Diagnostic Accuracy and Performance Analysis of a Scanner-Integrated Artificial Intelligence Model for the Detection of Intracranial Hemorrhages in a Traumatology Emergency Department.

Intracranial hemorrhages require an immediate diagnosis to optimize patient management and outcomes, and CT is the modality of choice in the emergency setting. We aimed to evaluate the performance of the first scanner-integrated artificial intelligence algorithm to detect brain hemorrhages in a routine clinical setting. This retrospective study includes 435 consecutive non-contrast head CT scans. Automatic brain hemorrhage detection was calculated as a separate reconstruction job in all cases. The radiological report (RR) was always conducted by a radiology resident and finalized by a senior radiologist. Additionally, a team of two radiologists reviewed the datasets retrospectively, taking additional information like the clinical record, course, and final diagnosis into account. This consensus reading served as a reference. Statistics were carried out for diagnostic accuracy. Brain hemorrhage detection was executed successfully in 432/435 (99%) of patient cases. The AI algorithm and reference standard were consistent in 392 (90.7%) cases. One false-negative case was identified within the 52 positive cases. However, 39 positive detections turned out to be false positives. The diagnostic performance was calculated as a sensitivity of 98.1%, specificity of 89.7%, positive predictive value of 56.7%, and negative predictive value (NPV) of 99.7%. The execution of scanner-integrated AI detection of brain hemorrhages is feasible and robust. The diagnostic accuracy has a high specificity and a very high negative predictive value and sensitivity. However, many false-positive findings resulted in a relatively moderate positive predictive value.

Digitized and structured informed patient consent before contrast-enhanced computed tomography: feasibility and benefits in clinical routine.

BACKGROUND: To evaluate the feasibility and benefits of digitized informed patient consent (D-IPC) for contrast-enhanced CT and compare digitized documentation with paper-based, conventional patient records (C-PR). METHODS: We offered D-IPC to 2016 patients scheduled for a CT. We assessed patient history (e.g., CT examinations, malignant or cardiovascular diseases) and contraindications (red flags) for a CT (e.g., thyroid hyperfunction, allergies) using a tablet device. We evaluated the success rate of D-IPC and compared patient age between the subgroups of patients who were able or unable to complete D-IPC. We analyzed the prevalence of marked questions and red flags (RF). RF were compared with the documentation from C-PR. We estimated greenhouse gas (GHG) emissions for paperless workflow and provide a cost-benefit analysis. RESULTS: Overall, 84.4% of patients completed D-IPC. They were younger (median 61 years) than unsuccessful patients (65 years; p < 0.001). Patients who marked questions (21.7%) were older than patients without inquiries (median 63.9 vs 59.5 years; p < 0.001). The most prevalent RF was thyroid disease (23.8%). RF were considered critical for contrast-agent injection in 13.7%, requiring personalized preparation. The detection rate for RF documented with D-IPC was higher than for C-PR (n = 385 vs. 43). GHG emissions for tablet production are 80-90 times higher than for paper production. The estimated costs were slightly higher for D-IPC (+ 8.7%). CONCLUSION: D-IPC is feasible, but patient age is a relevant factor. Marked questions and RF help personalize IPC. The availability of patient history by D-IPC was superior compared to C-PR.