OBJECTIVES: Tuberculosis (TB) incidence in Los Angeles County, California (5.3 per 100,000) is significantly higher than the US national average (2.8 per 100,000). Directly observed therapy (DOT) is the preferred strategy for active tuberculosis treatment but requires substantial resources. We partnered with the LA County Department of Public Health (LACDPH) to evaluate the cost-effectiveness of AiCure, a novel artificial intelligence (AI) treatment platform that allows for automated treatment monitoring, which may reduce treatment costs.

METHODS: We used a Markov model to compare DOT versus AiCure for active TB treatment in LA County. Individuals in the model transitioned between health states at rates estimated using data from a pilot study for AiCure (N=43) and comparable historical controls for DOT (N=71). Costs by treatment arm including personnel, technology, and licensing fees were provided by the LACDPH. We estimated total costs (2017, USD) and quality-adjusted life years (QALYs) by treatment arm over a 16-month horizon, the longest treatment length observed in the data, to calculate the incremental cost-effectiveness ratio (ICER) and net monetary benefits (NMB) of AiCure. To assess robustness of base results, we conducted deterministic (DSA) and probabilistic sensitivity analyses (PSA).

RESULTS: For the average patient, DOT treatment cost $4,894 and generated 1.03 QALYs over 16-months. AiCure treatment cost $3,377 for 1.05 QALYs, indicating that it would be a dominant strategy over DOT. At willingness-to-pay threshold of $150K/QALY, incremental NMB per-patient under AiCure versus DOT was $4,264. In univariate DSA, NMB were most sensitive to vocational nurse wage; however, AiCure remained dominant in all scenarios. In PSA, AiCure was dominant in 86.3% of 10,000 simulations (cost-effective in 96.5%).

CONCLUSIONS: AiCure for treatment of active TB is likely to be cost-effective relative to DOT for patients in LA County. Increased use of the novel AI platform could facilitate LACDPH’s vision of TB elimination.