AI-Assisted vs Usual Follow-up in Kidney Transplantation

NCT07842289 | Not Yet Recruiting

• 1 other identifier: 93899225.2.0000.5411
• Study Type: interventional
• Target: 140
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this clinical trial is to learn whether kidney transplant follow-up visits run by a health professional using an artificial intelligence (AI) computer helper are as good as usual follow-up visits with a doctor. People who receive a kidney transplant need check-up visits for the rest of their lives. These visits help keep the new kidney working well. As more people live longer with a transplant, clinics get busier. An AI helper may make visits more consistent and free up doctor time. This idea has not yet been tested well in real clinics. The main questions this study will answer are: Are AI-assisted visits as good as usual doctor visits? Trained reviewers will rate the quality of each visit. The reviewers will not know which type of visit they are rating. Are patients as satisfied with their visit? How long does the visit take, and how much time does the clinician spend on paperwork? Do the visits do a better job of checking key items, such as screening tests, vaccines, and transplant medicines? Are the visits safe for patients? Adults can take part if they have a working kidney transplant, if the transplant was at least 6 months ago, and if they can complete a routine visit on their own. Researchers will place 140 adults into two groups by chance, like flipping a coin. One group will have a visit run by a health professional who uses the AI helper. The other group will have a usual visit with a doctor. In both groups, the AI cannot order tests, change medicines, or make a diagnosis on its own. A clinician checks and approves everything. Participants will take part in one study follow-up visit. The visit will be audio-recorded so reviewers can rate it later. After the visit, participants will fill out a short satisfaction survey on a tablet.

Conditions

Kidney Transplant; Transplant Recipients

Keywords

Large Language Model; Clinical Decision Support; Kidney Transplant Follow-up; Non-Inferiority Trial; Patient Satisfaction

Outcome Measures

Primary Outcomes (1)

• Consultation quality measured by the MAAS-Global global score

  Overall quality of the follow-up consultation, scored with the MAAS-Global instrument, a validated tool for rating clinician consultation skills. Consultation quality is reported as the MAAS-Global global score, which ranges from 0 to 6, where 0 indicates the poorest consultation quality and 6 indicates the highest consultation quality (higher scores indicate better quality). Consultations are audio-recorded and scored by trained raters who are blinded to group allocation. This is the primary endpoint for the non-inferiority comparison between the AI-assisted consultation and the usual physician-led consultation.

  Consultation quality measured at Day 1

Secondary Outcomes (1)

• Patient satisfaction measured by the VSQ-9

  Patient satisfaction at day 1

Study Arms (2)

AI-Assisted Follow-up Consultation

EXPERIMENTAL

In this arm, a trained health professional conducts the routine follow-up consultation while a specialized large language model (LLM) assistant provides real-time support. The assistant uses a retrieval-augmented generation (RAG) pipeline indexed on KDIGO guidelines and clinic standard operating procedures, and supplies a structured content checklist, guideline-anchored suggestions with source citations, uncertainty flags, and a draft structured clinical note and orders. Guardrails prevent the assistant from finalizing medication changes, orders, or diagnoses. The responsible clinician reviews and verifies all findings, corrects inaccuracies, and approves and co-signs the encounter before any action is enacted (human-in-the-loop). The consultation follows a pre-specified content checklist and is audio-recorded for later blinded quality assessment.

Other: AI-Assisted Follow-up Consultation

Usual Physician-Led Follow-up

ACTIVE COMPARATOR

In this arm, participants receive standard physician-led kidney transplant follow-up according to routine clinic practice and current guidelines, without the AI assistant. The consultation comprises history-taking, medication reconciliation with a focus on immunosuppression, focused examination, and a management plan. The consultation follows the same pre-specified content checklist and targets a similar duration to the AI-assisted arm, and is audio-recorded for later blinded quality assessment.

Other: Usual Physician-Led Follow-up Consultation

Interventions

Usual Physician-Led Follow-up Consultation OTHER

Standard physician-led kidney transplant follow-up according to routine clinic practice and current guidelines, without the AI assistant. The consultation comprises history-taking, medication reconciliation with a focus on immunosuppression, focused examination, and a management plan, following the same pre-specified content checklist as the experimental arm.

Usual Physician-Led Follow-up

AI-Assisted Follow-up Consultation OTHER

A specialized large language model (LLM) assistant supports the consulting health professional in real time during a routine kidney transplant follow-up consultation. The assistant uses a retrieval-augmented generation (RAG) pipeline indexed on KDIGO guidelines and clinic standard operating procedures, and provides a structured content checklist, guideline-anchored suggestions with source citations, uncertainty flags, and a draft structured clinical note and orders. Guardrails prevent the assistant from finalizing medication changes, orders, or diagnoses. The responsible clinician reviews and verifies all findings, corrects inaccuracies, and approves and co-signs the encounter before any action is enacted (human-in-the-loop).

AI-Assisted Follow-up Consultation

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adults aged 18 years or older
• Have a working kidney transplant
• Received the kidney transplant at least 6 months ago
• Able to take part in a routine follow-up visit on their own
• Able to understand the study and give informed consent

You may not qualify if:

• Have a sudden or serious illness that needs urgent care
• Have a thinking or sensory problem that means they need another person's help during the visit
• Cannot communicate in Portuguese, the language used in the study
• Are taking part in another study that would conflict with this one

Sponsors & Collaborators

• UPECLIN HC FM Botucatu Unesp: lead

Study Sites (1)

UPECLIN

Botucatu, São Paulo, 18618-686, Brazil

Location

Related Publications (5)

• Rubin HR, Gandek B, Rogers WH, Kosinski M, McHorney CA, Ware JE Jr. Patients' ratings of outpatient visits in different practice settings. Results from the Medical Outcomes Study. JAMA. 1993 Aug 18;270(7):835-40.

  PMID: 8340982 BACKGROUND

• van Es JM, Schrijver CJ, Oberink RH, Visser MR. Two-dimensional structure of the MAAS-Global rating list for consultation skills of doctors. Med Teach. 2012;34(12):e794-9. doi: 10.3109/0142159X.2012.709652. Epub 2012 Sep 3.

  PMID: 22938687 BACKGROUND

• Miao J, Thongprayoon C, Suppadungsuk S, Garcia Valencia OA, Cheungpasitporn W. Integrating Retrieval-Augmented Generation with Large Language Models in Nephrology: Advancing Practical Applications. Medicina (Kaunas). 2024 Mar 8;60(3):445. doi: 10.3390/medicina60030445.

  PMID: 38541171 BACKGROUND

• Ayers JW, Poliak A, Dredze M, Leas EC, Zhu Z, Kelley JB, Faix DJ, Goodman AM, Longhurst CA, Hogarth M, Smith DM. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern Med. 2023 Jun 1;183(6):589-596. doi: 10.1001/jamainternmed.2023.1838.

  PMID: 37115527 BACKGROUND

• Kidney Disease: Improving Global Outcomes (KDIGO) Transplant Work Group. KDIGO clinical practice guideline for the care of kidney transplant recipients. Am J Transplant. 2009 Nov;9 Suppl 3:S1-155. doi: 10.1111/j.1600-6143.2009.02834.x.

  PMID: 19845597 BACKGROUND

MeSH Terms

Conditions

Patient Satisfaction

Condition Hierarchy (Ancestors)

Treatment Adherence and Compliance; Health Behavior; Behavior

Central Study Contacts

Luis Gustavo Modelli de Andrade, phD

CONTACT

+5514997980900; gustavo.modelli@unesp.br

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Two-arm, parallel-group, randomized, controlled non-inferiority trial with 1:1 allocation. Participants are assigned to either a health professional-led follow-up consultation supported in real time by a large language model with retrieval-augmented generation (AI-assisted arm) or a usual physician-led follow-up consultation (usual-care arm). Each participant takes part in a single study follow-up consultation. Because the nature of the intervention prevents masking of participants and treating clinicians, blinding is applied to the outcome assessors who rate consultation quality and to the statistician. Both arms follow an identical pre-specified content checklist and target a similar consultation duration to limit performance bias.

Study Record Dates

• First Submitted: September 16, 2026
• First Posted: September 25, 2026
• Study Start (Estimated): February 1, 2027
• Primary Completion (Estimated): April 1, 2028
• Study Completion (Estimated): June 1, 2028
• Last Updated: September 25, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will not share

Locations

BR (1)