Evidence for commercial AI in lung nodule CT: a systematic review of shifting research focus

Systematic review of 95 studies on commercial AI for pulmonary nodule CT assessment shows research shift from technical efficacy to diagnostic thinking and therapeutic efficacy, but patient outcomes and cost-effectiveness remain poorly studied; all studies had high risk of bias…

• The number of published studies rose from 14 in 2012–2017 to 95 by 2024.
• Early studies focused on quantification (46.7%) and lower efficacy levels (Levels 1–2: 83.3%); by 2024, malignancy prediction (28.6%) and higher levels (3–5) accounted for over a third of studies.
• All included studies had high risk of bias in at least one domain, and nearly two-thirds involved vendor funding or co-authorship.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.