A Quality-Control and Multimodal Clinical Intelligence (QC-MCI) Framework for Improving Reliability and Clinical Integration in AI-Enabled Radiology Workflows

Oyindamola Adebayo

doi:10.36948/ijfmr.2023.v05i02.89794

A Quality-Control and Multimodal Clinical Intelligence (QC-MCI) Framework for Improving Reliability and Clinical Integration in AI-Enabled Radiology Workflows

Author(s)	Oyindamola Adebayo
Country	United States
Abstract	Artificial intelligence (AI) is moving from image classification experiments into radiology worklists, reporting systems and clinical decision support. The central implementation problem is no longer whether an algorithm can produce a strong score on a retrospective test set. It is whether the combined system—data, software, radiologist, workflow and governance—continues to produce safe and useful decisions when it encounters routine clinical variation. This article proposes a Quality-Control and Multimodal Clinical Intelligence (QC-MCI) framework for that problem. The framework treats reliability as a property of the complete clinical pathway rather than of the model alone. It combines five linked functions: input quality control; multimodal clinical context integration; model and subgroup validation; human–AI interaction control; and continuous post-deployment monitoring with escalation. The framework is grounded in pre-April 2023 evidence and guidance, including radiology workflow studies, external-validation research, studies of hidden stratification and underdiagnosis bias, and the CLAIM, CONSORT-AI, SPIRIT-AI and DECIDE-AI reporting standards. Practical radiology studies have shown that AI assistance can reduce reading time or improve reader performance in defined settings, but they also show why local validation, clear operating procedures and monitoring are necessary. QC-MCI therefore recommends a staged pathway: verify the input, interpret image and clinical context together, test performance across relevant subgroups and sites, expose AI output at a controlled point in the reader’s workflow, record disagreement and overrides, and pause or recalibrate the system when safety signals emerge. The framework is a proposal for implementation and evaluation, not evidence that a particular AI product improves patient outcomes. Its value lies in making the quality-control and clinical-integration tasks explicit, measurable and assignable.
Keywords	Radiology; artificial intelligence; multimodal clinical intelligence; quality control; clinical workflow; external validation; human–AI interaction; patient safety; dataset shift
Field	Engineering
Published In	Volume 5, Issue 2, March-April 2023
Published On	2023-03-03
DOI	https://doi.org/10.36948/ijfmr.2023.v05i02.89794

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Quality-Control and Multimodal Clinical Intelligence (QC-MCI) Framework for Improving Reliability and Clinical Integration in AI-Enabled Radiology Workflows

Share this