Impact of Commercial Artificial Intelligence on Radiologist Reading Time for Pulmonary Nodule Evaluation at Chest CT.

Jasika Paramasamy; Arlette E Odink; Ties A Mulders; Daniel Bos; Aad van der Lugt; Joachim G J V Aerts; Jacob J Visser

doi:10.1148/radiol.260484

Home/Archive/PubMed

PubMed · 42678259

Impact of Commercial Artificial Intelligence on Radiologist Reading Time for Pulmonary Nodule Evaluation at Chest CT.

Jasika Paramasamy·Arlette E Odink·Ties A Mulders·Daniel Bos·Aad van der Lugt·Joachim G J V Aerts·Jacob J Visser

View original source ↗Export metadata ↓

Abstract

Background Chest CT is a primary method for identifying pulmonary nodules, yet interpreting scans remains time-intensive and demanding. Currently, artificial intelligence (AI) is expected to reduce reading times, but the effect of AI on reporting times in this setting is unknown. Purpose To evaluate the impact of a commercial AI software on radiologists' reading time for pulmonary nodule assessment on chest CT scans within a real-world clinical setting. Materials and Methods This retrospective study included patients who underwent chest CT examinations at a tertiary medical center between September 2021 and May 2024. The study period was divided into pre- and post-AI phases. The primary outcome was radiology reporting time. The association between AI implementation and reporting time was evaluated using a multivariable parametric Weibull shared frailty survival model adjusted for reader function, examination type, patient location, and requesting specialty, with clustering at the radiologist level. Interaction analyses assessed heterogeneity across prespecified subgroups. An exploratory extrapolation estimated projected workforce and financial impact. Results This study included 19 433 patients (mean age, 62 years ± 14.2 [SD]; 21 814 men; 39 323 chest CT examinations, 19 190 pre-AI, and 20 133 post-AI). AI implementation was associated with faster report completion (adjusted hazard ratio, 1.17; 95% CI: 1.14, 1.21; P < .001). The adjusted median reporting time decreased from 21.3 minutes pre-AI to 18.2 minutes post-AI (14.6% reduction; P < .001). Heterogeneity was observed across reader function (P < .001), examination type (P = .048), and requesting specialty (P = .03). The largest relative reductions were observed for CT thorax electrocardiogram-gated examinations (-41.1%; P < .001) and thoracic radiologists (-25.0%; P < .001), whereas emergency department examinations showed increased median reporting time (7.1%; P < .001). At institutional scan volumes (approximately 20 000-22 000 chest CT examinations annually), exploratory modeling suggested an approximate reduction of 0.5 full-time equivalent radiologist workload. Conclusion Implementation of commercial AI-assisted pulmonary nodule assessment on chest CT scans reduced radiologist reporting time in a real-world clinical setting. © The Author(s) 2026. Published by the Radiological Society of North America under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Iwasawa in this issue.

Explore related subjects

Humans Tomography, X-Ray Computed Retrospective Studies Male Artificial Intelligence Female Middle Aged Solitary Pulmonary Nodule Time Factors Radiography, Thoracic Lung Neoplasms Radiologists Aged Multiple Pulmonary Nodules Journal Article

Keep this discovery

BibTeX RIS

Jasika Paramasamy, Arlette E Odink, Ties A Mulders, Daniel Bos, Aad van der Lugt, Joachim G J V Aerts, Jacob J Visser. 2026. Impact of Commercial Artificial Intelligence on Radiologist Reading Time for Pulmonary Nodule Evaluation at Chest CT.. https://doi.org/10.1148/radiol.260484

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

Journal Article resource Aged subject Artificial Intelligence subject Female subject Humans subject Journal Article subject Lung Neoplasms subject Male subject Middle Aged subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related citations

PubMed2026

Novel non-contrast computed tomography parameters for predicting spontaneous stone passage and surgical requirement in ureteral stones: The role of ureteral wall thickness and dilatation ratio.

We investigated the predictive value of standard non-contrast computed tomography (NCCT) measurements, the ureteral dilatation ratio (DDR) and intraluminal urine stasis markers, for spontaneous stone passage (SSP) versus surgical intervention in patients with ureteral stones. We also evaluated ureteral wall thickness (UWT) as a practical clinical marker. This retrospective study included 461 patients diagnosed with ureteral stones via NCCT. Patients were categorised into two groups based on clinical outcomes: the spontaneous passage group (MET; n = 229) and the endoscopic surgery group (URS; n = 232). Stone volume, stone density (HU), UWT, DDR and intraluminal urine attenuation values were measured for all patients. Independent risk factors were identified using a multivariate logistic regression model and clinical cut-off values were determined via ROC curve analysis. Stone volume, density, UWT and hydronephrosis grade were all significantly higher in the URS group. Multivariate regression analysis revealed that increased UWT (OR: 5.03, 95% CI: 3.66-6.90; p < 0.001) was the strongest independent predictor of surgery. Higher DDR (OR: 1.88; p = 0.003), advanced hydronephrosis, stone volume, and density also increased surgical risk. A UWT cut-off ≥ 2.97 mm predicted surgery with 84.8% sensitivity and 84.3% specificity (AUC: 0.872). A DDR cut-off > 1.79 yielded 81.7% specificity and 40.4% sensitivity. UWT weakly correlated with stone volume (r = 0.145), indicating wall thickening reflects an inflammatory response rather than a mere mechanical consequence. UWT is a superior predictor of SSP failure, supported by increased DDR as a highly specific complementary risk factor. These parameters could help clinicians to identify patients who would benefit from early surgical counselling and intervention rather than prolonged conservative management.

Humans↗

PubMed2026

Physiologic age modifies the association between visceral fat predominance and urinary calcium excretion in adults with nephrolithiasis.

Although adiposity is associated with kidney stone disease, the relationship between abdominal fat distribution and urinary calcium excretion remains unclear. We investigated whether the CT-derived visceral-to-subcutaneous fat ratio (VSR) was associated with 24-hour urinary calcium excretion and whether physiologic age modified this association. This retrospective cross-sectional study included 308 adults with nephrolithiasis who underwent preoperative CT, stone removal, and postoperative metabolic evaluation. Participants were stratified into prespecified younger (men aged < 50 years and premenopausal women) and older (men aged ≥ 50 years and postmenopausal women) physiologic-age groups. Multivariable linear regression assessed the association between VSR and urinary calcium excretion and its modification by physiologic age. Results showed that VSR was not associated with urinary calcium excretion in the overall cohort, but its association differed significantly by physiologic age (P for interaction < 0.001). Among younger participants, each 1-unit higher VSR was associated with 2.07 mmol/day greater urinary calcium excretion (95% CI, 1.23-2.90), whereas no significant association was observed in the older group. These findings suggest that the metabolic relevance of visceral fat predominance differs by physiologic age, with a significant association observed only in younger adults. Prospective studies are needed to confirm these findings and determine their clinical implications.

Humans↗

PubMed2026

CT-Derived pelvic morphometry for preoperative risk assessment of recurrent unilateral inguinal hernia.

BACKGROUND: Recurrent inguinal hernia remains a significant challenge in abdominal wall surgery despite advances in mesh-based repair techniques and minimally invasive approaches. Although pelvic skeletal morphology has been implicated in inguinal hernia development, its association with recurrent disease remains incompletely understood. This study aimed to evaluate computed tomography (CT)-derived pelvic morphometric parameters and investigate their potential value in preoperative recurrence risk assessment. METHODS: This retrospective study included 251 male patients with preoperative abdominal CT examinations and complete clinical records who underwent elective inguinal hernia repair at a tertiary referral center. After applying the predefined eligibility criteria, 188 patients with unilateral inguinal hernias constituted the primary study cohort, including 162 primary and 26 recurrent unilateral hernias. The Radoievitch angle and Ami's line were measured independently by two blinded radiology residents using a standardized CT-based pelvic morphometric measurement protocol, and the mean values were used for analysis. Multivariable logistic regression and receiver operating characteristic (ROC) curve analyses were performed to evaluate the association between pelvic morphometric parameters and recurrent inguinal hernia. RESULTS: Patients with recurrent unilateral inguinal hernias demonstrated significantly greater affected-side Ami's line measurements (8.27 ± 0.63 vs. 7.90 ± 0.71 cm, p = 0.014) and larger Radoievitch angles (40.68 ± 4.02° vs. 38.80 ± 3.68°, p = 0.018) than patients with primary unilateral hernias. Both the Radoievitch angle (OR 1.14, 95% CI 1.01-1.28, p = 0.033) and Ami's line (OR 2.26, 95% CI 1.14-4.49, p = 0.020) remained independently associated with recurrent inguinal hernia after adjustment for age and body mass index. ROC analysis demonstrated modest discriminatory performance (AUC 0.634 for the Radoievitch angle and 0.633 for Ami's line), while the multivariable model incorporating age, body mass index, and Ami's line showed slightly improved discrimination (AUC 0.655). CONCLUSION: CT-derived pelvic morphometric parameters were independently associated with recurrent unilateral inguinal hernia. Although their individual discriminatory performance was modest, standardized CT-based pelvimetry may serve as an objective adjunctive tool for individualized preoperative recurrence risk assessment in patients who already undergo CT imaging for unrelated clinical indications. Prospective multicenter studies are warranted to validate these findings and determine their clinical applicability.

Humans↗