An observational study in ST Elevation (STEMI) Myocardial Infarction and Microvascular Obstruction (MVO), sponsored by Assiut University. Not yet recruiting. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-10-15.
Sponsored by Assiut University · Observational
This study aims to evaluate myocardial reperfusion in patients with ST-segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PCI).
Although primary PCI successfully restores blood flow in the blocked coronary artery, some patients continue to have impaired blood flow within the small vessels of the heart muscle, a condition known as microvascular obstruction (MVO). This complication may be associated with greater myocardial injury and poorer clinical outcomes.
The study will investigate whether artificial intelligence (AI)-derived electrocardiographic (ECG) features, coronary angiographic parameters, and cardiac magnetic resonance (CMR) findings can provide complementary information about myocardial reperfusion.
Patients undergoing primary PCI will be assessed using ECG and angiographic findings, while CMR will be used to evaluate myocardial injury and microvascular obstruction.
The main objective is to determine whether combining AI-derived ECG features and angiographic parameters can improve the prediction of CMR-detected microvascular obstruction after primary PCI.
The findings may help identify patients at increased risk of impaired myocardial reperfusion and support future risk assessment strategies following STEMI.
Background ST-segment elevation myocardial infarction (STEMI) is usually caused by acute thrombotic coronary occlusion and requires rapid reperfusion. Contemporary acute coronary syndrome guidance prioritizes primary percutaneous coronary intervention (PCI) when it can be delivered promptly, because shortening total ischemic time is central to myocardial salvage.
Restoration of epicardial patency, however, does not guarantee restoration of tissue-level perfusion. A patient may have a technically successful primary PCI with final TIMI grade 3 flow yet still have substantial coronary microvascular injury. Distal embolization, ischemia-reperfusion injury, endothelial swelling, capillary plugging, edema and intramyocardial hemorrhage can produce microvascular obstruction (MVO), which is associated with larger infarct size, impaired ventricular recovery and adverse remodeling.
Conventional bedside and cath-lab markers of myocardial reperfusion include ST-segment resolution (STR), final TIMI flow, myocardial blush grade (MBG) and corrected TIMI frame count (cTFC). These measurements are clinically accessible but capture different components of reperfusion and may remain discordant. Angiography-derived indices of microcirculatory resistance provide an additional pressure-wire-free estimate of microvascular dysfunction and have shown association with CMR-defined MVO and infarct size after STEMI.
Cardiac magnetic resonance (CMR) provides a reference tissue-level assessment after reperfused STEMI. Cine imaging quantifies ventricular volumes and function, while late gadolinium enhancement can quantify infarct size and identify MVO. When appropriate sequences are available, CMR can additionally characterize myocardial edema and intramyocardial hemorrhage. This makes CMR particularly suitable for validating whether electrical and angiographic markers truly reflect myocardial reperfusion.
Artificial intelligence (AI) offers a complementary approach to the routine 12-lead ECG. Traverse and colleagues reported that AI-detected features from pre- and post-reperfusion ECGs were associated with CMR-defined MVO after STEMI, supporting the concept that residual electrical signatures after reperfusion may contain information beyond conventional ST-segment analysis. Rather than developing a new deep-learning system from a small cohort, the present protocol proposes use of a validated AI-ECG platform to extract prespecified features, which will then be integrated with conventional ECG and angiographic variables and tested against CMR-defined myocardial injury.
The proposed study therefore treats reperfusion as a multimodality phenotype: electrical recovery on ECG, epicardial and tissue-level angiographic reperfusion in the cath lab, and tissue injury on CMR. Follow-up echocardiography will then determine whether this early phenotype is associated with subsequent left-ventricular (LV) recovery or adverse remodeling.
Rationale and Research Gap Previous studies have generally evaluated ECG, angiographic microvascular indices, or CMR findings in isolation. The recent AI-ECG study demonstrated proof-of-concept for identifying MVO from AI-detected ECG features, while recent angiography-derived microvascular resistance studies demonstrated incremental association with CMR-defined MVO and infarct size (2,5). However, the incremental value of integrating AI-derived ECG features with readily available angiographic reperfusion parameters in a prospective primary-PCI cohort remains insufficiently characterized, particularly when CMR is used as the tissue-level reference and later LV remodeling is assessed.
The proposed study will therefore determine whether AI-derived electrical reperfusion markers add information beyond conventional STR, MBG and cTFC for identifying CMR-defined MVO. The study will also evaluate whether the multimodality reperfusion phenotype is associated with infarct size, LV function and subsequent LV remodeling.
Research Question Can integration of artificial intelligence-derived ECG features with conventional electrocardiographic and angiographic reperfusion parameters improve identification of cardiac magnetic resonance-defined microvascular injury after successful primary PCI in patients with STEMI, and is this multimodality reperfusion phenotype associated with subsequent LV remodeling? Hypotheses Primary hypothesis Persistent abnormal AI-derived ECG features after successful primary PCI, particularly limited improvement from pre- to post-reperfusion ECG, are independently associated with CMR-defined MVO.
Secondary mechanistic hypotheses
Aim of the Work To evaluate the integrated value of artificial intelligence-derived ECG features and angiographic reperfusion parameters for identification of CMR-defined microvascular injury following successful primary PCI in patients with STEMI and to assess their relationship with subsequent LV functional recovery and remodeling.
688 studies on the registry are indexed under ST Elevation Myocardial Infarction; 184 are open to participants now.
This study's planned enrollment of 90 is below the median of 335 across 229 observational studies indexed under ST Elevation Myocardial Infarction.
Browse ST Elevation Myocardial Infarction studies →Assiut University is the lead sponsor of 5,050 studies on the registry; 2,174 are open to participants now.
Of its 14 completed or terminated interventional studies of FDA-regulated products, 0 (0%) have results posted.
Counted across the registry records on this site, refreshed daily.
Consecutive adult patients presenting with a first STEMI and treated with primary PCI will be screened. The primary analysis cohort will include patients with technically successful primary PCI, analyzable pre- and post-reperfusion ECGs, interpretable angiographic reperfusion assessment and diagnostic early CMR.
Inclusion criteria
This cohort will include adult patients presenting with ST-segment elevation myocardial infarction (STEMI) who undergo primary percutaneous coronary intervention (PCI). Participants will undergo assessment of conventional and artificial intelligence (AI)-derived electrocardiographic features, coronary angiographic parameters, and cardiac magnetic resonance (CMR) findings to evaluate myocardial reperfusion. Angiographic assessment will include parameters such as TIMI flow grade, myocardial blush grade, and corrected TIMI frame count. CMR will be used to assess myocardial injury and the presence and extent of microvascular obstruction (MVO). The study will investigate the association between ECG and angiographic parameters and CMR-detected MVO. All participants will belong to a single observational cohort, with subsequent comparisons according to the presence or absence of MVO. No experimental treatment allocation will be performed, and clinical management will follow standard insti
Incidence of Cardiac MRI-Detected Microvascular Obstruction After Primary PCI
The proportion of patients with microvascular obstruction (MVO) detected by contrast-enhanced cardiac magnetic resonance (CMR) following primary PCI. MVO will be identified as a hypointense region within the hyperenhanced infarcted myocardium on late gadolinium enhancement images. The primary outcome will be reported as the number and percentage of patients with MVO.
Time frame: Use the actual CMR acquisition window specified in your protocol. For example, if CMR is scheduled 3-7 days after PCI: Within 3-7 Days After Primary PCI [Copy] The 3-7-day window is an example, not a confirmed detail from your protocol.
Predictive performance of combined model
AUROC for prediction of CMR detected MVO
Time frame: 7 days
Infarct Size
Percentage of LV myocardial Mass on CMR
Time frame: 7 days
Left Ventricular ejection fraction
LVEF % by CMR
Time frame: 7 days
intramyocardial hemorrhage
Presence or absence on CMR.
Time frame: 7 days
No study locations are listed for this record.
Plan to share: No
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is not yet recruiting, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
ST Elevation Myocardial Infarction →