Objetivo: To evaluate the diagnostic efficacy of artificial intelligence (AI) software in detecting incidental pulmonary embolism (IPE) at CT and shorten the time to diagnosis with use of radiologist reading worklist prioritization.
Conclusión: El papel de la resonancia magnética hoy en día ya no está limitado a excluir causas subyacentes de deterioro cognitivo, sino que puede mostrar patrones de atrofia y otros datos con un alto valor predictivo para determinadas demencias que, aunque no son específicos ni únicos de cada patología, pueden ayudar a confirmar una sospecha diagnóstica o a identificar inicios tempranos de determinados procesos. Por ello es importante que los radiólogos conozcan los hallazgos típicos de las demencias más frecuentes.

Palabras clave: Resonancia magnética; Atrofia; Demencia; Enfermedad de Alzheimer; Parálisis supranuclear progresiva; Demencia vascular; Atrofia multisistémica; Enfermedad de Parkinson; Demencia frontotemporal

Purpose:
To evaluate the diagnostic efficacy of artificial intelligence (AI) software in detecting incidental pulmonary embolism (IPE) at CT and shorten the time to diagnosis with use of radiologist reading worklist prioritization.

Materials and Methods:
In this study with historical controls and prospective evaluation, regulatory-cleared AI software was evaluated to prioritize IPE on routine chest CT scans with intravenous contrast agent in adult oncology patients. Diagnostic accuracy metrics were calculated, and temporal end points, including detection and notification times (DNTs), were assessed during three time periods (April 2019 to September 2020): routine workflow without AI, human triage without AI, and worklist prioritization with AI.

Results:
In total, 11736 CT scans in 6447 oncology patients (mean age, 63 years ± 12 [SD]; 3367 men) were included. Prevalence of IPE was 1.3% (51 of 3837 scans), 1.4% (54 of 3920 scans), and 1.0% (38 of 3979 scans) for the respective time periods. The AI software detected 131 true-positive, 12 false-negative, 31 false-positive, and 11559 true-negative results, achieving 91.6% sensitivity, 99.7% specificity, 99.9% negative predictive value, and 80.9% positive predictive value. During prospective evaluation, AI-based worklist prioritization reduced the median DNT for IPE-positive examinations to 87 minutes (vs routine workflow of 7714 minutes and human triage of 4973 minutes). Radiologists’ missed rate of IPE was significantly reduced from 44.8% (47 of 105 scans) without AI to 2.6% (one of 38 scans) when assisted by the AI tool (P < .001).

Conclusion:
AI-assisted workflow prioritization of IPE on routine CT scans in oncology patients showed high diagnostic accuracy and significantly shortened the time to diagnosis in a setting with a backlog of examinations.