From: A weakly supervised deep learning model integrating noncontrasted computed tomography images and clinical factors facilitates haemorrhagic transformation prediction after intravenous thrombolysis in acute ischaemic stroke patients
Accuracy
Accuracy 95% CI
F1
F1 95% CI
Without ICH
0.686
(0.655,0.721)
0.814
(0.791,0.838)
Asymptomatic ICH
0.619
(0.508,0.73)
0.765
(0.674,0.844)
SICH
0.833
(0.5,1)
0.909
(0.667,1)