The electrocardiogram (ECG) is arguably the cardiologist’s best friend. Willem Einthoven’s invention created one of the most widely used diagnostic tests in clinical practice. The ECG is an easily available, patient-friendly, noninvasive, inexpensive, and reproducible technique, without peer for the diagnosis of myocardial ischemia, cardiac arrhythmias, structural changes of the myocardium, drug effects, and electrolyte and metabolic disturbances.¹ In addition to this, the ECG can provide information about the extent and severity of ischemia in acute coronary syndromes, assist in the localization of the site or pathway for tachycardias, identify heart failure patients who would benefit from cardiac resynchronization and identify familial diseases with risk of sudden cardiac death.

The ECG detects pathological changes prior to the development of structural changes in the heart. For instance, a strain pattern, defined as a down-sloping convex ST segment with inverted asymmetrical T-wave opposite the QRS axis in lead V5 or V6, is predictive of future risk of HF and death in hypertensive patients.² In fact, the 12 lead surface ECG is but one format to represent the electrical activity of the heart. Small changes in the morphology of the surface ECG, not visible to the human eye may reflect significant shifts in electrochemical messaging. Techniques such as signal averaged ECG, vectorcardiography aim to overcome these limitations and have been around for several decades.³ However, sophisticated and more advanced applications of the ECG have not found their way into the routine practice of clinical cardiology. Most of these are limited by low sensitivity which prohibits widespread application.

With advances in computational techniques and availability of big data collected from a variety of sources, there have been advances in unpacking the information encoded in several biologic signals. Deep learning is a type of machine learning technique with a diverse set of validated applications such as facial and speech recognition. Using deep learning to analyze retinal fundus images, Google has developed an algorithm that makes a diagnosis of diabetic retinopathy with a high degree of accuracy comparable to ophthalmologists.⁴ Furthermore, this algorithm detects cardiovascular events and even identifies gender from retinal images alone.⁵ This work represents a new way of scientific discovery, an alternative to the traditional hypothesis driven research approach. A data-driven approach can help generate newer hypothesis-guided experiments.

Deep learning for the analysis of ECG signals is an area of active research. Hannun and colleagues have shown comparable accuracy and even higher sensitivity for classifying arrhythmias using a deep neural network model versus board certified cardiologists.⁶ Work presented at scientific sessions 2019 from the University of Dusseldorf by Makimoto and colleagues showed that a convolutional neural network (CNN) was able to diagnose myocardial infarctions (MI) with more accuracy than cardiologists.⁷ The accuracy of MI recognition in ECGs by CNN was 84±2%, which was significantly higher than by cardiologists (64±7%, p<0.001). Designing clinical workflows where deep learning models provide rapid, expert level over read of ECGs, complemented by human oversight can have significant clinical impact.

The ECG signal represents the various electrical, chemical and mechanical events during the cardiac cycle. Deep learning algorithms have been able to decode these signals to make predictions about LVEF and diastolic dysfunction based on ECG data alone. Sengupta and colleagues used continuous wavelet transformation for post-processing the ECG signals and correlated several derived features for predicting abnormal myocardial relaxation as defined by abnormal tissue doppler.⁸ The area under the curve for their machine learning model for prediction of abnormal myocardial mechanical relaxation was 91% [CI: 0.86-0.95]. Attia and colleagues from Mayo Clinic presented their work at scientific sessions 2019 on predicting LVEF using single lead ECG signals acquired by an ECG-enabled stethoscope.⁹ A neural network previously used on 12-lead ECG for predicting EF was trained on single lead ECG data and was able to predict low EF with an area under the curve of 0.88 [CI:0.80-0.94] for EF<=35% and 0.81 [CI:0.72-0.88] for EF<50%

These findings and many others are constantly expanding the utility of the ECG in clinical practice wherein, the ECG provides more nuanced and finer details such as ejection fraction and predicts future outcomes with high accuracy. This represents significant progress from the days of the string galvanometer of Einthoven. Modern cardiovascular medicine is faced with many challenges related to prevention, diagnosis and treatment of disease, compounded by rising healthcare costs. The inexpensive and reliable best friend of the cardiologist – the ECG – can reveal its secrets to tackle these problems. The words of Einthoven remind us that there remains much to be done for decoding these secrets, “An instrument takes its true value not so much from the work it possibly might do but from the work it really does.”¹⁰ Future research is needed to validate the promise of these exciting new findings.

References:

1. Wellens HJ, Gorgels AP. The electrocardiogram 102 years after einthoven. Circulation. 2004;109:562-564
2. Okin PM, Devereux RB, Nieminen MS, Jern S, Oikarinen L, Viitasalo M, Toivonen L, Kjeldsen SE, Dahlof B, Investigators LS. Electrocardiographic strain pattern and prediction of new-onset congestive heart failure in hypertensive patients: The losartan intervention for endpoint reduction in hypertension (life) study. Circulation. 2006;113:67-73
3. Gatzoulis KA, Arsenos P, Trachanas K, Dilaveris P, Antoniou C, Tsiachris D, Sideris S, Kolettis TM, Tousoulis D. Signal-averaged electrocardiography: Past, present, and future. J Arrhythm. 2018;34:222-229
4. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J, Kim R, Raman R, Nelson PC, Mega JL, Webster DR. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402-2410
5. Poplin R, Varadarajan AV, Blumer K, Liu Y, McConnell MV, Corrado GS, Peng L, Webster DR. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng. 2018;2:158-164
6. Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, Ng AY. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 2019;25:65-+
7. Makimoto H, Hoeckmann M, Gerguri S, Clasen L, Schmidt J, Assadi-Schmidt A, Bejinariu A, Mueller P, Gloeckner D, Angendohr S, Brinkmeyer C, Kelm M. Abstract 13914: Artificial intelligence finds myocardial infaction in ecg more accurately than cardiologists. Circulation. 2019;140:A13914-A13914
8. Sengupta PP, Kulkarni H, Narula J. Prediction of abnormal myocardial relaxation from signal processed surface ecg. J Am Coll Cardiol. 2018;71:1650-1660
9. Attia ZI, Dugan J, Maidens J, Rideout A, Lopez-Jimenez F, Noseworthy PA, Asirvatham S, Pellikka PA, Ladewig DJ, Satam G, Pham S, Venkatraman S, Friedman P, Kapa S. Abstract 13447: Prospective analysis of utility of signals from an ecg-enabled stethoscope to automatically detect a low ejection fraction using neural network techniques trained from the standard 12-lead ecg. Circulation. 2019;140:A13447-A13447
10. Rosen MR. The electrocardiogram 100 years later: Electrical insights into molecular messages. Circulation. 2002;106:2173-2179

The views, opinions and positions expressed within this blog are those of the author(s) alone and do not represent those of the American Heart Association. The accuracy, completeness and validity of any statements made within this article are not guaranteed. We accept no liability for any errors, omissions or representations. The copyright of this content belongs to the author and any liability with regards to infringement of intellectual property rights remains with them. The Early Career Voice blog is not intended to provide medical advice or treatment. Only your healthcare provider can provide that. The American Heart Association recommends that you consult your healthcare provider regarding your personal health matters. If you think you are having a heart attack, stroke or another emergency, please call 911 immediately.

1. What is digital health? Digital health is the application of digital technology using mobile applications or wearable sensors for the betterment of health.¹ This offers a distinct pathway for advancing healthcare as compared to medical devices and drugs. Digital health is uniquely positioned to tackle multiple unmet needs in healthcare such as improving medication adherence, enhancing patient experience, increasing access to care and reducing healthcare costs. The digital health sector is on track to raise over $8.4 billion in 2019.² Riding on the winds of optimism from multiple stakeholders, digital health startups have an incredible opportunity and an equally important responsibility to deliver results. The Health Tech and Innovation Summit at the AHA Scientific Sessions 2019 in Philadelphia was the hub for thought leaders from academia and industry to build relationships and share insights on shaping the future of medicine. It offered a chance for early career members to make connections and learn about the current landscape of digital health.
2. The need for more evidence. During his AHA presidential address, Robert Harrington, MD emphasized, ‘evidence matters’. As the number of digital health startups claiming to disrupt healthcare continues to rise rapidly, it is becoming increasingly important to ascertain the credibility of these claims. Traditionally, drugs and devices are subject to strict regulatory oversight for the assessment of clinical efficacy and safety prior to widespread use. On the contrary, digital health startups are not directly incentivized for generating evidence for the validation of their technology. Mohamed Elshazly, MD who is a cardiac electrophysiologist and health tech entrepreneur shared his experience as the founder of Ember Medical, ‘Startups have to move fast with product development to keep up with the need for raising capital.’ Clinical trials need significant time and capital expenditure which many early startups cannot afford. For instance, conducting a NIH funded randomized trial from grant application to publication takes about seven years.³ 
3. Challenges faced by startups. Startups constantly cope with the pressures arising from limited resources and considerable uncertainty about the validity of their business model. That’s why many startups embrace a hypothesis-driven approach to conduct rapid testing for pressure testing assumptions regarding their business model.⁴ Unfortunately, many healthcare startups end up focusing heavily on product development and underestimate the value of understanding patient preferences and physician workflows.⁵ Elshazly shared an important statistic to give perspective, ‘Only 5% of startups ever succeed’. Although digital health presents a challenge, there is also an extra-ordinary opportunity for early career members and startups to come together for developing groundbreaking innovations that could revolutionize the practice of medicine. ‘This is where physicians can leverage the skills acquired in an academic environment and make a broader impact’, said Bimal Shah, MD, MBA, Chief Medical Officer at Livongo.
4. How to build a career in digital health? An important question for early career members is figuring out funding mechanisms to support themselves. Analysis of NIH funding shows that the age of obtaining the first independent grant funding is rising, while the overall funding capacity of the NIH is declining.⁶ Therefore, early career investigators stand to benefit from working with startups, doing clinical research and generating high quality evidence. For startups, these partnerships provide the opportunity to introduce scientific rigor in product development and conducting validation studies. It is important for early career members to be supported by senior mentors who share their vision. Maulik Majmudar, MD, medical officer at Amazon cautions, ‘It is crucial to find alignment between your personal goals and those of your organization. It is also important to show your value to the leadership by demonstrating success’. Shah shares another tip, ‘Health systems across the country are investing in creating centers for innovation. This can be another way to get support for working in this space’. In conclusion, with the changing healthcare landscape and the need for innovation in medicine, there is a need for clinician innovators. Early career investigators are uniquely positioned to lead the way in digital health. Gathering high quality evidence will be crucial to achieving the full potential of what digital health has to offer.

References:

1. Turakhia MP, Desai S, Harrington RA. The outlook of digital health for cardiovascular medicine challenges but also extraordinary opportunities. JAMA Cardiol. 2016 Oct 1;1(7):743-744. doi: 10.1001/jamacardio.2016.2661.
2. Digital health investments in 2019 poised to surpass 2018. Fierce Healthcare. 2019 https://www.fiercehealthcare.com/tech/4-2b-invested-digital-health-first-half-2019-as-sector-poised-to-surpass-2018
3. W. Riley, R. Glasgow et. al. Rapid, responsive, relevant (R3) research: a call for a rapid learning health research enterprise. Clin Transl Med. 2013 May 10;2(1):10. doi: 10.1186/2001-1326-2-10.
4. Eisenmann T RE, Dillard S. Hypothesis-driven entrepreneurship: The lean startup. Harvard Business School Background Note.812-095
5. Why do digital health startups keep failing? Fast Company. 2019. https://www.fastcompany.com/90251795/why-do-digital-health-startups-keep-failing
6. Rockey S. Age distribution of NIH principal investigators and medical school faculty. 2012. National Institutes of Health Extramural Nexus. https://nexus.od.nih.gov/all/2012/02/13/age-distribution-of-nih-principal-investigators-and-medical-school-faculty/

The views, opinions and positions expressed within this blog are those of the author(s) alone and do not represent those of the American Heart Association. The accuracy, completeness and validity of any statements made within this article are not guaranteed. We accept no liability for any errors, omissions or representations. The copyright of this content belongs to the author and any liability with regards to infringement of intellectual property rights remains with them. The Early Career Voice blog is not intended to provide medical advice or treatment. Only your healthcare provider can provide that. The American Heart Association recommends that you consult your healthcare provider regarding your personal health matters. If you think you are having a heart attack, stroke or another emergency, please call 911 immediately.