Emergency health care facilities lack automated medical form recognition systems necessary for efficient epidemiological and health surveillance analysis. The task is to extract handwritten text from the New York State (NYS) Pre-Hospital Care Report (PCR) and determine its ASCII translation. Our approach hybridizes image processing and semantic lexicon pruning to compensate for the otherwise enormous lexicon size. In this paper we expand on our IEEE CBMS 2001 paper [Automated Reading and Mining of Pre-hospital Care Reports][Medical Word Recognition Using a Computational Semantic Lexicon], which provided a conceptual overview, by probing into our recognizer design and performance measurements.