A Machine Learning-Driven Virtual Biopsy System For Kidney Transplant Patients.

In kidney transplantation, day-zero biopsies are used to assess organ quality and discriminate between donor-inherited lesions and those acquired post-transplantation. However, many centers do not perform such biopsies since they are invasive, costly and may delay the transplant procedure. We aim to generate a non-invasive virtual biopsy system using routinely collected donor parameters. Using 14,032 day-zero kidney biopsies from 17 international centers, we develop a virtual biopsy system. 11 basic donor parameters are used to predict four Banff kidney lesions: arteriosclerosis, arteriolar hyalinosis, interstitial fibrosis and tubular atrophy, and the percentage of renal sclerotic glomeruli. Six machine learning models are aggregated into an ensemble model. The virtual biopsy system shows good performance in the internal and external validation sets. We confirm the generalizability of the system in various scenarios. This system could assist physicians in assessing organ quality, optimizing allograft allocation together with discriminating between donor derived and acquired lesions post-transplantation.

Primary Sjögren's syndrome in South Australia.

OBJECTIVES: To describe clinical and serological characteristics of a South Australian primary Sjögren's syndrome (pSS) cohort. METHODS: The South Australian Sjögren's Syndrome Research Clinic and Database is a clinical cohort of patients with pSS at a single site. Baseline clinical and laboratory data from 172 patients were retrospectively examined to determine their prevalence and clinical associations. Results were compared to findings from 10,500 patients from The Big Data Sjogren Project Consortium; an international, multicentre registry established in 2014, which included the South Australian data. RESULTS: Of 172 South Australian patients with pSS, 90.1% were female with a mean age at diagnosis of 57 years. Ocular and oral sicca symptoms were common, affecting 97.1% and 99.4% respectively. Anti-Ro ± La positivity was detected in 82.6%, ANA positivity in 77%, and in 9% of patients both ANA and ENA were negative. Mean ESSDAI was 6.8 at baseline, slightly higher than the international cohort at 6.1; the most commonly positive domains being biological, articular and glandular. Pulmonary manifestations represented the most significant morbidity over time. Lymphoma was recorded in 5.2% of patients and congenital heart block in 4 offspring of 52 patients with longitudinal follow-up (7.7%), although incomplete data likely resulted in underestimation of both. CONCLUSIONS: Despite the relatively small sample size of the South Australian cohort, clinical and serological characteristics correspond closely with international descriptions.