmuClinical.NET was built using Microsoft .NET Framework 4. It’s components were developed based on the data set of the i2b2 2014 shared task track 2. nttmuClinical.NET employs a number of rule-based and machine learning methods. It also integrates several state-of-the-art natural language processing components available on the NuGet Gallery.
nttmuClinical.NET components include:
- Section heading recognition
- Risk factor recognition and time attribute assignment
- Smoking status classification
- Record format detection
- Tokenization, part-of-speech tagging and sentence boundary detection through MedPost.
References
- A context-aware approach for progression tracking of medical concepts in electronic medical records. Chang, N.-W., H.-J. Dai, J. Jonnagaddala, C.-W. Chen, R. T.-H. Tsai and W.-L. Hsu. J. of Biomedical Informatics 58(S): S150-S157 (2015)
- Recognition and Evaluation of Clinical Section Headings in Clinical Documents Using Token-Based Formulation with Conditional Random Fields. Hong-Jie Dai, Shabbir Syed-Abdul, Chih-Wei Chen and Chieh-Chen Wu. BioMed Research International, Volume 2015 (2015)