Increasing patient safety in drug trials with computer based analysis - a study with 13.000 resting ECGs

Today, the pharmaceutical industry relies on ECG recordings (digital Holter or 12 lead resting ECG) to ensure cardiac safety of subjects in drug trials. State of the art is a central ECG analysis in ECG core labs, where the ECGs are analyzed fully manual by specially trained technicians or experienced cardiologists. The ECGs are commonly analyzed within 48 hours after upload to the core lab, independent on whether the ECG is critical or not. In order to reduce the response time in case of critical ECGs, we have developed a 12 lead resting ECG analysis algorithm to quantitatively classify the ECGs (according to typical criteria applied by pharmaceutical sponsors). As bottom line statement, the ECGs are classified into ¿normal¿ (N), and ¿abnormal¿ (AN). The basic idea was to identify any abnormality and then prioritize the ECGs for over-read in the core lab. The algorithm was tested and validated against a data base of 12.980 ECGs of 1.223 patients, recorded in a drug trial and analyzed in a professional core lab. The following paper describes our methodology, and the results obtained with the above described data base. We also provide an outlook on how our new algorithm will be applied in future drug safety trials.