Key result
Time-domain heart rate variability analysis using artificial neural networks and support vector machines achieved 89.64% and 100% accuracy, respectively, in automated lung cancer prediction.
Why the study?
Does a time-domain heart rate variability feature-based automated system improve the prediction and staging of lung cancer compared to healthy controls?
Population
104 lung cancer participants and 30 control volunteers
Comparison
Time-domain heart rate variability feature-based… vs Control volunteers (for cancer prediction)
Design
Case-control
Authors
Loading...
May support non-invasive lung cancer screening; leaves open prospective validation before clinical adoption.
Case-Control (n=134)
Does a time-domain heart rate variability feature-based automated system improve the prediction and staging of lung cancer compared to healthy controls?
p-value: p=<0.05
HRV analysis using machine learning models (ANN and SVM) provides high accuracy for the noninvasive prediction and staging of lung cancer.
Shukla et al. (2018) conducted a case-control in Lung cancer (n=134). Time-domain heart rate variability (HRV) analysis vs. Control volunteers was evaluated on Automated cancer prediction accuracy (p=<0.05). Time-domain heart rate variability analysis using artificial neural networks and support vector machines achieved 89.64% and 100% accuracy, respectively, in automated lung cancer prediction.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: