Powerful Medical Receives €40 Million IPCEI Grant — read the full story

Publications

Abstracts
0
Clinical Studies
0
Clinical Investigations
0
Abstracts
0
Clinical Studies
0
Clinical Investigations
0

Chest Pain With Subtle But Lifesaving ECG Findings

This study presents a clinical case highlighting the diagnostic value of hyperacute T waves on electrocardiogram (ECG) for early detection of acute coronary occlusion. A 54-year-old woman presented with classic ischemic symptoms, yet her initial ECG was interpreted as normal by both automated analysis and clinician review. Closer inspection revealed subtle hyperacute T waves in the anterior leads, consistent with acute occlusion of the left anterior descending (LAD) artery. The case underscores how reliance on traditional ST-segment elevation criteria alone may delay recognition of life-threatening myocardial infarction.

AI-Enhanced Electrocardiogram for Detection of Occlusive Myocardial Infarction in High-Risk Non–ST-Segment Elevation Acute Coronary Syndrome

This study evaluates an AI-enhanced ECG model for detecting occlusive myocardial infarction (OMI) in patients with high-risk non–ST-segment elevation acute coronary syndrome, using angiography as the reference. The model improved rule-in accuracy with high specificity (78%) and reduced false-positive cath lab activations compared with standard care, while rule-out sensitivity remained limited on the initial ECG. Serial ECG analysis improved detection, supporting the use of AI as a triage aid alongside clinical judgment rather than a standalone diagnostic tool.

Detecting Occlusion Myocardial Infarction with an AI-Powered ECG Model: A Retrospective Cohort Study

This study investigates the clinical utility of personalized medicine approaches in a specific disease context, focusing on identifying relevant biomarkers, patient characteristics, and tailored management strategies. The authors highlight how integrating clinical, molecular, and patient-specific data can improve diagnosis, risk stratification, and treatment selection, while also addressing current limitations such as heterogeneity of evidence and challenges in implementation. Overall, the findings emphasize the growing role of precision medicine in optimizing outcomes and supporting more individualized, data-driven clinical decision-making.

Performance of Artificial Intelligence Powered ECG Analysis in Suspected ST-Segment Elevation Myocardial Infarction

This study evaluates the real-world performance of an AI-based ECG interpretation tool for detecting STEMI in patients undergoing emergent catheterization laboratory activation, using angiographic findings as the reference standard. Compared with standard clinical ECG interpretation, the AI model achieved higher sensitivity and specificity, significantly reducing false-positive activations while maintaining strong performance even in challenging cases such as arrhythmias or conduction abnormalities. These results suggest that AI-assisted ECG analysis can improve diagnostic accuracy, optimize triage, and support faster, more appropriate decision-making in acute coronary syndrome management.

An AI Model for Electrocardiogram Detection of Occlusion Myocardial Infarction: A Retrospective Study to Reduce False Positive Cath Lab Activations

This single-centre retrospective study examined whether an AI-powered ECG model (PMcardio’s Queen of Hearts OMI model) can better detect acute occlusion myocardial infarction (OMI) and reduce false-positive cardiac catheterization laboratory (CCL) activations compared with traditional STEMI millimetre criteria. The authors analysed 304 consecutive STEMI pathway activations over a 2-year period at a tertiary academic centre and applied the AI model to pre-angiography 12-lead ECGs, comparing its performance against standard STEMI criteria. The AI model showed higher sensitivity (89.2% vs 68.3%), higher specificity (72.9% vs 51.7%), greater overall accuracy (82.9% vs 61.8%), and a high AUROC of 0.884 for identifying true OMI, while correctly flagging nearly three-quarters of false-positive activations as non-OMI. These findings suggest that integrating a specialized AI-ECG model into existing STEMI alert pathways could meaningfully reduce unnecessary CCL activations without compromising the detection of true occlusions.

Bifascicular Block Associated With Myocardial Infarction: A Marker of Proximal Left Anterior Descending Artery Occlusion Confirmed by the Artificial Intelligence-Based Smartphone App Queen of Hearts

This single-patient case report describes an elderly man presenting with chest pain, hypotension, and bifascicular block (BFB)—a combination of right bundle branch block (RBBB) and left anterior fascicular block (LAFB)—whose ECG showed QRS‑concordant anterior and lateral ST‑segment elevation consistent with a STEMI‑equivalent / occlusive myocardial infarction (OMI) pattern. Urgent coronary angiography revealed a long, severely calcified, near‑occlusive proximal left anterior descending (LAD) artery lesion, successfully treated with primary PCI and drug‑eluting stent implantation, achieving TIMI 3 flow. The Queen of Hearts (PMcardio) AI‑based smartphone app correctly classified the ECG as STEMI‑equivalent, identified atrial flutter and BFB, and predicted reduced left ventricular ejection fraction, later confirmed by echocardiography (EF 38%). This case underscores BFB with concordant anterior ST elevation as a high‑risk marker of proximal LAD‑culprit OMI and provides anecdotal evidence that specialized AI‑enabled ECG interpretation can support rapid, accurate decision‑making in ACS. 

Artificial Intelligence Versus Human Expertise: ECG-Based Detection of Occlusive Myocardial Infarction After Cardiac Arrest

This single-centre study tested whether AI-based ECG analysis can detect occlusive myocardial infarction (OMI) after cardiac arrest using post-ROSC ECGs from 97 patients with subsequent coronary angiography. A dedicated deep neural network (Queen of Hearts, QoH) achieved the highest discrimination for acute coronary occlusion (AUC 0.85) and OMI (AUC 0.75), outperforming human experts, with a more balanced trade-off between sensitivity and specificity. In contrast, two large language model–based chatbots (ChatGPT and a GPT-based EKG Analyst) showed near-perfect sensitivity but almost no specificity, labelling nearly all ECGs as OMI and thus providing no meaningful diagnostic discrimination. These findings suggest that specialized ECG-trained AI, such as QoH, may serve as a useful adjunct in post-resuscitation decision-making. In contrast, general-purpose LLMs are currently unsuitable for critical ECG diagnosis.

Association Between Artificial Intelligence Detected Features on the ECG and Presence of Microvascular Obstruction

This study tested whether artificial intelligence (AI)–extracted electrocardiogram (ECG) features can identify microvascular obstruction (MVO) after reperfusion in anterior ST‑segment elevation myocardial infarction (STEMI). Using pre‑ and post‑percutaneous coronary intervention (PCI) ECGs and a logistic‑regression model built on PMcardio (API v2.5), the AI approach predicted CMR‑confirmed MVO with an AUC of 0.83, 94% specificity, and 60% sensitivity; the figure reports ~76% overall accuracy. By emphasizing high specificity, the model aims to flag patients very likely to harbor MVO when cardiac MRI is impractical, enabling rapid risk stratification at the point of care.

AI-Enabled ECG Analysis Improves Diagnostic Accuracy and Reduces False STEMI Activations: A Multicenter U.S. Registry

In a large, multi-center evaluation presented as Late-Breaking Science at the TCT 2025 conference, investigators assessed the diagnostic accuracy of the Queen of Hearts™ AI algorithm for ST-segment elevation myocardial infarction (STEMI) detection in emergency care. The study compared AI-enhanced ECG interpretation against standard triage protocols across three U.S. PCI centers, encompassing more than 1,000 patients who activated emergent reperfusion pathways. Published in JACC: Cardiovascular Interventions, the results demonstrated significantly improved accuracy and reduced false activations when using AI-driven analysis.

Electrocardiographic Diagnostic Possibilities for Atrial Fibrillation Using Artificial Intelligence: Differentiation from Sinus Rhythm and Other Arrhythmias with the Pmcardio App in Covid-19 Patients

This study evaluated how effectively artificial intelligence can detect atrial fibrillation (AF) in COVID-19 patients using ECG analysis. Researchers compared the PMcardio AI application’s performance with that of cardiologists and infectious disease specialists. Among 116 hospitalized COVID-19 patients, PMcardio achieved perfect diagnostic accuracy (sensitivity and specificity of 1.00) for AF detection, matching cardiologists and surpassing infectious disease specialists. The AI’s performance remained consistent across confidence levels, and its severity assessments correlated significantly with rhythm findings. These results highlight AI’s potential to improve arrhythmia detection, streamline care, and reduce unnecessary in-person evaluations during infectious disease outbreaks.

Door-to-balloon Time Outperforms St-segment Elevation in Predicting the Stemi vs. Nstemi Final Diagnosis

In a two-center registry study, investigators compared traditional STEMI/NSTEMI classification with angiographic and interventional diagnoses. Although guideline-defined ST-elevation criteria underpin quality metrics and reperfusion standards, they often fail to capture acute coronary occlusion myocardial infarction (OMI). This discordance has led to proposals for an OMI/Non-OMI paradigm, grounded in pathophysiology rather than ECG morphology. The study examined whether door-to-balloon time < 120 min aligns more closely with final cardiologist adjudication than either ST-segment elevation on ECG or angiographic evidence of TIMI 0–1 flow.

Hyperacute T Waves Are Specific for Occlusion Myocardial Infarction, Even Without Diagnostic St Elevation

This study aimed to derive and validate a quantitative definition of hyperacute T waves (HATW) by developing the HATW score and evaluating its diagnostic accuracy for identifying acute coronary occlusion in patients with possible ACS but without STEMI criteria.

Occlusion Myocardial Infarction: A Revolution in Acutecoronary Syndrome

The 2025 ACC Guideline for the Management of Patients With Acute Coronary Syndromes claims that “Patients with NSTEMI may have a partially occluded coronary artery leading to subendocardial ischemia, while those with STEMI typically have a completely occluded vessel leading to transmural myocardial ischemia and infarction.” This is accompanied by a visual representation of a partially occlusive thrombus labeled ‘NSTEMI’ above an electrocardiogram (ECG) showing ST depression and T wave inversion, and a completely occlusive thrombus labeled ‘STEMI’ above an ECG showing ST elevation. This paradigm has remained despite two decades of angiographic and evidence-based ECG advances, which highlight the multiple reasons why a revolution in acute coronary syndrome (ACS) is needed, and has begun.

Accuracy of cath lab activation decisions for STEMI-equivalent and mimic ECGs: Physicians vs. AI (PMcardio, queen of hearts)

This study aimed to measure physician accuracy for interpreting STEMI-equivalent and STEMI-mimic ECGs for catheterization laboratory activation (CLA) and compare their performance to a machine learning-based artificial intelligence algorithm, Queen of Hearts AI (QoH AI).

Artificial intelligence-enhanced ECG detection of acute coronary occlusion in chest pain patients with ST-elevation in lead aVR – A direct comparison to conventional ECG criteria

In a single‑centre retrospective study of 145 consecutive emergency‑department patients whose first ECG showed ≥1 mm ST‑elevation in lead aVR, investigators compared conventional electrocardiographic rules with a deep‑learning classifier (PMcardio “Queen of Hearts”) for recognising an acute coronary occlusion (ACO). Angiography and biomarker adjudication proved ACO in 19 patients (13 %). At an optimised probability threshold, the AI system achieved an area‑under‑the‑ROC curve of 0.918, detected 63 % of occlusions, and—crucially—generated no false‑positive calls in the 54‑patient rule‑out subgroup. By contrast, classic STEMI criteria identified only one in four occlusions and would have prompted between four and fourteen unnecessary emergency catheterisations.

AI-enhanced recognition of occlusions in acute coronary syndrome (AERO-ACS): a retrospective study

In a one‑year, single‑centre cohort of 217 cath‑lab patients (72 STEMI, 145 NSTEMI), the AERO‑ACS study tested PMcardio’s AI ECG against traditional ST‑elevation rules for detecting angiographic occlusion‑MI. The algorithm matched STEMI sensitivity (86.5 % vs 83.3 %) while raising specificity to 82.2 % (vs 66.0 %), achieved 100 % sensitivity in STEMI cases, and flagged occlusions linked to a 12‑fold higher in‑hospital mortality risk—suggesting more accurate triage with fewer unnecessary activations.

Failure of standard contemporary ST-elevation myocardial infarction electrocardiogram criteria to reliably identify acute occlusion of the left anterior descending coronary artery

ST-elevation (STE) criteria on the electrocardiogram (ECG) are poorly sensitive for acute coronary occlusion myocardial infarction (ACOMI or OMI). This study evaluates the sensitivity of STE criteria on serial ECGs for total left anterior descending (LAD) coronary artery occlusion. We compared STE criteria with expert interpretation and a validated artificial intelligence (AI) ECG model for diagnosing LAD OMI.

Validation of an artificial intelligence ECG model for detection of acute coronary occlusion myocardial infarction in unselected emergency department chest pain patients

Across 24 513 consecutive chest-pain presentations to five Swedish emergency departments, the Queen of Hearts (QoH) AI-ECG model detected acute coronary occlusion myocardial infarction with 52 % sensitivity and 99 % specificity. It outperformed an extended STEMI algorithm applied to the same cohort (41 % sensitivity, 95 % specificity) and more than doubled the sensitivity of classic STEMI criteria (55 % versus 26 %) while preserving comparable specificity (99 % versus 98 %). This real-world validation demonstrates that QoH markedly improves early ECG recognition of OMI in unselected, non-traumatic chest-pain patients.

Artificial Intelligence Based Detection of Acute Coronary Occlusion Compared to STEMI Criteria – External Validation Study in a Consecutive All-Comer German Chest Pain Unit Cohort

2nd place - DGK Young Investigator Awards 2025, Germany: In a real-world cohort of over 4,000 chest pain patients presenting to a German CPU, excluding obvious STEMI heart attacks diagnosed before arrival, an AI ECG model detected serious artery blockages (ACO) with 97.8% accuracy. It outperformed traditional STEMI criteria, achieving higher sensitivity (70.2% vs 28.8%) and fewer false positives.

Precordial Swirl Sign: A New ECG Pattern of Left Anterior Descending Artery Occlusion Myocardial Infarction

This study identifies the novel “precordial swirl sign,” a distinct ECG pattern that can uncover critical LAD coronary artery blockages often missed by standard STEMI criteria. It offers a promising step toward earlier and more accurate detection of high-risk heart attacks.

First Objective Definition of Hyperacute T-waves as a ST-segment Elevation Myocardial Infarction Equivalent ECG Finding

This abstract introduces the first objective definition of hyperacute T-waves — an early and often missed ECG sign of a severe heart attack. By accurately detecting blocked arteries even before classic signs appear, the new formula helps doctors identify high-risk patients sooner and deliver life-saving treatment faster.

Artificial Intelligence Detection of Occlusive Myocardial Infarction from Electrocardiograms Interpreted as “Normal” by Conventional Algorithms

Conventional ECG algorithms, humanly programmed to detect abnormalities based on fiducial points, frequently miss critical patterns of STEMI. AI-driven deep neural network models like PMcardio AI ECG offer significant potential in identifying these dangerous false negatives, reducing the risk of false reassurance, and enhancing clinical decision-making.

High Precision ECG Digitization Using Artificial Intelligence

This study presents a fully automated AI solution for high-precision digitization of paper ECGs, including smartphone photos. It enables rapid ECG conversion in under 7 seconds, maintaining strong performance even in low-quality or distorted images. Ideal for use in ambulances, primary care, or low-resource settings, it bridges the gap to advanced AI interpretation and secure digital sharing when native digital ECGs are unavailable.

ECG Patterns of Occlusion Myocardial Infarction: a Narrative Review

This comprehensive review highlights the limitations of the traditional STEMI/NSTEMI classification for heart attacks and advocates for a more precise approach to diagnosis and patient triage. Instead of relying solely on standard ECG criteria, this method focuses on ECG patterns that more accurately reflect the severity of underlying coronary vessel disease. By identifying high-risk ECG changes beyond current STEMI guidelines, clinicians can detect heart attacks earlier, initiate treatment faster, and ultimately improve patient outcomes.

Artificial Intelligence–Powered Electrocardiogram Detecting Culprit Vessel Blood Flow Abnormality: AI-ECG TIMI Study Design and Rationale

The AI-ECG TIMI study is a unique, multicenter registry currently enrolling patients to evaluate an AI-powered ECG model for detecting actively obstructed arteries in acute coronary syndrome (ACS). It is the first study to collect standard 12-lead ECGs precisely at the time of coronary angiography, providing novel insights into coronary occlusion and reperfusion. By identifying high-risk ECG patterns and assessing AI’s role in predicting intervention success, it paves the way for AI-driven precision cardiology in acute care.

The Crucial Role of Image Quality in AI-enabled ECG Digitization and Interpretation of Occlusion Myocardial Infarction

The effectiveness of AI-ECG tools depends on the quality of input data—poor ECG image quality can lead to critical misdiagnoses. This case shows how a low-quality scan triggered a false STEMI alert, later corrected with improved digitization. It underscores the importance of ensuring minimally acceptable image quality, as even advanced tools can’t fully correct severe distortions.

AI-Powered Smartphone Application for Detection of Left Ventricular Systolic Dysfunction using 12-Lead ECG

Rapid screening methods for heart failure (leading cause of unplanned hospitalizations and healthcare costs) in patients without symptoms are limited. This study validated PMcardio LVEF AI ECG model in identifying reduced heart function on widely accessible 12-lead ECGs. In a study of over 100-thousand patients, PMcardio demonstrated high performance (AUC 0.963) in detecting patients with reduced heart function offering a fast, non-invasive and scalable screening tool.
Female Patients with Occlusive Myocardial Infarction without ST Elevation Experience Longer Delays in Receiving Emergent Reperfusion

Female Patients with Occlusive Myocardial Infarction without ST Elevation Experience Longer Delays in Receiving Emergent Reperfusion

Up to a third of high-risk heart attacks go unrecognized by traditional ECG diagnostic criteria, causing dangerous delays—an effect even more pronounced in women, who remain understudied in this context. This analysis reveals a 4.4-hour treatment delay for initially misclassified female patients compared to males, highlighting the urgent need for modern, unbiased diagnostic solutions.
Deep-learning Assisted ECG-based Emergent Cathlab Activation

Deep-learning Assisted ECG-based Emergent Cathlab Activation: First Prospective Implementation of a Smartphone-based System

In its first prospective performance evaluation, the PMcardio STEMI AI ECG Model outperformed standard ECG machine readings, detecting high-risk coronary blockage with 95.7% sensitivity vs. 47.8%. By correctly flagging 15 initially missed patients, the AI model demonstrated its potential to strengthen triage accuracy and accelerate life-saving decisions.
Artificial Intelligence Tool Accurately Predicts Occlusion Myocardial Infarction And May Reduce False-Positive Cath Lab Activations

Artificial Intelligence Tool Accurately Predicts Occlusion Myocardial Infarction And May Reduce False-Positive Cath Lab Activations

A retrospective study at Washington University St. Louis evaluated the PMcardio STEMI AI ECG Model for optimizing heart attack triage in the ED. The model correctly identified all “true” cases and detected high-risk patients missed by the current ECG diagnostic framework. AI-flagged high-risk patients were more likely far more likely to receive appropriate management, supporting AI’s role in improving early ED decision-making.

AI-Enhanced Recognition of Occlusion in Acute Coronary Syndrome (AERO-ACS): A Retrospective Review

Conventional ECG criteria often fail to detect severe coronary blockages, leading to delayed treatment and worse outcomes. The team at Mt. Sinai Morningside performed a retrospective validation of the PMcardio STEMI AI ECG Model, demonstrating 81% sensitivity and 87% specificity in identifying high-risk patients. The AI model nearly doubled the sensitivity of STEMI criteria and correctly reclassified false positives, potentially reducing unnecessary catheterizations while ensuring no true heart attacks were missed.
From ST-Segment Elevation MI to Occlusion MI

State-of-the-Art Review – From ST-Segment Elevation MI to Occlusion MI: The New Paradigm Shift in Acute Myocardial Infarction

This state-of-the-art review explores the evolution of heart attack classification, challenging the limitations of the standard-of-care STEMI/NSTEMI framework. It advocates for a shift toward diagnosing heart attacks based on the presence of acute vessel occlusion rather than relying solely on standard ECG criteria. By redefining how myocardial infarctions are identified and managed, this approach has the potential to reduce misdiagnoses, optimize triage, and refine treatment prioritization in emergency cardiology.

Time for a Diagnostic Paradigm Shift From STEMI/​NSTEMI to OMI/​NOMI (DIFOCCULT-3)

DIFOCCULT-3 is a randomized controlled study actively enrolling patients across 23 sites in Turkey. It evaluates AI-assisted ECG interpretation in detecting high-risk heart attack patterns. By comparing traditional STEMI/NSTEMI classification with an occlusion/non-occlusion model, the trial aims to improve acute coronary blockage detection. The primary endpoint includes patient mortality and re-hospitalization at 1-year follow-up, assessing its impact on long-term patient outcomes.

Evaluating AI Prediction of Occlusive Myocardial Infarction from 12-lead ECGs After Resuscitated Out-of-Hospital Cardiac Arrest

Rapid detection of coronary vessel blockage in out-of-hospital-cardiac-arrest patients is crucial, as timely treatment improves survival and neurological outcomes. Standard ECG criteria often miss critical markers, delaying treatment. This analysis showed that the PMcardio STEMI AI ECG Model could detect them with high accuracy (88.7% sensitivity, 81.4% specificity), showing its potential to speed up diagnosis and improve patient care.

Performance of Artificial Intelligence Powered ECG Analysis in Suspected ST-Segment Elevation Myocardial Infarction

In one of the largest US regional STEMI care networks, the Midwest STEMI Consortium, the PMcardio STEMI AI Model accurately identified 89% of patients needing urgent management while reducing unnecessary catheterizations by 28%. AI-powered standardized ECG interpretation may optmize STEMI triage by reducing costly, unwarranted cath lab activations while ensuring precise and timely diagnosis.

Artificial Intelligence Driven Prehospital ECG Interpretation for the Reduction of False Positive Emergent Cardiac Catheterization Lab Activations

Activating the cardiac catheterization lab too frequently can strain healthcare resources, yet overlooking an acute myocardial infarction carries significant risk. Evaluated in a prehospital setting by Hennepin Emergency Services (USA), the PMcardio STEMI AI ECG Model showed potential to optimize emergency cardiac care and improve resource efficiency by reducing false catheterization lab activations by 34% without missing any “true” heart attacks.

Application of the Artificial Intelligence Model for Detection of Electrocardiographic Signs of Coronary Occlusion in Patients with Non ST-Elevation Acute Coronary Syndrome

Many heart attacks do not fit the textbook definition and occur without classic ST-elevation seen on ECG, complicating diagnosis. This single-center retrospective evaluation at the National Amosov Institute of Cardiovascular Surgery assessed the PMcardio STEMI AI ECG Model's ability to detect these subtle cases. The model achieved 85.3% accuracy, 67% sensitivity, and 93% specificity, highlighting its potential to help clinicians identify high-risk patients earlier, enabling timely and targeted care.

Single Center Retrospective Validation of an Artificial Intelligence ECG Model Detecting Acute Coronary Occlusion

In this single-center US-based cohort study of emergency department patients with suspected heart attacks, the PMcardio STEMI AI ECG Model outperformed standard STEMI criteria, improving detection sensitivity by 30%. Patients correctly identified by AI but missed by cardiologists faced notable treatment delays (~22 hours), underscoring the AI's potential to enable faster diagnosis and earlier intervention.

Artificial intelligence-based detection of occlusion myocardial infarction: first external validation in a German chest-pain unit cohort

In a large-scale retrospective validation involving over 1,700 consecutive patients presenting to German Chest Pain Units, the PMcardio STEMI AI ECG Model demonstrated high diagnostic accuracy (95.3%) and specificity (96.7%) in identifying high-risk patients typically missed by standard ECG interpretation. This highlights its potential to significantly improve emergency care through earlier detection and intervention in a real-world, broad clinical setting.

Validation of an Automated Artificial Intelligence System for 12‑lead ECG Interpretation

Trained on over 1 million ECGs, the PMcardio Core AI ECG Model was evaluated across six diagnostic categories, outperforming primary care physicians by up to 73% and matching cardiologists in overall accuracy. Additionally, it demonstrated clear superiority over traditional ECG machine-generated diagnoses, which are limited by rule-based algorithms, restricted pattern recognition, and an inability to incorporate clinical context.
International Evaluation of an Artificial Intelligence-powered ECG Model Detecting Acute Coronary Occlusion Myocardial Infarction

International Evaluation of an Artificial Intelligence-powered ECG Model Detecting Acute Coronary Occlusion Myocardial Infarction

As the leading publication in EHJ-Digital Health for the past year, this study presents the internal multi-centric validation of the PMcardio STEMI AI ECG Model for detecting acute coronary blockage. Trained on 18,616 ECGs, the model achieved an AUC of 0.938, with 80.6% sensitivity and 93.7% specificity. It significantly outperformed traditional STEMI criteria and matched expert interpretation, offering a groundbreaking advancement in emergent patient detection.

Poor Prognosis of Total Culprit Artery Occlusion in Patients Presenting with NSTEMI 

Traditional ECG criteria miss nearly one-third of heart attack patients with a fully occluded artery, mislabeling them as "NSTEMI" despite needing urgent care. This retrospective study of 10,000 patients found they face longer treatment delays and nearly double the one-year mortality of “acute” STEMI patients, highlighting the need for better ECG-based risk stratification and faster intervention.

Diagnostic Accuracy of a Smartphone Application for Artificial Intelligence-based Interpretation of 12-lead ECG in Primary Care (AMSTELHEART-1)

Accurately interpreting 12-lead ECGs in primary care can be challenging for clinicians due to limited training, time constraints, and variability in expertise. This study validated the PMcardio Core AI ECG Model for AI-driven ECG analysis, demonstrating 86% sensitivity and 92% specificity for major abnormalities, along with near-perfect accuracy for atrial fibrillation, highlighting its potential to enhance early case detection.

Utilizing Longitudinal Data in Assessing All-Cause Mortality in Patients Hospitalized with Heart Failure

In collaboration with the Cardiovascular Center Aalst in Belgium, Powerful Medical developed a machine learning algorithm to improve risk stratification in patients hospitalized with new or worsening heart failure. Trained on 2,449 patients and 151,451 exams, the model accurately predicts mortality across multiple time points (AUC-ROC 0.83–0.89), enabling proactive, yet personalized clinical interventions.

Stay on the pulse with our newsletter

Your submission was successful

Suites

Five suites.
One platform.
The full cardiac care journey.

PMcardio’s clinical suites cover the full spectrum of cardiac care — from acute emergency detection to longitudinal monitoring. Deploy the suites that match your priorities today, expand as your needs grow.

Minutes matter

Acute Care Suite

AI-powered detection and pathway coordination for time-critical cardiac events — including STEMI and OMI, pulmonary embolism / RV strain, and hyperkalemia.

  • stemi/OMI
  • pe/RV strain
  • hyperK

Find what ECGs Hide

Echo Screening Suite

AI-powered screening for structural heart disease directly from a 12-lead ECG — detecting reduced LVEF, aortic stenosis, HCM, and other SHD conditions that traditional ECG interpretation misses.

  • lvef
  • aortic stenosis
  • hcm

Ambulatory, automated

Remote Monitoring Suite

AI-powered analysis of ambulatory ECG recordings — Holter monitors, cardiac patches, and other continuous monitoring devices — with automated findings and longitudinal tracking.

  • holter
  • cardiac patches
  • arrhythmia burden

Beyond the clinic

Patient Suite

AI-powered ECG interpretation for consumer wearables and patient-facing devices — extending cardiac care beyond the clinic into everyday life.

  • wearable ECG Analysis
  • PPG Analysis

On-table intelligence

Angio Suite

AI-powered analysis of coronary angiography — automated stenosis quantification, TIMI frame count, guide wire detection, and myocardial blush grading in near real-time.

  • vessel segmentation
  • stenosis quant.
  • timi frames
  • blush grading

Governance, customization & configuration

Align the platform to your protocols — without a custom software project.

Configure escalation thresholds, roles, and reporting to match local pathway rules — while maintaining system-wide governance and consistency.

  • Configurable triggers, roles, and escalation workflows
  • Custom dashboards and views aligned to leadership needs
  • Controlled expansion to additional pathways over time

Outcomes, QA & performance intelligence​

Measure what matters — across every pathway, every site.

Turn pathway execution into dashboards and reporting that help leadership reduce variation, optimize time-to-treatment, and demonstrate value across every deployed suite.

  • Cross-site, cross-pathway, and team-level benchmarking
  • Time-to-treatment and pathway quality tracking
  • QA workflows, audit trails, and leadership reporting
  • Registry-aligned reporting support (NCDR Chest Pain-MI, AHA GWTG, and more)

Escalation & care coordination

Real-time routing that matches how your system actually runs.

Route critical cases to the right team with role-based notifications, escalation logic, and shared case context — across EMS, ED, cardiology, cath lab, and inpatient care.

  • Role-based alerting and escalation across departments and sites
  • Shared case context so receiving teams have what they need before the patient arrives
  • Integration with existing communication and alerting tools

AI-powered decision support

Clinically validated AI that spans the cardiac care journey.

Run multiple AI models on every recording — acute detection, screening, procedural quantification — with interpretable outputs and case-level explainability.

  • Queen of Hearts™ for STEMI/OMI detection
  • LVsense™ for reduced ejection fraction
  • Culprit Artery Prediction for pre-cath planning
  • Core AI for comprehensive rhythm and conduction analysis
  • Expanding model portfolio across Echo Screening, Remote Monitoring, and Angio Suites

Interoperability & deployment

Connect across your existing systems — without replacing them.

Ingest pathway-critical inputs from across your network and IT landscape, and deliver results where teams already work. Built for system-wide rollout with enterprise deployment patterns.

  • Connect to ECG devices, angiographic systems, and ambulatory monitors across sites
  • Launch PMcardio from the EHR / CVIS with secure links and SSO
  • Send results back to clinical systems where care is documented

All Supported ECG Findings

Rhythms
Sinus bradycardia • Sinus rhythm • Sinus tachycardia • Paced rhythm • Atrial fibrillation
Atrial fibrillation with rapid ventricular response • Atrial fibrillation with slow ventricular response • Atrial flutter • Atrial flutter with rapid ventricular response • Atrial flutter with slow ventricular response • Supraventricular tachycardia • Suspected junctional rhythm • Suspected junctional bradycardia • Suspected accelerated junctional rhythm • Wide QRS rhythm • Idioventricular rhythm • Wide QRS tachycardia

Myocardial Infarctions

  • STEMI
  • STEMI Equivalent
    Equivalent
Detects occlusive myocardial infarctions (OMIs) even without ST elevation (i.e. posterior STEMI, hyperacute T-waves, etc.). Negative for STEMI mimics (i.e. early repolarization, LVH, etc.)
  • High-Risk NSTEMI
    Represents a type 1 myocardial infarction caused by a transiently recanalized coronary occlusion—classically seen in patterns such as Wellens type A or B due to subtotal LAD obstruction, but possible in any infarct-related territory.
  • Culprit Detection
    AI-predicted likelihood scores for LAD, LCx, and RCA with 3D heart visualization highlighting the predicted culprit artery.

Conduction Abnormalities (Heart Blocks
1st degree AV block • 2nd degree AV block, type Wenckebach • Higher degree AV block • Complete right bundle branch block • Incomplete right bundle branch block • Complete left bundle branch block • Incomplete left bundle branch block • Nonspecific intraventricular conduction delay • Left anterior fascicular block • Left posterior fascicular block • Bifascicular block (RBBB + LAFB) • Bifascicular block (RBBB + LPFB) • Trifascicular block (RBBB + LAFB + AVBLOCK1) • Trifascicular block (RBBB + LPFB + AVBLOCK1)

LVEF
Reduced LVEF (≤40%) • Mildly reduced LVEF (41 – 49%) • No signs of reduced LVEF (≥50%)

Axis
Left cardiac axis deviation • Right cardiac axis deviation • Extreme cardiac axis deviation • Normal axis

Measurements
Heart rate • P wave • PR interval • QRS duration • QT interval • Corrected QT interval (Framingham formula) • RR interval • PP interval • ST elevations

Other Supported Diagnoses
Suspected long QT syndrome • Suspected short QT syndrome • Suspected atrial enlargement • Suspected ventricular hypertrophy • Premature complexes

Certain AI ECG Modules are CE-marked medical devices under EU MDR and only certified for marketing in the European Union and the United Kingdom. Powerful Medical technology has not yet been cleared or approved by the US Food and Drug Administration (FDA) for marketing in the USA. Not all modules of the PMcardio platform may be available in your region.

Dr. Tom De Potter, MD

Cardiologist at the Cardiac Center Aalst

Cardiologist specializing in Pacemaker Device Therapy and Electrophysiology. Leads the electrophysiology unit at the Heart Center in Aalst, holds an executive board position at the European Heart Academy, and serves as EHRA scientific program committee co-chair.

Dr. Martin Penicka, MD, PhD

Cardiologist at the Cardiac Center Aalst

Cardiologist at the Cardiac Center Aalst since 2009, specializing in non-invasive imaging and valvular disease. Fellow of the European Society of Cardiology (FESC) and the European Association of Cardiovascular Imaging (FEACVI).

Dr. Ward Heggermont, MD, PhD

Co-director at the Cardiovascular Center

Co-director at the Cardiovascular Center of Aalst Hospital, specializing in heart failure. Research focus at the intersection of cardiology, virology, and metabolism.

Prof. Dr. Robert Hatala, PhD

Co-founder and Chief Scientist

Head of the Arrhythmia and Pacing department at the National Institute of Cardiovascular Diseases in Slovakia. More than 150 publications and 10,000 citations. Contributor to ESC clinical practice guidelines and executive editor of the European Heart Journal since 2020.

Arieh Levy

Head of PMcardio for Individuals

Arieh leads the PMcardio for Individuals product at Powerful Medical, guiding its development as a clinical tool for emergency physicians, cardiologists, and primary care physicians. He holds a First Class MEng in Biomedical Engineering from Imperial College London, where he specialised in AI for cardiology, building physics-informed neural networks to model atrial electrical properties, giving him a background that bridges the clinical and technical demands of building a certified AI medical device used at the bedside every day.

Dr. Dave Pearson, MD​

Business Advisor

Academic emergency medicine physician, entrepreneur, investor, and researcher with nearly two decades at Atrium Health, one of US largest health systems. Brings expertise at the intersection of clinical care, healthcare innovation, and strategic leadership.

Prof. Stephen W. Smith, MD

Professor of Emergency Medicine

Faculty physician in Emergency Medicine at Hennepin County Medical Center and Professor of Emergency Medicine at the University of Minnesota. Co-inventor of the OMI paradigm and editor of Dr. Smith’s ECG Blog, the most-visited US-based ECG interpretation blog.

Prof. Emanuele Barbato, MD, PhD

President of EAPCI

Interventional cardiologist specializing in coronary artery disease and coronary physiology. Acting president of the European Association of Percutaneous Cardiovascular Interventions (EAPCI) and contributor to the clinical practice guidelines for STEMI care.

Scott Sharkey, MD

Chief Medical Officer

Chief Medical Officer of the Minneapolis Heart Institute Foundation and practicing cardiologist at Allina Health Minneapolis Heart Institute. Co-founder of the STEMI Midwest consortium and Takotsubo cardiomyopathy research program and a widely published clinical investigator in STEMI care.

Prof. Dr. Leor Perl, MD

Director of Cardiac Catheterization Institute

Director of Complex Cardiac Interventions and Chief Innovation Officer at Rabin Medical Center. Graduate of the Stanford Biodesign Program.

Suzanne J. Baron, MD, MSc

Director of Interventional Cardiology Research

Director of Interventional Cardiology Research at Massachusetts General Hospital. Holds a Master’s degree in health economics from Harvard School of Public Health. Expert in cardiovascular device impact on healthcare costs and patient-reported outcomes.

Prof. Marco Valgimigli, MD

Deputy Chief Cardiocentro Ticino Institute

Head of Cardiology at Cardiocentro Ticino and Principal Investigator of the TITAN-OMI randomized controlled trial. His research has shaped both European and US clinical practice guidelines on coronary stents, antithrombotic therapy, and vascular access.

Timothy D. Henry, MD

Medical Director of The Carl and Edyth Lindner Center

Leading expert in interventional cardiology and STEMI treatment. Co-founder and principal investigator of the Midwest STEMI Consortium, a registry of more than 20,000 consecutive STEMI activations. Presenting author for the TCT 2025 Late-Breaking Clinical Science on Queen of Hearts.

Matus Horvath

Head of People

Matus leads hiring strategy and culture at Powerful Medical, bringing a strong track record of building and scaling high-performing teams. He previously ran the People Team at Slido, the SaaS startup acquired by Cisco, where he played a key role in scaling a fast-growing, values-driven organization. His broader experience now shapes Powerful Medical’s growth, culture, and talent strategy.

Dr. Timea Kisova, MD

Clinical Research Lead

Timea leads Powerful Medical’s global external validation studies, including the multi-country AI ECG TIMI Study. With a background in biomedical sciences and a medical degree from Barts and The London School of Medicine and Dentistry, she brings the clinical discipline required to generate the prospective, real-world evidence behind every PMcardio module.

Dr. Anthony Demolder, MD, PhD

HF Pathway Lead

Research physician with a PhD on arrhythmias in heritable thoracic aortic disease. He has led international studies at the intersection of cardiology and AI — including earlier work on atrial fibrillation at AZ Sint-Jan Brugge — and now drives Powerful Medical’s heart failure pathway and LVsense™ AI model development.

Dr. Pendell Meyers, MD

ACS Pathway Lead

Emergency medicine physician, prolific educator, and Co-Editor of Dr. Smith’s ECG Blog. He is one of the leading voices behind the Occlusion Myocardial Infarction (OMI) paradigm, the clinical framework that reshaped how heart attacks are identified from the ECG — and which sits at the core of the Queen of Hearts™ model.

Adam Dej

Head of PMcardio for Organizations Engineering

Adam leads engineering for PMcardio for Organizations at Powerful Medical, driving platform architecture, backend systems, and infrastructure behind one of the company’s key growth products. He began programming at 13, entered professional IT at 17, and studied computer security at Comenius University’s Faculty of Mathematics, Physics and Informatics. Known for technical depth across distributed systems, infrastructure, and security, he builds scalable and resilient software with a sharp focus on customer impact. He also champions responsible use of AI and LLMs as force multipliers for modern engineering teams.

Gabriela Rovder Sklencarova

Head of Infrastructure

Gabriela designs the scalable, secure, distributed systems that keep PMcardio running around the clock for clinicians worldwide. She joined from Google, where she was a senior software engineer building core libraries that kept Google’s services resilient against billions of requests, and holds a BA and MA in Computer Science from the University of Cambridge.

Arezou Azar

US and Global Regulatory

Arezou leads Powerful Medical’s global regulatory strategy across the FDA, EU MDR, and international frameworks. She has been part of nearly every major breakthrough in AI cardiology and is an expert in US and global regulatory strategy, SaMD/digital health launches, with experience at Eko Health, Verily, AliveCor, Cardiologs, and Apple. She specializes in regulatory strategy in high-paced global organizations.

Adam Rafajdus

Head of AI

Adam is the Head of AI at Powerful Medical, working across the full lifecycle of bringing AI into clinical practice – from data infrastructure and model development to regulatory clearance. He leads the team behind the Queen of Hearts™ AI ECG models, the company’s ECG digitization pipeline, and its broader AI portfolio. Focused on AI since university, Adam joined as an MLOps Engineer and has grown into his current role over six years.


Mike Wall

VP of Sales

Mike brings more than twenty years at UnitedHealth Group to the table, where he served health plans, employer groups, and public-sector entities as a consultative healthcare sales executive. He combines market intelligence, clinical insight, and financial acumen — the three ingredients needed to bring AI-powered diagnostics into US health systems at scale.

Amani Farid

Head of Strategic Partnerships

Amani leads partnership strategy with a hands-on approach to integration, unlocking long-term value through collaboration and scale. A University of Chicago Law School-trained attorney and former M&A and capital markets associate at two top international law firms, she brings the rare combination of legal precision and commercial execution refined across nearly a decade at Stryker and as VP of Corporate Development at RapidAI — spanning medtech, digital health, and AI-driven diagnostics.

Michal Martonak

Commercial Lead

A mathematician by training, Michal leads commercial strategy, go-to-market, and strategic partnerships with healthcare providers and clinical institutions worldwide. He previously built Powerful Medical’s data and clinical partnerships function, acquiring the large-scale clinical datasets that underpin the company’s certified AI models.

Dr. Jozef Bartunek, MD, PhD

Co-founder and VP Clinical Strategy

Interventional cardiologist and Co-director of the Cardiovascular Center in Aalst, Belgium — one of the world’s leading heart centers. A Fogarty International NIH Fellow at Harvard Medical School and visiting Professor of Medicine at Catholic University Leuven, he has authored more than 240 peer-reviewed publications in heart failure and structural heart disease, and anchors Powerful Medical’s clinical and research strategy.

Simon Rovder

Co-founder and CTO

Simon began his engineering career at Microsoft and holds a Master’s degree in Informatics from the University of Edinburgh. He built and scaled Powerful Medical’s technology organization from the ground up to a team of 20+ engineers, leading the architecture of a CE-certified Class IIb medical device now deployed in hospitals across Europe.

Viktor Jurasek

Co-founder and CPO

Viktor was modding computer games before his teens and has spent the last decade shipping digital products across advertising, finance, and healthcare. As co-founder and CPO, he has led PMcardio’s product and design since the first prototype, setting the bar for how a clinical-grade tool should feel in a physician’s hands — fast, clear, and trustworthy at the point of care.

Felix Bauer

Co-founder and COO

Felix was part of the Hyperloop team that repeatedly competed and won in Elon Musk’s SpaceX Hyperloop Pod Competition. He holds a degree from the Technical University of Munich and brings a rare combination of engineering rigor, regulatory discipline, and operational excellence to the company, spearheading operations, compliance, regulatory, quality management, and global market access since day one.

Dr. Robert Herman, MD, PhD

Co-founder and Chief Medical Officer

Robert is a physician-scientist who served on the Research, Digital and Innovation Committee of the European Society of Cardiology. He bridges medicine and AI, connecting clinicians, researchers, regulators, and trial leaders to translate algorithms into clinical practice. He founded multiple AI ECG models, leads international clinical trials validating them, is a recipient of the Journal of the American College of Cardiology Spencer King Award, and was named to Forbes 30 Under 30 Europe 2024.

Martin Herman

Co-founder and CEO

Martin started coding at 14 and moved to Silicon Valley at 18, founding several companies including a US-based startup before returning to Europe with his brother Robert to build Powerful Medical. He comes from a family of doctors, which shaped his conviction that AI belongs wherever it can genuinely save lives. Forbes 30 Under 30 (Europe 2024).

Heart Attacks are #1 cause of death world-wide and killing about 12 milions people a year.

Clinical Definition of Problem

Contrary to popular belief, a heart attacks isn’t a blockage inside of the heart. A heart attack is a blockage of the coronary arteries supplying the heart muscle with oxygenated blood.

So let’s assume you get a blood clot here — it blocks the blood flow downstream, meaning the heart muscle doesn’t get oxygenated blood and heart tissue downstream starts to die.

Clinical Solution​

The way to fix it is relatively simple – doctors put in a stent that opens up the artery and renews blood flow. The latest clinical practice guidelines recommend that this “stenting” happens within 90 minutes from symptom onset.

If you don’t, even if you put in the stent in later, the heart tissue downstream has already been permanently damaged, which reduces the heart’s ability to pump blood. This is the leading cause of heart failure and increases 1-year mortality by two-fold.

Time is muscle.

You have just 90 minutes to diagnose the patient, bring them to the hospital and put in the stent, otherwise there is permanent damage. So problem is, that 1 in 2 heart attacks get initially misdiagnosed at the first point of contact.

Discover the future of medical work with us.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut elit tellus, luctus nec ullamcorper mattis, pulvinar dapibus leo.