LIMSI ICD10 coding Experiments on CépiDC Death Certificate Statements

We describe LIMSI experiments in ICD10 coding of death certificate statements with the CépiDc dataset of the CLEF eHealth 2016 Track 2. We tested a classifier with humanly-interpretable output, based on IR-style ranking of candidate ICD10 diagnoses. A tf.idf-weighted bagof-feature vector was built for each training set code by merging all the statements found for this code in the training data. Given a new statement, we ranked candidate codes with Cosine similarity. Features included meta-information and n-grams of normalized tokens. We also prepared an ICD chapter classifier with the same method and used it to rerank the top-k codes (k=2) returned by the code classifier. For development we focused on mono-code statements and obtained a P@1 of 0.749 increased to 0.778 by chapter reranking. On the test data we returned one code for each statement, leaving multiple code assignment for future work, and obtained a precision, recall and F-measure of (0.7650, 0.5686, 0.6524).