From ESH 2016 LB 1 JeanPierre Fauvel MD CHU Lyon Hôpital E Herriot Lyon France Overview Online risk prediction tool created to aid optimizing treatment of diabetic nephropathy ID: 931824
Download Presentation The PPT/PDF document "ALICE-PROTECT Study Yields Online Risk P..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
ALICE-PROTECT Study Yields Online Risk Prediction Tool in Diabetic Nephropathy
From ESH 2016 | LB 1:
Jean-Pierre
Fauvel
, MD
CHU Lyon,
Hôpital
E Herriot, Lyon,
France
Slide2Overview
Online risk prediction tool created to aid optimizing treatment of diabetic nephropathy
ALICE-PROTECT study data of patients with type 2 diabetes (T2D) and diabetic nephropathy used for Bayesian modeling
Online tool predicts 2-year risk of cardiovascular (CV) event
Access for online calculator:
https://www.hed.cc/?s=cvevent&t=CV%20Event
ALICE-PROTECT Study
Prospective, observational study
Primary outcome: number of patients at 2 years with blood pressure <130/80
mmHg
and proteinuria <0.5 g daily
986 patients, mean age 70 years, mean
eGFR
42 ml/min/1.73 m
2
, 66% patients had proteinuria >1 g daily
630 patients alive at 2 years; 39 patients had CV event during Year 1; 26 patients died from CV
cause
Reference
: Joly D et al.
Diabetes Res
Clin
Pract
2015
Slide4Proportion of Patients with a Cardiovascular Event in ALICE-PROTECT
% of the population
Slide5Variables in Bayesian Model
Patient Characteristics
Age, sex, body mass index, blood pressure, ethnicity, smoking habits
Medical History
Stroke, sleep apnea, peripheral arterial disease, ischemic heart disease, heart failure, diabetes duration, hypertension duration, retinopathy
Slide6Variables in Bayesian Model
Biology
eGFR, potassium, low-density lipoprotein
cholesterol,
HbA
1c
, proteinuria, hemoglobin
Treatment
Renin angiotensin system blockers, ASE, insulin, statin, diuretics, antithrombotic agent
Slide7Variables in Bayesian Model
Created Bayesian network to simulate data, using original data from ALICE-PROTECT study
Simulation calibrated with 2000 simulated individual data, 1000 with and 1000 without a CV event; multiple links found between variables
Bayesian network mimics usual medical thinking by physicians, analyzes large number of
variables
Used increasingly as diagnostic tools for medical decision
making
Slide8ALICE-PROTECT Study Yields Online Risk Prediction Tool in Diabetic Nephropathy
From ESH 2016 | LB 1:
Jean-Pierre
Fauvel
, MD
CHU Lyon,
Hôpital
E Herriot, Lyon,
France