Pesce, Francesco

Artificial intelligence (AI)–based protein structure prediction has rapidly entered nephrology, providing plausible atomic models for channels, transporters, receptors and scaffolds that previously lacked structural information. AlphaFold and RoseTTAFold now underpin mechanistic interpretations of inherited kidney diseases, including autosomal-dominant polycystic kidney disease, cystinosis and Alport syndrome, and support experimental design in cryo-electron microscopy and cryo-electron tomography. For nephrologists, this means that renal proteins no longer need to be treated as black boxes: genetic, biochemical and physiological data can now be mapped onto concrete three-dimensional scaffolds. However, the apparent precision of AI models can be misleading. Renal proteins frequently fall within underrepresented classes, including multipass membrane proteins, intrinsically disordered scaffolds, and human-specific isoforms with shallow multiple sequence alignments, where confidence scores may not accurately reflect model reliability. Current predictors typically deliver static snapshots, whereas transporters, channels and slit-diaphragm complexes function as dynamic ensembles embedded in specific lipid and macromolecular environments. Attempts to use AlphaFold directly for variant classification or to estimate changes in thermodynamic stability or function show only modest agreement with mutagenesis data, particularly for gain-of-function and dominant-negative alleles that depend on subtle conformational and interaction changes. Common pitfalls include overinterpreting oligomeric stoichiometry inferred from AlphaFold Multimer, reading too much into domain orientations with high predicted aligned error, and dismissing low-confidence regions as modelling failures rather than recognising intrinsically disordered, potentially regulatory segments. Integrative approaches combining cryo-electron tomography, crosslinking mass spectrometry and molecular dynamics can mitigate these limitations but remain labour-intensive and low-throughput. An explainable, hypothesis-driven use of AI that treats predicted structures as working scaffolds to be cross-validated against imaging, biophysics and functional assays offers the most reliable path towards a genuinely mechanistic nephrology and responsible clinical translation of AI-based structural insights.

Abstract Myelodysplastic syndromes (MDS) are clinically and biologically diverse disorders, emphasizing the need for personalized treatment approaches. The International Working Group for Prognostication of MDS (IWG_PM) recently introduced a molecular classification, referred to as the MDS taxonomy, that categorizes patients into 16 subgroups based on 21 gene mutations, 6 cytogenetic abnormalities, and loss of heterozygosity (LOH) at TP53 and TET2 loci. This study sought to validate and enhance the clinical relevance of the MDS taxonomy by analyzing a large retrospective cohort ( n = 5136) and transcriptomic data from a prospective cohort ( n = 477). The taxonomy successfully identified subgroups with distinct clinical characteristics and disease progression patterns. However, incorporating gene interactions from taxonomy subgroups did not improve the prognostic performance of the Molecular International Prognostic Scoring System (IPSS‐M). We further assessed whether the taxonomy could guide management in patients receiving disease‐modifying therapies. Except for the “ TP53 ‐complex” subgroup, taxonomy classifications were not predictive of hypomethylating agent response or transplant outcomes. Nonetheless, they correlated with overall survival, suggesting that while both IPSS‐M and the taxonomy capture disease biology, other non‐genetic factors may influence treatment response. RNA sequencing confirmed the biological distinctiveness of the taxonomy groups. Transcriptomic profiling of CD34+ bone marrow cells revealed unique, homogeneous gene expression patterns, particularly within the AML‐like, bi TET2 , SF3B1 , and TP53 ‐complex subgroups. Further integration of multi‐omics data may refine MDS classification, improving clinical decision‐making and guiding the development of targeted therapies.

Rare diseases affect over 300 million individuals worldwide yet remain underdiagnosed and poorly characterized due to fragmented data, small cohorts, and phenotypic heterogeneity. Advances in artificial intelligence (AI) are enabling integration of genomics, imaging, electronic health records, and patient-generated data to support diagnosis, phenotyping, prognosis, and therapeutic discovery. In kidney care, these capabilities are reflected in tools for genomic variant prioritization, AI-assisted histopathology, and integrated risk stratification models for rare and complex kidney diseases. This review synthesizes current AI applications across the rare disease continuum and proposes a clinically grounded framework to distinguish exploratory models from systems that are methodologically robust and operationally deployable. We highlight advances that address data sparsity and heterogeneity, alongside persistent challenges in validation, generalizability, equity, and workflow integration. Finally, we outline future directions, including federated learning, digital twins, and AI-driven clinical decision agents, as pathways toward precision-guided, workflow-integrated rare disease care.

Background The clinical heterogeneity of systemic lupus erythematosus exceeds the resolution of conventional disease activity instruments. Artificial intelligence offers the analytical infrastructure to engage with this complexity, yet the translation of AI models into clinical practice remains limited. Methods This review critically appraises the current evidence for AI applications across the SLE clinical workflow, including computational phenotyping, diagnosis, disease activity monitoring, organ-specific predictive modelling, and treatment personalization. Studies were evaluated for external validation, prospective testing, algorithmic fairness, explainability, and regulatory status. Findings AI applications across the SLE clinical workflow show uneven methodological maturity. Diagnostic and monitoring tools include the SLERPI index, with multinational external validation, and an LSTM flare-prediction model (C-index 0.897). Treatment personalization is anchored by serum IgA2 anti-dsDNA, the only SLE response biomarker validated across independent trials, and by multi-stain deep learning on renal biopsies (AUC 0.84, three external centers). Predictive modelling for organ-specific manifestations has progressed unevenly: cardiovascular risk stratification (SLECRISK) and a multicenter thrombocytopenia model are the most mature, while neuropsychiatric, gastrointestinal, and ocular applications remain single-center proofs of concept. External validation is the exception across SLE prediction models, no AI tool has received regulatory clearance, and populations most affected by SLE remain underrepresented in training data. Conclusions AI demonstrates genuine analytical capability in SLE but the translation gap is defined by insufficient validation, limited explainability, and absent equity evidence. Closing it will require fewer published models and more validated tools, optimization for clinical impact rather than discrimination alone, and demonstration of performance equity across the demographic spectrum of the disease.

ABSTRACT Bayesian statistics is gaining momentum in biomedical research, offering a flexible and intuitive framework for integrating prior knowledge, managing uncertainty, and informing decision-making. In nephrology, a field marked by complex pathophysiology, small patient populations, and evolving therapeutic landscapes, Bayesian approaches may provide critical advantages over traditional statistical methods. Bayesian methodologies may help reshape nephrology by improving trial efficiency, refining diagnostic and prognostic precision, and strengthening causal inference. We conducted a comprehensive narrative review of peer-reviewed literature on Bayesian applications in nephrology, highlighting studies in adaptive clinical trial designs, dynamic risk prediction models, network meta-analyses, pharmacokinetic modeling, and Bayesian Mendelian randomization approaches, including Bayesian model averaging frameworks. Bayesian adaptive designs enabled more efficient and ethically sound trials, such as the WIndow-of-opportunity clinical trial platform for evaluation of novel treatment strategies in REnal cell cancer (WIRE) platform study in renal cell carcinoma. In diagnostics and prognostics, Bayesian models allowed individualized inference from dynamic data, as demonstrated in estimated glomerular filtration rate trajectory analyses and mortality prediction. Bayesian network meta-analyses improved comparative effectiveness research by incorporating probabilistic treatment rankings, while Bayesian frameworks strengthened causal inference through methods like Mendelian randomization (MR) -Bayesian Model Averaging and Bayesian Kernel Machine Regression. Bayesian approaches have emerging applications in nephrology, promoting a probabilistic framework that enhances the interpretation of complex clinical and research data and supports more individualized patient care. Their integration into both research and clinical practice requires investment in education and training, interdisciplinary collaboration, and the development of accessible analytical tools. Embracing Bayesian methods is likely to play an important role in advancing precision medicine and improving patient outcomes in nephrology.

PURPOSE Chronic myelomonocytic leukemia (CMML) is a rare myeloid neoplasm characterized by clinical heterogeneity and is associated with poor outcomes. To date, limited molecular information has been incorporated into disease classification and risk stratification. We aimed to integrate genomic features into the clinical decision-making process for CMML. PATIENTS AND METHODS We analyzed a retrospective cohort of 3013 patients with CMML (training set) and a prospective population of 516 patients (validation set). Using an innovative framework for multimodal data analysis, we developed molecular-based disease taxonomy and prognostication. RESULTS Unsupervised clustering identified nine entities with distinct genomic features and outcomes ( P < .001), including splicing machinery, transcription factors, signal transduction and tyrosine kinase pathways aberrations, and high-risk molecular signatures. Notably, 15% of patients showed molecular/clinical overlap with other myeloid neoplasms. We integrated molecular and clinical information to build the international CMML Prognostic Scoring System (iCPSS), incorporating mutations in nine genes together with hematologic parameters and cytogenetic abnormalities. The iCPSS identified five groups with distinct probability of overall and leukemia-free survival in both training and validation cohorts ( P < .001), outperforming existing prognostic models. Importantly, 55% of patients were reassigned to higher or lower risk groups by the iCPSS. Decision analysis demonstrated that iCPSS could refine the optimal timing of allogeneic transplantation at the individual level; compared with conventional prognostic tools, iCPSS-based decision modeling changed transplantation strategy in 31% of cases, resulting in a significant gain-in-life expectancy for eligible patient population ( P < .001). A federated learning platform was implemented to enable continuous, privacy-preserving model update across multiple centers. CONCLUSION Molecular information improves CMML classification and prognostication, supports more effective clinical decision making, and potentially refines the design of clinical trials.

Background: Artificial intelligence in nephrology has largely focused on predictive models for outcomes such as acute kidney injury (AKI), chronic kidney disease (CKD) progression, and transplant complications. Although these models demonstrate technical performance, their real-world clinical impact has remained limited because prediction alone rarely translates into coordinated clinical action. Clinical artificial intelligence agents represent workflow-native systems that operate in real time, interact bidirectionally with clinical environments, adapt to evolving patient and workflow states, and support coordinated clinical action rather than generating isolated predictions. This review proposes clinical artificial intelligence agents as a new paradigm for integrating artificial intelligence directly into nephrology workflows. Methods: We conducted a narrative synthesis of emerging literature on artificial intelligence systems, agentic artificial intelligence architectures, clinical decision support, and digital health infrastructures relevant to kidney care. Drawing from interdisciplinary sources in medicine, health informatics, and artificial intelligence research, we developed a conceptual framework describing the architecture, governance requirements, and evaluation principles of clinical artificial intelligence agents in nephrology. Results: Clinical artificial intelligence agents represent workflow-integrated systems capable of continuously perceiving patient data, reasoning under clinical constraints, planning tasks, and supporting coordinated clinical actions over time. We describe a layered architecture consisting of perception, cognition, planning and control, action, and learning components. Potential applications span the nephrology care continuum, including CKD management, AKI monitoring, dialysis and continuous renal replacement therapy (CRRT) optimization, kidney transplantation care coordination, glomerulonephritis management, and supervised patient-facing systems. Conclusions: Clinical artificial intelligence agents shift the role of artificial intelligence from isolated prediction toward longitudinal clinical orchestration. Future evaluation should prioritize workflow integration, time-to-action, clinician oversight, safety, and patient-centered outcomes rather than relying solely on traditional model performance metrics. This roadmap provides a conceptual foundation for the responsible development and clinical integration of agentic artificial intelligence systems in nephrology.