Multifunction cardiogram

Multifunction CardioGramTM (MCGTM) is the world's first Internet based non-invasive diagnostic tool that adopts Applied Systems Engineering prinicpals using Digital Signal Processing, i.e. DSP, Data-mining and Supervised Machine Learning to aid physicians to make rapid and much more accurate diagnosis of heart diseases. It is an FDA and AMA approved to diagnose myocardial ischemia due to Coronary Artery Disease (CAD). MCG extracts resting ECG data between the two electrical cources (leads V5 and II) to measure the interactions between Myocardium and intra-cardiac blood flow to accurately detect CAD without the stress, radiation, chemicals and invasiveness of the current modality set. This ground breaking Computational Systems Biology technology that will fundamentally change how heart disease is diagnosed. It is the culmination of the efforts of two generations of dedicated scientists, mathematicians, engineers and physicians over the course of three decades. MCG uses rapid, automated, cloud-based DSP applications, empirically derived digitized clinical database, and machine learning tools through the internet to give people around the world the access to the most accurate diagnostic system ever created, directly from primary care providers' offices or a patient's home, bypassing the need for costly and inaccurate imaging technologies currently in use in cardiologists' offices. We created MCG Technology to solve an intractable problem in cardiology: the extreme and unacceptable inaccuracies of the traditional EKG. EKG can only detect approximately 1/3 (one third) of patients with severe coronary artery disease, leaving them in danger of dying from their undetected illness. The problem is even worse for women, leading in part to more women dying from heart disease than men. The time has come for a much needed, radical change that MCG represents, delivering 5 - 8 times more accurate diagnosis than traditional EKGs. In addition, a double-blind and perspective clinical validation trial comparing MCG with the current gold-standard imaging tool – nuclear myocardial perfusion scan (MPI), using coronary angiogram results as the final judge, MCG was twice as accurate as MPI! (Strobeck, Mangieri, Rainford, Imhoff J. Am. Coll. Cardiol.)

Function

The MCG test consists of an 82 second test where leads II and V5 resting cardiac electrical signals are collected, digitized, encrypted and sent to Premier Heart's data center. The data is then analyzed and transformed into multiple mathematical functions. These mathematical models produce a matrix based on 166 different indices that are then compared against a database of more than 40,000 patients with a broad range of clinically verified myocardial ischemia. A summarized report is returned to the physician via internet connection to the MCG unit in less than 10 minutes.

Performance of an MCG Test: A Four Step Process

MCG is performed in the following four steps.

Step 1:

Multiple cycles of complete resting ECG analog signals from leads II and V5 are recorded by a portable device from a patient at the point of care. The recorded signals are then digitized, encrypted and securely transmitted along with the patient’s demographic information to a central data center for processing.

Step 2:

The computers at the central data center perform a Fast-Fourier-Transformation of the signals from each lead, preparing them for a series of additional mathematical transformations. Research over the last three decades has demonstrated that these mathematical functions are able to extract physiological information embedded in between the two left ventricular leads, II and V5.

Step 3: MCG mathematically transforms the complex non-linear information obtained in Step 2. The mathematical transformations employed include multiple non-linear mathematical functions such as auto and cross power spectra, cross-correlation, coherence, impulse-response and phase shift. These functions produce 166 indices. The index patterns from an individual patient are compared to similar patterns obtained from people whose MCG data has been entered into a large empirical database. This database consists of over 27,000 people with CAD, whose CAD status and severity is included in the database and has been confirmed by coronary angiography. Importantly, the database also contains MCG results from many patients who have one or more non-ischemic cardiac diseases. Therefore, the database is used to distinguish MCG patterns in patients with cardiac ischemia from MCG patterns in patients with non-ischemic cardiac disease and those with both cardiac ischemia and non-ischemic cardiac disease(s). Approximately 13,000 of the patients in the database have had normal coronary angiograms or have been determined to not have CAD after independent evaluations by two cardiologists. The database has been carefully accumulated over many years, and the MCG patterns of each entrant have been validated and correlated with the presence (or absence) and severity of CAD. The database has been designed to be robust and to minimize bias by including, among other things, 49% of its data from women and an age range of 14-100 in the CAD and non-CAD groups, as well as people with many forms of heart disease (e.g., arrhythmias, hypertrophy, cardiomyopathy), in addition to CAD. The database also contains other clinical and diagnostic data from all 40,000+ patients, including information about other non-cardiac disease entities. Step 4:

Based on the comparison to the reference database, an overall ischemia severity score (ranging from 0 to 20) is reported.

(See Exhibit 4 for an overview of the MCG process).

Clinical Application

MCG data has been used to predict the findings of coronary angiography in several carefully designed and well-conducted prospective double-blind validation clinical trials (Grube 2007, Grube 2008, Weiss 2002, Hosokawa 2008, which are included as Exhibits 5, 6, 7 and 8, respectively). These trials were conducted in seven countries and three continents (North America, Asia and Europe). In these studies, MCG was performed on patients who were scheduled for elective coronary angiography by cardiologists who, on the basis of clinical impression and standard non-invasive testing, believed that the patients had an intermediate to high risk of having relevant coronary artery stenosis (CAS). Relevant CAS was defined as a 70% or greater stenosis of one or more major epicardial arteries or a 50% or greater occlusion of the left main coronary artery. The patients in these trials represent "real-world" care, much like the patients studied by Patel. In this regard, it is not surprising that the percentage of patients who were found to have relevant CAS in each of these trials was similar to the percentage who had relevant CAS in the Patel study. This means that even though the treating cardiologists believed that some patients in these four trials were at high risk for significant CAD, the patients studied in these trials were, in reality, at intermediate risk of having significant heart disease rather than at high risk. Therefore, these trial results are directly applicable to most patients seen with suspected CAD. These four trials of MCG were designed to compare the accuracy of MCG versus the accuracy of the standard of care (i.e., clinical impression coupled with standard noninvasive testing) in predicting the existence of relevant CAS. This direct comparison to predict the findings of coronary angiography – the gold standard test - has never, to our knowledge, been published in the medical literature from 1949 to the present. The studies were all similarly designed as follows:

• All patients (n=1076) underwent MCG prior to coronary angiography for any indication. o Angiographers and staff at each study site were blinded to all MCG results and findings. • Coronary angiography was recorded digitally and underwent central review by two independent cardiologists who were blinded to the MCG results. (see Exhibit 9, the attestation, and the Curriculum Vitae, of the clinical trial monitor as to the appropriate blinding of the angiographic and MCG results from the relevant parties) • An MCG score of 4.0 or higher was considered indicative of a hemodynamically relevant coronary artery stenosis of >70% in at least one large-sized vessel. • All of the trials, whether single or multi-center from three continents in seven countries, produced statistically reproducible results.

Each of the trials had similar findings. Strobeck (2009, see Exhibit 10) combined the results of these studies into a meta-analysis that reported the following:

• MCG correctly classified 941 of the 1076 patients with or without relevant stenosis. • Sensitivity/specificity: 91.2%/84.6% (in agreement with above mentioned peer review published trials). • Positive/negative predictive value: 81.9%/92.6% (in agreement with above mentioned peer review published trials). • The results were similar across all studies and were not affected by sex, ethnicity, geographic location or Framingham risk score.

This diagnostic performance compares favorably to other non-invasive diagnostic tests. For example, a review of stress scintigraphy studies reported a wide range of sensitivities from 44%-89% and specificities of 89%-94% for 2+ vessel disease (Elhendy 2002, see Exhibit 11). Numerous studies of exercise echocardiography as a diagnostic tool for CAD have been conducted, and reported sensitivities range from 31% to over 90%, while specificities range from 46% to nearly 100% (Geleijnse 2007, Marwick 2009, Smart 2000. See Exhibits 12, 13 and 14, respectively). These studies also show that these modalities are less accurate for patients with single vessel CAD. The inability of standard noninvasive diagnostic tests to accurately diagnose CAD in women has been a longstanding problem in cardiology. Importantly, in each of these trials, the sensitivity, specificity and positive and negative predictive values of MCG in predicting the existence of relevant CAS in women was just as good as it was in men. These data were recently published by Strobeck et al. 2011 (see Exhibit 15) in a metaanalysis. The authors concluded that the sensitivity and specificity of MCG for detecting relevant CAD in women, as diagnosed by coronary angiography, appears to be equal to or better than those of other resting or stress ECG/imaging modalities. This may be because the database against which individual patient data is compared takes into account the physiological differences between males and females as well as physiological changes due to aging. This is accomplished by populating the database with approximately half of the data coming from women (normal women and women with heart disease), and by grouping the data by age group and sex (e.g., men aged 51–60, 61-70 and women aged 51–60, 61-70, etc.). In other words, the MCG database design is both age and sex "normalized." In summary, these trials provide evidence that MCG is a clinically useful tool for assisting physicians in the diagnosis of CAD in women. Strobeck et al. (2011, see Exhibit 16) have also completed a Paired Comparison of MCG with stress single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) in 165 consecutive patients who were at intermediate risk of having CAD based on clinical findings and who agreed to undergo both MCG and stress SPECT, followed by elective angiography if SPECT was abnormal or valvular heart disease was present. They represent the diagnostic experience of a typical "real world" cardiology practice. The definition of relevant CAS was the same as that used in the other studies. Similar to the above meta-analysis, an MCG score of <4 was used to indicate the absence of relevant CAD. A total of 116 patients with abnormal SPECT MPI tests, persistent chest pain or significant VHD were entered into the final analysis. The following results were reported:

Accuracy

Recent clinical trials comapring MCG to FFR (Fractional Flow Reserve) conducted independently in several institutions showed that MCG's has improved specificity (from 83% to 94%!) http://openheart.bmj.com/content/1/1/e000144.full.pdf+html If Dr. Joseph Shen's seven categories levels of myocardial ischemia (from the mildest early forms to the most severe stage of the disease process) are used using his new session analysis, it is possible that the accuracy could reach 95%! Also, regression analysis of patient's risk factors and biomarkers not only indicate the added value, but also, the model would push the accuracy to 100%!!

Prospective double blind clinical trails have demonstrated MCG's diagnostic accuracies with overall sensitivity at 90+%, specificity at 83% and a negative predictive value of 93% when compared to the gold standard coronary angiography [2,3,4,5,and 6]. Recently, MCG was compared to myocardial perfusion imaging (MPI) scan or nuclear stress testing. The peer review published evidence shows that MCG, a non-invasive, stress free test performed better: it generated better sensitivity (91% MCG vs. 85% MPI), specificity (87% MCG vs. only 14% MPI) and accuracy (92% MCG vs. 45% MPI). See comparison table below:

Parameter (%) MCG SPECT P-Values True positive 48 45 < 0.02 True negative 55 9 < 0.01 False positive 8 54 < 0.02 False negative 5 8 < 0.01 Confidence Intervals Sensitivity 91% 85% 0.79 – 0.97 Specificity 87% 14% 0.76 – 0.94 NPV 86% 45% 0.81 – 0.97 Parameter (%) MCG SPECT P-Values Accuracy (%) 92% 53% P < .001

Theory

MCG Technology is designed and engineered to use the principles of Cybernetics or Control Theory (discovered by Norbert Wiener) applied to biological systems (see the attached introductory chapters) approach to model the entire human heart as "a whole system", i.e. Applied Systems Engineering. This is achieved using a series of mathematical functions to deconstruct then reconstruct the information regarding the feed back embedded between the input (lead II) and the output (lead V5) or vice versa. The computational electrophysiological diagnostic system depicts the interaction between the entire myocardium and its intracardiac blood supply using the electrical signals collected from only two left ventricular leads (V5 and II), backed by a large cross sectional empirical database.

MCG Technology embodies a systems analysis approach and is the first clinically valid and commercially viable device increasingly used by physicians in their daily practices successfully to improve diagnostic accuracy for certain difficult to diagnose heart diseases, i.e. coronary ischemia.

Scientists and engineers have used similar methods to measure things such as the performance of an electrical grid in a geographic region, the predictability/interoperability/stability of a financial system, or even the presence of dark matters in the universe. MCG is the first system of this kind used to study the human heart.

In fact, the ability to detect coronary ischemia from resting EKG signals has been highly sought after and reagrded as "the Holy Grail" of diagnotic cardiology. Although, some cardiologists may not like to acknowledge this uncomfortable fact due to the potential financial losses they will suffer if MCG replaces their high costs imaging modalities, when MCG is used in primary care physicians' offices and at patients' homes. Imaging diagnostic machine makers, such as EKG, Stress EKG, CT, PET, MRI, Echo, Nuclear Scanners may also feel the same pressure, if MCG were to be widely adopted by physicians and patients around the globe.

Multifunction Cardiogram (MCG) Technology is a New Approach to the Diagnosis of Myocardial Ischemia

MCG is a non-invasive test that uses a systems engineering analysis approach to aid physicians in obtaining an objective and quantitative diagnosis of CAD, helping to address the limitations of stress tests and stress imaging modalities. A computational electrophysiological diagnostic tool, it does not involve the administration of any drug, radiation, physical or mental stress induction. Rather, it uses six mathematical transformations to study cardiac electrical signals. These transformations enable detection and analysis of changes to an individual’s electro-myocardial physiologic function that result from alterations in coronary artery blood flow. Instead of merely retrieving summed information about the electrical activity of cardio-myocytes at a single time point during a single cardiac cycle, as a traditional ECG does, MCG is specifically engineered to collect data over an 82-second period synchronously from only two leads, thereby obtaining information about the dynamic interaction of the myocardium and intracardiac blood flow over multiple complete cardiac cycles. MCG digitizes the individual’s electrical signals, deconstructs them via the aforementioned six mathematical transformations into multiple functional components (called indices) and then reconstructs them by mathematically integrating the indices into a cohesive pattern that allows rapid computerized pattern recognition. This deconstruction and resynthesis of the information extracted from these multiple functions allows one to study the interactions between the information obtained from each lead, which is impossible using conventional means such as a 12 lead ECG. By comparing the individual’s pattern to other patterns contained in a large database (described below), it is possible to model, quantify and understand the ongoing stress-strain interaction between the myocardium and intracardiac blood flow, which results in the ability to directly and objectively identify chronic or acute ischemic alterations that cannot be detected or measured by a traditional ECG.

It is important to emphasize that both the analytic approach and the information in the database have been validated. First, the indices and patterns obtained from the mathematical transformations have been empirically derived as well as verified and validated to be clinically meaningful. Second, all of the patient data entered into the database, against which an individual’s patterns are compared for the purposes of obtaining diagnostic information, has also been validated and verified. The index cluster and pattern for each patient’s data has been correlated with the findings of coronary angiography, other relevant diagnostic work-up and the final diagnosis of the treating physician, which has been verified by at least two independent expert diagnosticians in the field.

To accept the patient’s clinical information as part of the empirical database, there must have been an agreement between the two experts. If the two experts did not agree, a third expert reviewed the data. Any patient with unreliable data (e.g., inability to determine the record source, incomplete data entry, the patient’s diagnosis from unverifiable information, or an unusable MCG due to poor quality) was not included in the database. As information in the database accumulated, additional requisite internal validation, internal to the engineering process, was performed. After these validation procedures were completed and the system’s final iteration met the intended purposes of the original design, external peer review quality clinical validation trials of the entire system were carried out (i.e., the published clinical trials discussed below). As described below, the trials were designed to ask and answer specific questions relating to how accurately MCG predicts the existence of significant coronary artery disease in patients scheduled to undergo coronary angiography. The most recent trial compared MCG to myocardial stress testing with nuclear imaging, in this regard.

It is important to note that, defying convention, MCG is not merely a Signal Averaged ECG (SAECG), nor is it any type of usual modified ECG waveform analysis technologies, automatically assumed by the so-called "experts" in cardiology. Rather, it is an entirely new methodology based on a multifunction mathematical model of the electro-mechanical function of the heart using relational electrical data from two leads over multiple cardiac cycles instead of electrical data from a portion of one cardiac cycle (e.g., information contained in the standard "P, QRS, S-T" and T-wave segments from each individual lead). The conceptual difference between an ECG and the MCG is as follows: the ECG treats the heart as a single dipole that emits electrical currents into a three dimensional space as vectors. Physicians must be trained in how to read and interpret each of the single cycle ECG waveforms, which are broken into segments that are measured (e.g., the degree of S-T segment elevation or depression) one lead and one cardiac cycle at a time, and then integrate the data from each lead into a single interpretation that, in terms of detecting ischemia, is a rather insensitive snapshot of the heart. MCG, on the other hand, treats the heart as a whole organ by transforming the synchronous (and simultaneously collected) multi-cycle electrical data into a mathematical model that can be easily deconstructed into components and then reassembled to obtain a detailed understanding of the real-time in vivo, dynamic interactions between intracardiac blood flow and the myocardium. The result is that the indices discovered from this mathematical analysis extract (or generate) additional, heretofore unknown, information from the two cardiac leads, allowing identification of ischemia in a way that is impossible with traditional ECG technology. Unlike with a conventional ECG, the detection of ischemia using MCG is completely automated, and no physician expert reading or interpretation is required. Therefore, no "disagreement" between interpreters is possible for each test.

Clinical Accuracy

Premier Heart's Multifunction CardioGram TM a.k.a. MCG is the first of its kind adopting Cybernetic principles [3] based on Systems Analysis. It is the marriage of computer technology, digital empirical clinical database and clinical expertise to solve modern medicine's difficult challenges [1], such as accurate stress, radiation and drug-free non-invasive diagnosis of myocardial ischemia due to coronary artery disease.

In a recent clinical study by John Strobeck, M.D., MCG was compared directly with SPECT Nuclear MPI, and the results were verified using Coronary Angiography. In this study, hemodynamically relevant stenosis was diagnosed at cardiac catheterization in 53 of 116 patients (46%). The MCG device, after performing a computational analysis of two resting ECG leads (II and V5) in the frequency domain, calculated a "disease- severity" score from 0 to 20 for each patient. The severity score was significantly higher for patients with relevant coronary stenosis (5.4 ± 1.9 vs. 2.5 ± 1.9). The MCG (using a cut-off score for relevant stenosis of ≥ 4.0) correctly classified 103 of the 116 patients (89%) enrolled in the study as either having or not having relevant coronary stenosis (sensitivity- 91%; specificity- 87%; NPV- 92%; PPV- 86%). Subgroup analysis showed no significant influence of sex, age, history of hypertension, presence of LVH, history of diabetes, history of previous revascularization procedures (CABG or PCI), or resting ECG morphology, on the MCG device’s diagnostic performance. However, in 12 patients who were anemic at the time of their participation in the study, there was a trend toward a lower MCG specificity (71%) but this was not statistically significant due to the small number of anemic patients. SPECT nuclear myocardial perfusion imaging was abnormal in 99 of the 116 patients undergoing catheterization (85%), but only correctly classified 54 of the 116 patients (47%) entered in the study as either having or not having relevant coronary stenosis (sensitivity-85%; specificity–14%; NPV – 53%; PPV- 45%).

The new mathematical, resting ECG signal analysis Internet Based technology adopting Cybernetic principles in Systems Theory (MultiFunction-CardioGram) has been shown in this paired-comparison trial between the MCG, SPECT nuclear myocardial perfusion imaging, and coronary angiography to safely, accurately, and objectively identify patients with relevant coronary stenosis (>70%) with high sensitivity and specificity and high negative predictive value. Its overall performance was equal to, if not better, than SPECT nuclear MPI. Its potential use in the early evaluation of symptomatic coronary artery disease is present.

MCG is a completely non-traditional approach with a foundation in applied bio-mathematics based on Systems Analysis. Systems analysis is the dissection of a system into its component pieces to study how those component pieces interact and work. The MCG technology performs a systems analysis first and then subsequently a systems synthesis. Systems synthesis is the re-assembly of a system's component pieces back into a whole system-it is hoped an improved system. Through systems analysis and synthesis, we may add, delete, and modify system components toward our goal of improving the overall system. The approach of systems thinking is fundamentally different from the traditional ways of thinking and conducting business. Instead of focusing on the individual pieces of what is being studied, systems thinking focuses on the feed back relationships between the output of interest and another part of the same system. Therefore, instead of isolating smaller and smaller parts of a system, say an individual (or multiple) iron channel(s) or a protein, DNA or RNA molecule in vitro, or a segment of a single lead ECG signal analog waveform, such as S-T segment or Q-T interval, in contrast, systems analysis involves a much broader view of the system of interest, in our case the human heart as the whole organ, by looking at larger and larger interactions of at least two "life signal sources" the organ system and enabling us to understand the dynamics of the life organ better from a panoramic or the "big picture" view in vivo and in real time.

External links

Additional References

This article is issued from Wikipedia - version of the 10/31/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.