1
|
DuBay DA, Su Z, Morinelli TA, Baliga P, Rohan V, Bian J, Northrup D, Pilch N, Rao V, Srinivas TR, Mauldin PD, Taber DJ. Development and future deployment of a 5 years allograft survival model for kidney transplantation. Nephrology (Carlton) 2019; 24:855-862. [PMID: 30198104 DOI: 10.1111/nep.13488] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/04/2018] [Indexed: 01/13/2023]
Abstract
AIM Identifying kidney transplant patients at highest risk for graft loss prior to loss may allow for effective interventions to improve 5 years survival. METHODS We performed a 10 years retrospective cohort study of adult kidney transplant recipients (n = 1747). We acquired data from electronic health records, United Network of Organ Sharing, social determinants of health, natural language processing data extraction, and real-time capture of dynamically evolving clinical data obtained within 1 year of transplant; from which we developed a 5 years graft survival model. RESULTS Total of 1439 met eligibility; 265 (18.4%) of them experienced graft loss by 5 years. Graft loss patients were characterized by: older age, being African-American, diabetic, unemployed, smokers, having marginal donor kidneys and cardiovascular comorbidities. Predictive dynamic variables included: low mean blood pressure, higher pulse pressures, higher heart rate, anaemia, lower estimated glomerular filtration rate peak, increased tacrolimus variability, rejection and readmissions. This Big Data analysis generated a 5 years graft loss model with an 82% predictive capacity, versus 66% using baseline United Network of Organ Sharing data alone. CONCLUSION Our analysis yielded a 5 years graft loss model demonstrating superior predictive capacity compared with United Network of Organ Sharing data alone, allowing post-transplant individualized risk-assessed care prior to transitioning back to community care.
Collapse
Affiliation(s)
- Derek A DuBay
- Department of Surgery, Medical University of South Carolina, Charleston, South Carolina, USA
| | - Zemin Su
- Division of General Internal Medicine and Geriatrics, Medical University of South Carolina, Charleston, South Carolina, USA
| | - Thomas A Morinelli
- Department of Surgery, Medical University of South Carolina, Charleston, South Carolina, USA
| | - Prabhakar Baliga
- Department of Surgery, Medical University of South Carolina, Charleston, South Carolina, USA
| | - Vinayak Rohan
- Department of Surgery, Medical University of South Carolina, Charleston, South Carolina, USA
| | - John Bian
- Division of General Internal Medicine and Geriatrics, Medical University of South Carolina, Charleston, South Carolina, USA
| | - David Northrup
- Office of the Chief Information Officer, Medical University of South Carolina, Charleston, South Carolina, USA
| | - Nicole Pilch
- Department of Clinical Pharmacy and Outcomes Sciences, College of Pharmacy, Medical University of South Carolina, Charleston, South Carolina, USA
| | - Vinaya Rao
- Department of Surgery, Medical University of South Carolina, Charleston, South Carolina, USA
| | | | - Patrick D Mauldin
- Division of General Internal Medicine and Geriatrics, Medical University of South Carolina, Charleston, South Carolina, USA
| | - David J Taber
- Department of Surgery, Medical University of South Carolina, Charleston, South Carolina, USA.,Department of Pharmacy, Ralph H Johnson VAMC, Charleston, South Carolina, USA
| |
Collapse
|
2
|
Tapak L, Hamidi O, Amini P, Poorolajal J. Prediction of Kidney Graft Rejection Using Artificial Neural Network. Healthc Inform Res 2017; 23:277-284. [PMID: 29181237 PMCID: PMC5688027 DOI: 10.4258/hir.2017.23.4.277] [Citation(s) in RCA: 24] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2017] [Revised: 08/17/2017] [Accepted: 09/10/2017] [Indexed: 12/13/2022] Open
Abstract
OBJECTIVES Kidney transplantation is the best renal replacement therapy for patients with end-stage renal disease. Several studies have attempted to identify predisposing factors of graft rejection; however, the results have been inconsistent. We aimed to identify prognostic factors associated with kidney transplant rejection using the artificial neural network (ANN) approach and to compare the results with those obtained by logistic regression (LR). METHODS The study used information regarding 378 patients who had undergone kidney transplantation from a retrospective study conducted in Hamadan, Western Iran, from 1994 to 2011. ANN was used to identify potential important risk factors for chronic nonreversible graft rejection. RESULTS Recipients' age, creatinine level, cold ischemic time, and hemoglobin level at discharge were identified as the most important prognostic factors by ANN. The ANN model showed higher total accuracy (0.75 vs. 0.55 for LR), and the area under the ROC curve (0.88 vs. 0.75 for LR) was better than that obtained with LR. CONCLUSIONS The results of this study indicate that the ANN model outperformed LR in the prediction of kidney transplantation failure. Therefore, this approach is a promising classifier for predicting graft failure to improve patients' survival and quality of life, and it should be further investigated for the prediction of other clinical outcomes.
Collapse
Affiliation(s)
- Leili Tapak
- Modeling of Noncommunicable Diseases Research Center, Department of Biostatistics, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Omid Hamidi
- Department of Science, Hamedan University of Technology, Hamedan, Iran
| | - Payam Amini
- Department of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, Iran
| | - Jalal Poorolajal
- Research Center for Health Sciences & Department of Epidemiology, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran
| |
Collapse
|
4
|
Choi JY, Kwon OJ. The impact of post-transplant hemoglobin level on renal allograft outcome. Transplant Proc 2013; 45:1553-7. [PMID: 23726618 DOI: 10.1016/j.transproceed.2012.11.030] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2012] [Revised: 10/10/2012] [Accepted: 11/20/2012] [Indexed: 10/26/2022]
Abstract
BACKGROUND Anemia is a common complication of chronic renal disease and renal transplantation. Early post-transplant anemia is the consequence of blood loss, immunosuppressant therapy, and failure to produce sufficient erythropoietin. Late post-transplant anemia has been attributed to drug therapy, renal dysfunction, and infection. The effect of post-transplant anemia on renal allograft survival and acute rejection rates is not established. The aim of this study was to examine the impact of post-transplant anemia on renal function and allograft outcomes. MATERIALS AND METHODS We included 411 patients who underwent living or deceased donor renal transplantations in our center from April 1990 to March 2010. The patients were divided into 2 groups according to their postoperative hemoglobin level at 1 month: anemic group (<12.0 g/dL in men, <11.0 g/dL in women) and nonanemic group (≥ 12.0 g/dL in men, ≥ 11.0 g/dL in women). The outcome measures included postoperative serum creatinine levels at 12 and 36 months, acute and chronic rejection rates, as well as long-term graft survival. RESULTS The acute and chronic rejection rates were significantly higher in the anemic group: 28.1% versus 19.7% (P = .000) and 24.1% versus 19.7% (P = .027), respectively. Postoperative serum creatinine levels at 12 and 36 months were not significantly different in patients with functioning grafts regardless of their anemia status (P = .530 and P = .430, respectively). Graft survival was lower with anemia: 85.4% versus 93.8% at 5 years, and 74.8% versus 83.5% at 10 years (P = .040). CONCLUSIONS Post-transplant anemia was associated with poorer renal function at 12 months, higher acute rejection rates, and worse long-term renal allograft outcomes compared with subjects displaying normal hemoglobin levels.
Collapse
Affiliation(s)
- J Y Choi
- Department of Surgery, College of Medicine, Hanyang University, Seoul, Korea
| | | |
Collapse
|
5
|
Sert I, Colak H, Tugmen C, Dogan SM, Karaca C. Anemia in living donor kidney transplantation. Transplant Proc 2013; 45:2238-43. [PMID: 23714109 DOI: 10.1016/j.transproceed.2012.12.008] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2012] [Revised: 11/12/2012] [Accepted: 12/03/2012] [Indexed: 11/19/2022]
Abstract
BACKGROUND We evaluated the prevalence of pretransplantation and posttransplantation anemia and its effect on serum creatinine levels among living donor kidney transplant recipients. METHODS We reviewed retrospectively 170 adult patients who underwent living donor kidney transplantation between 1994 and 2009. We defined anemia as hemoglobin (Hb) ≤12 g/dL for women and ≤13 g/dL for men with severe anemia as Hb <11 g/dL for both men and women (World Health Organization criteria). Patients were also categorized according to Hb levels less than or greater than 10 g/dL for correlation with recipient serum creatinine levels at months 1, 3, 6, and 12. RESULTS Mean recipient and donor ages were 33 ± 10 and 45 ± 12 years, respectively. Mean cold ischemia time was 76 ± 43 minutes. At the time of transplantation, anemia and severe anemia prevalences were 86.7% and 58.8%, respectively. Anemia was observed in 64 patients (42.1%) at posttransplantation month 3. Pretransplantation severe anemia was a good predictor of both Hb levels and anemia presence posttransplantation. Pretransplantation anemia and severe anemia caused greater requirements for posttransplantation blood transfusions (P < .05). Younger age and female gender were significant risk factors for severe anemia pretransplantation. There was a significant correlation between posttransplantation Hb levels and serum creatinine levels at 12 month (P = .01). Recipient female gender and longer hospital stay were significant risk factors for both anemia and severe anemia posttransplantation. Higher recipient weight and history of acute rejection episode were also significant for posttransplantation severe anemia. CONCLUSION This study indicated that successful kidney transplantation had a positive effect on Hb levels. Posttransplantation anemia predicted worse graft function in the first month after transplantation.
Collapse
Affiliation(s)
- I Sert
- Tepecik Training and Research Hospital, Department of Organ Transplantation, İzmir, Turkey.
| | | | | | | | | |
Collapse
|