Public articles linked to the same research event.
Acta radiologica (Stockholm, Sweden : 1987) This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.
This retrospective study analyzed 4027 consecutive non-contrast head CT examinations from a large emergency hospital in southwest Sweden to compare three commercial AI algorithms for ICH detection, finding substantial variation with only Aidoc demonstrating clinically relevant accuracy (90.3% sensitivity, 99.0% specificity), while a simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity (P < 0.001), comparable to two radiologists.