Table 6 Studies exploring model-based TCD methods

Data-based models

 Schmidt system ID model [154]

Schmidt [154]

TBI, 11

–

2

Schmidt [155]

TBI, 17

–

2

Schmidt [156]

Hydrocephalus, 21

–

3

Budohoski [157]

TBI, 292

–

2

Cardim [147]

TBI, 40

2

2

Cardim [148]

Hydrocephalus, 53

–

1

Schmidt [158]

TBI, 137

–

3

Schmidt [159]

Varied cerebral diseases, 41

–

2

 SCA Schmidt model [160]

Schmidt [160]

TBI, 135; hemorrhagic stroke, 10

–

2

 Schmidt fuzzy pattern model [161]

Schmidt [161]

TBI, 103

3

2

 Calibrated Schmidt model [162]

Schmidt [162]

Brain lesions, 13

–

2

Schmidt [159]

Varied cerebral diseases, 41

–

2

 Nonlinear Schmidt model [163]

Xu [163]

TBI, 14; hydrocephalus, 9

–

2

 Data mining [164]

Hu [164]

TBI, 9

–

2

Kim [165]

TBI, 57

–

2

 Ensemble sparse classifiers [166]

Kim [166]

TBI, 80

2

–

 Semisupervised learning model [167]

Kim [167]

TBI/SAH/NPH, 90

4

–

 Linear discriminant analysis [168]

Aggarwal [168]

ALF, 16

2

–

 SVM [169]

Chacon [169]

TBI, 8

–

4

 Random forest [170]

Wadehn [170]

TBI, 36

3

–

Theory-based models

 Kashif model [171]

Kashif [171]

TBI, 37

3

3

Park [125]

TBI, 11

2

3

 Pressure corrected Kashif model [172]

Noraky [172]

SAH, 5

–

3

 DC Kashif model [125]

Park [125]

TBI, 11

3

3

Hybrid models

 Hybrid model

Wang [173]

SAH/TBI, 2

–

4