Autopsy is an important source of data for education and quality control. The aim of this study was comparison of ante- to post-mortem findings to detect weak points of intensive care unit (ICU) care. Patients who died in our 14-bed university medical ICU care and underwent an autopsy examination over 20 months (September 2007 to May 2009) were included. Modified Goldman's criteria were used to categorise discrepancies between diagnoses and post-mortem findings. A triad algorithm was constructed to analyse individual ante- to post-mortem findings. One hundred and seventy post-mortem examinations were conducted (45.6% autopsy rate). Major diagnostic discrepancies were detected in 20 patients (11.8%); four class I (2.4%) and 16 class II (9.4%). Massive pulmonary embolism with cardiac arrest was the most common class I discrepancy (75%). Triad analysis of major class I discrepancies showed that all patients had a history of chronic disease; the majority (75%) had a short ICU length of stay. In 75% adequate tests were used to detect disorders. There were interpretation problems of bedside data in complex emergency clinical conditions, especially with less experienced ICU physicians. Inappropriate or incorrectly interpreted diagnostic procedures were performed in more than half of cases with class II discrepancies (9/16, 56%). Abdominal ultrasonography was misleading in 31% (5/16) cases with class II discrepancies. In conclusion, triad algorithm analysis revealed problematic interpretation of bedside diagnostics in emergency cases by inexperienced physicians in class I major discrepancies detected at autopsy. No correct test and wrong interpretation of abdominal ultrasonography were major causes of class II discrepancies.