Evidence-Based Medicine (EBM) aims to apply the best available evidence gained from scientific methods to clinical decision making. A generally accepted criterion to formulate evidence is to use the PICO framework, where PICO stands for Problem/Population, Intervention, Comparison, and Outcome. Automatic extraction of PICO-related sentences from medical literature is crucial to the success of many EBM applications. In this work, we present our Aceso system, which automatically generates PICO-based evidence summaries from medical literature.
this dataset is used in training of Aceso, which has samples of PICO annotated by human.
In this folder are all training sets.
The columns in the table represent: original text, cleaned text, cui corresponding to the text
./PICO_Heartdisease heart disease dataset. This is the dataset marked by the experts in the initial stage with reference to the systematic review.
This is a training set based on the ebm-nlp dataset. We combine consecutive identically labeled words in sentences in the original data set into phrases as training samples.
Aceso's input needs words and corresponding concepts. Input files in ./PICO_EBMNLP have generated concepts using MetaMap.