Cardiovascular Diseases, Chronic Kidney Disease
Conditions
Keywords
chronic kidney disease, cardiovascular disease, artificial inteligence, predictors
Brief summary
This is an observational longitudinal study which will collect routine demographic, laboratory and clinical parameters of patients with chronic kidney disease (CKD) in the Silesian and Warmia and Mazury Regions (Poland) aimed at predicting incident cardiovascular disease and cardiovascular and renal events using machine learning and artificial intelligence approaches. There will be a subgroup analysis of patients with diabetes and CKD.
Detailed description
This is a prospective, observational study seeking to collate demographic, laboratory, and clinical data from patients with CKD hospitalized at two academic centres: the Department of Internal Medicine, Diabetology and Nephrology in Zabrze, Silesia, and the Clinic of Nephrology, Hypertension and Internal Medicine in Olsztyn, Warmia and Mazury. Patients will receive telephone check-ups annually post-discharge and will be proposed to attend on-site follow-up health checks. Patients will be followed up annually for 10 years or until death if occurs earlier, in order to collect information related to new onset cardiovascular events and progression to macroalbuminuria and/or doubling of serum creatinine with decrease of eGFR to less than 45 ml/min./1.73m2 (compared to baseline) or the onset of end stage renal disease (ESRD) or renal death. ESRD is defined as initiation of maintenance dialysis or kidney transplantation. All procedures, except eye fundus imaging for hospitalized patients align with standard nephrology ward care that patients agree for upon hospitalization. The Medical University of Silesia and the University of Warmia and Mazury, Collegium Medicum obtained study approvals from the respective independent university- or chamber of physicians-based bioethics committees for performing fundus imaging during hospital stay and annual telephone contacts as well as on- site health checks for the longitudinal patient follow-up observation. With patient consent, annual on-site visits will entail blood and urine assessments, ECG, retinal imaging via the fundus camera, and examinations for peripheral and cardiac autonomic neuropathy among those with diabetes. Biochemical analyses will focus on assessing serum creatinine, lipid profile, HbA1c for diabetic patients, and the urine albumin-creatinine ratio (UACR). With a decade-long prospective follow-up focused on documenting new cardiovascular and renal events, the primary objective is to identify patients with CKD at the highest risk of cardiovascular disease and CKD progression. This goal will be achieved by implementing machine learning techniques to analyze clinical parameters that are easy to obtain in everyday clinical practice.
Interventions
None listed
Sponsors
University of Warmia and Mazury in Olsztyn
University of Liverpool
Medical University of Silesia
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* CKD defined as estimated glomerular filtration rate (eGFR) \< 60ml/min/1.73 m2 and/or urine albumin creatinine ratio ( UACR) \> 30 mg/g lasting at least 3 months * CKD regardless of eGFR/albuminuria when documented otherwise (by means of imaging, renal biopsy result, genetic background, etc)
Exclusion criteria
* Death during hospital stay * Terminal stage of cancer * Lack of an informed consent
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| End-Stage Renal Disease or Renal Death | Annually, 10 years from enrollment | Onset of end-stage renal disease requiring initiation of maintenance dialysis or kidney transplantation, or death due to renal causes. |
| Death Due to Cardiovascular Cause | Annually, 10 years from enrollment | Death where the primary cause is attributed to cardiovascular disease. |
| Progression of Chronic Kidney Disease | Annually, 10 years from enrollment | Progression to macroalbuminuria or doubling of serum creatinine with a decrease of eGFR to less than 45 ml/min/1.73m\^2 compared to baseline. |
| Incident Coronary Artery Disease | Annually, 10 years from enrollment | New occurrence of coronary artery disease as diagnosed by standard medical procedures. |
| Myocardial Infarction | Annually, 10 years from enrollment | New occurrence of myocardial infarction as confirmed by electrocardiogram and/or biomarkers. |
| New onset heart failure or exacerbation of heart failure | Annually, 10 years from enrollment | New-Onset Heart Failure: Diagnosis based on the ESC guidelines, which include symptoms such as breathlessness, ankle swelling, and fatigue; objective evidence of cardiac dysfunction or structural abnormality in echocardiography; and response to treatment directed towards heart failure. Hospitalization for decompensated heart failure: Requires unscheduled admission to a healthcare facility with heart failure as the primary reason for admission. |
| Stroke or Transient Ischemic Attack | Annually, 10 years from enrollment | New occurrence of stroke as confirmed by neuroimaging or transient ischemic attack ascertained by typical symptoms. |
| Peripheral Vascular Disease Peripheral Vascular Disease Peripheral Vascular Disease Peripheral Vascular Disease Peripheral Vascular Disease | Annually, 10 years from enrollment | New diagnosis of peripheral vascular disease confirmed by imaging studies. |
| Atrial Fibrillation | Annually, 10 years from enrollment | Incident atrial fibrillation confirmed by electrocardiogram. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Cluster analyses. | 10 years from enrollment | Use of statistical cluster analysis to identify patterns within primary outcome measures. |
| Machine-learning predictors of outcomes, including ECG predictors and retinal imaging predictors. | 10 years from enrollment | Using new statistical methods in predicting outcomes |
Countries
Poland
Contacts
Primary ContactKatarzyna Nabrdalik, assoc. Prof
Backup ContactTomasz Stompór, Prof.
Outcome results
None listed