Assuring high quality medical care has remained an elusive goal because of several problems which have hampered development of effective medical audit programs: inadequate patient data, unreasonable evaluative criteria and insensitive audit procedures. The present study demonstrates the use of a clinical algorithm to help overcome these problems. An examination of medical record data from a series of 703 laceration patients treated in an emergency service yielded only 27 cases (4 per cent) with medical records sufficiently complete to use for auditing physician compliance with algorithmic criteria. Substituting a structured checklist for the handwritten note increased this rate to 86 per cent. A computer-assisted branching audit of 1,400 laceration cases demonstrated that 1) physician compliance with an algorithmic instruction varied significantly (p less than .001) according to the specific instruction, and 2) compliance with a given instruction varied significantly (p less than .001) across different providers. These results underscore the need for medical audit with educational feedback which is provider specific.