Fig. 1: A translated semi-structured raw EMR sample from an Anhui provincial hospital, including gold standard for diagnosis codes and names, and main contributory records comprising structured short text and unstructured long free text. | npj Digital Medicine

Fig. 1: A translated semi-structured raw EMR sample from an Anhui provincial hospital, including gold standard for diagnosis codes and names, and main contributory records comprising structured short text and unstructured long free text.

From: Optimising the paradigms of human AI collaborative clinical coding

Fig. 1

The colour coding and text styles in the gold standard indicate the types of corrections on the issues of informally written (using non-standardised terms) and three types of mistakes from the structured short text are marked.

Back to article page