Marc Raynaud1, Olivier Aubert2, Gillian Divard2, Peter P Reese3, Nassim Kamar4, Daniel Yoo1, Chen-Shan Chin5, Élodie Bailly6, Matthias Buchler6, Marc Ladrière7, Moglie Le Quintrec8, Michel Delahousse9, Ivana Juric10, Nikolina Basic-Jukic10, Marta Crespo11, Helio Tedesco Silva12, Kamilla Linhares12, Maria Cristina Ribeiro de Castro13, Gervasio Soler Pujol14, Jean-Philippe Empana1, Camilo Ulloa15, Enver Akalin16, Georg Böhmig17, Edmund Huang18, Mark D Stegall19, Andrew J Bentall19, Robert A Montgomery20, Stanley C Jordan18, Rainer Oberbauer21, Dorry L Segev22, John J Friedewald23, Xavier Jouven24, Christophe Legendre2, Carmen Lefaucheur25, Alexandre Loupy26. 1. Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France. 2. Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France; Kidney Transplant Department, Necker Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France. 3. Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France; Renal Electrolyte and Hypertension Division, University of Pennsylvania School of Medicine, Philadelphia, PA, USA. 4. Université Paul Sabatier, INSERM, Department of Nephrology and Organ Transplantation, CHU Rangueil & Purpan, Toulouse, France. 5. Deep Learning in Medicine and Genomics, DNAnexus, San Francisco, CA, USA. 6. Nephrology and Immunology Department, Bretonneau Hospital, Tours, France. 7. Nephrology Dialysis Transplantation Department, University of Lorraine, Centre Hospitalier Universitaire Nancy, Nancy, France. 8. Department of Nephrology, Centre Hospitalier Universitaire Montpellier, Montpellier, France. 9. Department of Transplantation, Nephrology and Clinical Immunology, Foch Hospital, Suresnes, France. 10. Department of Nephrology, Arterial Hypertension, Dialysis and Transplantation, University Hospital Centre Zagreb, School of Medicine University of Zagreb, Zagreb, Croatia. 11. Department of Nephrology, Hospital del Mar Barcelona, Spain. 12. Hospital do Rim, Escola Paulista de Medicina, Universidade Federal de São Paulo, São Paulo, Brazil. 13. Renal Transplantation Service, Hospital das Clinicas da Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil. 14. Unidad de Trasplante Renopancreas, Centro de Educacion Medica e Investigaciones Clinicas Buenos Aires, Buenos Aires, Argentina. 15. Kidney Transplantation Department, Clinica Alemana de Santiago, Santiago, Chile. 16. Renal Division Montefiore Medical Centre, Kidney Transplantation Program, Albert Einstein College of Medicine, NY, USA. 17. Division of Nephrology and Dialysis, Department of Medicine III, General Hospital Vienna, Vienna, Austria. 18. Department of Medicine, Division of Nephrology, Comprehensive Transplant Centre, Cedars Sinai Medical Centre, Los Angeles, CA, USA. 19. William J von Liebig Centre for Transplantation and Clinical Regeneration, Mayo Clinic, Rochester, MN, USA. 20. New York University Langone Transplant Institute, New York, NY, USA. 21. Nephrology, Medical University of Vienna, Vienna, Austria. 22. Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA. 23. Kidney Transplantation Department, Northwestern University Feinberg School of Medicine, Chicago, IL, USA. 24. Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France; Cardiology Department, European Georges Pompidou Hospital, Paris, France. 25. Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France; Kidney Transplant Department, Saint-Louis Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France. 26. Paris Translational Research Centre for Organ Transplantation, INSERM, PARCC, Université de Paris, Paris, France; Kidney Transplant Department, Necker Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France. Electronic address: alexandre.loupy@inserm.fr.
Abstract
BACKGROUND: Kidney allograft failure is a common cause of end-stage renal disease. We aimed to develop a dynamic artificial intelligence approach to enhance risk stratification for kidney transplant recipients by generating continuously refined predictions of survival using updates of clinical data. METHODS: In this observational study, we used data from adult recipients of kidney transplants from 18 academic transplant centres in Europe, the USA, and South America, and a cohort of patients from six randomised controlled trials. The development cohort comprised patients from four centres in France, with all other patients included in external validation cohorts. To build deeply phenotyped cohorts of transplant recipients, the following data were collected in the development cohort: clinical, histological, immunological variables, and repeated measurements of estimated glomerular filtration rate (eGFR) and proteinuria (measured using the proteinuria to creatininuria ratio). To develop a dynamic prediction system based on these clinical assessments and repeated measurements, we used a Bayesian joint models-an artificial intelligence approach. The prediction performances of the model were assessed via discrimination, through calculation of the area under the receiver operator curve (AUC), and calibration. This study is registered with ClinicalTrials.gov, NCT04258891. FINDINGS: 13 608 patients were included (3774 in the development cohort and 9834 in the external validation cohorts) and contributed 89 328 patient-years of data, and 416 510 eGFR and proteinuria measurements. Bayesian joint models showed that recipient immunological profile, allograft interstitial fibrosis and tubular atrophy, allograft inflammation, and repeated measurements of eGFR and proteinuria were independent risk factors for allograft survival. The final model showed accurate calibration and very high discrimination in the development cohort (overall dynamic AUC 0·857 [95% CI 0·847-0·866]) with a persistent improvement in AUCs for each new repeated measurement (from 0·780 [0·768-0·794] to 0·926 [0·917-0·932]; p<0·0001). The predictive performance was confirmed in the external validation cohorts from Europe (overall AUC 0·845 [0·837-0·854]), the USA (overall AUC 0·820 [0·808-0·831]), South America (overall AUC 0·868 [0·856-0·880]), and the cohort of patients from randomised controlled trials (overall AUC 0·857 [0·840-0·875]). INTERPRETATION: Because of its dynamic design, this model can be continuously updated and holds value as a bedside tool that could refine the prognostic judgements of clinicians in everyday practice, hence enhancing precision medicine in the transplant setting. FUNDING: MSD Avenir, French National Institute for Health and Medical Research, and Bettencourt Schueller Foundation.
BACKGROUND: Kidney allograft failure is a common cause of end-stage renal disease. We aimed to develop a dynamic artificial intelligence approach to enhance risk stratification for kidney transplant recipients by generating continuously refined predictions of survival using updates of clinical data. METHODS: In this observational study, we used data from adult recipients of kidney transplants from 18 academic transplant centres in Europe, the USA, and South America, and a cohort of patients from six randomised controlled trials. The development cohort comprised patients from four centres in France, with all other patients included in external validation cohorts. To build deeply phenotyped cohorts of transplant recipients, the following data were collected in the development cohort: clinical, histological, immunological variables, and repeated measurements of estimated glomerular filtration rate (eGFR) and proteinuria (measured using the proteinuria to creatininuria ratio). To develop a dynamic prediction system based on these clinical assessments and repeated measurements, we used a Bayesian joint models-an artificial intelligence approach. The prediction performances of the model were assessed via discrimination, through calculation of the area under the receiver operator curve (AUC), and calibration. This study is registered with ClinicalTrials.gov, NCT04258891. FINDINGS: 13 608 patients were included (3774 in the development cohort and 9834 in the external validation cohorts) and contributed 89 328 patient-years of data, and 416 510 eGFR and proteinuria measurements. Bayesian joint models showed that recipient immunological profile, allograft interstitial fibrosis and tubular atrophy, allograft inflammation, and repeated measurements of eGFR and proteinuria were independent risk factors for allograft survival. The final model showed accurate calibration and very high discrimination in the development cohort (overall dynamic AUC 0·857 [95% CI 0·847-0·866]) with a persistent improvement in AUCs for each new repeated measurement (from 0·780 [0·768-0·794] to 0·926 [0·917-0·932]; p<0·0001). The predictive performance was confirmed in the external validation cohorts from Europe (overall AUC 0·845 [0·837-0·854]), the USA (overall AUC 0·820 [0·808-0·831]), South America (overall AUC 0·868 [0·856-0·880]), and the cohort of patients from randomised controlled trials (overall AUC 0·857 [0·840-0·875]). INTERPRETATION: Because of its dynamic design, this model can be continuously updated and holds value as a bedside tool that could refine the prognostic judgements of clinicians in everyday practice, hence enhancing precision medicine in the transplant setting. FUNDING: MSD Avenir, French National Institute for Health and Medical Research, and Bettencourt Schueller Foundation.
Authors: Roman D Büllow; Jon N Marsh; S Joshua Swamidass; Joseph P Gaut; Peter Boor Journal: Curr Opin Nephrol Hypertens Date: 2022-02-14 Impact factor: 3.416
Authors: Ștefan Busnatu; Adelina-Gabriela Niculescu; Alexandra Bolocan; George E D Petrescu; Dan Nicolae Păduraru; Iulian Năstasă; Mircea Lupușoru; Marius Geantă; Octavian Andronic; Alexandru Mihai Grumezescu; Henrique Martins Journal: J Clin Med Date: 2022-04-18 Impact factor: 4.964
Authors: Martin Tepel; Subagini Nagarajah; Qais Saleh; Olivier Thaunat; Stephan J L Bakker; Jacob van den Born; Morten A Karsdal; Federica Genovese; Daniel G K Rasmussen Journal: Front Immunol Date: 2022-07-25 Impact factor: 8.786