Computer-Based Rhythm Interpretations Are No Substitute for Cardiologist
Aug 10, 2005
Americans will receive an estimated 100 million electrocardiograms (ECGs) this year to diagnose heart disease – including heart attack, acute angina, and hypertrophy (enlarged heart). A new study finds that computer-based rhythm interpretation – a standard feature of most modern electrocardiograms – is often inaccurate, and without physician intervention, could lead to a false heart rhythm diagnosis. The NewYork-Presbyterian Hospital/Weill Cornell Medical Center study is published in last month's Journal of Electrocardiology.
Based on an analysis of 4,297 consecutive ECG recordings at NewYork-Presbyterian/Weill Cornell, 13.2 percent of computer-based rhythm statements required physician revision. Nearly half (45.7 percent) of all inaccurate rhythm statements involved the 343 patients with pacemakers. Of these, three quarters (258) had computer interpretations that required physician revision. Excluding patients with pacemakers, the required revision rate for computer-based rhythm statements was 7.8 percent.
"Despite improvements in the computer algorithm, our study finds that computer rhythm statements can be flawed and therefore must remain secondary to the expertise and judgment of a physician, and physician checking – or 'over-reading' – to verify or correct computer-based electrocardiogram rhythm diagnoses remains mandatory," says Dr. Paul D. Kligfield, the study's senior author, Professor of Medicine in the Greenberg Division of Cardiology at Weill Medical College of Cornell University, and Attending Physician at NewYork-Presbyterian/Weill Cornell.
"It is very possible to miss conditions like atrial fibrillation, atrial flutter, etc. if an experienced cardiologist does not look at the ECG. It is also possible for the computer to state that these irregular rhythms are present when they are not," continues Dr. Kligfield. "Misdiagnosis of cardiac rhythm can delay treatment – such as blood thinners to prevent blood clots with some rhythms such as atrial fibrillation – or suggest the wrong treatment."
"Unfortunately, there is sometimes an over-reliance on computer interpretation of the ECG," says Dr. Kligfield. "The computer is good, and it is getting better, but alone it is not good enough," he adds. By contrast, for more than 25 years, every single computer-based ECG at NewYork-Presbyterian/Weill Cornell has been checked by an attending cardiologist, and all diagnostic statements modified when appropriate.
The study found a significant degree of false negative rhythm diagnoses by computer: 10 percent of primary rhythms other than normal heart rhythm – including atrial fibrillation, atrial flutter, and atrial tachycardia – were incorrectly stated to be normal rhythms by the computer algorithm.
The failings identified by the study for patients without pacemakers are a result of the ECG software algorithm – not a hardware problem, says Dr. Kligfield. The pacemaker recognition issue is undergoing hardware and software redesign by the manufacturer. "In the case of patients with pacemakers, the problem is predominantly one of not recognizing the modern pacemaker signal, which is very small in both amplitude and duration compared with the electrical signal of the heart. And, sometimes, even when the pacemaker signal is detected, it is just not interpreted correctly in terms of the overall rhythm of the heart."
"Our findings highlight the importance of current efforts to understand the clinical implication of, and to improve, these diagnostic algorithms," says Dr. Kligfield.
The study made use of the most recent version of GE Healthcare Technologies MUSE 12 SL software. All results were checked by one of two cardiologists, and all disagreements with the initial computer rhythm statement were reviewed by the second cardiologist to achieve physician consensus, which was used as the "gold standard" for rhythm diagnosis.
Half or more of U.S. hospitals and cardiologists use the GE Healthcare ECG system. "GE is aware of this situation, as well as of the current study's findings, and is actively working to improve this, as they have been all along," says Dr. Kligfield.
The study was co-authored by Dr. Peter M. Okin, Professor of Medicine in the Greenberg Division of Cardiology at Weill Medical College of Cornell University and Attending Physician at NewYork-Presbyterian/Weill Cornell, and Dr. Kimble Poon, a recent graduate of Weill Medical College and current intern at UCLA Medical Center who worked on this study while he was a medical student at Weill Cornell.
An editorial entitled "A New Look at an Old Question – How Good Is the Computer in the Diagnosis of Arrhythmias?" accompanies the study. The editorial proposes ways to improve ECG interpretive programs.
An electrocardiogram – abbreviated as ECG or EKG – is a test that measures the electrical activity of the heartbeat. With each beat, an electrical impulse (or "wave") travels through the heart. This wave causes the muscle to squeeze and pump blood from the heart. Using several sensors called electrodes that rest on parts of the patient's body, an ECG displays this electrical activity as a number of waveforms representing the timing and intensity of this electrical activity. These waveforms are interpreted by a built-in computer algorithm, and separately by a cardiologist, in order to provide a diagnosis. There is no pain or risk associated with having an electrocardiogram.
The high quality electrocardiograph was developed by Willem Einthoven and introduced into clinical medicine in 1902, an accomplishment for which he received the Nobel Prize in Medicine in 1924. The first computer-based rhythm interpretations were introduced in the mid-1970s.