Human Versus Computer-based Predictions of Long Allograft Survival (iBox vs Human)

Computer Based, vs Human Based Assessment of Kidney Allograft Failure Prediction and Stratification

The clinical decision-making after kidney transplantation is mainly driven by patient individual assessment. However, this task remains difficult and uncertain due to the integration of complex and numerous parameters. We aim to evaluate and compare the ability of transplant physicians to predict long term allograft survival compared with a computer-based survival prediction algorithm (iBox system).

Study Overview

• Status: Completed
• Conditions: Kidney Transplant Failure
• Intervention / Treatment: Device: Computer based assessment (iBox); Other: Physician assessement

Detailed Description

400 kidney transplant recipients among the cohort of 4,000 patients from the Paris Transplant Group prospective kidney transplant cohort (NCT03474003) were randomly selected. We generated an anonymized electronic health record for each included patient including a total of 60 classical kidney transplant prognostic parameters comprising baseline transplant and recipient characteristics, together with post-transplant parameters including allograft function, proteinuria, histology, diagnoses, and immunological profile collected during the first-year post-transplant. The time of risk evaluation for the human and the iBox system were at 1-year post transplant and the death censored allograft survival predictions made at 7 years after risk assessment. We enrolled transplant physicians at various stages of their careers (residents, fellows and seniors) to assign death censored graft survival probabilities at 7 years post risk assessment. The physicians were blinded to the actual patient outcome (allograft failure) and the iBox predictions. The physicians-based predictions will then be compared with the iBox system, a validated computer-based kidney survival prediction system.

• Study Type: Observational
• Enrollment (Actual): 400

Contacts and Locations

Study Locations

• France
  • Île-de-France
    • Paris, Île-de-France, France, 75015
      • Paris Translational Centre for Organ Transplantation

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

400 (10%) of the patients were randomly selected with an evaluation available at one-year post-transplant from the Paris Transplant Group cohort, which gathers 4,000 consecutive patients over 18 years of age prospectively enrolled at the time of kidney transplantation from a living or deceased donor at Necker Hospital, Saint-Louis Hospital, Foch Hospital, and Toulouse Hospital between January 1, 2005, and January 1, 2014, in France.

Description

Inclusion Criteria:

• transplant evaluation available at one year post-transplant

Exclusion Criteria:

• no

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

Paris Transplant Group cohort; 400 (10%) of the patients were randomly selected from 4,000 consecutive patients over 18 years of age prospectively enrolled at the time of kidney transplantation from a living or deceased donor at Necker Hospital, Saint-Louis Hospital, Foch Hospital, and Toulouse Hospital between January 1, 2005, and January 1, 2014, in France.

Device: Computer based assessment (iBox); Individual allograft survival probabilities of death censored allograft survival seven years after the time of risk evaluation, computed using the iBox (NCT03474003), a qualified prognostication system designed to predict long term allograft survival up to seven years after evaluation.; Other: Physician assessement; Based on anonymized electronic health records, physicians have to determine a percentage of death censored allograft survival seven years after the time of risk evaluation,

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Death censored allograft failure seven years after risk assessment	Predictions performances to predict allograft failure defined as a patient's definitive return to dialysis or preemptive kidney retransplantation after risk assessment.	7 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Evaluation of the parameters' importance in the prediction for physicians	Mean decrease in accuracy from a random survival forest from each physician will be used to determine the relative importance of the first ten parameters that led to their predictions.	7 years
Inter-rater agreement	Fleiss kappa will be used to measure inter-rater agreement between each physician's ranking	7 years

Collaborators and Investigators

• Sponsor: Paris Translational Research Center for Organ Transplantation

Publications and helpful links

General Publications

• Loupy A, Aubert O, Orandi BJ, Naesens M, Bouatou Y, Raynaud M, Divard G, Jackson AM, Viglietti D, Giral M, Kamar N, Thaunat O, Morelon E, Delahousse M, Kuypers D, Hertig A, Rondeau E, Bailly E, Eskandary F, Bohmig G, Gupta G, Glotz D, Legendre C, Montgomery RA, Stegall MD, Empana JP, Jouven X, Segev DL, Lefaucheur C. Prediction system for risk of allograft loss in patients receiving kidney transplants: international derivation and validation study. BMJ. 2019 Sep 17;366:l4923. doi: 10.1136/bmj.l4923.

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2018
• Primary Completion (Actual): December 31, 2021
• Study Completion (Actual): December 31, 2021

Study Registration Dates

• First Submitted: June 2, 2021
• First Submitted That Met QC Criteria: June 7, 2021
• First Posted (Actual): June 8, 2021

Study Record Updates

• Last Update Posted (Actual): March 28, 2023
• Last Update Submitted That Met QC Criteria: March 27, 2023
• Last Verified: March 1, 2023

More Information

Terms related to this study

• Keywords: kidney transplantation; iBox; individual risk prediction; long-term allograft outcome
• Other Study ID Numbers: iBoxvsHuman

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No