Developing A Random Forest Algorithm to Identify Patent Foramen Ovale and Atrial Septal Defects in Ontario Administrative Databases

Abstract

Purpose: Routinely collected administrative data is widely used for population-based research. However, although clinically very different, atrial septal defects (ASD) and patent foramen ovale (PFO) share a single diagnostic code (ICD-9: 745.5, ICD-10: Q21.1). Using machine-learning based approaches we developed and validated an algorithm to differentiate between PFO and ASD patient populations within healthcare administrative data. Methods: Using data housed at ICES, we identified patients who underwent transcatheter closure in Ontario between October 2002 and December 2017 using a code (1HN80GPFL, N = 4680). A novel random forest model was developed using demographic and clinical information. Those patients who had undergone transcatheter closure and had records in the CorHealth Ontario cardiac procedure registry (N = 1482) were used as the reference standard. Several algorithms were tested and evaluated for accuracy, sensitivity, and specificity. Variable importance was examined via mean decrease in Gini index. Results: We tested 7 models in total. The final model included 24 variables, including demographic, comorbidity, and procedural information. After hyperparameter tuning, the final model achieved 0.76 accuracy, 0.76 sensitivity, and 0.75 specificity. Patient age group had the greatest influence on node impurity, and thus ranked highest in variable importance. Conclusions: Our random forest classification method achieved reasonable accuracy in identifying PFO and ASD closure in administrative data. The algorithm can now be applied to evaluate long term PFO and ASD closure outcomes in Ontario. Future external validation studies are recommended to further test the algorithm.

Atrial fibrillation after transcatheter patent foramen ovale closure: To measure is to know

“…For example, the random forest classification method used by the aithors had a moderate accuracy of 76% for discriminating PFO from atrial septal defect occlusions procedures with a balanced sensitivity and specificity of 76% and 75%, respectively. 6 Similarly, endpoint adjudication was also based on administrative data analysis using an algorithm with a sensitivity of 80.7% and specificity of 99.1%. 7 Nevertheless, these types of analyses based on administrative data deserve merit due to the high number of patients, low proportions of dropouts or losses to follow-up, and for most their ability to identify gaps in the literature.…”