Dataset Information

Forecasting of Patient-Specific Kidney Transplant Function With a Sequence-to-Sequence Deep Learning Model.

ABSTRACT:

Importance

Like other clinical biomarkers, trajectories of estimated glomerular filtration rate (eGFR) after kidney transplant are characterized by intra-individual variability. These fluctuations hamper the distinction between alarming graft functional deterioration or harmless fluctuation within the patient-specific expected reference range of eGFR.

Objective

To determine whether a deep learning model could accurately predict the patient-specific expected reference range of eGFR after kidney transplant.

Design, setting, and participants

A multicenter diagnostic study consisted of a derivation cohort of 933 patients who received a kidney transplant between 2004 and 2013 with 100 867 eGFR measurements from University Hospitals Leuven, Belgium, and 2 independent test cohorts: with 39 999 eGFR measurements from 1 170 patients, 1 from University Hospitals Leuven, Belgium, receiving transplants between 2013 and 2018 and 1 from Hannover Medical School, Germany, receiving transplants between 2003 and 2007. Patients receiving a single kidney transplant, with consecutive eGFR measurements were included. Data were analyzed from February 2019 to April 2021.

Exposures

In the derivation cohort 100 867 eGFR measurements were available for analysis and 39 999 eGFR measurements from the independent test cohorts.

Main outcomes and measures

A sequence-to-sequence model was developed for prediction of a patient-specific expected range of eGFR, based on previous eGFR values. The primary outcome was the performance of the deep learning sequence-to-sequence model in the 2 independent cohorts.

Results

In this diagnostic study, a total of 933 patients in the training sets (mean [SD] age, 53.5 [13.3] years; 570 male [61.1%]) and 1170 patients in the independent test sets (cohort 1 [n = 621]: mean [SD] age, 58.5 [12.1] years; 400 male [64.4%]; cohort 2 [n = 549]: mean [SD] age, 50.1 [13.0] years; 316 male [57.6%]) who received a single kidney transplant most frequently from deceased donors, the sequence-to-sequence models accurately predicted future patient-specific eGFR trajectories within the first 3 months after transplant, based on the previous graft eGFR values (root mean square error, 6.4-8.9 mL/min/1.73 m2). The sequence-to-sequence model predictions outperformed the more conventional autoregressive integrated moving average prediction model, at all input/output number of eGFR values.

Conclusions and relevance

In this diagnostic study, a sequence-to-sequence deep learning model was developed and validated for individual forecasting of kidney transplant function. The patient-specific sequence predictions could be used in clinical practice to guide physicians on deviations from the expected intra-individual variability, rather than relating the individual results to the reference range of the healthy population.

SUBMITTER: Van Loon E

PROVIDER: S-EPMC8719239 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundRenal replacement therapy (RRT) is a public health problem worldwide. Kidney transplantation (KT) is the best treatment for elderly patients' longevity and quality of life.ObjectivesThe primary endpoint was to compare elderly versus younger KT recipients by analyzing the risk covariables involved in worsening renal function, proteinuria, graft loss, and death one year after KT. The secondary endpoint was to create a robot based on logistic regression capable of predicting the likelihood that elderly recipients will develop worse renal function one year after KT.MethodUnicentric retrospective analysis of a cohort was performed with individuals aged ≥60 and <60 years old. We analysed medical records of KT recipients from January to December 2017, with a follow-up time of one year after KT. We used multivariable logistic regression to estimate odds ratios for elderly vs younger recipients, controlled for demographic, clinical, laboratory, data pre- and post-KT, and death.Results18 elderly and 100 younger KT recipients were included. Pretransplant immune variables were similar between two groups. No significant differences (P > 0.05) between groups were observed after KT on laboratory data means and for the prevalences of diabetes mellitus, hypertension, acute rejection, cytomegalovirus, polyomavirus, and urinary infections. One year after KT, the creatinine clearance was higher (P = 0.006) in youngers (70.9 ± 25.2 mL/min/1.73 m2) versus elderlies (53.3 ± 21.1 mL/min/1.73 m2). There was no difference in death outcome comparison. Multivariable analysis among covariables predisposing chronic kidney disease epidemiology collaboration (CKD-EPI) equation <60 mL/min/1.73 m2 presented a statistical significance for age ≥60 years (P = 0.01) and reduction in serum haemoglobin (P = 0.03). The model presented goodness-fit in the evaluation of artificial intelligence metrics (precision: 90%; sensitivity: 71%; and F 1 score: 0.79).ConclusionRenal function in elderly KT recipients was lower than in younger KT recipients. However, patients aged ≥60 years maintained enough renal function to remain off dialysis. Moreover, a learning machine application built a robot (Elderly KTbot) to predict in the elderly populations the likelihood of worse renal function one year after KT.

Project description:Interstitial fibrosis, tubular atrophy, and inflammation are major contributors to kidney allograft failure. Here we sought an objective, quantitative pathological assessment of these lesions to improve predictive utility and constructed a deep-learning-based pipeline recognizing normal vs. abnormal kidney tissue compartments and mononuclear leukocyte infiltrates. Periodic acid- Schiff stained slides of transplant biopsies (60 training and 33 testing) were used to quantify pathological lesions specific for interstitium, tubules and mononuclear leukocyte infiltration. The pipeline was applied to the whole slide images from 789 transplant biopsies (478 baseline [pre-implantation] and 311 post-transplant 12-month protocol biopsies) in two independent cohorts (GoCAR: 404 patients, AUSCAD: 212 patients) of transplant recipients to correlate composite lesion features with graft loss. Our model accurately recognized kidney tissue compartments and mononuclear leukocytes. The digital features significantly correlated with revised Banff 2007 scores but were more sensitive to subtle pathological changes below the thresholds in the Banff scores. The Interstitial and Tubular Abnormality Score (ITAS) in baseline samples was highly predictive of one-year graft loss, while a Composite Damage Score in 12-month post-transplant protocol biopsies predicted later graft loss. ITASs and Composite Damage Scores outperformed Banff scores or clinical predictors with superior graft loss prediction accuracy. High/intermediate risk groups stratified by ITASs or Composite Damage Scores also demonstrated significantly higher incidence of estimated glomerular filtration rate decline and subsequent graft damage. Thus, our deep-learning approach accurately detected and quantified pathological lesions from baseline or post-transplant biopsies and demonstrated superior ability for prediction of post-transplant graft loss with potential application as a prevention, risk stratification or monitoring tool.