Software

1. Long-Term Disease Prediction Using Unstructured Clinical Nursing Notes: a long-term aggregation mechanism intended to recognize the onset of the disease with the earliest detected symptoms.
2. Attention neural model for automated diagnostic coding: eliminates dependency on structured electronic medical records by design of a multi-channel convolutional attention network with explainability.
3. Automated Diagnostic Code Group Prediction: disease prediction from unstructured nursing notes, using matrix factorization techniques.
4. Multi-label classification of unstructured clinical notes: fuzzy similarity matching with vector space and topic modelling approaches for ICD-9 code classification.
5. Extraction of clinical concepts from Heterogeneous clinical notes: coherence based topic-modeling techniques were employed to capture the semantic textual features with emphasis on human interpretability.
6. Classification of unstructured clinical notes: term weighting of nursing notes aggregated using similarity for developing an effective CDSS.
7. Contextual representation of Social data: character, word and document-level representation of tweet data for regional-level mortality rate prediction.