P6422Physician vs machine: an innovative ST-elevation myocardial infarction pathway through artificial intelligence

Background

The diagnosis of ST-Elevation Myocardial Infarction (STEMI) has traditionally relied on a cardiologist's interpretation of an Electrocardiogram (EKG). This cumbersome process is costly, inefficient and out of date. Artificial Intelligence (AI) -guided algorithms can provide point-of-care, accurate STEMI diagnosis that will facilitate STEMI management.

Purpose

To demonstrate the feasibility of an automated AI-guided EKG analysis for STEMI diagnosis.

Methods

An observational, retrospective, case-control study. Sample: 8,511 EKG cardiologist-annotated records, including 4,255 STEMI cases. Records excluded patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes by wavelet system, segmentation of each EKG into individual heartbeats (90,592 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, “STEMI” and “Not-STEMI” classes were considered for each heartbeat, individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

The model achieved an accuracy of 96.5%, with a sensitivity of 96.3%, and a specificity of 96.8%.

Conclusion(s)

1) AI-guided interpretation of the EKG can reliably diagnose STEMI; 2) AI algorithms can be incorporated into ambulance systems for pre-hospital diagnosis, single page activation, emergency department bypass, facilitating more efficient STEMI pathways.

P1464Adoption of feedback to validate a machine learning model for single lead STEMI detection

Background

We have explored the performance of a single lead EKG with Artificial Intelligence (AI) based algorithms in STEMI diagnosis, thus far lead V2 has yielded the best results. Anticipating the performance of the LUMENGT-AI model, we designed a feedback strategy with healthcare centers to expand the validation of our work.

Purpose

To create a pragmatic alternative to the existing gold standard, a 12-lead EKG, for STEMI diagnosis.

Methods

An observational, retrospective, case-control study. Sample: 2,543 exclusively STEMI (anterior, inferior and lateral wall) diagnosis, EKG records. Feedback: From healthcare centers, confirming STEMI diagnosis and location, was obtained (thrombolysis, primary Percutaneous Coronary Intervention (PCI), pharmaco invasive therapy or coronary artery bypass surgery). Records excluded other patient and medical information. Sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes using the wavelet system, segmentation of each EKG into individual heartbeats (53,667 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented; “STEMI” and “Not-STEMI” classes were considered for each heartbeat per lead; individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

V2 was the most precise lead with an Accuracy of 93.6%, a Sensitivity of 89%, and a Specificity of 94.7%.

Conclusions

The strategic adoption of feedback from healthcare centers provided strong validation of our model. The results of AI-augmented, single lead EKG are encouraging. We anticipate that this approach will become a promising methodology in STEMI detection.

P6421Can cardiologists rely on artificial intelligence to identify the culprit vessel in STEMI?

Background

The importance of culprit lesion identification is critical for risk stratification of a patient with an ST-Elevation Myocardial Infarction (STEMI). The aforementioned provide patients with a more elaborated strategy of management and treatment either they are treated with PCI or less invasive techniques such as thrombolysis. We report a novel approach that employs AI-guided electrocardiogram (EKG) algorithms for rapid and accurate identification of the culprit STEMI vessel.

Purpose

To create an innovative, machine learning tool for a more effective risk stratification of STEMI patients.

Methods

An observational, retrospective, case-control study. Sample: 2,542 exclusively STEMI diagnosis EKG records that included post discharge feedback from healthcare centers, confirming diagnosis and culprit vessel (Left Main Coronary Artery [LMCA]; Left Anterior Descending [LAD]; Right Coronary Artery [RCA]; Left Circumflex Artery [LCX]; Saphenous Vein Graft [SVG]). Records excluded other patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes using a wavelet system, segmentation of each EKG into individual heartbeats (27,125 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented; “LCMA”, “LAD”, “LCX”, “RCA”, “SVG”, and “No Information” classes were considered for each heartbeat; individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample was used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

Global Accuracy: 79.4%; LAD: Sensitivity 86.2%; Specificity 84.8%. RCA: Sensitivity 85.7%; Specificity 83.7%. LCX: Sensitivity 43.5%; Specificity 96.9%.

Conclusions

Coupling an AI-augmented algorithm and 12-lead EKG provides encouraging results for STEMI culprit vessel localization. Overall, risk stratification is possible for individual lesions located in the LAD and RCA. However, our approach yielded uncertain results in the LCX territory. We plan to continue to exploring variables for improvement of our results.

P3352Telemedicine transcends national boundaries in quest of creating a behemoth ami program

Background

The Latin America Telemedicine Infarct Network (LATIN) has exploited the remarkable competence of telemedicine for remote guidance. In doing so, LATIN created a mammoth population-based AMI network that employed experts located several hundred miles away to guide the reperfusion strategies for almost 800,000 screened patients. In this pioneering project, telemedicine was initially utilized to guide AMI management within national confines. We speculated whether LATIN telemedicine navigation could outstrip countrywide borders.

Purpose

To maximally harness the vast possibilities of telemedicine for improving AMI care.

Methods

During its pilot phase, LATIN began as a hub and spoke, AMI system in Colombia where 20 spokes (small community health centers and rural clinics) were configured with 3 hubs that could perform Primary PCI. These sites were linked through web-based connectivity. Expert cardiologists, located 50–250 miles away in Bogota, Colombia, used sophisticated telemedicine platforms for urgent EKG diagnosis and teleconsultation of the entire AMI process. Based upon the duration of chest pain and travel time to the hub, these experts guided patients through guideline-based strategies of thrombolysis, pharmaco invasive management or primary PCI. Efficiency of the telemedicine process was measured with the new metric of time to telemedicine diagnosis (TTD). Cloud computing, GPS navigation, and numerous business intelligent tools were gradually incorporated into LATIN telemedicine. As systems became more scalable, the program was expanded to Brazil, where LATIN flourished. Over the last 18 months, LATIN telemedicine capabilities have been pressed across national boundaries. Presently, all 82 LATIN centers in Mexico are guided by experts located in Bogota, Colombia and the 7 Argentina centers channeled through Santiago, Chile.

Results

784,947 patients were screened for AMI at 350 LATIN centers (Brazil 143, Colombia 118, Mexico 82, Argentina 7). Navigation pathways are depicted in the attached figure. TTD remains extremely low in all four countries, and comparable efficiency and tele-accuracy have been achieved. With expanded geographic reach, 8,448 (1.08%) patients were diagnosed with STEMI and 3,911 (46.3%) urgently reperfused, including 3,049 (78%) with Primary PCI. Time to TTD ranged between 2.8 to 5.8 minutes, with a mean of 3.5 min. Tele-accuracy was 98.5%, D2B 51 min, and in-hospital mortality 5.2%. Various other comparative metrics for the 4 countries are being gathered and will be available at the time of presentation.

Conclusions

LATIN demonstrates the robust ability of telemedicine to transcend national boundaries to guide AMI management. This strategy can be adopted in under-developed countries in Asia and Africa to provide an umbrella of AMI care for the millions of disadvantaged patients.

P1742Is time to telemedicine diagnosis (TTD) analogous to door to balloon time?

Background

Telemedicine is a powerful, cost-efficient, and scalable tool for population-based AMI management. Traditional metrics of D2N, D2B do not gauge telemedicine effectiveness. We explored the utility of TTD in 784,947-screened patients within the Latin America Telemedicine Infarct Network (LATIN).

Purpose

To evaluate the competence of TTD as an efficiency indicator in telemedicine.

Methods

LATIN employed a spoke-hub strategy to expand access in Brazil, Colombia, Mexico, and Argentina. Small clinics (spokes) in remote areas were strategically connected to PCI-capable facilities (hubs). Experts at 4 remote locations provided urgent EKG diagnosis via tele-consultation, additionally, they triggered ambulance dispatch and implementation of guidelines-based protocols. Investing in updated telemedicine technology provided a system-wide TTD reduction.

Results

714,450 patients were screened for AMI at 350 LATIN centers (Brazil 143, Colombia 118, Mexico 82, Argentina 7). Within our territories 8,448 (1.08%) patients were diagnosed as STEMI; 3,911 (46.3%) were urgently reperfused, of those 3,049 (78%) underwent Primary PCI. TTD was 3 min, demonstrating 98.9% tele-accuracy. D2B was 51 min; in-hospital mortality 5.2%. We encountered a linear correlation between D2B and TTD. The latter was, also, inversely related to the number of screened patients - both associations are favorable for LATIN.

Conclusions

TTD is an important indicator of telemedicine efficiency. LATIN will continue to explore this value's strength and other important associations.

P1466Can physicians trust a machine learning algorithm to diagnose ST elevation myocardial infarction?

Background

For the past years, the medical field has been taking advantage of the endless possibilities that Artificial Intelligence (AI) provides. Using computer-aided devices that can perform and interpret electrocardiograms (EKG) accurately pushes current healthcare boundaries. We present the LUMENGT-AI, this model can handle large datasets, multiclass diagnoses, complex EKG morphology, and still detect ST Elevation MI (STEMI) accurately.

Purpose

To develop an innovative AI-based system for automated STEMI specific EKG analysis.

Methods

An observational, retrospective, case-control study. Sample: 8,511 EKG records, previously diagnosed as “normal”, “abnormal” (over 200 conditions) or “STEMI” (4,255 cases). Records excluded patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes by wavelet system, segmentation of each EKG into individual heartbeats (90,592 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, “STEMI” and “Not-STEMI” classes were considered for each heartbeat, individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

Ground Truth Score – Accuracy (94.1%), Sensitivity (87.8%), Specificity (98.1%) – see the comparison to published data in Table.

Conclusions

A statistical analysis allowed us to compare STEMI recognition efficiency between physicians and our model. The LUMENGT algorithm results secured its place as a reliable tool to diagnose STEMI faster and more accurately than physicians.

P1751LATIN - A template for effective AMI management in developing countries

Background

In resource-constrained nations, population-based AMI coverage is daunting. Telemedicine can transform the situation through an efficient, cost-effective and scalable program called the Latin America Telemedicine Infarct Network (LATIN). We present our innovative hub-spoke strategy, that has served >780,000 patients.

Purpose

To use telemedicine protocols to demonstrate appropriate access to quality AMI care, encompassing remote areas.

Methods

LATIN required technology and process metrics optimization as well as a scrupulous site selection, during a 12-month pilot. Spokes represent our strategy's nucleus; they consist of small, rural clinics and resource-limited facilities that are connected to PCI-capable hubs. Spokes require constant (3-T) training: Triage, Telemedicine, and Transportation. The latter two categories are the most challenging because they demand constant upgrading.

Results

784,395 patients were screened at 350 LATIN centers (Brazil 143, Colombia 118, Mexico 82, Argentina 7). A total of 8,440 (1.08%) patients were diagnosed with AMI; 3,924 (46.5%) were urgently reperfused including 3,048 (77.7%) who underwent PCI. Globally, Time to Telemedicine Diagnosis (TTD) was 3 min exhibiting 98.9% tele-accuracy, D2B was 51 min, additionally, in-hospital mortality was 5.2%. Major reasons for non-treatment of patients were insurance, lack of ICU beds and delayed presentation.

Conclusions

LATIN is a valuable healthcare system prototype for developing countries. Our hub-spoke strategy focuses on providing adequate AMI management for populations. However, aspects such as ambulance availability, insurance denial and lack of ICU beds must be targeted to improve performance.

P6142LATIN telemedicine - expanded umbrella of cost-effective ami coverage for 100 million people

Background

AMI is a unique entity where the immediate diagnosis can be made by a single test, the EKG. Despite this matchless attribute of easy diagnosis, developing (and some developed) countries lack resources and efficient pathways for urgent and reliable diagnosis of AMI. With Latin Telemedicine Infarct Network (LATIN), we have previously presented Telemedicine as a pragmatic solution for urgent and accurate diagnosis of AMI. In this work, we reveal pathways of scalable population-based AMI management models.

Purpose

To utilize telemedicine as a foundation pillar for creating cost-effective and global models of AMI management.

Methods

LATIN pilot tested the hypothesis of remote guidance of AMI management and expanded access by creating a hub and spoke, STEMI systems of care that exploited regional resources. A highly efficient, web-based, cloud-computing prototype was developed and scrupulously monitored with a new metric of time to telemedicine diagnosis (TTD). STEMI systems of care were created to efficiently triage the diagnosed patients for being treated with thrombolysis, pharmaco-invasive management or Primary PCI. This stratagem had enormous provincial variability and was constrained mainly by ambulance structure. Telemedicine and IT costs were forced lower and enabled a cost-effective process to hugely provide access to 100 million patients located in poorer regions of Colombia, Brazil, Mexico, and Argentina. Education and training have formed the mantra for LATIN and stakeholder development, and ambulance systems development has remained immutable goals.

Results

Almost 800,000 patients were successfully screening through LATIN with a cost for accurate STEMI diagnosis of < $3, a tele accuracy that exceeded 95% and with TTD <4 minutes. A total of 8,440 (1.1%) of patients were diagnosed with AMI in this manner and 3,924 (46.5%) urgently reperfused, mainly with Primary PCI (3,048, 77.8%). D2B times have been lowered now to 51 minutes but this is fortuitous, as several PCI-capable facilities are small, and direct transfer to the catheterization laboratory is easy. Door in and Door out times and transport times remain high as a large number of patients are denied by insurance and other payers for treatment. Overall, mortality is 5.2%.

Conclusions

Global financial and philanthropic institutions should contemplate models analogous to LATIN for saving the lives of millions of poor patients in developing countries from AMI.

3035Synergy of artificial intelligence and single lead EKG to detect and localize STEMI

Background

The cumbersome, standard 12-lead electrocardiogram (EKG) challenges an efficient detection of ST-Elevation Myocardial Infarction (STEMI) in pre-hospital (ambulances) and hospital (portable devices) settings. We believe that our machine-learning algorithm embedded into a single lead EKG will be successful in acute care settings.

Purpose

To incorporate Artificial Intelligence-guided, single lead EKG interpretation, to facilitate easy and accurate STEMI detection in urgent situations.

Methods

This is an observational, retrospective, case-control study. A subset sample was generated from the International Telemedical Systems (ITMS) database that contains cardiologist annotated EKG records. Subset: A total of 2,542 exclusively confirmed STEMI diagnosis EKG records from enrolled healthcare centers in Mexico, Colombia, and Brazil; including specific ischemic heart wall (anterior, inferior, and lateral). Following discharge of treated patients, confirmation of STEMI diagnosis was obtained as feedback from healthcare centers. Records were anonymized EKG that excluded all medical information. Sample: A Standard 12 lead, 10-seconds length, 500Hz sampling frequency EKG was fed to the LUMENGT-AI STEMI detecting algorithm. Preprocessing: Detection of QRS complexes by wavelet system, segmentation of each EKG record into individual heartbeats (total dataset 27,152 beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, three classes were considered for individual heartbeats: “Anterior”, “Inferior” and “Lateral”, each corresponding to the heart wall affected. These individual probabilities were aggregated to generate the final label for each of the 12 leads. Training & Testing: 90% and 10% of the dataset was used respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with a NVidia GTX 1070 GPU, 8GB RAM.

Results

Accuracy – Lead V2 (91.7%); Sensitivity Anterior wall – Lead V2 (97.4%); Sensitivity for Lateral wall – Lead I (10.0%); and Sensitivity for Inferior wall – Lead V2 (93.6%).

Conclusions

AI algorithms merged with a Single lead approach detect and localize STEMI within any setting. The V2 lead yields superior results for mapping of ischemic areas of the heart among the anterior and inferior walls. In contrast, diagnosis remains suboptimal for identifying the lateral wall. The usage of synergistic technologies facilitates easy, fast and early STEMI triage and management.

P6418The continued proficiency of artificial intelligence for interpreting EKG: single lead EKG for STEMI culprit lesion localization

Background

Traditionally, the 12-lead electrocardiogram (EKG) has been used for diagnosing ST-Elevation Myocardial Infarction (STEMI) and for identifying the culprit lesion. We have previously demonstrated the impact of combining a Single Lead approach with Artificial Intelligence (AI) to replace tasks previously dominated by the 12 lead EKG. This research explores the role of the single lead EKG in identifying a culprit lesion.

Purpose

To test the use of a single lead approach to accurately locate the culprit vessel.

Methods

An observational, retrospective, case-control study. Sample: 2,542 exclusively STEMI diagnosis EKG records that included post discharge feedback from healthcare centers, confirming diagnosis and culprit vessel (Left Main Coronary Artery [LMCA]; Left Anterior Descending [LAD]; Right Coronary Artery [RCA]; Left Circumflex Artery [LCX]; Saphenous Vein Graft [SVG]). Records excluded other patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing:detection of QRS complexes using a wavelet system, segmentation of each EKG into individual heartbeats (27,125 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented; “LCMA”, “LAD”, “CX”, “RCA”, “SVG”, and “No Information” classes were considered for each heartbeat per lead; individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample was used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

Accuracy: 77.4% Lead III; Sensitivity: LMCA (Lead aVL 25%); LAD (Lead aVF 87.8%); RCA (Leads V1, V3 92.9%); LCX (Lead aVL 21.7%).

Conclusions

Our results yielded the dominance of a specific single lead to each culprit vessels, aVF for LAD and V1 and V3 for RCA. We continue testing with different algorithms to search for reliable results for the LMCA and LCX. Nonetheless, conjugating a Single Lead EKG with an AI-augmented algorithm enables faster and easier management for patients that present with STEMI affecting the LAD and RCA territories.

P2426Validating the diagnostic value of a machine learning algorithm for STEMI detection

Background

We have previously reported the use of Artificial Intelligence (AI) guided EKG analysis for detection of ST-Elevation Myocardial Infarction (STEMI). To demonstrate the diagnostic value of our algorithm, we compared AI predictions with reports that were confirmed as STEMI.

Purpose

To demonstrate the absolute proficiency of AI for detecting STEMI in a standard12-lead EKG.

Methods

An observational, retrospective, case-control study. Sample: 5,087 EKG records, including 2,543 confirmed STEMI cases obtained via feedback from health centers following appropriate patient management (thrombolysis, primary Percutaneous Coronary Intervention (PCI), pharmacoinvasive therapy or coronary artery bypass surgery). Records excluded patient and medical information. The sample was derived from the International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes by wavelet system, segmentation of each EKG into individual heartbeats (53,667 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, “STEMI” and “Not-STEMI” classes were considered for each heartbeat, individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVIDIA GTX 1070 GPU, 8GB RAM.

Results

The model yielded an accuracy of 97.2%, a sensitivity of 95.8%, and a specificity of 98.5%.

Conclusion(s)

Our AI-based algorithm can reliably diagnose STEMI and will preclude the role of a cardiologist for screening and diagnosis, especially in the pre-hospital setting.

P575Merging technologies to provide Mexico an innovative nationwide AMI management network

Background

“Cόdigo Infarto”, the vast patient-centric, app-based, educational crusade of the Mexican Society of Interventional Cardiology (SOCIME) has been combined with the Latin America Telemedicine Infarct Network (LATIN) to create a comprehensive, national AMI program for Mexico.

Purpose

To demonstrate the benefits of amalgamating educational initiatives of national cardiology societies with a global telemedicine program for improving AMI management.

Methods

“Cόdigo Infarto” App connects patients to a network of several hundred cardiologists and 250 Primary PCI-capable labs. LATIN provides the partnership with its robust telemedicine platform, a hub-spoke strategy that supports patient's access to appropriate medical management. Remotely located experts, in Colombia, provide urgent EKG diagnosis via tele-consultation to the entire LATIN Mexico network. They activate ambulance dispatch and implement guideline-based protocols.

Results

Numerous “Cόdigo Infarto” sites have incorporated LATIN to provide a simple and accelerated management of AMI patients. Currently, the partnership (7 hubs, 78 spokes) has screened 19,886 patients. A total of 359 STEMI cases (1.8%) have been diagnosed; 118 patients (33%) were urgently reperfused, Primary PCI was performed in 74% of the latter cases. D2B time was 41 min. Reasons for the lack of treatment include delayed presentation, lack of ICU beds and insurance denials. Currently, these constraints are being methodically probed. Updated results will be available at time of presentation.

Conclusions

The synergy of the AMI initiative for Mexico provides a template for similar initiatives in developing countries.

Allelic frequencies of three VNTRs in intron 40 of the human von Willebrand factor gene in types 1, 2, and 3 von Willebrand disease patients and controls of a Brazilian population

Intron 40 of the human von Willebrand factor (vWF) gene contains a polymorphic region with three variable-number tandem repeats (VNTRs), type (ATCT)n. In the present report, we evaluated the allelic frequencies of these three VNTRs in a population constituted by 51 Brazilian Caucasian and 25 Types 1, 2, and 3 von Willebrand disease (vWD) patients, and performed segregation analysis in eight families affected by vWD Types 1 and 2. Three pairs of primers were used to amplify independently nucleotides 1640-1794 (VNTR 3), 1890-1991 (VNTR 1), and 2215-2396 (VNTR 2) from intron 40. The observed heterozygosities (0.86, 0.66, and 0.66 for VNTRs 3, 1, and 2, respectively) were in accordance with the expected heterozygosities derived from the allele frequencies (0.81, 0.64, and 0.70, respectively). Although the three VNTRs were highly polymorphic, VNTR 3 showed the highest values of heterozygosity [Haemostasis 25 (1995) 264; Hum. Mol. Genet. 1 (1992) 287.].