Surgery – Diagnostic testing – Cardiovascular
Reexamination Certificate
2000-09-25
2003-06-03
Schaetzle, Kennedy (Department: 3762)
Surgery
Diagnostic testing
Cardiovascular
C128S920000
Reexamination Certificate
active
06572560
ABSTRACT:
BACKGROUND
1. Technical Field
The present invention relates generally to systems and methods for cardiac evaluation and, in particular, to a multi-modal cardiac diagnostic decision support system and method.
2. Background Description
In the context of the rapidly increasing cost of health care, the role of the primary care physician as a gatekeeper to the resources of the medical system is critical. The challenge in using health care resources in a cost-effective manner is especially acute in the area of heart sounds and murmurs evaluation.
A brief description of the conventional method for auscultation of the heart will now be given. The heart is listened to using a stethoscope. The primary heart sounds with reference to the sys/diastolic phase of the heart are identified. It is then determined whether there are any abnormal heart sounds present, such as murmurs and/or clicks. The relative loudness, duration, intensity pattern, spectral quality and time sequence of the heart sounds are assessed. The heart sounds are interpreted in terms of the physiological model of the action of the heart muscle, valves and chambers. A hypothesis is then developed about any possible disease states based on the acoustic evidence and knowledge of the patient's medical history. Possible diagnoses are differentiated by varying the placement of the microphone, the patient's posture, or by having the patient execute different maneuvers that accentuate or diminish certain heart sounds. The accumulated evidence is evaluated for the presence of heart disease. It is then decided whether to refer the patient for diagnostic imaging, particularly ultrasound.
A description of some of the many disadvantages of conventional auscultation of the heart will now be given. Auscultation of the heart is a difficult task, for many reasons. The stethoscope itself transfers only a small fraction of the acoustic signal at the chest surface to the listener's ears, and filters the cardiac acoustic signal in the process.
Much of the signal energy in many heart sounds is below the threshold of human hearing, and this situation only tends to worsen with increased age of the listener. Auscultation also relies on correctly determining the correspondence of the primary heart sounds with the systolic and diastolic phase of the heart, which is made more difficult when the systolic and diastolic intervals are more equal, typically at elevated heart rates. Auscultation also relies on detecting the correct sequence of brief events that are closely spaced in time, something that is difficult for human listeners.
Learning auscultation is also difficult because diagnostic instructional manuals rely on subjective descriptions of heart sounds, which require much practice to appreciate.
Furthermore, the practice and teaching of the clinical skill of auscultation of the heart has declined among physicians. Recent tests have demonstrated that physicians can identify reliably only a small number of standard heart sounds and murmurs, as described by Burdick et al., in “Physical Diagnosis Skills of Physicians in Training: A Focused Assessment”, Acad. Emerg. Med., 2(7), pp. 622-29, July 1995; Mangione et al., in “Cardiac Auscultatory Skills of Internal Medicine and Family Practice Trainees: A Comparison of Diagnostic Proficiency”, Journal of the American Medical Association, 278(9), pp. 717-22, September 1997; Gracely et al., in The Teaching and Practice of Cardiac Auscultation During Internal Medicine and Cardiology Training: A Nationwide Survey”, Annals of Internal Medicine, 119(1), pp. 47-54, July 1997. Consequently, serious heart murmurs in many patients go undetected by physicians.
Furthermore, the decline in auscultation skills has led to an over-reliance on echocardiography, resulting in a large number of unnecessary and expensive diagnostic studies. As a result, reimbursement for echocardiography has recently come under scrutiny by Medicare.
Accordingly, it would be desirable and highly advantageous to have multi-modal cardiac diagnostic decision support system and method capable of aiding in auscultation of the heart.
SUMMARY OF THE INVENTION
The present invention is directed to a multi-modal cardiac diagnostic decision support system and method. The invention may be used to aid a physician in performing the following tasks: detect valvular heart diseases that might otherwise go undiagnosed; discriminate pathological from innocent heart murmurs, to make a better decision about referring a patient for an echocardiography study; and rationalize, and document the basis for, the referral decision.
The invention allows physicians to provide better health care to their patients at a lower cost, detect otherwise undiagnosed heart disease, save the health care system the costs of unnecessary echocardiography referrals, and facilitate reimbursement for well-justified referrals.
According to a first aspect of the invention, there is provided a method for extracting features from cardiac acoustic signals. A cardiac acoustic signal is obtained. Physiologically significant features are extracted from the cardiac acoustic signal, using a neural network.
According to a second aspect of the invention, the physiologically significant features correspond to at least one of basic heart sounds and components of the basic heart sounds.
According to a third aspect of the invention, there is provided a method for evaluating cardiac acoustic signals. A cardiac acoustic signal is obtained. The cardiac acoustic signal is analyzed with a wavelet decomposition to extract time-frequency information. Basic heart sounds are identified using neural networks applied to the extracted time-frequency information.
According to a fourth aspect of the invention, there is provided a method for determining cardiac event sequences from cardiac acoustic signals. A cardiac acoustic signal is obtained. A sequence of features extracted from the cardiac acoustic signal are processed by a probabilistic finite-state automaton to determine a most probable sequence of cardiac events given the cardiac acoustic signal.
According to a fifth aspect of the invention, the probabilistic finite-state automaton is a hidden markov model.
According to a sixth aspect of the invention, there is provided a method for extracting clinical findings from cardiac acoustic signals. A cardiac acoustic signal is obtained. The cardiac acoustic signal is processed to determine a most probable sequence of cardiac events given the cardiac acoustic signal. The clinical findings are extracted from the sequence of cardiac events.
According to a seventh aspect of the invention, the method further includes the step of determining whether to refer the patient for echocardiography, based upon the extracted clinical findings.
According to an eighth aspect of the invention, the method further includes the step of determining whether to refer the patient for further treatment by a cardiac specialist, based upon the extracted clinical findings.
According to a ninth aspect of the invention, the clinical findings correspond to findings which are typically derived from auscultation of a heart.
According to a tenth aspect of the invention, the clinical findings correspond to basic heart sounds and murmurs.
According to an eleventh aspect of the invention, the clinical findings include at least one of present intensity, intensity profile, duration, time-alignment, and sequence and spectral quality features.
According to a twelfth aspect of the invention, there is provided a method for determining the presence of cardiac diseases. A cardiac acoustic signal of a patient is obtained. The cardiac acoustic signal is processed to find evidence of cardiac diseases. Data corresponding to a medical record of the patient is received. A diagnostic recommendation corresponding to a probability of the cardiac diseases being present in the patient is provided, based upon an analysis of the evidence and data using Bayesian networks.
According to a thirteenth aspect of the invention, the method further includes the step of d
Reichek Nathaniel
Watrous Raymond L.
Droesch Kristen
Paschburg Donald B.
Schaetzle Kennedy
Zargis Medical Corp.
LandOfFree
Multi-modal cardiac diagnostic decision support system and... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Multi-modal cardiac diagnostic decision support system and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multi-modal cardiac diagnostic decision support system and... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3142964