Lieske, John C.

Introduction and Objective: Kidney stone growth and new stone formation are common clinical trial endpoints and are associated with future symptomatic events. To date, a manual review of CT scans has been required to assess stone growth and new stone formation, which is laborious. We validated the performance of a software algorithm that automatically identified, registered, and measured stones over longitudinal CT studies. Methods: We validated the performance of a pretrained machine learning algorithm to classify stone outcomes on longitudinal CT scan images at baseline and at the end of the 2-year follow-up period for 62 participants aged >18 years in the Prevention of Urinary Stones with Hydration (PUSH) randomized controlled trial. Stones were defined as an area of voxels with a minimum linear dimension of 2 mm that was higher in density than the mean plus 4 standard deviations of all nonnegative HU values within the kidney. The four outcomes assessed were: (1) growth of at least one existing stone by ≥2 mm, (2) formation of at least one new ≥2 mm stone, (3) no stone growth or new stone formation, and (4) loss of at least one stone. The accuracy of the algorithm was determined by comparing its outcomes to the gold standard of independent review of the CT images by at least two expert clinicians. Results: The algorithm correctly classified outcomes for 61 paired scans (98.4%). One pair that the algorithm incorrectly classified as stone growth was a new renal artery calcification on end-of-study CT. Conclusions: An automated image analysis method validated for the prospective PUSH trial was highly accurate for determining clinical outcomes of new stone formation, stone growth, stable stone size, and stone loss on longitudinal CT images. This method has the potential to improve the accuracy and efficiency of clinical care and endpoint determination for future clinical trials.

ABSTRACT Human alanine:glyoxylate aminotransferase (AGT) is a liver peroxisomal enzyme that metabolizes glyoxylate, the oxalate precursor, to glycine. AGT deficiency, due to recessive pathogenic changes in the AGXT gene, results in calcium oxalate accumulation and kidney stones, a condition known as primary hyperoxaluria type 1 (PH1). Most missense variants lead to PH1 by causing AGT misfolding, but their effects manifest differently based on the presence of two polymorphic variants, p.Pro11Leu (p.P11L) and p.Ile340Met (p.I340M), which are usually present in linkage disequilibrium and generate the minor haplotype. While the p.P11L substitution reduces AGT global stability and worsens the effects of pathogenic changes, the p.I340M exerts a stabilizing effect whose role on PH1 pathogenesis has never been elucidated. The p.Ile279Thr (p.I279T) variant is frequent in healthy populations (0.29%), mainly on the major allele, but we present data from six PH1 families (eight patients) suggesting p.I279T as a PH1 pathogenic allele. Interestingly, in these families, p.Thr279 is always associated with p.Leu11 and p.Ile340, thus with a split AGXT haplotype. Analysis of the effects of the p.I279T mutation by in silico predictions, biochemical analyses on purified proteins, and expression in two cellular models of disease ( AGXT1 ‐KO HepG2 and CHO cells) shows that it causes a folding defect that is exacerbated by p.P11L but mitigated by p.I340M, thus explaining why p.Thr279 is pathogenic just on the p.Leu11–p.Ile340 haplotype. These data indicate that genetic screenings for PH1 should document the AGXT haplotype, including its components, to obtain an accurate diagnosis and possible prognostic information.