Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis - a proof of concept study.

INTRODUCTION: Prosthetic valve endocarditis (PVE) is a serious complication of prosthetic valve implantation, with an estimated yearly incidence of at least 0.4-1.0%. The Duke criteria and subsequent modifications have been developed as a diagnostic framework for infective endocarditis (IE) in clinical studies. However, their sensitivity and specificity are limited, especially for PVE. Furthermore, their most recent versions (ESC2015 and ESC2023) include advanced imaging modalities, e.g., cardiac CTA and [18F]FDG PET/CT as major criteria. However, despite these significant changes, the weighing system using major and minor criteria has remained unchanged. This may have introduced bias to the diagnostic set of criteria. Here, we aimed to evaluate and improve the predictive value of the modified Duke/ESC 2015 (MDE2015) criteria by using machine learning algorithms. METHODS: In this proof-of-concept study, we used data of a well-defined retrospective multicentre cohort of 160 patients evaluated for suspected PVE. Four machine learning algorithms were compared to the prediction of the diagnosis according to the MDE2015 criteria: Lasso logistic regression, decision tree with gradient boosting (XGBoost), decision tree without gradient boosting, and a model combining predictions of these (ensemble learning). All models used the same features that also constitute the MDE2015 criteria. The final diagnosis of PVE, based on endocarditis team consensus using all available clinical information, including surgical findings whenever performed, and with at least 1 year follow up, was used as the composite gold standard. RESULTS: The diagnostic performance of the MDE2015 criteria varied depending on how the category of 'possible' PVE cases were handled. Considering these cases as positive for PVE, sensitivity and specificity were 0.96 and 0.60, respectively. Whereas treating these cases as negative, sensitivity and specificity were 0.74 and 0.98, respectively. Combining the approaches of considering possible endocarditis as positive and as negative for ROC-analysis resulted in an excellent AUC of 0.917. For the machine learning models, the sensitivity and specificity were as follows: logistic regression, 0.92 and 0.85; XGBoost, 0.90 and 0.85; decision trees, 0.88 and 0.86; and ensemble learning, 0.91 and 0.85, respectively. The resulting AUCs were, in the same order: 0.938, 0.937, 0.930, and 0.941, respectively. DISCUSSION: In this proof-of-concept study, machine learning algorithms achieved improved diagnostic performance compared to the major/minor weighing system as used in the MDE2015 criteria. Moreover, these models provide quantifiable certainty levels of the diagnosis, potentially enhancing interpretability for clinicians. Additionally, they allow for easy incorporation of new and/or refined criteria, such as the individual weight of advanced imaging modalities such as CTA or [18F]FDG PET/CT. These promising preliminary findings warrant further studies for validation, ideally in a prospective cohort encompassing the full spectrum of patients with suspected IE.

Improved [18F]FDG PET/CT Diagnostic Accuracy for Infective Endocarditis Using Conventional Cardiac Gating or Combined Cardiac and Respiratory Motion Correction (CardioFreezeTM).

Infective endocarditis (IE) is a serious and diagnostically challenging condition. [18F]FDG PET/CT is valuable for evaluating suspected IE, but it is susceptible to motion-related artefacts. This study investigated the potential benefits of cardiac motion correction for [18F]FDG PET/CT. In this prospective study, patients underwent [18F]FDG PET/CT for suspected IE, combined with a conventional cardiac gating sequence, a data-driven cardiac and respiratory gating sequence (CardioFreezeTM), or both. Scans were performed in adherence to EANM guidelines and assessors were blinded to patients' clinical contexts. Final diagnosis of IE was established based on multidisciplinary consensus after a minimum of 4 months follow-up and surgical findings, whenever performed. Seven patients participated in the study, undergoing both an ungated [18F] FDG-PET/CT and a scan with either conventional cardiac gating, CardioFreezeTM, or both. Cardiac motion correction improved the interpretability of [18F]FDG PET/CT in four out of five patients with valvular IE lesions, regardless of the method of motion correction used, which was statistically significant by Wilcoxon's signed rank test: p = 0.046. In one patient the motion-corrected sequence confirmed the diagnosis of endocarditis, which had been missed on non-gated PET. The performance of the two gating sequences was comparable. In conclusion, in this exploratory study, cardiac motion correction of [18F]FDG PET/CT improved the interpretability of [18F]FDG PET/CT. This may improve the sensitivity of PET/CT for suspected IE. Further larger comparative studies are necessary to confirm the additive value of these cardiac motion correction methods.

18F-FDG PET/CT in Infective Endocarditis: Indications and Approaches for Standardization.

PURPOSE OF REVIEW: Additional imaging modalities, such as FDG-PET/CT, have been included into the workup for patients with suspected infective endocarditis, according to major international guidelines published in 2015. The purpose of this review is to give an overview of FDG-PET/CT indications and standardized approaches in the setting of suspected infective endocarditis. RECENT FINDINGS: There are two main indications for performing FDG-PET/CT in patients with suspected infective endocarditis: (i) detecting intracardiac infections and (ii) detection of (clinically silent) disseminated infectious disease. The diagnostic performance of FDG-PET/CT for intracardiac lesions depends on the presence of native valves, prosthetic valves, or implanted cardiac devices, with a sensitivity that is poor for native valve endocarditis and cardiac device-related lead infections, but much better for prosthetic valve endocarditis and cardiac device-related pocket infections. Specificity is high for all these indications. The detection of disseminated disease may also help establish the diagnosis and/or impact patient management. Based on current evidence, FDG-PET/CT should be considered for detection of disseminated disease in suspected endocarditis. Absence of intracardiac lesions on FDG-PET/CT cannot rule out native valve endocarditis, but positive findings strongly support the diagnosis. For prosthetic valve endocarditis, standard use of FDG-PET/CT is recommended because of its high sensitivity and specificity. For implanted cardiac devices, FDG-PET/CT is also recommended, but should be evaluated with careful attention to clinical context, because its sensitivity is high for pocket infections, but low for lead infections. In patients with prosthetic valves with or without additional aortic prosthesis, combination with CTA should be considered. Optimal timing of FDG-PET/CT is important, both during clinical workup and technically (i.e., post tracer injection). In addition, procedural standardization is key and encompasses patient preparation, scan acquisition, reconstruction, subsequent analysis, and clinical interpretation. The recommendations discussed here will hopefully contribute to improved standardization and enhanced performance of FDG-PET/CT in the clinical management of patients with suspected infective endocarditis.

The value of 18F-FDG PET/CT for the diagnosis of device-related infections in patients with a left ventricular assist device: a systematic review and meta-analysis.

BACKGROUND: Left ventricular assist devices (LVADs) are increasingly used for the treatment of advanced heart failure. LVADs improve quality of life and decrease mortality, but the driveline carries substantial risk for major infections. These device-related LVAD and driveline infections are difficult to diagnose with conventional imaging. We reviewed and analysed the current literature on the additive value of 18F-fluorodeoxyglucose positron emission tomography combined with computed tomography (FDG-PET/CT) imaging for the diagnosis of LVAD-related infections." MATERIALS/METHODS: We performed a systematic literature review using several databases from their inception until the 31st of December, 2019. Studies investigating the diagnostic performance of FDG-PET/CT in patients with suspected LVAD infection were retrieved. After a bias risk assessment using QUADAS-2, a study-aggregate meta-analysis was performed on a per examination-based analysis. RESULTS: A total of 10 studies were included in the systematic review, eight of which were also eligible for study-aggregate meta-analysis. For the meta-analysis, a total of 256 FDG-PET/CT scans, examining pump/pocket and/or driveline infection, were acquired in 230 patients. Pooled sensitivity of FDG-PET/CT was 0.95 (95% confidence interval (CI) 0.89-0.97) and pooled specificity was 0.91 (95% CI 0.54-0.99) for the diagnosis of device-related infection. For pump/pocket infection, sensitivity and specificity of FDG-PET/CT were 0.97 (95%CI 0.69-1.00) and 0.93 (95%CI 0.64-0.99), respectively. For driveline infection, sensitivity and specificity were 0.96 (95%CI 0.88-0.99) and 0.99 (95%CI 0.13-1.00) respectively. Significant heterogeneity existed across studies for specificity, mostly caused by differences in scan procedures. Predefined criteria for suspicion of LVAD and/or driveline infection were lacking in all included studies. CONCLUSIONS: FDG-PET/CT is a valuable tool for assessment of device-related infection in LVAD patients, with high sensitivity and high, albeit variable, specificity. Standardization of FDG-PET/CT procedures and criteria for suspected device-related LVAD infections are needed for consistent reporting of FDG-PET/CT scans.