Clinical Impact of Radiologist's Alert System on Patient Care for High-risk Incidental CT Findings: A Machine...

Area of Science:

• Radiology
• Medical Informatics
• Oncology

Background:

• Efficient communication between radiologists and clinicians is vital for managing incidental computed tomography findings (ICTFs).
• High-risk ICTFs require prompt clinical attention and follow-up to ensure appropriate patient care.
• Existing systems may not adequately address the communication gap for critical incidental findings.

Purpose of the Study:

• To introduce and evaluate a Radiologist's Alert and Patient Care Follow-up System (APCFS) for high-risk ICTFs.
• To analyze the characteristics and frequency of high-risk ICTFs detected by the APCFS.
• To identify factors associated with the occurrence of high-risk ICTFs.

Main Methods:

• Retrospective analysis of 52,331 computed tomography (CT) examinations from 2019-2021.
• Implementation of the APCFS to flag high-risk ICTFs and prompt clinician follow-up.
• Utilized machine learning to identify risk factors associated with high-risk ICTFs, including imaging protocols, areas, and clinical departments.

Main Results:

• Approximately 0.96% (507/52,331) of CT examinations revealed high-risk ICTFs, predominantly affecting the lung (18.0%).
• Therapeutic interventions were required in 23.1% of cases, with surgery in 52.1% of those. Neoplastic lesions, including malignancies, accounted for 66.7% of confirmed diagnoses.
• Key risk factors identified included specific imaging protocols (e.g., aortic valve implantation planning), imaging areas (e.g., whole-body imaging), and clinical departments (e.g., cardiology).

Conclusions:

• The APCFS effectively identifies high-risk ICTFs in approximately 1% of CT examinations.
• The occurrence of high-risk ICTFs is associated with specific imaging protocols, imaging areas, and clinical departments.
• This system facilitates timely management of critical incidental findings, potentially improving patient outcomes.