Comparative Effectiveness and Cost-Effectiveness of an Artificial Intelligence Workflow for Small Renal Mass Diagnosis on Computed Tomography.

INTRODUCTION

Small renal masses are increasingly detected on imaging, but their accurate classification as benign, indolent, or aggressive remains challenging. Such classification can aid further diagnostic workup, improving patient outcomes and saving costs. Artificial intelligence (AI) models show promise in this area. Here, we evaluate the cost-effectiveness of 3 such models compared with standard of care (SOC).

METHODS

We developed a Markov microsimulation model to simulate clinical and economic outcomes in 10,000 patients aged 40 to 75 years with small renal masses over a 10-year horizon. We compared 4 strategies: SOC, MRI + AI, and 2 CT + AI models (with or without image embeddings). The model reported total costs, quality-adjusted life years gained, and incremental cost-effectiveness ratios, with 100 simulations per scenario.

RESULTS

CT + AI Model 1 (without embeddings) had the lowest cost ($9079.65) and highest quality-adjusted life years gained (8.8207), outperforming SOC ($10,601.23, 8.8000), MRI + AI ($10,178.30, 8.8108), and CT + AI Model 2 ($9177.93, 8.8205). CT + AI Model 2 (with embeddings) was dominant in 28% of simulations. The costs of CT + AI Model imaging could increase from $265 to $2358.58, while remaining cost-effective (incremental cost-effectiveness ratio ≤ willingness to pay) compared with the MRI + AI Model.

CONCLUSIONS

CT-based AI models are cost-effective alternatives to SOC and MRI-based AI, offering better outcomes at lower cost. Their value stems from accurate risk stratification, enabling timely intervention and reducing overtreatment. These findings support the clinical and economic utility of AI in renal mass evaluation.