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.

Circulating monocytes expressing senescence-associated features are enriched in COVID-19 patients with severe disease.

Accurate biomarkers for predicting COVID-19 severity have remained an unmet need due to an incomplete understanding of virus pathogenesis and heterogeneity among patients. Cellular senescence and its pro-inflammatory phenotype are suggested to be a consequence of SARS-CoV-2 infection and potentially drive infection-dependent pathological sequelae. Senescence-associated markers in infected individuals have been identified primarily in the lower respiratory tract, while little is known about their presence in more easily accessible bio-specimens. Here, we measured the abundance of senescence-associated signatures in whole blood, plasma and peripheral blood mononuclear cells (PBMCs) of COVID-19 patients and patients without an infection. Bulk transcriptomic and targeted proteomic assays revealed that the level of senescence-associated markers, including the senescence-associated secretory phenotype (SASP), is predictive of SARS-CoV-2 infection. Single-cell RNA-sequencing data demonstrated that a senescence signature is particularly enriched in monocytes of COVID-19 patients, partially correlating with disease severity. Our findings suggest that monocytes are prematurely induced to senescence by SARS-CoV-2 infection, might contribute to exacerbating a SASP-like inflammatory response and can serve as markers and predictors for COVID-19 and its sequelae.

Screening for asymptomatic deep vein thrombosis in COVID-19 patients admitted to the medical ward: a cross-sectional study.

PURPOSE: Patients with COVID-19 have an increased risk for venous thrombo-embolism (VTE), especially pulmonary embolism. The exact prevalence of asymptomatic DVT is not known, as is the usefulness of screening for DVT in patients admitted to ward with COVID-19. We have studied the prevalence of asymptomatic DVT. METHODS: We performed a cross-sectional observational multi-center study at four university medical centers in The Netherlands. All adult patients admitted with COVID-19 to a medical ward were eligible for inclusion, including patients who were transferred back from the ICU to the ward. The study protocol consisted of weekly cross-sectional rounds of compression ultrasound. RESULTS: In total, 125 patients were included in the study. A significant proportion of patients (N = 34 (27%)) had developed a VTE during their admission for COVID-19 before the study ultrasound was performed. In most VTE cases (N = 27 (79%)) this concerned pulmonary embolism. A new asymptomatic DVT was found in 5 of 125 patients (4.0%; 95% CI 1.3-9.1%) (Table 2). Nine patients (7.2%; 95% CI 3.3-13.2%) developed a VTE (all PE) diagnosed within 28 days after the screening US was performed. CONCLUSION: We have shown a low prevalence (4%) of newly discovered asymptomatic DVT outside the ICU-setting in COVID-19 patients. Despite this low prevalence, nine patients developed PE (7%) within 28 days after ultrasound. This favors the hypothesis of local thrombus formation in the lungs. Based on our findings and literature, we do not recommend US-screening of asymptomatic patients with COVID-19 admitted to the ward.

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.

Early hydroxychloroquine but not chloroquine use reduces ICU admission in COVID-19 patients.

BACKGROUND: The global push for the use of hydroxychloroquine (HCQ) and chloroquine (CQ) against COVID-19 has resulted in an ongoing discussion about the effectivity and toxicity of these drugs. Recent studies report no effect of (H)CQ on 28-day mortality. We investigated the effect of HCQ and CQ in hospitalized patients on the non-ICU COVID-ward. METHODS: A nationwide, observational cohort study was performed in The Netherlands. Hospitals were given the opportunity to decide independently on the use of three different COVID-19 treatment strategies: HCQ, CQ, or no treatment. We compared the outcomes between these groups. The primary outcomes were 1) death on the COVID-19 ward, and 2) transfer to the intensive care unit (ICU). RESULTS: The analysis included 1064 patients from 14 hospitals: 566 patients received treatment with either HCQ (n = 189) or CQ (n = 377), and 498 patients received no treatment. In a multivariate propensity-matched weighted competing regression analysis, there was no significant effect of (H)CQ on mortality on the COVID ward. However, HCQ was associated with a significantly decreased risk of transfer to the ICU (hazard ratio (HR) = 0.47, 95% CI = 0.27-0.82, p = 0.008) when compared with controls. This effect was not found in the CQ group (HR = 0.80, 95% CI = 0.55-1.15, p = 0.207), and remained significant after competing risk analysis. CONCLUSION: The results of this observational study demonstrate a lack of effect of (H)CQ on non-ICU mortality. However, we show that the use of HCQ - but not CQ - is associated with a 53% reduction in risk of transfer of COVID-19 patients from the regular ward to the ICU. Recent prospective studies have reported on 28-day, all-cause mortality only; therefore, additional prospective data on the early effects of HCQ in preventing transfer to the ICU are still needed.

Relevance of healthcare-associated pneumonia for empirical antibiotic therapy in the Netherlands.

BACKGROUND: There is no consensus whether patients with healthcare-associated pneumonia (HCAP) should be considered as a patient with hospital-acquired pneumonia (HAP) and treated with broad-spectrum antibiotics, or as a patient with community-acquired pneumonia (CAP), and treated with narrow-spectrum antibiotics. HCAP research has focused mostly on the predictive value for non-susceptibility to broad-spectrum antibiotics and multi-drug resistant pathogens, in settings with moderate to high levels of antibiotic resistance. We investigated whether HCAP criteria predicts non-susceptibility to different empirical strategies, including narrow-spectrum antibiotics in the Dutch setting. METHODS: In a post hoc analysis of patients with moderate-severe CAP in seven Dutch hospitals, we compared in vitro antibiotic susceptibilities of definite and possible causative pathogens of CAP and HCAP to amoxicillin and broader antibiotic regimens. In a sensitivity analysis, pathogens with missing susceptibilities were assumed susceptible (best-case scenario) or non-susceptible (worst-case scenario). RESULTS: Among 2,283 patients with moderate-severe CAP, 23.1% (n = 527) were classified as HCAP. Non-susceptibility to amoxicillin ranged from 11.3% (95% CI 9.9-12.8%; best-case) to 14.4% (95% CI 12.8-16.1%; worst-case) in CAP patients and from 16.7% (95% CI 13.8-20.1%; best-case) to 19.7% (95% CI 16.6-23.3%; worst-case) in HCAP patients. The largest reduction in non-susceptibility was achieved by adding ciprofloxacin to amoxicillin treatment in both CAP patients (10% absolute risk reduction) and HCAP patients (11-16% reduction). CONCLUSIONS: In the Netherlands, HCAP criteria predict higher amoxicillin non-susceptibility in patients hospitalized with moderate-severe CAP. Although broadening the antibiotic spectrum of empiric treatment reduced the likelihood of non-susceptibility, absolute reductions of non-susceptibility in HCAP patients were too low to justify the universal use of broad-spectrum empirical therapy.No abstract available.

Response Adjusted for Days of Antibiotic Risk (RADAR): evaluation of a novel method to compare strategies to optimize antibiotic use.

OBJECTIVES: The Response Adjusted for Days of Antibiotic Risk (RADAR) statistic was proposed to improve the efficiency of trials comparing antibiotic stewardship strategies to optimize antibiotic use. We studied the behaviour of RADAR in a non-inferiority trial in which a ß-lactam monotherapy strategy (n = 656) was non-inferior to fluoroquinolone monotherapy (n = 888) for patients with moderately severe community-acquired pneumonia. METHODS: Patients were ranked according to clinical outcome, using five or eight categories, and antibiotic use. RADAR was calculated as the probability that the ß-lactam group had a more favourable ranking than the fluoroquinolone group. To investigate the sensitivity of RADAR to detrimental clinical outcome we simulated increasing rates of 90-day mortality in the ß-lactam group and performed the RADAR and non-inferiority analysis. RESULTS: The RADAR of the ß-lactam group compared with the fluoroquinolone group was 60.3% (95% CI 57.9%-62.7%) using five and 58.4% (95% CI 56.0%-60.9%) using eight clinical outcome categories, all in favour of ß-lactam. Sample sizes for RADAR were 38% (250/653) and 89% (580/653) of the non-inferiority sample size calculation, using five or eight clinical outcome categories, respectively. With simulated mortality rates, loss of non-inferiority of the ß-lactam group occurred at a relative risk of 1.125 in the conventional analysis, whereas using RADAR the ß-lactam group lost superiority at a relative risk of mortality of 1.25 and 1.5, with eight and five clinical outcome categories, respectively. CONCLUSIONS: RADAR favoured ß-lactam over fluoroquinolone therapy for community-acquired pneumonia. Although RADAR required fewer patients than conventional non-inferiority analysis, the statistic was less sensitive to detrimental outcomes.

Predictors for individual patient antibiotic treatment effect in hospitalized community-acquired pneumonia patients.

OBJECTIVE: Our objective was to identify clinical predictors of antibiotic treatment effects in hospitalized patients with community-acquired pneumonia (CAP) who were not in the intensive care unit (ICU). METHODS: Post-hoc analysis of three prospective cohorts (from the Netherlands and Spain) of adult patients with CAP admitted to a non-ICU ward having received either ß-lactam monotherapy, ß-lactam + macrolide, or a fluoroquinolone-based therapy as empirical antibiotic treatment. We evaluated candidate clinical predictors of treatment effects in multiple mixed-effects models by including interactions of the predictors with empirical antibiotic choice and using 30-day mortality, ICU admission and length of hospital stay as outcomes. RESULTS: Among 8562 patients, empirical treatment was ß-lactam in 4399 (51.4%), fluoroquinolone in 3373 (39.4%), and ß-lactam + macrolide in 790 (9.2%). Older age (interaction OR 1.67, 95% CI 1.23-2.29, p 0.034) and current smoking (interaction OR 2.36, 95% CI 1.34-4.17, p 0.046) were associated with lower effectiveness of fluoroquinolone on 30-day mortality. Older age was also associated with lower effectiveness of ß-lactam + macrolide on length of hospital stay (interaction effect ratio 1.14, 95% CI 1.06-1.22, p 0.008). CONCLUSIONS: Older age and smoking could influence the response to specific antibiotic regimens. The effect modification of age and smoking should be considered hypothesis generating to be evaluated in future trials.