Abstract
Reducing the shortage of organ donations to meet the demands of patients on the waiting list has being a major challenge in organ transplantation. Because of the shortage, organ matching decision is the most critical decision to assign the limited viable organs to the most “suitable” patients. Currently, organ matching decisions are only made by matching scores calculated via scoring models, which are built by the first principles. However, these models may disagree with the actual post-transplantation matching performance (e.g., patient's post-transplant quality of life (QoL) or graft failure measurements). In this paper, we formulate the organ matching decision-making as a top-N recommendation problem and propose an Adaptively Weighted Top-N Recommendation (AWTR) method. AWTR improves performance of the current scoring models by using limited actual matching performance in historical datasets as well as the collected covariates from organ donors and patients. AWTR sacrifices the overall recommendation accuracy by emphasizing the recommendation and ranking accuracy for top-N matched patients. The proposed method is validated in a simulation study, where KAS [60] is used to simulate the organ-patient recommendation response. The results show that our proposed method outperforms seven state-of-the-art top-N recommendation benchmark methods.
- [1] . 2005. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering 17, 6 (June 2005), 734–749.
DOI: https://doi.org/10.1109/TKDE.2005.99 Google ScholarDigital Library
- [2] . 2018. An efficient method for kidney allocation problem: A credibility-based fuzzy common weights data envelopment analysis approach. Health Care Management Science 21, 4 (December 2018), 587–603.
DOI: https://doi.org/10.1007/s10729-017-9414-6Google Scholar - [3] . 2011. Nonsimultaneous chains and dominos in kidney-paired donation—Revisited. American Journal of Transplantation 11, 5 (2011), 984–994.
DOI: https://doi.org/10.1111/j.1600-6143.2011.03481.xGoogle ScholarCross Ref
- [4] . 2013. Fairness, efficiency, and flexibility in organ allocation for kidney transplantation. Operations Research 61, 1 (February 2013), 73–87.
DOI: https://doi.org/10.1287/opre.1120.1138 Google ScholarDigital Library
- [5] . 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine Learning 3, 1 (January 2011), 1–122.
DOI: https://doi.org/10.1561/2200000016 Google ScholarDigital Library
- [6] . 2010. A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization 20, 4 (January 2010), 1956–1982.
DOI: https://doi.org/10.1137/080738970 Google ScholarDigital Library
- [7] . 2012. Exact matrix completion via convex optimization. Communications of the ACM 55, 6 (June 2012), 111–119.
DOI: https://doi.org/10.1145/2184319.2184343 Google ScholarDigital Library
- [8] . 2007. Learning to rank: From pairwise approach to listwise approach. In Proceedings of the 24th International Conference on Machine learning (ICML’07), Association for Computing Machinery, Corvalis, Oregon, USA, 129–136.
DOI: https://doi.org/10.1145/1273496.1273513 Google ScholarDigital Library
- [9] . 2021. PRIME: A personalized recommender system for information visualization methods via extended matrix completion. ACM Trans. Interact. Intell. Syst. 11, 1, Article 7 (April 2021), 30 pages.Google Scholar
- [10] . 2014. Low rank sparse linear methods for top-n recommendations. In 2014 IEEE International Conference on Data Mining, 90–99.
DOI: https://doi.org/10.1109/ICDM.2014.112 Google ScholarDigital Library
- [11] . 2010. Performance of recommender algorithms on top-n recommendation tasks. In Proceedings of the Fourth ACM Conference on Recommender Systems
(RecSys’10) , Association for Computing Machinery, Barcelona, Spain, 39–46.DOI: https://doi.org/10.1145/1864708.1864721 Google ScholarDigital Library
- [12] . 2009. Search Engines: Information Retrieval in Practice (1st ed.). Addison-Wesley Publishing Company, USA. Google Scholar
Digital Library
- [13] . 1995. One-attribute sequential assignment match processes in discrete time. Operations Research 43, 5 (October 1995), 879–884.
DOI: https://doi.org/10.1287/opre.43.5.879 Google ScholarDigital Library
- [14] . 2004. Item-based top-N recommendation algorithms. ACM Transactions on Information Systems 22, 1 (January 2004), 143–177.
DOI: https://doi.org/10.1145/963770.963776 Google ScholarDigital Library
- [15] . 2013. Long-term factors influencing survival after kidney transplantation. Transplantation Proceedings 45, 1 (January 2013), 129–133.
DOI: https://doi.org/10.1016/j.transproceed.2012.08.014Google Scholar - [16] . 1994. Ideal spatial adaptation by wavelet shrinkage. Biometrika 81, 3 (September 1994), 425–455.
DOI: https://doi.org/10.1093/biomet/81.3.425Google ScholarCross Ref
- [17] . 2015. Evaluating recommender systems. In Recommender Systems Handbook, (eds.). Springer US, Boston, MA, 265–308.
DOI: https://doi.org/10.1007/978-1-4899-7637-6_8Google ScholarCross Ref
- [18] . 2005. Fuzzy organ allocation system for cadaveric kidney transplantation. Transplantation 80, 12 (December 2005), 1648–1653.
DOI: https://doi.org/10.1097/01.tp.0000183287.04630.05Google Scholar - [19] . 2017. DeepFM: A factorization-machine based neural network for CTR prediction. (March 2017). Retrieved March 26, 2021 from http://arxiv.org/abs/1703.04247v1Google Scholar
- [20] . 2017. Convergence of ADMM for multi-block nonconvex separable optimization models. Frontiers of Mathematics in China 12, 5 (October 2017), 1139–1162.
DOI: https://doi.org/10.1007/s11464-017-0631-6Google Scholar - [21] . 2015. Statistical Learning with Sparsity: The Lasso and Generalizations. CRC Press. Google Scholar
Digital Library
- [22] . 2017. Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web (WWW’17), International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, 173–182.
DOI: https://doi.org/10.1145/3038912.3052569Google Scholar - [23] . 1999. An algorithmic framework for performing collaborative filtering. In Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’99), Association for Computing Machinery, Berkeley, California, USA, 230–237.
DOI: https://doi.org/10.1145/312624.312682 Google ScholarDigital Library
- [24] . 2004. Latent semantic models for collaborative filtering. ACM Transactions on Information Systems 22, 1 (January 2004), 89–115.
DOI: https://doi.org/10.1145/963770.963774 Google ScholarDigital Library
- [25] . 2013. Low-rank matrix completion using alternating minimization. In Proceedings of the Forty-fifth Annual ACM Symposium on Theory of Computing
(STOC’13) , Association for Computing Machinery, Palo Alto, California, USA, 665–674.DOI: https://doi.org/10.1145/2488608.2488693 Google ScholarDigital Library
- [26] . 2019. Dynamic quality-process model in consideration of equipment degradation. 51, 3 (July 2019), 217–229.Google Scholar
- [27] . 2010. Factor in the neighbors: Scalable and accurate collaborative filtering. ACM Transactions on Knowledge Discovery from Data 4, 1 (January 2010), 1:1–1:24.
DOI: https://doi.org/10.1145/1644873.1644874 Google ScholarDigital Library
- [28] . 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (August 2009), 30–37.
DOI: https://doi.org/10.1109/MC.2009.263 Google ScholarDigital Library
- [29] . 1972. Generalized linear models. Journal of the Royal Statistical Society: Series A (General) 135, 3 (1972), 370–384.Google Scholar
Cross Ref
- [30] . 2011. Sparse linear methods for top-n recommender systems. In 2011 IEEE 11th International Conference on Data Mining, 497–506.
DOI: https://doi.org/10.1109/ICDM.2011.134 Google ScholarDigital Library
- [31] . 2017. Selection of candidates for lung transplantation: The first Italian consensus statement. Transplantation Proceedings 49, 4 (May 2017), 702–706.
DOI: https://doi.org/10.1016/j.transproceed.2017.02.026Google Scholar - [32] . 2000. Health-related quality of life after solid organ transplantation: A prospective, multiorgan cohort study. Annals of Surgery 232, 4 (October 2000), 597–607. Retrieved September 27, 2020 from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1421192/Google Scholar
- [33] . 2012. Bayesian personalized ranking from implicit feedback. arXiv:1205.2618 [cs, stat] (May 2012). Google Scholar
Digital Library
- [34] RFI. 2008. Kidney Allocation Concepts: Request for Information. OPTN/UNOS Kidney Transplantation Committee (2008).Google Scholar
- [35] . 2011. Introduction to recommender systems handbook. In Recommender Systems Handbook, Francesco Ricci, Lior Rokach, Bracha Shapira and Paul B. Kantor (eds.). Springer US, Boston, MA, 1–35. Google Scholar
Digital Library
- [36] . 1989. A resource allocation problem in a random environment. Operations Research 37, 2 (April 1989), 329–338.
DOI: https://doi.org/10.1287/opre.37.2.329 Google ScholarDigital Library
- [37] . 2004. Kidney exchange. The Quarterly Journal of Economics 119, 2 (May 2004), 457–488.
DOI: https://doi.org/10.1162/0033553041382157Google ScholarCross Ref
- [38] . 1985. Kidney transplantation: A simulation model for examining demand and supply. Management Science 31, 5 (March 1985), 515–526.
DOI: https://doi.org/10.1287/mnsc.31.5.515 Google ScholarDigital Library
- [39] . 2007. Probabilistic matrix factorization. In Proceedings of the 20th International Conference on Neural Information Processing Systems (NIPS’07), Curran Associates Inc., Vancouver, British Columbia, Canada, 1257–1264. Google Scholar
Digital Library
- [40] . 2001. Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th International Conference on World Wide Web, Association for Computing Machinery, Hong Kong, China, 285–295.
DOI: https://doi.org/10.1145/371920.372071 Google ScholarDigital Library
- [41] . 2018. Analysis of the Eurotransplant Kidney Allocation Algorithm: How should we balance utility and equity? Transplant Proc 50, 10 (December 2018), 3010–3016.
DOI: https://doi.org/10.1016/j.transproceed.2018.08.040Google Scholar - [42] . 2005. Kidney paired donation and optimizing the use of live donor organs. JAMA 293, 15 (April 2005), 1883–1890.
DOI: https://doi.org/10.1001/jama.293.15.1883Google ScholarCross Ref
- [43] . 2013. Evaluation of recommendations: Rating-prediction and ranking. In Proceedings of the 7th ACM Conference on Recommender Systems (RecSys’13), Association for Computing Machinery, Hong Kong, China, 213–220.
DOI: https://doi.org/10.1145/2507157.2507160 Google ScholarDigital Library
- [44] . 2010. The right kidney for the right recipient: The status of deceased donor kidney allocation reform. Seminars in Dialysis 23, 3 (2010), 248–252.
DOI: https://doi.org/10.1111/j.1525-139X.2010.00723.xGoogle Scholar - [45] . 2017. Why do we have the kidney allocation system we have today? A history of the 2014 kidney allocation system. Human Immunology 78, 1 (January 2017), 4–8.
DOI: https://doi.org/10.1016/j.humimm.2016.08.008Google Scholar - [46] . 2009. A survey of collaborative filtering techniques. Advances in Artificial Intelligence 2009, (January 2009), 4:2.
DOI: https://doi.org/10.1155/2009/421425 Google ScholarDigital Library
- [47] . 1996. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological) 58, 1 (1996), 267–288.
DOI: https://doi.org/10.1111/j.2517-6161.1996.tb02080.xGoogle ScholarCross Ref
- [48] . 2012. Patient preferences for the allocation of deceased donor kidneys for transplantation: A mixed methods study. BMC Nephrology 13, 1 (April 2012), 18.
DOI: https://doi.org/10.1186/1471-2369-13-18Google Scholar - [49] . 2013. A theoretical analysis of NDCG type ranking measures. arXiv:1304.6480 [cs, stat] (April 2013).Google Scholar
- [50] . 2019. Global convergence of ADMM in nonconvex nonsmooth optimization. Journal of Scientific Computing 78, 1 (January 2019), 29–63.
DOI: https://doi.org/10.1007/s10915-018-0757-z Google ScholarDigital Library
- [51] . 1972. Excitatory and inhibitory interactions in localized populations of model neurons. Biophys J. 12, 1 (January 1972), 1–24.Google Scholar
Cross Ref
- [52] . 2009. Predictability of survival models for waiting list and transplant patients: calculating LYFT. American Journal of Transplantation 9, 7 (2009), 1523–1527.
DOI: https://doi.org/10.1111/j.1600-6143.2009.02708.xGoogle Scholar - [53] . 2008. Calculating life years from transplant (LYFT): Methods for kidney and kidney-pancreas candidates. American Journal of Transplantation 8, 4p2 (2008), 997–1011.
DOI: https://doi.org/10.1111/j.1600-6143.2008.02177.xGoogle Scholar - [54] . 2015. Coordinate descent algorithms. arXiv:1502.04759 [math] (February 2015).Google Scholar
- [55] . 2013. Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization. Math. Comp. 82, 281 (2013), 301–329.
DOI: https://doi.org/10.1090/S0025-5718-2012-02598-1Google ScholarCross Ref
- [56] . 2011. Split Bregman method for large scale fused Lasso. Computational Statistics & Data Analysis 55, 4 (April 2011), 1552–1569.
DOI: https://doi.org/10.1016/j.csda.2010.10.021 Google ScholarDigital Library
- [57] . 2002. Optimal control of a paired-kidney exchange program. Management Science 48, 3 (March 2002), 328–342.
DOI: https://doi.org/10.1287/mnsc.48.3.328.7732 Google ScholarDigital Library
- [58] 2004. WHO | Transplantation. Retrieved August 2, 2020 from https://www.who.int/topics/transplantation.Google Scholar
- [59] 2020. CPRA Calculator - OPTN. Retriefved from https://optn.transplant.hrsa.gov/resources/allocation-calculators/cpra-calculator/.Google Scholar
- [60] Kidney Allocation System - Professional Education - OPTN. Retrieved August 2, 2020 from https://optn.transplant.hrsa.gov/learn/professional-education/kidney-allocation-system/.Google Scholar
- [61] Organ Donation and Transplantation Statistics: Graph Data | Organ Donor. Retrieved August 2, 2020 from https://www.organdonor.gov/statistics-stories/statistics/data.html.Google Scholar
- [62] National Data - OPTN. Retrieved August 2, 2020 from https://optn.transplant.hrsa.gov/data/view-data-reports/national-data.Google Scholar
- [63] Living Donation Facts and Resources from UNOS | Living Donor Transplants. Retrieved March 20, 2021 from https://unos.org/transplant/living-donation/.Google Scholar
- [64] How we match organs - UNOS. Retrieved August 2, 2020 from https://unos.org/transplant/how-we-match-organs/.Google Scholar
- [65] EPTS Calculator - OPTN. Retrieved August 2, 2020 from https://optn.transplant.hrsa.gov/resources/allocation-calculators/epts-calculator/.Google Scholar
- [66] KDPI Calculator - OPTN. Retrieved August 2, 2020 from https://optn.transplant.hrsa.gov/resources/allocation-calculators/kdpi-calculator/.Google Scholar
Index Terms
Adaptively Weighted Top-N Recommendation for Organ Matching
Recommendations
Personalized hybrid recommendation for group of users
Novel group hybrid method combining collaborative and content-based recommendation.Proposed method improves the quality of recommended items ordering.Proposed method increases the recommendation precision for very Top-N results.Applicable for single ...
Top-N recommendation through belief propagation
CIKM '12: Proceedings of the 21st ACM international conference on Information and knowledge managementThe top-n recommendation focuses on finding the top-n items that the target user is likely to purchase rather than predicting his/her ratings on individual items. In this paper, we propose a novel method that provides top-n recommendation by ...
Local Item-Item Models For Top-N Recommendation
RecSys '16: Proceedings of the 10th ACM Conference on Recommender SystemsItem-based approaches based on SLIM (Sparse LInear Methods) have demonstrated very good performance for top-N recommendation; however they only estimate a single model for all the users. This work is based on the intuition that not all users behave in ...






Comments