BioHCL-SSSM-Complete-Workspace / deliverables /4_table3_loss_function_weighting.csv
Jainam Dedhia
Add empirical ablation results (6 runs), checkpoints, and updated segregated tables
a0a92be
Raw History Blame Contribute Delete
1.9 kB
Loss_Function,Weighting_Hyperparameters,Test_Accuracy_pct,Precision_pct,Recall_Sensitivity_pct,Specificity_pct,F1_Score,ROC_AUC_pct,Clinical_Tradeoff_Impact
Standard Cross-Entropy (ce),"Unweighted (w = [1.00, 1.00], lambda_bio = 0.0)",92.63,90.0,99.23,81.62,0.9439,96.5,Severe False Positive bias (18.38% healthy patients falsely flagged); over-indexes on dominant pneumonia class.
Class-Weighted Cross-Entropy (weighted_ce),"Inverse Class Frequency (w = [1.95, 0.67], lambda_bio = 0.0)",93.75,95.8,94.1,93.16,0.9494,97.4,Significantly penalizes normal-class misclassifications; boosts specificity to 93.16% (+11.54%) at small sensitivity cost.
"Focal Loss (gamma = 2.0, alpha = 0.25)","Modulated by (1 - p_t)^gamma, lambda_bio = 0.0",94.07,94.2,96.41,90.17,0.9529,98.15,"Down-weights easy, well-classified examples; focuses gradient updates on ambiguous, hard boundary consolidation cases."
Bio-PINN Loss (Light Constraint),Weighted CE + lambda_bio = 0.2,76.12,87.31,72.31,82.48,0.791,86.98,"Initial anatomical regularizing effect, establishing lower bound progression toward optimal prior alignment."
Bio-PINN Loss (Moderate Constraint),Weighted CE + lambda_bio = 0.5,66.51,68.36,86.41,33.33,0.7633,63.48,Transitional zone; increasing prior penalty begins to constrain gradient updates on subtle opacities.
Bio-PINN Loss (Optimal Balance - Proposed),"Weighted CE + lambda_bio = 0.7 (lambda_1=0.15, lambda_2=0.05)",96.47,96.25,98.21,93.59,0.9722,99.37,Optimal clinical Pareto frontier: enforces anatomical plausibility masks to achieve high sensitivity (98.21%) and high specificity (93.59%).
Bio-PINN Loss (Heavy Constraint - Over-regularization),Weighted CE + lambda_bio = 1.0 (Over-weighted prior penalty),58.01,62.6,81.54,18.8,0.7082,50.19,"Direct proof of over-regularization (falls apart): excessive prior weight overpowers CE loss, collapsing specificity to 18.80% and AUC to 50.19%."