12-lead EKG Research Articles

Abstract 14626: Dissecting Out Risk Factors: A Case of Spontaneous Coronary Artery Dissection Without Traditional Risk Factors, in the Presence of Methamphetamine Use

Introduction: Methamphetamine use is not a traditional risk factor for spontaneous coronary artery dissection (SCAD). There have been several case reports suggesting an association between methamphetamine use and SCAD. Case: We present a case of a 50-year-old female with a history of hypertension, hyperlipidemia, stroke, and active tobacco use who presented with substernal chest pain radiating to the back and abdomen with associated dyspnea and diaphoresis. The patient was also taking warfarin for a prior history of deep venous thrombosis. Her serum 5 th generation troponin level was elevated to a peak of 1135 ng/L, and a 12-lead EKG showed ST-elevations not meeting STEMI criteria (1mm in V3, 2mm in V4, and 0.5mm in V5). Coronary angiography showed a short section of SCAD type 1 involving the mid portion of the LAD with TIMI 3 flow. There was no significant atherosclerotic disease throughout any of the vessels. The patient was managed conservatively with medical therapy and had resolution of her pain. CT-angiography of the chest, abdomen and pelvis was performed to rule out dissection involving the aorta and its branches and was unrevealing. Urine toxicology screening returned positive for methamphetamine. Given a lack of other traditional risk factors aside from gender, the patient was diagnosed with SCAD secondary to methamphetamine use. Discussion: Traditional risk factors for SCAD include female sex, fibromuscular dysplasia, connective tissue disease, multiparity (our patient was parity 1), and exogenous hormone use. Methamphetamine use as well as prescription amphetamines have been associated with SCAD in several case reports. SCAD tends to occur in women with an absence of risk factors for coronary artery disease. However, even in patients with multiple risk factors for atherosclerosis and an absence of risk factors for SCAD, SCAD should not be excluded in the differential when a history of amphetamine use is elicited.

Artificial intelligence-guided, single-lead EKG may be a game-changer for symptom-to-balloon time reduction in ST-elevated myocardial infarction

Abstract Background Over decades, efforts to shave off life-saving minutes from ST-Elevated Myocardial Infarction (STEMI) care centred on reducing door-to-needle and door-to-balloon times. We firmly believe that symptom-to-balloon time should prove a better focus to this end. Challenges come with this goal as it heavily relies on a patient's perception and initiative to seek care, which we deem intelligent and wearable Artificial Intelligence (AI)-driven Single Lead EKG technologies as an attractive solution in modern-day cardiology. Purpose To provide an accurate, accessible, and cost-effective AI-driven Single Lead STEMI detection algorithm that can be embedded into wearable devices and employed in a self-administered fashion. Methods Database: EKG records from Mexico, Colombia, Argentina, and Brazil from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10[s] length with a sampling frequency of 500 Hz, including the following balanced classes: angiographically confirmed and unconfirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding those mentioned above). Cardiologists manually checked the label of each record to ensure precision. Pre-processing: We discard the first and last 250 samples as they may contain a standardisation pulse. The study applied a digital low pass filter of order 5 with a frequency cut-off of 35 Hz. The mean was subtracted from each Lead. Classification: The determined classes were “STEMI” (Including STEMI in different locations of the myocardium – anterior, inferior, and lateral); and “Not-STEMI” (Combination of randomly sample, branch blocks, non-specific ST-T changes, and abnormal records – 25% of each). Training and Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. A different model was trained and tested for each Lead, using the central 4,500 samples of the records. The last dense layer outputs a probability for each report of being STEMI or Not-STEMI. Lead V2 showed the best overall results. The model was further tested through the same methodology using the best Lead with a subset of the previous data, excluding the unconfirmed STEMI EKG records (Total 7,230 12-lead EKG records for Confirmed Only STEMI dataset). Performance metrics were reported for each experiment and compared. Results Combined STEMI data: Accuracy: 91.2%; Sensitivity: 89.6%; Specificity: 92.9%. Confirmed STEMI Only dataset: Accuracy: 92.4%; Sensitivity: 93.4%; Specificity: 91.4% (Figure 1). Conclusion By assiduously improving the quality of the model's input, we continue to assess our algorithm's performance and reliability for future clinical validation as a potential remote monitoring and early STEMI detection device. Funding Acknowledgement Type of funding sources: None.

Performance metrics of AI-enhanced single lead EKG maintained after entry of organised clustered data

Abstract Background Our experience in creating innovative Artificial Intelligence-guided single lead EKG methodologies for ST-Elevation Myocardial Infarction (STEMI) detection within complex EKG records has been previously validated. Purpose By expanding the intricate variables of our previously tested algorithm input, we seek to further improve our STEMI detecting tool. Methods 11,567 12-lead EKG records (10-s length, 500 Hz sample frequency) derived from the Latin America Telemedicine Infarct Network database from April 2014 to December 2019. From these records, we included the following balanced classes: angiographically confirmed and unconfirmed STEMI (divided by wall affected), branch blocks, non-specific ST-T changes, normal, and abnormal (Remaining 200+ CPT codes). Cardiologist annotations ensured precision (Ground truth). Determined classes were “STEMI” and “Not-STEMI”. A 1-D Convolutional Neural Network model was trained and tested for each lead with dataset proportions of 90/10, respectively. The last dense layer outputs a probability for each record being STEMI/Not-STEMI. The analysis also included performance metrics and false-negative reports. Results Overall, the most promising Single lead for STEMI detection was V2 (91.2% Accuracy, 89.6% Sensitivity, and 92.9% Specificity). 55% of false negatives were inferior wall STEMI (Table 1). Conclusion Appreciable progress of our new methodology compared to our previous experiences in AI-guided Single Lead for STEMI detection, especially for lead V2. By performing a thorough analysis of false-negative reports, we aspire to identify potential areas of STEMI detection weakness which will become the focus of future ventures. Funding Acknowledgement Type of funding sources: None.

BIOPROSTHETIC AORTIC VALVE FAILURE IN END-STAGE RENAL DISEASE AND REINTERVENTION

BIOPROSTHETIC AORTIC VALVE FAILURE IN END-STAGE RENAL DISEASE AND REINTERVENTION

SIMPLIFIED EKG ONLY METHOD TO ACHIEVE PHYSIOLOGIC PACING

His pacing (His-P) and left bundle branch pacing (LBB-P) are new modalities to obtain a more physiologic pacing (PP); they require however, new tools and new skills. We describe a simplified method to achieve LBB-P, using only a 12-lead EKG to guide lead deployment; mid septum (not too anterior close to His area or LV summit and not too posterior is sought).

PO-674-07 EKG TECHNOLOGY: IT IS TIME FOR A CHANGE!

Technology for obtaining pediatric EKGs has not changed in over 70 years. Current guidelines recommend a 12-lead EKG, which takes approximately 7 minutes to complete. Newer adult technology utilizes between 1-6 leads for EKG analysis. There has not been a study in pediatrics to assess the minimum number of leads required to attain diagnostic accuracy.

3rd-Degree Atrioventricular Block.

3rd-Degree Atrioventricular Block.

Abstract 9216: Fontaine Leads and Their Further Modifications in Arrhythmogenic Cardiomyopathy

Introduction: Epsilon wave, one of the major criteria for the diagnosis of arrhythmogenic cardiomyopathy (ACM), is present in only 30% of ACM patients. Fontaine Leads have been shown to facilitate the visualization of Epsilon waves. Hypothesis: Modified Fontaine leads may help in better visualization of Epsilon waves in ACM patients than standard Fontaine leads. Methods: We prospectively enrolled ACM patients under our follow-up. Fontaine and the modified Fontaine EKGs were recorded ( Figure 1A ). The duration and amplitude of Epsilon waves, when present, were measured. Duration-amplitude product (DAP) was computed and compared. Results: EKGs of seventeen patients were available for analysis. Four patients (24%) had an Epsilon wave on a 12 lead EKG. Thirteen patients (76%) had Epsilon waves either on 12 lead EKG or Fontaine modification leads. These 13 patients (10 males and 3 females; mean age: 40.5 ±13 years) were included in the analysis. ( Table 1 ) Epsilon waves were seen in 10 (77%) patients in Standard Fontaine Leads. In the rest of the modifications, Epsilon waves were seen in 85% (11), 77% (10), 80% (8), and 80% (8) in Right, Left, Right-Left, and Left-Right Fontaine leads, respectively. ( Table 1 ) In only one patient (8%), the Standard Fontaine Epsilon wave had maximum DAP. Right, Left, Right-Left, and Left-Right Fontaine leads had maximum DAP in 5 (39%), 3 (23%), 2 (20%), and 3 (30%) patients, respectively. Conclusions: A modified Fontaine lead position may facilitate the Epsilon wave visualization in patients suffering from ACM when standard EKG and Fontaine lead EKGs fail to do so. A well-designed randomized study may be needed to evaluate the utility of modified Fontaine Leads in ACM.

Abstract 13331: Case Report Of Transient Right Bundle Branch Block With S1q3t3 Pattern In Acute Pulmonary Embolism

69 year old woman with hypertension, sleep apnea and who had a recent knee replacement, was brought in to the emergency room (ER) for syncope. She had her physiotherapy session earlier in the day and became symptomatic with dizziness and shortness of breath and passed out. In the ER she had a systolic blood pressure (SBP) of 90mmHg and an oxygen saturation (O2 sat) of 80% on room air. She was given fluid bolus with improvement of SBP to 110mmHg. O2 sat improved to 99% with 10L of oxygen. Treatment was started with full dose of Enoxaparin subcutaneously. A 12-lead electrocardiogram (EKG) showed sinus tachycardia (ST) at 117 beats per minute (BPM), right bundle branch block (RBBB) and S1Q3T3 pattern. A bedside echocardiogram showed right ventricular (RV) distension. A CT-angiogram showed bilateral main stem pulmonary emboli (PE) with signs of RV strain. Patient was admitted and remained hemodynamically stable. A repeat EKG done the following day showed ST at 110 BPM with resolution of RBBB. An echocardiogram done now showed normal RV size and function. Patent was eventually discharged home on full dose apixaban. Q3S1T3 Figure 1 - ST, RBBB, S1Q3T3 pattern Figure 2 - ST Discussion: The patient presented with new RBBB (Figure 1) due to RV strain from acute PE as shown by the CT-angiogram and bedside echocardiogram. The EKG also showed S1Q3T3 pattern. With the resolution of the RV strain the following day, as noted on the subsequent echocardiogram, the 12 lead EKG showed the resolution of the RBBB and the QRS complex became narrow (Figure 2). RBBB is thought to be caused by acute RV overload and dilatation, accompanied by subendocardial ischemia in the right bundle. The S1Q3T3 pattern is historically considered as a “classic” EKG pattern associated with acute PE, even though it is neither sensitive nor specific for acute PE. Conclusion: The RBBB along with the S1Q3T3 pattern and its resolution with improvement of RV hemodynamics, is the first reported case in the literature.

VASOPRESSIN-INDUCED ST-ELEVATION MYOCARDIAL INFARCTION

TOPIC: Critical Care TYPE: Fellow Case Reports INTRODUCTION: Vasopressin is commonly used to restore blood pressure in hyperdynamic hemodynamic states, thereby reducing catecholamine requirements. The effects of vasopressin are primarily caused by the rise in the mean arterial pressure (MAP) due to systemic vasoconstriction, which, depending on the infusion rate, can also produce notable vasoconstrictive effects on the coronary microvasculature thereby reducing coronary blood flow despite an increase in coronary perfusion pressure. Here we present an interesting case of vasopressin-induced ST-elevation myocardial infarction (STEMI) on postoperative day two of cardiac catheterization for initial STEMI. CASE PRESENTATION: A 67-year-old male with a past medical history of hypertension, hypothyroidism presented to the emergency department (ED) with the complaint of left shoulder pain. In the ED waiting room, the patient suddenly collapsed losing consciousness, and was found to be in cardiac arrest. ACLS protocol was immediately started and ROSC was achieved. An electrocardiogram (EKG) was performed which showed STEMI in the anterolateral leads. Code STEMI was activated, and the patient was taken for the cardiac catheterization where LAD stenosis was observed and stented. Post-procedure, the patient was transferred to Cardiac ICU, where an amiodarone drip was initiated for recurrent episodes of non-sustained ventricular tachycardia. The hospital course was further complicated with pneumonia leading to acute hypoxemic respiratory failure and septic shock. The patient was placed on norepinephrine and appropriate antibiotics. Vasopressin was added to reduce catecholamine requirements and to achieve a target MAP. On postoperative day two, the patient was noted to have ST elevation on the tele monitor, a twelve lead EKG confirmed anteroseptal STEMI. A left heart catheterization revealed a patent LAD stent with no new findings and recommendations were made to stop vasopressin infusion and to continue the rest of the treatment. The patient was successfully extubated to BiPAP, eventually made a slow and steady recovery, and was discharged home with follow-up appointments. DISCUSSION: It has been shown that the levels of vasopressin increase as part of the stress response, which has been shown to exert vasoconstrictive effects on the coronary arteries mainly in the non-epicardial vessels of the microcirculation. These high levels in states like myocardial infarction can lead to coronary slow phenomenon mediating ischemia-perfusion injury. CONCLUSIONS: In advanced distributive shock with accompanied cardiogenic shock state, utmost caution should be taken as the vasoconstrictor properties of vasopressin are not accompanied by positive inotropic qualities, which may depress cardiac function even further as a result of impaired coronary blood flow despite increased coronary artery perfusion pressure and in severe cases can lead to myocardial ischemia. REFERENCE #1: Nobian A, Mohamed A, Spyridopoulos I. The role of arginine vasopressin in myocardial infarction and reperfusion. Kardiol Pol. 2019 Oct 25;77(10):908–17. REFERENCE #2: Hauser B, Asfar P, Calzia E, Laporte R, Georgieff M, Radermacher P. Vasopressin in vasodilatory shock: is the heart in danger? Crit Care. 2008;12(2):132. REFERENCE #3: Asfar P, Radermacher P. Vasopressin and ischaemic heart disease: more than coronary vasoconstriction? Crit Care. 2009;13(4):169. DISCLOSURES: No relevant relationships by Mohammed Ali, source=Web Response No relevant relationships by Humayun Anjum, source=Web Response No relevant relationships by Rahul Dadhwal, source=Web Response No relevant relationships by Salim Surani, source=Web Response

Ultrasound for Critical Care Physicians: Sometimes It’s Better to Be Lucky than Smart

We recently responded to a code arrest alert in the rehabilitation ward of our hospital. The patient was a 47-year-old man who experienced nausea and diaphoresis during physical therapy. Shortly after the therapists helped him sit down in bed, he became unconsciousness and pulseless. The initial code rhythm was a narrow-complex pulseless electrical activity (PEA). He was intubated, received three rounds of epinephrine during approximately 10 minutes of ACLS/CPR before return of spontaneous circulation (ROSC), and was subsequently transferred to the ICU. Shortly after arriving, a 12-lead EKG was performed (Figure 1), and PEA recurred. Approximately ten-minutes into this second episode of ACLS, a cardiology consultant informed the code team of an S1,Q3,T3 pattern on the EKG. A point-of-care (POC) echocardiogram performed during rhythm checks was technically-limited, but showed a dilated hypokinetic right ventricle (Video 1). Approximately twenty-minutes into the arrest, 50mg tissue plasminogen activator (tPA) was administered, and return …

Calciphylaxis in Association With Hungry Bone Syndrome. A Possible Risk Factor?

Background: Calciphylaxis (calcific uremic arteriolopathy) is a rare complication seen in, although not limited to, patients with end-stage renal disease (ESRD). The abnormal regulation of calcium (Ca) and phosphorus (P) homeostasis in this patient group results in intravascular Ca deposition. These patients often develop secondary/tertiary hyperparathyroidism, presenting unique treatment challenges. When patients do not respond to medical therapy, parathyroidectomy is an option that may be complicated by hungry bone syndrome (HBS). We present a case of a patient with calciphylaxis with HBS post-parathyroidectomy.Case Report: The patient is a 41 y.o. male with ESRD on hemodialysis who presented with lower extremity ulcers complicated by calciphylaxis. On admission, the PTH was elevated at 2200 U with a normal corrected Ca 8.7 and P 8.5. He was found to have a non-displaced pathologic fracture of the right femoral neck. CT scan of the neck revealed nodular parathyroid hyperplasia affecting all four glands. His hyperparathyroidism was managed medically with cinacalcet, phosphate binder, and sodium thiosulfate to optimize his condition before surgery.He underwent a subtotal parathyroidectomy, with post-op course complicated by HBS. Repeat labs showed PTH 444, P 6.1, corrected Ca 7.4, and ionized Ca <4. Despite frequent repletion with IV Ca and addition of calcitriol, he remained persistently hypocalcemic with symptoms (paresthesia, perioral numbness) and prolonged QTc (560 ms) on 12-lead EKG. After weighing the more imminent risk of unstable arrhythmia versus exacerbation of HBS by targeting too high of a Ca level post-op, ICU admission was decided where Ca levels could be more closely monitored and titrated. The patient eventually demonstrated an improvement in his Ca level and symptoms.Discussion: This patient with ESRD complicated by hyperparathyroidism presented with ulcers and calciphylaxis refractory to medical therapy, requiring parathyroidectomy. HBS was a concern in this particular patient given his risk factors.Hypocalcemia is an expected electrolyte imbalance that usually resolves within 2–4 days after parathyroidectomy. Severe and persistent hypocalcemia on day 4 after the procedure should raise concern for HBS. It has been shown that the risk is higher in patients who have secondary hyperparathyroidism, prolonged duration of elevated PTH, age >60, and radiologic evidence of bone disease.ConclusionCalciphylaxis is an uncommon but potentially fatal illness seen in ESRD patients associated with Ca and P abnormalities. Whether this may increase the risk of HBS status-post parathyroidectomy is unknown; however, HBS requiring ICU management to treat refractory hypocalcemia has been reported in this group1. It is arguable that calciphylaxis may serve to identify such patients.(1) Hassanein M, et al. BMJ Case Rep 2018;11:e226696. doi:10.1136/bcr-2018–226696

Abstract 14131: Proof of Concept: Interpretation of EKG With Image Recognition and Convolutional Neural Networks

Introduction: EKGs are the cornerstone of management in cardiovascular diseases. There have been multiple efforts to computerize the EKG interpretation with algorithms, which unfortunately are machine specific and proprietary. We propose the development of an image recognition model which can be used to read EKG strips (which use standard notations) and hence be used universally. Method: A convolutional neural network (CNN) was trained to classify 12-lead EKGs between seven clinically important diagnostic classes (Figure 1a). Pre-labeled EKG recordings (6-60s) from a publicly available data set on PhysioNet were used to construct the images. The EKG images displayed the 12 channel traces, of 2.5s each, on a consistent 4x3 grid at a resolution of 800x800 pixels (Figure 1a). The data set (23,336 images) was divided into training, tuning, and validation sets; containing 70%, 15%, and 15% of the images, respectively. An austere variation of the MobileNetV3 model was trained from the ground up on the labeled training set. Stochastic gradient descent (SGD) was used to minimize the cross-entropy loss. Training was halted when the tuning loss had not improved from its previous minimum by 0.05% over the past 10 epochs. Results: The model trained over 52 epochs of batches of 32 images. The model’s accuracy was tested using the validation set (which was not used for development of model) and reported as a confusion matrix (Figure 1b). The accuracy per class varies from 69-91%. Conclusion: We used a labeled dataset of EKG images to develop a CNN model to predict seven different diagnostic classes with good accuracy. This is a novel approach to EKG interpretation as an image recognition problem and thus generates the ability to create diagnostic algorithms that are not dependent on proprietary voltage signals generated by commercial EKG machines. With the addition of more images to the data set and higher computing power we are confident that we can achieve enhanced accuracy.

Abstract 14494: Once You 1c It, You Can’t Unsee It: A Case of Flecainide Toxicity

Introduction: Flecainide is a class 1c antiarrhythmic commonly used for the treatment of atrial and ventricular arrhythmias in the absence of underlying structural heart disease. The significant proarrhythmic effects of the drug warrant familiarity with the drug and its toxicity. Flecainide overdose, whether intentional or iatrogenic, is a life threatening emergency with mortality rates as high as 22.5%. We present a case of intentional flecainide overdose and its management. Case: A 78-year-old man with a history of heart failure, paroxysmal atrial fibrillation on flecainide, presented to a local ED after a suicide attempt. He was initially hemodynamically stable and a 12-lead EKG revealed a wide-QRS bradyarrhythmia (See figure 1). Electrolyte panel showed normal potassium and pH. During transport to our tertiary cardiac intensive care unit, the patient declined and was critically ill on arrival. The diagnosis of flecainide toxicity was suspected and therapy was initiated on arrival. Despite therapy with sodium bicarbonate and fat emulsion, the patient continued to decline. Renal replacement therapy was started and the patient was evaluated for mechanical circulatory support. Ultimately, the patient’s family elected for palliative extubation. The patient’s flecainide level returned more than four times above the therapeutic range. Discussion: This case highlights the importance of a high index of suspicion when faced with a wide-QRS arrythmia in a patient with suspected antiarrhythmic overdose. The persistence of these rhythms after correction of acid-base abnormalities and electrolyte derangements should prompt aggressive, empiric treatment of potential overdose. The presence of electromechanical dyssynchrony in this context is an ominous sign and should prompt simultaneous evaluation for biventricular mechanical circulatory support concomitant with medical therapy for suspected overdose. Figure 1

Baby steps in the path of modifying the role of cardiologists for interpreting EKG for AMI

Abstract Background EKG interpretation is slowly transitioning to a physician-free, Artificial Intelligence (AI)-driven endeavor. Our continued efforts to innovate follow a carefully laid stepwise approach, as follows: 1) Create an AI algorithm that accurately identifies STEMI against non-STEMI using a 12-lead EKG; 2) Challenging said algorithm by including different EKG diagnosis to the previous experiment, and now 3) To further validate the accuracy and reliability of our algorithm while also improving performance in a prehospital and hospital settings. Purpose To provide an accurate, reliable, and cost-effective tool for STEMI detection with the potential to redirect human resources into other clinically relevant tasks and save the need for human resources. Methods Database: EKG records obtained from Latin America Telemedicine Infarct Network (Mexico, Colombia, Argentina, and Brazil) from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10-seconds length with sampling frequency of 500 [Hz], including the following balanced classes: unconfirmed and angiographically confirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding the ones included in other classes). The label of each record was manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: The first and last 250 samples were discarded as they may contain a standardization pulse. An order 5 digital low pass filter with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: The determined classes were STEMI (STEMI in different locations of the myocardium – anterior, inferior and lateral); Not-STEMI (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training &amp; Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10; respectively. The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. Additional testing was performed with a subset of the original dataset of angiographically confirmed STEMI. Results See Figure Attached – Preliminary STEMI Dataset Accuracy: 96.4%; Sensitivity: 95.3%; Specificity: 97.4% – Confirmed STEMI Dataset: Accuracy: 97.6%; Sensitivity: 98.1%; Specificity: 97.2%. Conclusions Our results remain consistent with our previous experience. By further increasing the amount and complexity of the data, the performance of the model improves. Future implementations of this technology in clinical settings look promising, not only in performing swift screening and diagnostic steps but also partaking in complex STEMI management triage. Funding Acknowledgement Type of funding source: None

Waddling beyond door to balloon times and impinging true ischemic times with artificial intelligence-guided single lead EKG for STEMI detection

Abstract Background The present process of STEMI detection is cumbersome as it utilizes outdated equipment and requires a trained technician and an expert cardiologist. We have developed a patient-administered, Artificial Intelligence (AI) guided, Single Lead EKG for early STEMI detection. Purpose To answer the question “Is early STEMI detection possible with a Single Lead EKG?” Methods We experimented with an AI-guided algorithm for a single-lead EKG for STEMI detection with the following step-wise developments: 1) An AI algorithm that predictably interprets STEMI using a 12-lead EKG; 2) An AI algorithm for STEMI detection using a single-lead EKG; 3) A methodology for identifying the best single lead to detect STEMI; 4) Advanced AI algorithms for STEMI localization with a single-lead EKG. The AI methodology was as follows: Sample: The mammoth Latin American Telemedicine Infarct Network telemedicine database that provides an umbrella of AMI management to 100 million patients in Brazil, Colombia, Mexico, Chile, and Argentina was queried for cardiologist annotated EKG. A total of 8,511 EKG and 90,592 classified heartbeats were selected for the experiments. Preprocessing: segmentation of each ECG into individual heartbeats. Training &amp; Testing: 90% and 10%, respectively, of the total dataset. Classification: 1-D Convolutional Neural Network; classes were construed for each heartbeat. Performance indicators were calculated per lead. Results The algorithm was able to provide an accuracy of 91.9%. Lead V2 yielded the best results among individual leads for STEMI detection. Conclusions Early experiments provide a framework for augmenting STEMI detection with the use of AI-guided, single lead techniques. Such approaches seem rational as we target the reduction of true STEMI ischemic times. Funding Acknowledgement Type of funding source: None

Artificial intelligence methodology: multi-label classification of abnormal EKG records

Abstract Background Our previous experience with Artificial Intelligence (AI)-conducted EKG characterization displayed outstanding results in fast and reliable identification of Normal EKGs within the International Telemedical System (ITMS)'s massive record repository. By expanding the array of recognizable cardiovascular entities, we upgraded our methodology to accurately discriminate an anomaly amongst a highly complex database of EKG records. Purpose To present a feasible AI-guided filter that can accurately discriminate and classify Normal and Abnormal EKG records within a multilabeled cardiologist-annotated EKG database. Methods ITMS developed and tested the “One Click”' process, a “Normal/Abnormal” EKG assessing AI algorithm, by incorporating it into their digital EKG reading platform where cardiologists continuously report their findings remotely in real time. To ameliorate the diagnostic range of the algorithm, a separate dataset of 121,641 12-lead EKG records was consolidated from the ITMS database from October 2011 to January 2019. Only de-identified data was used. Preprocessing: The first 2s of each short lead and 9s of the long lead were considered. Limb leads I, II and III; and precordial leads V1, V2, V3, and V5 were used. The mean was removed from each lead. AI models/Classification: Two models were created and tested independently based on the method of EKG acquisition (69,852 records transtelephonic [TTP]; 52,259 mobile transmission [MOB]). Each record is categorized into six disjoint classes based on the most common types of cardiac disorders (Low/null co-occurrence pathologies in these datasets were grouped into analogous groups). Training/Testing: Distribution of both sets per transmission type was performed through a greedy algorithm, which identified multiple diagnoses per EKG record and labeled it separately to the corresponding group, ensuring sufficient samples per class. Detailed class distribution is shown below. An inception convolutional neural network was implemented; “Normal” or “Abnormal” labels were assigned to each EKG record independently and were compared to cardiologists' reports; performance indicators were calculated for each model and group. Results MOB model accrued an average accuracy of 86.7%; sensitivity of 90.5%; and specificity of 83.9%. TTP model yielded an average accuracy of 77.2%; sensitivity of 91.1%; and specificity of 69.4% (Lower values were attributed to the “Ventricular Complexes” group, which challenged the algorithm by having a smaller ratio of abnormal exams). Detailed results of each training set are shown below. Conclusion Providing an effective and reliable multilabel-capable EKG triaging tool remains a challenging but attainable goal. Continuous systematic enhancement of our AI-driven methodology has led us to satisfactory, yet imperfect results which compel us to further study and improve our efforts to provide a trustworthy cardiologist-friendly triage device. Funding Acknowledgement Type of funding source: None

Innovative techniques to construct powerful artificial intelligence algorithms for st-elevation myocardial infarction

Abstract Background With the sudden advent of Artificial Intelligence (AI), incorporation of these technologies into key aspects of our working environment has become an ever so delicate task, especially so when dealing with time-sensitive and potentially lethal scenarios such as ST-Elevation Myocardial Infarction (STEMI) management. By further expanding into our successful experiences with AI-guided algorithms for STEMI detection, we implemented an innovative ensemble method into our methodology as we seek to improve the algorithm's predictive capabilities. Purpose Through the ensemble method, we combined two ML techniques to boost our previous experiments' accuracy and reliability. Methods Database: EKG records obtained from Latin America Telemedicine Infarct Network (Mexico, Colombia, Argentina, and Brazil) from April 2014 to December 2019. Dataset: Two separate datasets were used to train and test two sets of AI algorithms. The first comprised of 11,567 records and the second 7,286 records, each composed of 12-lead EKG records of 10-second length with sampling frequency of 500 Hz, including the following balanced classes: unconfirmed &amp; angiographically confirmed STEMI (first model); angiographically confirmed STEMI only (second model); and, for both models, we included branch blocks, non-specific ST-T abnormalities, normal, and abnormal (200+ CPT codes, excluding the ones included in other classes). Label per record was manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: First and last 250 samples were discarded to avoid a standardization pulse. An order 5 digital low pass filter with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: The determined classes were STEMI and Not-STEMI (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training &amp; Testing: The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. These probabilities were calculated for each model (Model 1 trained with Complete STEMI dataset and Model 2 trained with confirmed STEMI only dataset) and aggregated using the mean aggregation to generate the final label for each record. A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90%/10%; respectively. Results are reported for both testing datasets (Complete and confirmed STEMI only records). Results Complete STEMI Dataset: Accuracy: 96.5% Sensitivity: 96.2% Specificity: 96.9% – Confirmed STEMI only Dataset: Accuracy: 98.5% Sensitivity: 98.3% Specificity: 98.6%' Conclusion(s) While Model 1 and Model 2 achieved similar performances with promising results on their own, applying a combination of both through the ensemble model exhibits a clear improvement in performance when applied to both datasets. This provides a blueprint for advanced automated STEMI detection through wearable devices. Funding Acknowledgement Type of funding source: None

Enhancing AI-guided STEMI detection algorithms by incorporating higher quality fiduciary EKG elements

Abstract Background As EKG interpretation paradigms to a physician-free milieu, accumulating massive quantities of distilled pre-processed data becomes a must for machine learning techniques. In our pursuit of reducing ischemic times in STEMI management, we have improved our Artificial Intelligence (AI)-guided diagnostic tool by following a three-step approach: 1) Increase accuracy by adding larger clusters of data. 2) Increase the breadth of EKG classifications to provide more precise feedback and further refine the inputs which ultimately reflects in better and more accurate outputs. 3) Improving the algorithms' ability to discern between cardiovascular entities reflected in the EKG records. Purpose To bolster our algorithm's accuracy and reliability for electrocardiographic STEMI recognition. Methods Dataset: A total of 7,286 12-lead EKG records of 10-seconds length with a sampling frequency of 500 Hz obtained from Latin America Telemedicine Infarct Network from April 2014 to December 2019. This included the following balanced classes: angiographically confirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal, and abnormal (200+ CPT codes, excluding the ones included in other classes). Labels of each record were manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: First and last 250 samples were discarded to avoid a standardization pulse. Order 5 digital low pass filters with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: Determined classes were “STEMI” and “Not-STEMI” (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training &amp; Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. Additional testing was performed with a subset of the original complete dataset of unconfirmed STEMI. Performance indicators (accuracy, sensitivity, and specificity) were calculated for each model and results were compared with our previous findings from past experiments. Results Complete STEMI data: Accuracy: 95.9% Sensitivity: 95.7% Specificity: 96.5%; Confirmed STEMI: Accuracy: 98.1% Sensitivity: 98.1% Specificity: 98.1%; Prior Data obtained in our previous experiments are shown below for comparison. Conclusion(s) After the addition of clustered pre-processed data, all performance indicators for STEMI detection increased considerably between both Confirmed STEMI datasets. On the other hand, the Complete STEMI dataset kept a strong and steady set of performance metrics when compared with past results. These findings not only validate the consistency and reliability of our algorithm but also connotes the importance of creating a pristine dataset for this and any other AI-derived medical tools. Funding Acknowledgement Type of funding source: None

AI and telemedicine: total remote guidance of AMI management

Abstract Background For a decade, Latin American Telemedicine Infarct Network (LATIN) Telemedicine has transformed AMI management in Brazil, Colombia, Mexico, Chile, and Argentina. With a hub and spoke strategy, AMI coverage was expanded to 100 million population and 877,177 telemedicine encounters were performed. Cost savings from avoiding unnecessary transfer of patients was $291 million. We are now rapidly escalating on a path to making the telemedicine process “physician-free” by utilizing Artificial Intelligence (AI) protocols. Purpose To demonstrate that AI can replace a cardiologist for remote AMI telemedicine guidance. Methods The process of total AI guidance focused on both aspects of our telemedicine strategy – accurate AMI diagnosis and tele-guidance of the entire STEMI process. We developed our innovative approach by initially creating AI algorithms for computer-aided diagnosis. Next, we incorporated logistic variables (duration of chest pain, transfer times to LATIN hub, etc) to the algorithm for physician-free triage into thrombolysis, primary PCI and pharmaco-invasive management. The intent of creating AI algorithms was early STEMI detection and triage. After the patient was efficiently transferred to the hub, a final treatment decision was made by the hub cardiologists. Results Three crucial areas of telemedicine efficiency are being monitored – Time-to-Telemedicine Diagnosis (TTD), Door-In-Door-Out (DIDO) and Transfer Times (TT). All are showing improvements. Detailed results will be available at the time of presentation. Conclusions We are encouraged with the possibility of making the entire telemedicine guidance of AMI management “physician-free”. Next-Gen improvements are being contemplated by including a Single Lead EKG for AMI detection that will impact symptom-to-balloon times. Funding Acknowledgement Type of funding source: None