Clinical applications of artificial intelligence in autosomal dominant polycystic kidney disease

Clinical Snapshot

Key Findings

• P Value: Not reported at review level

• Effect Size: Not reported — no quantitative pooled effect sizes provided; individual study performance metrics cited narratively without aggregation

• Primary Outcome: Qualitative synthesis of AI applications in ADPKD across four domains: (1) imaging-based TKV measurement, (2) prediction of kidney function decline, (3) genetic variant identification and genotype-phenotype characterisation, and (4) clinical trial optimisation

• Nnt Or Sensitivity: Not reported — no pooled sensitivity, specificity, AUC, NNT, or hazard ratios synthesised across studies; individual AI model performance metrics referenced qualitatively without meta-analytic aggregation

• Confidence Interval: Not reported — no confidence intervals for pooled estimates; narrative review design precludes formal precision estimation

Clinical Application

AI-powered TKV measurement tools (e.g., automated segmentation software) are increasingly available in tertiary nephrology centres but require validated imaging protocols, specialist infrastructure, and radiological expertise. Machine learning-based risk prediction models remain largely research-grade without widespread clinical deployment. Regulatory clearance, interoperability with existing electronic health record systems, and clinician training represent significant implementation barriers. Cost-effectiveness data are absent from this review. In Australia, ADPKD affects approximately 1 in 400–1,000 individuals and is a leading cause of kidney failure requiring renal replacement therapy. Tolvaptan (Jynarque) is TGA-approved and PBS-listed (since 2020) for rapidly progressive ADPKD, with eligibility determined partly by TKV trajectory — making accurate AI-assisted TKV measurement directly clinically relevant. The RACGP and KHA-CARI guidelines support TKV-based risk stratification. However, no AI tools for ADPKD management are currently TGA-registered as medical devices in Australia. Australian nephrology centres with MRI capacity (predominantly metropolitan tertiary hospitals) would be best positioned to pilot AI-assisted TKV monitoring. Equity of access for rural and Indigenous Australians with ADPKD remains a significant concern not addressed by this review. Adults with confirmed or suspected ADPKD undergoing imaging surveillance, genetic testing, or risk stratification for disease progression and kidney replacement therapy planning. Most relevant to patients in Mayo Imaging Classification risk categories B–E where TKV-based prognostication guides tolvaptan eligibility.

Abstract

Autosomal dominant polycystic kidney disease (ADPKD) is the most common genetic kidney disorder leading to kidney failure. Recent advancements in artificial intelligence (AI) are transforming the diagnosis, risk stratification, management and prognostication in ADPKD by enabling more accurate assessments and individualized care. AI-powered imaging tools enhance the measurement of total kidney volume (TKV), improving the precision and efficiency of monitoring disease progression and more reliable assessment of therapeutic response. Machine learning algorithms can integrate genetic, imaging and clinical data to predict kidney function decline, facilitating personalized treatment strategies. In addition, AI is being used to identify genetic variants and to refine genotype-phenotype relationships, offering deeper insights into disease variability. AI-enabled monitoring technologies can support longitudinal tracking of TKV measurements obtained through magnetic resonance imaging or computed tomography, thereby improving clinical decision-making and management. Furthermore, AI can optimize clinical trial design by improving patient selection, prediction of treatment responses and safety monitoring. Despite these promising developments, integrating AI into the clinical practice remains controversial and may pose several challenges. This review highlights the emerging clinical applications of AI in ADPKD, emphasizing its potential to advance precision medicine and improve patient outcomes.

References

1. 1.Ebrahimi, N., Cheungpasitporn, W., Chebib, F. T., Borghol, A. H., Ghozloujeh, Z. G., Norouzi, S., & Abdipour, A. (2026). Clinical applications of artificial intelligence in autosomal dominant polycystic kidney disease. Nephrology, Dialysis, Transplantation: Official Publication of the European Dialysis and Transplant Association – European Renal Association. https://doi.org/10.1093/ndt/gfag010