Cited 0 times in

Impact of a deep learning-based brain CT interpretation algorithm on clinical decision-making for intracranial hemorrhage in the emergency department

Authors
 So Yeon Choi  ;  Ji Hoon Kim  ;  Hyun Soo Chung  ;  Sona Lim  ;  Eun Hwa Kim  ;  Arom Choi 
Citation
 SCIENTIFIC REPORTS, Vol.14(1) : 22292, 2024-09 
Journal Title
SCIENTIFIC REPORTS
Issue Date
2024-09
MeSH
Adult ; Algorithms* ; Brain / diagnostic imaging ; Clinical Decision-Making* ; Deep Learning* ; Emergency Service, Hospital* ; Female ; Humans ; Intracranial Hemorrhages* / diagnostic imaging ; Male ; ROC Curve ; Sensitivity and Specificity ; Tomography, X-Ray Computed* / methods
Keywords
Brain computed Tomography ; Deep learning-based assistive algorithm ; Emergency Medical professionals ; Intracranial hemorrhage
Abstract
Intracranial hemorrhage is a critical emergency that requires prompt and accurate diagnosis in the emergency department (ED). Deep learning technology can assist in interpreting non-enhanced brain CT scans, but its real-world impact on clinical decision-making is uncertain. This study assessed a deep learning-based intracranial hemorrhage detection algorithm (DLHD) in a simulated clinical environment with ten emergency medical professionals from a tertiary hospital’s ED. The participants reviewed CT scans with clinical information in two steps: without and with DLHD. Diagnostic performance was measured, including sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve. Consistency in clinical decision-making was evaluated using the kappa statistic. The results demonstrated that DLHD minimally affected experienced participants’ diagnostic performance and decision-making. In contrast, inexperienced participants exhibited significantly increased sensitivity (59.33–72.67%, p < 0.001) and decreased specificity (65.49–53.73%, p < 0.001) with the algorithm. Clinical decision-making consistency was moderate among inexperienced professionals (k = 0.425) and higher among experienced ones (k = 0.738). Inexperienced participants changed their decisions more frequently, mainly due to the algorithm’s false positives. The study highlights the need for thorough evaluation and careful integration of deep learning tools into clinical workflows, especially for less experienced professionals.
DOI
10.1038/s41598-024-73589-0
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Emergency Medicine (응급의학교실) > 1. Journal Papers
Yonsei Authors
Kim, Ji Hoon(김지훈) ORCID logo https://orcid.org/0000-0002-0070-9568
Chung, Hyun Soo(정현수) ORCID logo https://orcid.org/0000-0001-6110-1495
Choi, Arom(최아롬)
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/200815
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links