Table 5 Evaluation of machine learning algorithms using k-fold cross-validation.

From: Enhancing breast cancer diagnosis through machine learning algorithms

Algorithms

k-fold

Accuracy

Precision

Recall

SVM

2

0.5112

0.5072

0.7812

3

0.4732

0.4722

0.4554

4

0.4598

0.4554

0.4107

5

0.5200

0.5143

0.7232

6

0.4978

0.4981

0.5759

7

0.4933

0.4939

0.5402

8

0.5335

0.5248

0.7098

9

0.5066

0.5053

0.6384

10

0.5288

0.5219

0.6920

Random forest

2

0.8549

0.8700

0.8661

3

0.8773

0.8673

0.8750

4

0.8772

0.8813

0.8616

5

0.8862

0.8813

0.8616

6

0.8795

0.8802

0.8527

7

0.8772

0.8739

0.8661

8

0.8683

0.8843

0.8527

9

0.8640

0.8767

0.8571

10

0.8795

0.8733

0.8616

Decision tree

2

0.8594

0.8826

0.8393

3

0.8505

0.8624

0.8393

4

0.8616

0.8744

0.8393

5

0.8572

0.8692

0.8304

6

0.8572

0.8664

0.8393

7

0.8772

0.8761

0.8527

8

0.8772

0.8826

0.8393

9

0.8618

0.8721

0.8527

10

0.8639

0.8710

0.8438

Logistic Regression

2

0.6138

0.6232

0.5759

3

0.6318

0.6398

0.6027

4

0.6384

0.6462

0.6116

5

0.6384

0.6462

0.6116

6

0.6385

0.6476

0.6071

7

0.6339

0.6402

0.6116

8

0.6339

0.6429

0.6027

9

0.6407

0.6507

0.6071

10

0.6386

0.6476

0.6071

KNN

2

0.7344

0.8070

0.6161

3

0.7388

0.7956

0.6429

4

0.7433

0.7914

0.6607

5

0.7477

0.8101

0.6473

6

0.7545

0.8167

0.6562

7

0.7567

0.8108

0.6696

8

0.7612

0.8128

0.6786

9

0.7520

0.8020

0.6696

10

0.7698

0.8135

0.7009

ANN

2

0.6228

0.6316

0.5893

3

0.7256

0.7919

0.6116

4

0.7433

0.7978

0.6518

5

0.7223

0.7653

0.6696

6

0.7213

0.7765

0.6205

7

0.7279

0.7725

0.6518

8

0.7277

0.7713

0.6473

9

0.7368

0.7880

0.6473

10

0.5783

0.5686

0.6473

Back to article page