Predicting acute and long-term mortality in a cohort of pulmonary embolism patients using machine learning

El-Bouri, Wahbi K.; Sanders, Alexander; Lip, Gregory Y.H.

doi:10.1016/j.ejim.2023.07.012

Cited by 7 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining a miniaturized and automatized image-based bioassay and machine learning approaches, we extract individual patient signatures directly reflecting the quantitative and qualitative impact of natalizumab on primary cells from the patients. It reached a prediction power above 70% and presents predictive values of accuracy and F1-score comparable or above those of other studies that applied machine learning methods to predict clinical outcome in other disease settings 36,37 . We anticipate that our workflow could be generalized to the testing of other therapeutic antibodies across multiple clinical indications.…”

Section: Discussionsupporting

confidence: 66%

Morphological profiling of T cells predicts clinical response to VLA-4-targeting natalizumab therapy in patients with multiple sclerosis

Chaves,

Silva,

Nakaya

et al. 2024

Preprint

View full text Add to dashboard Cite

Despite the efficacy of natalizumab in Multiple Sclerosis (MS) treatment, approximately 30% of patients do not respond favorably. Individual heterogeneity of T-cell response to VLA-4 natalizumab-mediated blockade may underlie disparities in treatment efficacy. Here, a high-content cell imaging (HCI) pipeline was implemented to profile the in vitro effects of natalizumab on VLA-4-stimulated leukocytes from MS patients prior to treatment. Unsupervised clustering of image data partially discriminated non-responder MS patients based on morphology, F-actin organization, and signaling-related features in CD8+ T cells. Treatment response was assessed through a Random Forest approach with predictive performance of 91% for a discovery cohort and 70% for a validation cohort. Unfavorable treatment response was associated with the inefficacy of natalizumab to impair the ability of pretreated CD8+ T cells to spread over VCAM-1. Our study unveils that CD8+ T cells from individual MS patients display heterogeneous susceptibility to natalizumab in vitro and highlights the potential of HCI-based pretreatment monitoring to assist individualized treatment prescription.

show abstract

Section: Discussionsupporting

confidence: 66%

Morphological profiling of T cells predicts clinical response to VLA-4-targeting natalizumab therapy in patients with multiple sclerosis

Chaves,

Silva,

Nakaya

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…[21] equaled only 0.76, what needed to translate on poorer results of TTE prediction effectiveness of the presented results. Moreover, lower prediction values of PESI are met in retrospective studies and venous thromboembolism registries (AUC 0.64-0.7) and higher in single center surveys, reaching even 0.925 [31][32][33]. These values highly derive from study group populations characteristics and data collection manners.…”

Section: Discussionmentioning

confidence: 99%

Echocardiographic parameters as adjuncts to the Pulmonary Embolism Severity Index in predicting 30-day mortality in acute pulmonary embolism patients

Wiliński,

Chukwu,

Skwarek

et al. 2024

Pol Heart J

View full text Add to dashboard Cite

show abstract

“…Finally, increasing the amount of training data can enable us to obtain more information and make diverse learning in most cases, as well as increase the chances of achieving better results. Some important studies use 70% or 80% of samples in the training set (46)(47)(48). We randomly assigned 1,434 cases to the sample, with 50% of the cases used as the training set and the rest as the test set, to improve the efficiency of model validation.…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Identifying the risk factors of ICU-acquired fungal infections: clinical evidence from using machine learning

Zhao,

Lai,

Tang

et al. 2024

Front. Med.

View full text Add to dashboard Cite

BackgroundFungal infections are associated with high morbidity and mortality in the intensive care unit (ICU), but their diagnosis is difficult. In this study, machine learning was applied to design and define the predictive model of ICU-acquired fungi (ICU-AF) in the early stage of fungal infections using Random Forest.ObjectivesThis study aimed to provide evidence for the early warning and management of fungal infections.MethodsWe analyzed the data of patients with culture-positive fungi during their admission to seven ICUs of the First Affiliated Hospital of Chongqing Medical University from January 1, 2015, to December 31, 2019. Patients whose first culture was positive for fungi longer than 48 h after ICU admission were included in the ICU-AF cohort. A predictive model of ICU-AF was obtained using the Least Absolute Shrinkage and Selection Operator and machine learning, and the relationship between the features within the model and the disease severity and mortality of patients was analyzed. Finally, the relationships between the ICU-AF model, antifungal therapy and empirical antifungal therapy were analyzed.ResultsA total of 1,434 cases were included finally. We used lasso dimensionality reduction for all features and selected six features with importance ≥0.05 in the optimal model, namely, times of arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary catheter, and invasive mechanical ventilation. The area under the curve of the model for predicting ICU-AF was 0.981 in the test set, with a sensitivity of 0.960 and specificity of 0.990. The times of arterial catheter (p = 0.011, OR = 1.057, 95% CI = 1.053–1.104) and invasive mechanical ventilation (p = 0.007, OR = 1.056, 95%CI = 1.015–1.098) were independent risk factors for antifungal therapy in ICU-AF. The times of arterial catheter (p = 0.004, OR = 1.098, 95%CI = 0.855–0.970) were an independent risk factor for empirical antifungal therapy.ConclusionThe most important risk factors for ICU-AF are the six time-related features of clinical parameters (arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary catheter, and invasive mechanical ventilation), which provide early warning for the occurrence of fungal infection. Furthermore, this model can help ICU physicians to assess whether empiric antifungal therapy should be administered to ICU patients who are susceptible to fungal infections.

show abstract

Predicting acute and long-term mortality in a cohort of pulmonary embolism patients using machine learning

Cited by 7 publications

References 26 publications

Morphological profiling of T cells predicts clinical response to VLA-4-targeting natalizumab therapy in patients with multiple sclerosis

Morphological profiling of T cells predicts clinical response to VLA-4-targeting natalizumab therapy in patients with multiple sclerosis

Echocardiographic parameters as adjuncts to the Pulmonary Embolism Severity Index in predicting 30-day mortality in acute pulmonary embolism patients

Identifying the risk factors of ICU-acquired fungal infections: clinical evidence from using machine learning

Contact Info

Product

Resources

About