Diagnostic Performance of Artificial Intelligence Algorithms in Prediction of Acute Coronary Syndrome Based on White Blood Cell Properties

Diagnostic Performance of Artificial Intelligence Algorithms in Prediction of Acute Coronary Syndrome Based on White Blood Cell Properties (AI-ACS Trial)

The goal of this observational study is to evaluate whether artificial intelligence (AI) algorithms can predict or exclude acute coronary syndrome (ACS) in adults using data generated by routine hematology testing. The main questions the study aims to answer are:

• Can AI algorithms based on white blood cell (WBC) data predict or exclude ACS in subjects with suspected ACS?
• Can erythrocyte (EC) and/or thrombocyte (TC) data, where available, improve or complement WBC-based AI prediction of ACS?
• How does the diagnostic performance of the AI algorithms compare with high-sensitivity cardiac troponin (hs-cTn), and can the combination of AI algorithms and hs-cTn improve diagnostic performance?

Participants will undergo clinical assessment and blood testing as part of usual clinical care. Their previously generated clinical information, hematology data, and hs-cTn results will be used to train and test the AI algorithms. Participation in the study does not determine the indication for coronary angiography or treatment, and no additional study-specific treatments are performed.

Study Overview

• Status: Recruiting
• Conditions: Angina Pectoris; Acute Coronary Syndrome; NSTEMI - Non-ST Segment Elevation MI; STEMI - ST Elevation Myocardial Infarction; Unstable Angina (UA)

Detailed Description

The AI-ACS clinical trial is an observational, prospective, single-center case-control study conducted at the Medical University of Graz. The trial is designed to assess the diagnostic performance of AI algorithms using hematology data to predict or exclude ACS in adult subjects.

The primary focus of the study is the use of WBC data generated by routine hematology testing. In addition, EC and/or TC data may be used, where available, to explore whether these data can predict or exclude ACS independently or improve WBC-based ACS prediction. The diagnostic performance of the AI algorithms will be compared with high-sensitivity cardiac troponin (hs-cTn), and the performance of combined AI and hs-cTn approaches will also be evaluated.

The AI-ACS trial consists of two main phases: training of AI models and testing of AI models.

For training of AI models, subjects will be assigned to the control cohort, case cohort, supplementary cohort, or rule-out cohort. The control cohort includes subjects with suspected ACS but exclusion of a culprit lesion during coronary angiography. The case cohort includes subjects with suspected ACS and identification of a culprit lesion during coronary angiography. The supplementary cohort includes subjects with no or stable angina pectoris and no indication for revascularization during coronary angiography. The rule-out cohort includes subjects with suspected non-ST elevation ACS and NSTEMI rule-out who did not undergo coronary angiography within 72 hours. WBC data from the control, case, and supplementary cohorts will be used to train AI models, while WBC data from the rule-out cohort may be used to optimize AI training by semi-supervised learning. Whenever available, EC and/or TC data may also be used for exploratory AI training, either alone or in combination with WBC data.

For testing of AI models, a separate all-comer cohort will be used. This cohort includes subjects presenting to the emergency department with suspected ACS. WBC and/or EC/TC data from the all-comer cohort will be used to evaluate the diagnostic performance of trained AI models. Data used for testing will not be included in the training set, in order to avoid data leakage and to ensure unbiased evaluation of model performance.

The anticipated maximum number of subjects to be recruited is 3,350. Of these, 2,350 subjects will be recruited for training of AI models and 1,000 subjects will be recruited for testing of AI models. The training population includes the control cohort, case cohort, supplementary cohort, and rule-out cohort. The testing population consists of the separate all-comer cohort.

Hematology data are collected from routine blood tests performed as part of usual clinical care, using hematology analyzers. Clinical assessment, ECG interpretation, hs-cTn measurement, coronary angiography, and treatment decisions are performed according to current clinical guidelines and are independent of study participation. The presence or absence of ACS is determined based on clinical diagnostic procedures, including coronary angiography and review board evaluation where applicable.

The diagnostic performance of the AI models will be evaluated using receiver operating characteristic (ROC) curve analysis, area under the ROC curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value. The diagnostic performance of hs-cTn and combined AI plus hs-cTn approaches will also be assessed. Training of AI models is planned to be repeated at regular intervals as the number of included datasets increases.

The study includes procedures for data validation, source data verification, data management, and quality control to support the accuracy, completeness, and integrity of the data collected. Missing or inconsistent data will be addressed according to the statistical analysis and data management procedures defined in the protocol.

• Study Type: Observational
• Enrollment (Estimated): 3350

Contacts and Locations

• Study Contact: Name: Dimitrij Shulkin, M.Sc.; Phone Number: +43-676-5150578; Email: shulkin@robotdreams.co
• Study Contact Backup: Name: Johannes Gollmer, Dr. univ.; Email: johannes.gollmer@medunigraz.at

Study Locations

• Austria
  • Styria / Steiermark
    • Graz, Styria / Steiermark, Austria, 8036
      • Recruiting
      • Landeskrankenhaus-Universitätsklinikum Graz
      • Contact: Heiko Bugger, MD; Phone Number: +43 316 385 30177; Email: heiko.bugger@medunigraz.at

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Patients recruited at LKH-Universitätsklinikum Graz / Medical University of Graz, including subjects presenting to the emergency department or facilities of the Department of Cardiology, including the cardiac catheter laboratory and outpatient facilities. The study population includes adults with suspected acute coronary syndrome as well as subjects with no or stable angina pectoris depending on cohort assignment.

Description

Inclusion Criteria:

General inclusion criteria:

• Male or female, aged 18 years or above.
• Participant is willing and able to give informed consent for participation in the study.
• Collection of WBC and hs-cTn data must be possible.
• Criteria for timing of blood sampling for collection of WBC and hs-cTn data must be fulfilled, where applicable.

Case cohort:

• Suspicion of STEMI or NSTE-ACS according to current ESC guidelines.
• Coronary angiography must have been performed within 72 hours after initial suspicion of ACS.
• For patients qualifying for observation according to ESC guidelines, coronary angiography is not mandatory and time limits do not apply.
• Confirmation of STEMI or NSTE-ACS by identification of a culprit lesion using coronary angiography; identical evaluation results by review board required.
• For observation patients without coronary angiography, final discharge diagnosis is used to decide about the presence or absence of NSTEMI and/or ACS.
• Criteria for timing of blood sampling for collection of WBC and hs-cTn data must be fulfilled.

Control cohort:

• Suspicion of STEMI or NSTE-ACS according to current ESC guidelines.
• Coronary angiography must have been performed within 72 hours after initial suspicion of ACS.
• No identification of a culprit lesion compatible with diagnosis of STEMI or NSTE-ACS during coronary angiography; identical evaluation results by review board required.
• Criteria for timing of blood sampling for collection of WBC and hs-cTn data must be fulfilled.

Supplementary cohort:

• Subject presents without chest pain or with stable angina pectoris.
• No indication for revascularization during coronary angiography; identical evaluation results by review board required.
• Exclusion of elevated hs-cTn.
• Criteria for timing of blood sampling for collection of WBC and hs-cTn data must be fulfilled.
• Between initial blood sampling to collect WBC data and coronary angiography, the subject must not develop suspicion of ACS.

Rule-out cohort:

• Suspicion of NSTE-ACS and NSTEMI rule-out according to current ESC guidelines, i.e. very low initial hs-cTn value, or low initial hs-cTn value and no significant 1-hour/2-hour change in hs-cTn value.
• No coronary angiography within 72 hours.
• Criteria for timing of blood sampling for collection of WBC and hs-cTn data must be fulfilled.

All-comer cohort:

• Subject presents to the emergency department with suspected ACS.
• Clinical assessments, ECG, and measurements of hs-cTn, single or serial measurement, must be conducted according to ESC guidelines.
• Collection of WBC data must be performed at initial blood withdrawal after admission to the emergency department.
• Review board evaluations must confirm the presence or absence of a culprit lesion if coronary angiography was performed, as outlined for the case and control cohorts.

Exclusion Criteria:

• Age below 18 years.
• Subject refuses informed consent.
• Collection of WBC and hs-cTn data is not possible.
• Criteria for timing of blood sampling for collection of WBC and hs-cTn data cannot be fulfilled.
• Suspicion of ACS occurs in subjects with no or stable angina pectoris any time between initial blood sampling and start of coronary angiography.

Study Plan

How is the study designed?

Number of groups / cohorts

5

Cohorts and Interventions

Group / Cohort
Control-Cohort; Subjects with suspected ACS but exclusion of a culprit lesion during coronary angiography.
Case-Cohort; Subjects with suspected ACS and identification of a culprit lesion during coronary angiography.
Supplementary cohort; Subjects with no or stable angina pectoris and no indication for revascularization during coronary angiography.
Rule Out; Subjects with suspected NSTE-ACS and STEMI Rule-Out that did not undergo coronary angiography <72h.
All-comer cohort; Subjects presenting to the emergency department with suspected acute coronary syndrome (ACS). This cohort is used for testing the AI models. Clinical assessment, ECG, and high-sensitivity cardiac troponin (hs-cTn) measurements are performed according to current ESC guidelines. White blood cell (WBC) data are collected at the initial blood withdrawal after admission to the emergency department. If coronary angiography is performed, review board evaluation confirms the presence or absence of a culprit lesion.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Training of AI models	Diagnostic performance of AI models in predicting ACS, evaluated by area under curve (AUC) under the receiver operating characteristic (ROC) curve	36 months
Testing of AI models	Diagnostic performance of AI models in predicting ACS, evaluated by AUC under ROC curve ; Specificity and sensitivity of AI models to predict ACS in subjects with suspected ACS, calculated from AUC under ROC curve	36 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Training of AI models	Sensitivity of AI models to predict ACS ; Specificity of AI models to predict ACS	36 months
Testing of AI models:	Sensitivity of AI models to predict ACS; Specificity of AI models to predict ACS; Sensitivity of hs-cTn to predict ACS; Specificity of hs-cTn to predict ACS; Combined sensitivity of AI models and hs-cTn to predict ACS; Combined specificity of AI models and hs-cTn to predict ACS; AUC under ROC curve of hs-cTn predicting ACS; AUC under ROC curve of AI models and hs-cTn predicting ACS; Difference in predicting ACS between hs-cTn and AI models using AUC under ROC curve	36 months

Collaborators and Investigators

• Sponsor: RobotDreams GmbH

Study record dates

Study Major Dates

• Study Start (Actual): February 1, 2024
• Primary Completion (Estimated): July 31, 2026
• Study Completion (Estimated): December 31, 2026

Study Registration Dates

• First Submitted: April 22, 2024
• First Submitted That Met QC Criteria: April 22, 2024
• First Posted (Actual): April 25, 2024

Study Record Updates

• Last Update Posted (Actual): June 24, 2026
• Last Update Submitted That Met QC Criteria: June 21, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; ACS; AI; Troponin; Machine learning; white blood cell; hematology analyzer
• Additional Relevant MeSH Terms: Pain; Neurologic Manifestations; Vascular Diseases; Cardiovascular Diseases; Pathologic Processes; Heart Diseases; Infarction; Necrosis; Myocardial Ischemia; Myocardial Infarction; Ischemia; Chest Pain; Pathological Conditions, Signs and Symptoms; Signs and Symptoms; ST Elevation Myocardial Infarction; Non-ST Elevated Myocardial Infarction; Acute Coronary Syndrome; Angina Pectoris; Angina, Unstable
• Other Study ID Numbers: AI ACS

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No