Looking for a needle in the haystack? A case for detecting adverse drug events (ADE) in clinical notes

Detection and prevention of adverse drug events (ADEs) forms a large part of the patient safety efforts in any healthcare organization. Detection of laboratory and medication based ADEs is well-studied through the use of rule-based systems, however identifying descriptive ADEs, such as somnolence, is a challenging problem. Signals for the detection of these ADEs can often only be found in free-text clinical notes. We describe the automated detection of descriptive ADEs in free-text clinician notes.