Personalized Rituximab Treatment Based on Artificial Intelligence in Membranous Nephropathy (iRITUX)

Official title

Study of Artificial Intelligence-based Personalized Rituximab Treatment Protocol in Membranous Nephropathy

Overview

Membranous nephropathy is an autoimmune disease affecting the kidney, and the most common cause of nephrotic syndrome in non-diabetic Caucasian adults. The course of this disease is highly variable from one individual to another, ranging from spontaneous remission to progressive chronic kidney disease. The identification of autoantibodies - e.g., the phospholipase A2 receptor type 1 (PLA2R1) - has promoted the use of immunosuppressive drugs such as rituximab which is now a safe and effective first-line treatment for the management of membranous nephropathy. However, up to 40% of patients do not respond to a first course of rituximab treatment. In nephrotic patients, due to urinary drug loss, rituximab blood level is lower than in other autoimmune diseases treated with rituximab without proteinuria. This high urinary drug loss decreases the drug exposure, potentially explaining why rituximab regimen with low dose infusions (375 mg/m2) did not demonstrate efficacy after month-6 compared to a non-immunosuppressive antiproteinuric treatment in a previous study. In contrast, a regimen of two 1-g infusions two weeks apart was associated with a significantly greater remission rate after 6 months. Recently, the investigators have shown that after two 1-g rituximab infusions, the rituximab blood level 3 months after the first rituximab infusion, was correlated with the likelihood of remission after 6 and 12 months of the rituximab treatment. Patients with positive rituximab blood level 3 months after treatment had a higher chance of remission at month-6 and at month-12 than patients with an undetectable rituximab level at month-3. Nowadays, machine learning algorithms are increasingly used in medicine, especially in pharmacology, to predict the exposure to a drug, the initial dose to administer or the interval between two infusions. The objective of this study is to use a machine learning algorithm predicting the risk of having an undetectable residual level of rituximab 3 months after treatment, in order to propose a personalized treatment management with early additional doses of rituximab for the patients at risk.

Interventions

• Drug RiTUXimab Injection
  Dose administered will depend on randomisation and for experimental Arm on the risk of having undetectable rituximab level after 3 months

Primary outcome measures

• Clinical remission (complete or partial) after 6 months of rituximab initiation [Time frame: 6 months]

Secondary outcome measures (12)

• Complete clinical remission after 12 months of rituximab initiation [Time frame: 12 months]
• Partial clinical remission after 12 months of rituximab initiation [Time frame: 12 months]
• Immunological remission: anti-PLA2R1 depletion [Time frame: 12 months]
• Change in urine protein/creatinine ratio (UPCR) [Time frame: 12 months]
• Change in serum creatinine [Time frame: 12 months]
• Change in renal function [Time frame: 12 months]
• Change in the immunological status of the disease [Time frame: 12 months]
• Appearance of anti-drug antibodies after rituximab treatment [Time frame: 12 months]
• Rituximab underdosed patients [Time frame: 3 months]
• Serious adverse events [Time frame: 84 months]
• Adaptation of symptomatic treatment [Time frame: 84 months]
• Model improvement through machine learning [Time frame: 6 months]

Eligibility criteria

Inclusion criteria

• Age ≥ 18 years
• Ongoing episode of membranous nephropathy diagnosed by the presence of anti-PLA2R1 antibodies detected by ELISA (≥ 14 RU/ml, EUROIMMUN): the result must be validated by the Coordination team before randomization.
• Nephrotic syndrome defined by proteinuria > 3.5 g/24h (or UPCR > 3.5 g/g) and serum albumin < 30 g/L at diagnosis
• Estimated Glomerular Filtration Rate (CKD-EPI formula) > 30 mL/min/1,73 m2
• Indication for rituximab treatment according to the KDIGO and French guidelines
• Non-immunosuppressive antiproteinuric treatment at stable dose for 2 weeks according to French guidelines, including a renin angiotensin aldosterone system inhibitor, a diuretic and a low-salt diet at maximal tolerated dose (i.e., absence of orthostatic hypotension and no increase in creatinine > 30%)

Exclusion criteria

• Secondary Membranous nephropathy related to cancer, infection, systemic lupus, drug
• Diagnosis of PLA2R1-associated Membranous nephropathy not confirmed by the Coordination team (validation mandatory for randomization)
• Pregnancy or breastfeeding
• Immunosuppressive treatment (including rituximab) in the 6 months preceding inclusion
• Presence of anti-rituximab antibodies detected by Central Lab
• Cancer under treatment
• Patients with active, severe infections
• Hypersensitivity to the active substance or excipients
• Patients severely immunocompromised
• Severe heart failure or severe, uncontrolled cardiac disease

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Treatment

Study locations

France · 14 centers

• CHU de BESANCON — Besançon
• CHU de BORDEAUX - Hôpital Pellegrin — Bordeaux
• CHU de CAEN — Caen
• AP-HP - Hôpital H. Mondor — Créteil
• HCL - Hôpital E. Herriot — Lyon
• AP-HM - Hôpital de la Conception — Marseille
• CHU de NICE — Nice
• CHU de Nîmes - Hôpital CAREMEAU — Nîmes
• … and 6 more centers

Publications

• Teisseyre M, Destere A, Cremoni M, Zorzi K, Brglez V, Benito S, Bailly L, Fernandez C, Seitz-Polski B. Artificial intelligence-based personalised rituximab treatment protocol in membranous nephropathy (iRITUX): protocol for a multicentre randomised control trial. BMJ Open. 2025 Apr 2;15(4):e093920. doi: 10.1136/bmjopen-2024-093920. PMID 40180405

Identifiers

NCT: NCT06341205 · 22-APN-01

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗