The promise of machine learning applications in solid organ transplantation

Gotlieb, Neta; Azhie, Amirhossein; Sharma, Divya; Spann, Ashley; Suo, Nan-Ji; Tran, Jason; Orchanian‐Cheff, Ani; Wang, Bo; Goldenberg, Anna; Chassé, Michaël; Cardinal, Héloïse; Cohen, Joseph; Lodi, Andrea; Dieudé, Mélanie; Bhat, Mamatha

doi:10.1038/s41746-022-00637-2

Cited by 43 publications

(31 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…47 ML algorithms are now being applied to a variety of SOT research questions. 48 To our knowledge, our study represents the first time that a ML model has been used to assess variable importance in determining which SOT recipients developed a malignancy.…”

Section: Discussionmentioning

confidence: 95%

Multicenter analysis of immunosuppressive medications on the subsequent risk of malignancy in solid organ transplant recipients

Shaw

Haque

Fitzsimons

et al. 2022

Preprint

View full text Add to dashboard Cite

Solid organ transplant is a curative treatment for end organ disease. However, the immunosuppressive therapy required to prevent graft rejection increases the likelihood of developing a subsequent malignancy. This retrospective cohort study from a multi-center academic hospital system investigated solid organ transplantation, immunosuppression, and the risk of subsequent malignancy. Of the 5,591 patients and 6,142 transplanted organs studied, there were 517 subsequent malignancies identified. Skin cancer was the most common type of malignancy to be diagnosed, whereas liver cancer was the first malignancy to present at a median time of one-year post-transplant. Subsequent malignancy was proportionally more often diagnosed in non-Hispanic White transplant recipients compared to other racial groups. Heart and lung transplant recipients had relatively higher rates of subsequent malignancy than liver and kidney transplant recipients, but this finding was not significant upon adjusting for immunosuppressive medications. Multivariate cox proportional hazard analysis and random forest variable importance calculations identified statistically significant correlations with sirolimus and azathioprine and high rates of malignancy after transplant, while tacrolimus was associated with low rates of post-transplant neoplasia.

show abstract

Section: Discussionmentioning

confidence: 95%

Multicenter analysis of immunosuppressive medications on the subsequent risk of malignancy in solid organ transplant recipients

Shaw

Haque

Fitzsimons

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…One future potential application of radiomic transplant algorithms lies in predictive modeling of waitlist mortality, donor–recipient matching, survival prediction, and posttransplant complications diagnosis, allowing optimization of immunosuppression and management. 31…”

Section: Discussionmentioning

confidence: 99%

Radiomics in Kidney Transplantation: A Scoping Review of Current Applications, Limitations, and Future Directions

et al. 2023

View full text Add to dashboard Cite

Radiomics is increasingly applied to the diagnosis, management, and outcome prediction of various urological conditions. The purpose of this scoping review is to evaluate the current evidence of the application of radiomics in kidney transplantation, especially its utility in diagnostics and therapeutics. An electronic literature search on radiomics in the setting of transplantation was conducted on PubMed, EMBASE, and Scopus from inception to September 23, 2022. A total of 16 studies were included. The most widely studied clinical utility of radiomics in kidney transplantation is its use as an adjunct to diagnose rejection, potentially reducing the need for unnecessary biopsies or guiding decisions for earlier biopsies to optimize graft survival. Technology such as optical coherence tomography is a noninvasive procedure to build high-resolution optical cross-section images of the kidney cortex in situ and in real time, which can provide histopathological information of donor kidney candidates for transplantation, and to predict posttransplant function. This review shows that, although radiomics in kidney transplants is still in its infancy, it has the potential for large-scale implementation. Its greatest potential lies in the correlation with conventional established diagnostic evaluation for living donors and potential in predicting and detecting rejection postoperatively.

show abstract

“…To tackle this challenge, tools for statistical analysis are crucially needed. [18,19] Statistical methods have become increasingly popular for examining data, with machine learning (ML) being at the forefront of recent developments. Although ML algorithms require significant processing power, the increased computational capacity of ML in recent years has enabled the potential for intelligent systems.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Piezoelectric Tile Performance in Flat and Mountainous Terrains Through Deep Neural Network

Adhikari,

Singh,

Sagar

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

Piezoelectric tiles harvest mechanical vibrations and convert them into electrical energy, making them an attractive energy‐harvesting technology. However, their performance is heavily influenced by the terrain where they are installed. Traditional experimental methods for predicting their performance on different terrains are time‐consuming, so a computational approach is necessary to improve efficiency. To address this, a machine learning‐based approach is proposed using Artificial Neural network (ANN) and Deep neural network (DNN) with the Tanh activation function to predict piezoelectric tile performance in diverse terrains. The models are trained on an experimental dataset consisting of four terrains, including Flat terrain (FT) and Hilly Terrain (HT) 1, 2, 3 with road angles of 0, 3, 6, and 10 degrees. A finite element model is also established to optimize the piezoelectric tile and estimate the suitable parameter range to prevent damage to the tile during experiments. The results indicate that the DNN model performs better than the ANN model, achieving high accuracy in predicting piezoelectric tile performance on different terrains. These findings suggest that machine learning can provide a time and cost‐effective way for predicting the performance of piezoelectric tiles in varied terrains, thereby facilitating betters installation and maintenance decisions for piezoelectric tile systems.

show abstract

The promise of machine learning applications in solid organ transplantation

Cited by 43 publications

References 57 publications

Multicenter analysis of immunosuppressive medications on the subsequent risk of malignancy in solid organ transplant recipients

Multicenter analysis of immunosuppressive medications on the subsequent risk of malignancy in solid organ transplant recipients

Radiomics in Kidney Transplantation: A Scoping Review of Current Applications, Limitations, and Future Directions

Prediction of Piezoelectric Tile Performance in Flat and Mountainous Terrains Through Deep Neural Network

Contact Info

Product

Resources

About