Abstract Rationale Primary Ciliary Dyskinesia (PCD) is a rare, genetic disorder of motile cilia function that leads to chronic sinopulmonary infections, bronchiectasis, and progressive lung damage. For many patients, delayed diagnosis leads to irreversible pulmonary decline and a premature need for lung transplantation. Early identification, particularly at birth, can enable appropriate management, reduce hospitalizations, and delay disease progression. However, the economic impact of diagnostic timing has not been quantified systematically. Our goal is to model lifetime healthcare costs and quality-of-life outcomes associated with early versus late diagnosis of PCD using an Artificial intelligence (AI) -assisted cost-effectiveness simulation. Methods We developed an AI-powered Monte Carlo simulation incorporating real-world cost estimates (USD) for four categories: hospitalizations, medications and supplies, lung transplantation, and other medical care (including specialist visits, diagnostics, airway-clearance devices, and pulmonary rehabilitation). Two scenarios were modeled: (A) diagnosis at birth with comprehensive management and no transplant; (B) diagnosis in mid-adulthood following years of poor management and subsequent lung transplantation. Base-case inputs were derived from U. S. national cost databases and the literature on rare lung diseases. Quality-adjusted life years (QALYs) were estimated using utilities for stable disease (0. 88), exacerbations (0. 70), hospitalization (0. 60), and post-transplant (0. 70). Ten thousand stochastic iterations were evaluated for mean lifetime costs, QALYs, and the probability of cost-effectiveness. Results The mean lifetime cost per patient was 330, 000 for early diagnosis (A) versus 1, 990, 000 for late diagnosis (B), yielding an incremental saving of 1. 66 million. The difference was primarily driven by avoided transplants and a reduced frequency of hospitalizations (0. 5 vs. 2 per year). Average lifetime QALYs were 34. 9 for A and 31. 4 for B (+3. 5 QALYs). In probabilistic sensitivity analysis, early diagnosis was cost-saving in 98. 5% of simulations and cost-effective (100, 000/QALY) in 100% of runs. Conclusions AI-based simulation demonstrates that early diagnosis and management of PCD can reduce lifetime healthcare expenditures by more than 1. 6 million per patient, while also improving quality of life. Incorporating predictive analytics into newborn screening programs could optimize early detection, reduce long-term expenses, and avert progression to end-stage lung disease. These findings support health-policy efforts that prioritize early diagnostic strategies and resource allocation for rare respiratory disorders. This abstract is funded by: Ponce Research Institute and Cilia4PR
Martinez et al. (Fri,) studied this question.