Artificial intelligence support in MR imaging of incidental renal masses: an early health technology assessment

Abstract

Objective: This study analyzes the potential cost-effectiveness of integrating an artificial intelligence (AI)-assisted system into the differentiation of incidental renal lesions as benign or malignant on MR images during follow-up.

Materials and methods: For estimation of quality-adjusted life years (QALYs) and lifetime costs, a decision model was created, including the MRI strategy and MRI + AI strategy. Model input parameters were derived from recent literature. Willingness to pay (WTP) was set to $100,000/QALY. Costs of $0 for the AI were assumed in the base-case scenario. Model uncertainty and costs of the AI system were assessed using deterministic and probabilistic sensitivity analysis.

Results: Average total costs were at $8054 for the MRI strategy and $7939 for additional use of an AI-based algorithm. The model yielded a cumulative effectiveness of 8.76 QALYs for the MRI strategy and of 8.77 for the MRI + AI strategy. The economically dominant strategy was MRI + AI. Deterministic and probabilistic sensitivity analysis showed high robustness of the model with the incremental cost-effectiveness ratio (ICER), which represents the incremental cost associated with one additional QALY gained, remaining below the WTP for variation of the input parameters. If increasing costs for the algorithm, the ICER of $0/QALY was exceeded at $115, and the defined WTP was exceeded at $667 for the use of the AI.

Conclusions: This analysis, rooted in assumptions, suggests that the additional use of an AI-based algorithm may be a potentially cost-effective alternative in the differentiation of incidental renal lesions using MRI and needs to be confirmed in the future.

Clinical relevance statement: These results hint at AI's the potential impact on diagnosing renal masses. While the current study urges careful interpretation, ongoing research is essential to confirm and seamlessly integrate AI into clinical practice, ensuring its efficacy in routine diagnostics.

Key points: • This is a model-based study using data from literature where AI has been applied in the diagnostic workup of incidental renal lesions. • MRI + AI has the potential to be a cost-effective alternative in the differentiation of incidental renal lesions. • The additional use of AI can reduce costs in the diagnostic workup of incidental renal lesions.

Keywords: Artificial intelligence; Cost-effectiveness analysis; Incidental findings; Kidney; MRI.

Fig. 1

Economic model for the diagnostic options of the MRI strategy and the MRI + AI strategy. For each outcome a Markov model analysis was performed. AI, artificial intelligence; M, Markov model; MRI, magnetic resonance imaging; N, negative; P, positive

Fig. 2

The Markov model with the respective states and their potential transition

Fig. 3

Scatterplot of Effectiveness and cost of the scenario “MRI” vs the scenario “MRI + AI” for 30,000 exemplary iterations (A). Although there is quite an overlap between the two scenarios, overall the iterations of the scenario “MRI + AI” show higher effectiveness and lower costs. Cost-effectiveness acceptability curve for a Willingness-to-pay threshold ranging from $0/QALY to $200,000/QALY (B). The base case scenario at $100,000/QALY is indicated by the blue bar. Results show that in the base case scenario, a majority of the iterations for the scenario “MRI + AI” are cost-effective. MRI, magnetic resonance imaging; AI, artificial intelligence; QALY, quality-adjusted life year; WTP, willingness-to-pay

Fig. 4

Deterministic sensitivity analysis presented as a tornado diagram (MRI + AI strategy vs. MRI strategy), showing how the variation of input parameters influences the incremental cost-effectiveness ratio in the base case scenario. The expected value in the base case scenario is marked with a blue line and the willingness-to-pay of $100,000/QALY with a green line. BC, base case; Sens, sensitivity; Spec, specificity; MRI, magnetic resonance imaging; AI, artificial intelligence; ICER, incremental cost-effectiveness ratio; QALY, quality-adjusted life year; WTP, willingness-to-pay

Fig. 5

Threshold analysis showing maximum cost for the use of AI dependent on the underlying WTP threshold. AI, artificial intelligence; ICER, incremental cost-effectiveness ratio; QALY, quality-adjusted life year; WTP, willingness-to-pay