Key result
A random forest model using 19 HRV indices predicted cardiac arrest in smokers with 93.61% accuracy and an AUC of 0.95, outperforming decision tree and logistic regression models.
Why the study?
Smoking is a specific hazard factor for cardiovascular pathology, but data on smoking and heart death had not been previously reviewed.
Does a machine learning model based on HRV parameters accurately predict cardiac arrest in smokers?
Does a machine learning model based on HRV parameters accurately predict cardiac arrest in smokers?
Absolute Event Rate: 93.61% vs 88.5%
A random forest machine learning model utilizing Heart Rate Variability parameters can predict cardiac arrest in smokers with high accuracy and discrimination.
No takes yet. Share an insight, caveat, or question.
HRV-based random forest model shows promise for cardiac arrest prediction in smokers; hypothesis-generating and requires prospective validation before clinical adoption.
Shashikant et al. (2019) studied Cardiac arrest in smokers. Random forest model vs. Logistic regression and decision tree models was evaluated on Accuracy of predicting cardiac arrest. A random forest model using 19 HRV indices predicted cardiac arrest in smokers with 93.61% accuracy and an AUC of 0.95, outperforming decision tree and logistic regression models.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: