Back

AI Algorithm Deployment and Utilization: Strategies to Facilitate Clinical Workflow Implementation and Integration

Erdal, B. S.; Laugerette, A.; Fair, K.; Zimmermann, M.; Demirer, M.; Gupta, V.; Odonnell, T.; White, R. D.

2023-09-20 radiology and imaging
10.1101/2023.09.19.23295729 medRxiv
Show abstract

Based on past experiences of the Center for Augmented Intelligence in Imaging (CAII) [Department of Radiology, Mayo Clinic Florida], depending on the project, 10 to 20 months has typically been required to realize the successful creation (data curation and algorithm development), and utilization (integration, testing, and operationalization) of an AI algorithm [Figure 1]. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=127 SRC="FIGDIR/small/23295729v1_fig1.gif" ALT="Figure 1"> View larger version (17K): org.highwire.dtl.DTLVardef@11dba0forg.highwire.dtl.DTLVardef@a240cborg.highwire.dtl.DTLVardef@4c0b3forg.highwire.dtl.DTLVardef@767a2d_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOFigure 1:C_FLOATNO AI algorithm evolution typically requires 10 to 20 months, consisting of four consecutive phases: 1. data identification and extraction; 2. data cleansing and labeling; 3. algorithm development with training and tuning; and 4. Implementation and integration with testing and operationalization. C_FIG This manuscript delineates the related challenges and opportunities for greater efficiency in completing the clinical workflow implementation and integration of an AI algorithm. Strategies exploiting conventional data standards in facilitating the completion of such deployment and utilization goals within the operations of a busy Radiology practice are described. Methodologies and techniques employed during this initial phase of the CAII-Siemens D&A AI collaboration to address the previously mentioned challenges and opportunities are depicted with use-case examples.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.