Key result
Random forest model outperforms Wells score plus D-dimer for PE diagnosis with AUC ~0.81.
Why the study?
Acute pulmonary embolism is often missed or misdiagnosed due to non-specific presentation, prompting the development of a machine learning model to facilitate quick, precise diagnosis compared to existing clinical probability assessment models.
Does a machine learning model based on eight clinical and laboratory features improve the diagnostic accuracy for acute pulmonary embolism compared with the Wells score, revised Geneva score, and Years algorithm in patients with suspected acute pulmonary embolism?
Cohort (n=658)
3:1 random division into training (n=340) and testing (n=114) sets
No
Does a machine learning model based on eight clinical and laboratory features improve the diagnostic accuracy for acute pulmonary embolism compared with the Wells score, revised Geneva score, and Years algorithm in patients with suspected acute pulmonary embolism?
Effect estimate: AUC 0.813 vs 0.709 (Wells score with D-dimer) (95% CI 0.729-0.880)
Absolute Event Rate: 0.813% vs 0.709%
p-value: p=0.030
A random forest machine learning model incorporating eight routine clinical and laboratory variables demonstrated superior diagnostic discrimination for acute pulmonary embolism compared with the Wells score combined with D-dimer and comparable performance to the revised Geneva score and Years algorithm.
May support ML-based PE diagnosis; hypothesis-generating and requires prospective validation before practice change.
BACKGROUND: Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models. METHODS: This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Naïve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis. RESULTS: The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726. CONCLUSIONS: Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.
No takes yet. Share an insight, caveat, or question.
Xi et al. (2023) conducted a cohort in Suspected acute pulmonary embolism (APE) (n=658). Random forest (RF) machine learning model based on eight clinical features (D-dimer, cTnT, arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure) vs. Wells score combined with D-dimer, revised Geneva score with D-dimer, and Years algorithm was evaluated on Diagnostic performance (area under the receiver operating characteristic curve [AUC]) for acute pulmonary embolism in the testing dataset (AUC 0.813 vs 0.709 (Wells score with D-dimer), 95% CI 0.729-0.880, p=0.030). The random forest machine learning model achieved an AUC of 0.813 (95% CI 0.729-0.880) in the testing set for diagnosing acute pulmonary embolism, significantly outperforming the Wells score with D-dimer (AUC 0.709, P = 0.030).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: