Interactive Tables 1 - 4

Search:

**Table 1. Baseline clinical characteristics**
	Variable	Traditional (n = 132)	Laser (n = 62)	P_value
1	BMI	24.08 (3.03)	24.06 (2.97)	0.9665
2	Diastolic BP	86.97 (11.12)	74.35 (20.54)	<0.001
3	Systolic BP	121.82 (11.37)	123.55 (7.26)	0.2126
4	Heart Rate	76.48 (5.96)	74.76 (5.57)	0.0484
5	Pulse Oximetry	96.70 (1.80)	96.66 (1.76)	0.8741
6	Blood Loss	11.59 (17.64)	0.03 (0.52)	<0.001
7	Surgical Time	28.70 (5.44)	27.06 (5.94)	0.0684
8	Age	-	-	<0.001
9	Age 18–29	79 (59.85%)	6 (9.68%)	-
10	Age 30–39	16 (12.12%)	6 (9.68%)	-
11	Age 40–49	4 (3.03%)	6 (9.68%)	-
12	Age 50–59	4 (3.03%)	13 (20.97%)	-
13	Age 60–69	9 (6.82%)	21 (33.87%)	-
14	Age 70–79	10 (7.58%)	10 (16.13%)	-
15	Age 80–89	7 (5.30%)	0 (0.00%)	-
16	Age 90–99	3 (2.27%)	0 (0.00%)	-
17	Obese	8 (6.06%)	3 (4.84%)	0.9918
18	Overweight	34 (25.76%)	19 (30.65%)	0.5894
19	Diabetes	11 (8.33%)	19 (30.65%)	<0.001
20	Bleeding, Edema, Pain, or Infection	57 (43.18%)	1 (1.61%)	<0.001

Showing 1 to 20 of 20 entries

Previous1Next

Note: Values are presented as mean (SD) for continuous variables and n (%) for categorical variables.

Search:

**Table 2. Hyperparameter tuning**
	Model	Algorithm_Type	Resampling_Method	Hyperparameter_Tuned	Tuning_Range	Final_Selected_Configuration
1	Logistic Regression	Linear Classifier	None, SMOTE, ROS	Penalty (penalty)	L2	Resampling = SMOTE; penalty = L2; C = 1.0
2				Inverse Regularization Strength (C)	0.0001, 1.0
3	Random Forest	Ensemble Classifier	None, SMOTE, ROS	Number of Estimators (n_estimators)	10, 50	Resampling = SMOTE; n_estimators = 50; max_depth = None; min_samples_split = 5
4				Maximum Depth (max_depth)	None, 10
5				Minimum Samples Split (min_samples_split)	2, 5
6	Support Vector Machines	Kernel-based Classifier	None, SMOTE, ROS	Kernel Type (kernel)	linear, rbf, poly, sigmoid	Resampling = None; kernel = rbf; C = 100; gamma = auto
7				Cost Parameter (C)	0.0001 to 100 (log scale)
8				Gamma (gamma)	0.001, 0.01, 0.05, 0.1, 0.2, 0.5, scale, auto

Showing 1 to 8 of 8 entries

Previous1Next

Search:

**Table 3. Bootstrapped performance metrics (95% confidence intervals) for predictive models of postoperative complications**
	Metric	Logistic	RF	SVM
1	Precision / PPV	0.571 (0.469–0.663)	0.706 (0.596–0.810)	0.725 (0.623–0.826)
2	Average Precision	0.809 (0.704–0.899)	0.737 (0.613–0.875)	0.832 (0.735–0.913)
3	Recall (Sensitivity)	0.897 (0.817–0.966)	0.828 (0.719–0.917)	0.862 (0.765–0.939)
4	Specificity	0.713 (0.632–0.783)	0.853 (0.786–0.910)	0.860 (0.797–0.915)
5	F1	0.698 (0.603–0.778)	0.762 (0.667–0.837)	0.787 (0.706–0.857)
6	AUC ROC	0.900 (0.849–0.943)	0.887 (0.826–0.940)	0.907 (0.855–0.950)
7	Brier Score	0.137 (0.117–0.160)	0.105 (0.077–0.136)	0.105 (0.077–0.134)

Showing 1 to 7 of 7 entries

Previous1Next

Search:

**Table 4. SVM outcome comparison**
	Metric	Traditional	Laser	Total
1	Observed Complications (n)	57	1	58
2	SVM Predicted Positive (n)	69	0	69
3	True Positive (TP)	50	0	50
4	True Negative	58	59	117
5	False Negative (FN)	7	1	8
6	False Positive (FP)	17	2	19

Showing 1 to 6 of 6 entries

Previous1Next