1
|
Wheless L, Baker L, Edwards L, Anand N, Birdwell K, Hanlon A, Chren MM. Development of Phenotyping Algorithms for the Identification of Organ Transplant Recipients: Cohort Study. JMIR Med Inform 2020; 8:e18001. [PMID: 33156808 PMCID: PMC7759442 DOI: 10.2196/18001] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2020] [Revised: 07/21/2020] [Accepted: 10/31/2020] [Indexed: 12/20/2022] Open
Abstract
Background Studies involving organ transplant recipients (OTRs) are often limited to the variables collected in the national Scientific Registry of Transplant Recipients database. Electronic health records contain additional variables that can augment this data source if OTRs can be identified accurately. Objective The aim of this study was to develop phenotyping algorithms to identify OTRs from electronic health records. Methods We used Vanderbilt’s deidentified version of its electronic health record database, which contains nearly 3 million subjects, to develop algorithms to identify OTRs. We identified all 19,817 individuals with at least one International Classification of Diseases (ICD) or Current Procedural Terminology (CPT) code for organ transplantation. We performed a chart review on 1350 randomly selected individuals to determine the transplant status. We constructed machine learning models to calculate positive predictive values and sensitivity for combinations of codes by using classification and regression trees, random forest, and extreme gradient boosting algorithms. Results Of the 1350 reviewed patient charts, 827 were organ transplant recipients while 511 had no record of a transplant, and 12 were equivocal. Most patients with only 1 or 2 transplant codes did not have a transplant. The most common reasons for being labeled a nontransplant patient were the lack of data (229/511, 44.8%) or the patient being evaluated for an organ transplant (174/511, 34.1%). All 3 machine learning algorithms identified OTRs with overall >90% positive predictive value and >88% sensitivity. Conclusions Electronic health records linked to biobanks are increasingly used to conduct large-scale studies but have not been well-utilized in organ transplantation research. We present rigorously evaluated methods for phenotyping OTRs from electronic health records that will enable the use of the full spectrum of clinical data in transplant research. Using several different machine learning algorithms, we were able to identify transplant cases with high accuracy by using only ICD and CPT codes.
Collapse
Affiliation(s)
- Lee Wheless
- Department of Dermatology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Laura Baker
- Department of Dermatology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - LaVar Edwards
- Department of Dermatology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Nimay Anand
- Meharry Medical College, Nashville, TN, United States
| | - Kelly Birdwell
- Division of Nephrology and Hypertension, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Allison Hanlon
- Department of Dermatology, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Mary-Margaret Chren
- Department of Dermatology, Vanderbilt University Medical Center, Nashville, TN, United States
| |
Collapse
|
2
|
Waller KMJ, De La Mata NL, Hedley JA, Rosales BM, O'Leary MJ, Cavazzoni E, Ramachandran V, Rawlinson WD, Kelly PJ, Wyburn KR, Webster AC. New blood-borne virus infections among organ transplant recipients: An Australian data-linked cohort study examining donor transmissions and other HIV, hepatitis C and hepatitis B notifications, 2000-2015. Transpl Infect Dis 2020; 22:e13437. [PMID: 32767859 DOI: 10.1111/tid.13437] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2020] [Revised: 07/29/2020] [Accepted: 07/30/2020] [Indexed: 01/11/2023]
Abstract
BACKGROUND Blood-borne viral infections can complicate organ transplantation. Systematic monitoring to distinguish donor-transmitted infections from other new infections post transplant is challenging. Administrative health data can be informative. We aimed to quantify post-transplant viral infections, specifically those transmitted by donors and those reactivating or arising new in recipients. METHODS We linked transplant registries with administrative health data for all solid organ donor-recipient pairs in New South Wales, Australia, 2000-2015. All new recipient notifications of hepatitis B (HBV), C (HCV), or human immunodeficiency virus (HIV) after transplant were identified. Proven/probable donor transmissions within 12 months of transplant were classified using an international algorithm. RESULTS Of 2120 organ donors, there were 72 with a viral infection (9/72 active, 63/72 past). These 72 donors donated to 173 recipients, of whom 24/173 already had the same infection as their donor, and 149/173 did not, so were at risk of donor transmission. Among those at risk, 3/149 recipients had proven/probable viral transmissions (1 HCV, 2 HBV); none were unrecognized by donation services. There were no deaths from transmissions. There were no donor transmissions from donors without known blood-borne viruses. An additional 68 recipients had new virus notifications, of whom 2/68 died, due to HBV infection. CONCLUSION This work confirms the safety of organ donation in an Australian cohort, with no unrecognized viral transmissions and most donors with viral infections not transmitting the virus. This may support targeted increases in donation from donors with viral infections. However, other new virus notifications post transplant were substantial and are preventable. Data linkage can enhance current biovigilance systems.
Collapse
Affiliation(s)
- Karen M J Waller
- Faculty of Health and Medicine, Sydney School of Public Health, Centre for Organ Donation Evidence, University of Sydney, Sydney, NSW, Australia
| | - Nicole L De La Mata
- Faculty of Health and Medicine, Sydney School of Public Health, Centre for Organ Donation Evidence, University of Sydney, Sydney, NSW, Australia
| | - James A Hedley
- Faculty of Health and Medicine, Sydney School of Public Health, Centre for Organ Donation Evidence, University of Sydney, Sydney, NSW, Australia
| | - Brenda M Rosales
- Faculty of Health and Medicine, Sydney School of Public Health, Centre for Organ Donation Evidence, University of Sydney, Sydney, NSW, Australia.,Department of Renal Medicine, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Michael J O'Leary
- New South Wales Organ and Tissue Donation Service, Sydney, NSW, Australia.,Department of Intensive Care Medicine, Royal Prince Alfred Hospital, Camperdown, NSW, Australia
| | - Elena Cavazzoni
- New South Wales Organ and Tissue Donation Service, Sydney, NSW, Australia
| | - Vidiya Ramachandran
- Serology and Virology Division, NSW Health Pathology Randwick Prince of Wales Hospital, Randwick, NSW, Australia
| | - William D Rawlinson
- Serology and Virology Division, NSW Health Pathology Randwick Prince of Wales Hospital, Randwick, NSW, Australia.,Schools of SOMS, BABS and Women's and Children's, University of NSW, Kensington, NSW, Australia
| | - Patrick J Kelly
- Faculty of Health and Medicine, Sydney School of Public Health, Centre for Organ Donation Evidence, University of Sydney, Sydney, NSW, Australia
| | - Kate R Wyburn
- Department of Renal Medicine, Royal Prince Alfred Hospital, Camperdown, NSW, Australia.,Faculty of Health and Medicine, Sydney Medical School, University of Sydney, Sydney, NSW, Australia
| | - Angela C Webster
- Faculty of Health and Medicine, Sydney School of Public Health, Centre for Organ Donation Evidence, University of Sydney, Sydney, NSW, Australia.,Centre for Transplant and Renal Research, Westmead Hospital, Sydney, NSW, Australia
| |
Collapse
|
3
|
Solves P, Mirabet V, Alvarez M. Hepatitis B transmission by cell and tissue allografts: How safe is safe enough? World J Gastroenterol 2014; 20:7434-7441. [PMID: 24966613 PMCID: PMC4064088 DOI: 10.3748/wjg.v20.i23.7434] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/28/2013] [Revised: 01/04/2014] [Accepted: 02/20/2014] [Indexed: 02/06/2023] Open
Abstract
More than 2 million human tissue transplants (bone, tendon, cartilage, skin, cornea, amniotic membrane, stem cells, heart valve, blood vessel, etc.), are performed worldwide every year. Cells and tissues are shared between countries which have different regulations and laboratory equipment and represent a risk of hepatitis B virus (HBV) transmission that has become a global safety concern. While the risk of transfusion-transmitted HBV infection from blood donations has been estimated, the rate of HBV transmission from donors to recipients of allografts is unknown and varies between different tissues. There are various important ways of reducing the transmission risk, but donor screening and donor testing are still the main factors for preventing HBV transmission. HBV detection is included in the routine screening tests for cell and tissue donors. The standard test for preventing transplant-transmitted hepatitis B is the hepatitis B surface antigen. The implementation of methods involving nucleic acid amplification and the new generation of reactives to detect viral antibodies or antigens with an immunoassay, has increased the sensitivity and the specificity of the screening tests. The objective of our research was to review the literature and critically analyse the different steps for avoiding HBV transmission in cell and tissue donors, focusing on the screening tests performed.
Collapse
|