Harvard Community Health Plan and the Center for Intelligent Information Retrieval are developing tools to support automated quality fo care measurement from clinical text data. A statistically based text classification system uses semantic features in computerized encounter notes to identify acute exacerbations of asthma. Individual encounter notes are sorted in bins of highly likely, highly unlikely and uncertain likelihood of documenting exacerbation, and then aggregated into episodes of exacerbation for frequency analysis. It is estimated that this approach could reduce the burden of manual chart review by 65%.