| Autor: |
Rebecca Darlay, Matthew E. Nargol, Edwin P. Su, Rohan M. Bhalekar, Rachelle Hornick, Shonali Natu, Benedicte A. Lie, Moreica B. Pabbruwe, Alan Stewart, Benjamin Wainwright, Renee Ren, Thomas J. Joyce, Nish Shyam, Antoni V.F. Nargol, David J. Langton, Susan Waller |
| Rok vydání: |
2021 |
| Předmět: |
|
| Popis: |
Joint replacement surgery provides pain relief and restoration of mobility for millions of patients around the world each year.[1] However, the release of wear debris from implant surfaces can limit the lifespan of a prosthesis through the promotion of inflammatory responses.[2] Implants must therefore be constructed from materials with sufficient durability and biocompatibility. One such material is cobalt chrome alloy, which is used in the majority of joint replacements.[3] Unfortunately, it is recognised that some patients develop lymphocyte mediated delayed type hypersensitivity (DTH) responses to this material,[4] a response which may result in extensive bone and soft tissue destruction.[5] A genetic predisposition to DTH has been proposed[6], though specific genes have yet to be identified, or the effects quantified. Here we show that variation in HLA class II genotype influences an individual’s susceptibility to DTH. HLA-DQ haplotypes encoding peptide binding grooves with greater affinity for the N terminal peptide sequence of albumin (containing two recognised metal binding sites) confer a greater risk of DTH. We describe the development and validation of a machine learning algorithm to investigate the possibility that a patient’s genotype and basic clinical parameters may be used to predict DTH. Incorporating this novel finding, gradient boosted survival analysis machine learning models were trained and validated using results from 606 patients from three international units. These models were assessed using Uno’s c-index, time-dependent AUROCs, and integrated calibration index performance statistics. At present, there are no tests in widespread clinical use which use a patient’s genetic profile to guide implant selection or inform post-operative management. The algorithm described herein may address this issue. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
