What is the clinical evidence from this study?

Study design: Cohort. Population: Heart failure with preserved ejection fraction (HFpEF) (n=134). Intervention: Rule-based Clinical Decision Support System (CDSS) vs. Expert consensus interpretation. Primary outcome: Diagnostic discrimination for probable HFpEF (AUC 0.93, 95% CI 0.89-0.97).

What does this research mean for the field?

A rule-based Clinical Decision Support System for stress echocardiography matches expert assessments in 93% of cases and demonstrates high diagnostic discrimination (AUC = 0.93) for probable HFpEF. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

April 19, 2026Open Access

Rule-based clinical decision support system for automated assessment of left ventricular diastolic function during stress echocardiography

Key Result

The rule-based Clinical Decision Support System matched expert assessments in 93% of cases and demonstrated high diagnostic discrimination for probable HFpEF with an AUC of 0.93.

Key Points

This research aims to improve the assessment of left ventricular diastolic function during stress echocardiography using a rule-based decision support system.
Developed and validated a rule-based clinical decision support system for diastolic function assessment.
Conducted a study with a prospective cohort of 134 patients during semi-supine bicycle stress echocardiography.
Collected echocardiographic and Doppler data using advanced imaging systems.
Applied rule-based logic in accordance with established guidelines.
The system matched expert assessments in 93% of cases.
Accurately identified stress-induced diastolic dysfunction in 85% of cases.
Demonstrated high diagnostic agreement with an ICC greater than 0.94.
Achieved an area under the curve (AUC) of 0.92 for discrimination.

Study Design

Type

Cohort (n=134)

Blinding

Blinded

Multicenter

Structured PICO

Does a rule-based Clinical Decision Support System (CDSS) improve diagnostic agreement and efficiency for assessing left ventricular diastolic function during stress echocardiography in patients with suspected HFpEF compared to expert consensus?

Population

134 adult patients with clinical suspicion of HFpEF (exertional dyspnea with LVEF ≥50%), mean age 61.3 ± 8.7 years, 86.2% female, based in Uzbekistan. Key exclusions: moderate to severe valvular heart disease, significant arrhythmias, unstable coronary artery disease, recent myocardial infarction, acute or systemic inflammatory diseases, and poor echocardiographic imaging window.

Intervention

Rule-based Clinical Decision Support System (CDSS) using deterministic rules derived from ASE/EACVI guidelines to automate left ventricular diastolic function assessment during semi-supine bicycle stress echocardiography.

Comparator

Manual interpretation by two independent senior echocardiographers (expert consensus) blinded to each other's assessments and the CDSS outputs.

Outcome

Diagnostic agreement (ICC and Cohen's kappa) and discrimination (AUC) for identifying diastolic dysfunction and probable HFpEF compared to expert consensus.surrogate

A rule-based CDSS provides highly accurate, transparent, and time-efficient automated assessment of diastolic function during stress echocardiography, matching expert consensus in 93% of cases.

Main Result

Effect estimate: AUC 0.93 (95% CI 0.89-0.97)

Limitations

Relies on manual input of echocardiographic and clinical variables, which may introduce operator-dependent variability.
Single-center validation study conducted using two ultrasound platforms.
Requires broader validation across multiple institutions, patient populations, and ultrasound vendors.

Abstract

Background Heart failure with preserved ejection fraction (HFpEF) remains challenging to diagnose due to the complexity of diastolic function assessment during stress echocardiography, where multiple hemodynamic parameters must be evaluated under time pressure. Explainable artificial intelligence, specifically rule-based Clinical Decision Support Systems (CDSS), offers promising improvements in reproducibility and interpretability. Methods A rule-based CDSS was developed and clinically validated to automate left ventricular diastolic function assessment during semi-supine bicycle stress echocardiography. A prospective cohort of 134 patients (mean age 61.3 ± 8.7 years) with exertional dyspnea and preserved left ventricular ejection fraction (LVEF 50%) was enrolled, excluding individuals with significant valvular pathologies, arrhythmias, or unstable ischemia. Echocardiographic and Doppler data were collected using Toshiba Aplio500 and Esaote MyLabSIGMA systems. The algorithm incorporated manual input of measurements, computed derived indices (e.g., diastolic reserve index, myocardial stiffness, vascular resistance), and applied rule-based logic in accordance with ASE/EACVI (2016/2022) guidelines and the ESC HFpEF consensus. Results The CDSS generated diagnostic conclusions within 3 min per case, matching expert assessments in 93% of cases and correctly identifying stress-induced diastolic dysfunction in 85%. It demonstrated high diagnostic agreement (ICC 0.94) and discrimination (AUC = 0.92). Rule-based outputs, such as “Impaired diastolic reserve” or “Right ventricular dysfunction under load,” were based on combinations of parameters (e.g., E/e′ 15, Δe′ ≤ 0, TAPSE 17 mm, PCWR 12 mmHg). Conclusion The explainable, guideline-compliant CDSS enables real-time, transparent analysis of diastolic function, supporting improved diagnostic consistency and augmented physician decision-making in cardiovascular care.

Bookmark

View Full Paper