Skip to main content

Table 4 Performance of the general classifier (that is, trained on patients with all etiologies) and of the specific classifiers (independently trained on subgroups of specific etiology) for predicting outcome in subgroup of different etiologies using EEG features. AUC and 95% confidence intervals

From: Standardized visual EEG features predict outcome in patients with acute consciousness impairment of various etiologies

 

Stroke

TBI/NS

TBI

MIII

HIE

No etiology

Predicting survival

General classifier

.695

.955

.944

.697

.958

.737

[.433 .878]

[.734 1.000]

[.628 1.000]

[.423 .894]

[.827 .996]

[.442 .936]

Specific classifiers

.666

.694

.800

.452

.833

.646

[.534 .769]

[.469 .851]

[.571 .907]

[.290 .628]

[.741 .902]

[.488 .775]

Predicting

Favorable outcome

      

 General classifier

.706

.819

.866

.742

.921

.678

[.474 .880]

[.472 .972]

[.500 1.000]

[.475 .909]

[.762 .979]

[.404 .876]

 Specific classifiers

.662

.651

.723

.396

.865

.652

[.510 .776]

[.480 .803]

[.547 .851]

[.240 .568]

[.781 .923]

[.512 .765]

  1. HIE hypoxic–ischemic encephalopathy, MIII metabolic, intoxication, infection, inflammation, TBI traumatic brain injury, TBI/NS traumatic brain injury combined with other non-vascular non-traumatic neurosurgical diagnoses