Early identification and detection of cancer following lung transplantation is crucial for improving survival rates. This study utilizes data analytics techniques to predict de novo malignancies after lung transplantation in recipients with no prior cancer history. The purpose of this study is to identify critical factors influencing post-transplant malignancy occurrence to improve survival rates. A dataset of 30,917 individuals, 25% of whom developed post-transplant malignancy, was utilized in this study. Several well-known machine learning techniques were applied to this dataset to develop predictive models for malignancy following lung transplantation. The findings indicated that gradient boosting outperformed all other predictive models trained with the dataset, achieving an area under the ROC curve (AUC) of 0.746. The analysis revealed that the recipient's DR52 Antigen, BMI, CMV status, and total serum albumin levels were identified as critical factors influencing the occurrence of de novo malignancies. Lung transplant recipients face heightened de novo post-transplant malignancy risk due to immunosuppression. This study particularly underscores HLA-DR's association with a reduced likelihood of malignancy. Tailored surveillance protocols for lung transplant recipients could help mitigate this risk, if proven cost-effective, ensuring optimal care for this vulnerable patient group.
GaglioPJCotlerSJ. Liver transplantation in adults: long-term management of transplant recipients. 2018. UpToDate [online]. Available at: www. UpToDateInc. com (accessed January 7, 2020).
2.
ZwartESYükselEPannekoekA, et al.De novo carcinoma after solid organ transplantation to give insight into carcinogenesis in general—a systematic review and meta-analysis. Cancers2021; 13: 1122.
3.
GognaSRamakrishnaKJohnS. Post transplantation cancer. 2019.
4.
ZadehATaylorDBertsosM, et al.Predicting sports injuries with wearable technology and data analysis. Inf Syst Front2021; 23: 1023–1037.
5.
MassieABKurickaLSegevDL. Big data in organ transplantation: registries and administrative claims. Am J Transplant2014; 14: 1723–1730.
6.
AgasthiPBurasMRSmithSD, et al.Machine learning helps predict long-term mortality and graft failure in patients undergoing heart transplant. General Thorac Cardiovasc Surg2020; 68: 1369–1376.
7.
GotliebNAzhieASharmaD, et al.The promise of machine learning applications in solid organ transplantation. NPJ Digit Med2022; 5: 89.
8.
MekovEIlievaV. Machine learning in lung transplantation: where are we?La Presse Méd2022; 51: 104140.
9.
OztekinADelenDKongZJ. Predicting the graft survival for heart–lung transplantation patients: an integrated data mining methodology. Int J Med Inf2009; 78: e84–e96.
10.
NursetyoAASyed-AbdulSUddinM,et al.Graft rejection prediction following kidney transplantation using machine learning techniques: a systematic review and meta-analysis. MedInfo2019; 21: 10–14.
11.
GholamzadehMAbtahiHSafdariR. Machine learning-based techniques to improve lung transplantation outcomes and complications: a systematic review. BMC Med Res Methodol2022; 22: 331.
12.
NosoudiNZadehAWhiteH, et al.The predictive value of serum bilirubin in the post-liver transplant de novo malignancy: a data mining approach. Healthc Anal2022; 2: 100094.
13.
Van TrigtPDavisRDShaefferGS, et al.Survival benefits of heart and lung transplantation. Ann Surg1996; 223: 576.
14.
HsichEMThuitaLMcNamaraDM, et al.Variables of importance in the scientific registry of transplant recipients database predictive of heart transplant waitlist mortality. Am J Transplant2019; 19: 2067–2076.
15.
DavisAEMehrotraSFriedewaldJJ, et al.Improving geographic equity in kidney transplantation using alternative kidney sharing and optimization modeling. Med Decis Making2015; 35: 797–807.
16.
AyllónMDCiriaRCruz-RamírezM, et al.Validation of artificial neural networks as a methodology for donor-recipient matching for liver transplantation. Liver Transplant2018; 24: 192–203.
17.
MedvedDNuguesPNilssonJ. Simulating the outcome of heart allocation policies using deep neural networks. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018. IEEE.
18.
WeismüllerTJProkeinJBeckerT, et al.Prediction of survival after liver transplantation by pre-transplant parameters. Scand J Gastroenterol2008; 43: 736–746.
19.
RajiCChandraSV. Graft survival prediction in liver transplantation using artificial neural network models. J Comput Sci2016; 16: 72–78.
20.
KazemiAKazemiKSamiA,et al.Identifying factors that affect patient survival after orthotopic liver transplant using machine-learning techniques. Exp Clin Transplant2019; 17: 775–783.
21.
KantidakisGPutterHLanciaC, et al.Survival prediction models since liver transplantation-comparisons between cox models and machine learning techniques. BMC Med Res Methodol2020; 20: 1–14.
22.
LiuC-LSoongR-SLeeW-C, et al.Predicting short-term survival after liver transplantation using machine learning. Sci Rep2020; 10: 1–10.
23.
LauLKankanigeYRubinsteinB, et al.Machine-learning algorithms predict graft failure after liver transplantation. Transplantation2017; 101: e125.
24.
AminiMBagheriADelenD. An explanatory analytics model for identifying factors indicative of long-versus short-term survival after lung transplantation. Decis Anal J2022; 3: 100058.
25.
MedvedDOhlssonMHöglundP, et al.Improving prediction of heart transplantation outcome using deep learning techniques. Sci Rep2018; 8: 3613.
26.
ZadehABroachCNosoudiN, et al.Building analytical models for predicting de novo malignancy in pancreas transplant patients: a machine learning approach. Expert Syst Appl2024; 237: 121584.
27.
ZadehAHShardaR. Modeling brand post popularity dynamics in online social networks. Decis Support Syst2014; 65: 59–68.
28.
Hassan ZadehAZolbaninHMShardaR,et al.Social media for nowcasting flu activity: spatio-temporal big data analysis. Inf Syst Front2019; 21: 743–760.
29.
Hosmer JrDWLemeshowSSturdivantRX. Applied logistic regression. 3rd ed. New Jersey: John Wiley & Sons, 2013.
30.
ShreveJSchneiderHSoysalO. A methodology for comparing classification methods through the assessment of model stability and validity in variable selection. Decis Support Syst2011; 52: 247–257.
31.
MillerA. Subset selection in regression. 2nd ed. London: Chapman and Hall/CRC, 2002.
HastieTTibshiraniRFriedmanJH,et al.The elements of statistical learning: data mining, inference, and prediction. New York: Springer, 2009.
34.
BreimanL., Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. New York: Chapman & Hall, 2017.
35.
FullerCMBirosDPDelenD. An investigation of data and text mining methods for real world deception detection. Expert Syst Appl2011; 38: 8392–8398.
36.
BrownIMuesC. An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Syst Appl2012; 39: 3446–3453.
37.
EmanetNÖzHRBayramN,et al.A comparative analysis of machine learning methods for classification type decision problems in healthcare. Decis Anal2014; 1: 1–20.
38.
FriedmanJH. Greedy function approximation: a gradient boosting machine. Ann Statist2001; 1: 1189–1232.
39.
FriedmanJH. Stochastic gradient boosting. Comput Statist Data Anal2002; 38: 367–378.
40.
ZhangZZhaoYCanesA, et al.Predictive analytics with gradient boosting in clinical medicine. Ann Transl Med2019; 7: 152.
41.
ZadehAHAlsabiQRamirez-VickJE,et al.Characterizing basal-like triple negative breast cancer using gene expression analysis: a data mining approach. Expert Syst Appl2020; 148: 113253.
42.
BreimanL. Random forests. Mach Learn2001; 45: 5–32.
43.
ZadehACombsKBurkeyB, et al.Pet analytics: predicting adoption speed of pets from their online profiles. Expert Syst Appl2022; 204: 117596.
44.
BishopCM. Neural networks for pattern recognition. New York: Oxford university press, 1995.
45.
QuinlanJR. Induction of decision trees. Mach Learn1986; 1: 81–106.
46.
HuangC-LLiaoH-CChenM-C. Prediction model building and feature selection with support vector machines in breast cancer diagnosis. Expert Syst Appl2008; 34: 578–587.
47.
ParkBGParkYJooDJ, et al.Clinical significance of donor-specific anti-HLA-DR51/52/53 antibodies for antibody-mediated rejection in kidney transplant recipients. Korean J Transplant2019; 33: 47.
48.
PatiSIrfanWJameelA, et al.Obesity and cancer: a current overview of epidemiology, pathogenesis, outcomes, and management. Cancers2023; 15: 485.
49.
IyengarNMHudisCADannenbergAJ. Obesity and inflammation: new insights into breast cancer development and progression. Am Soc Clin Oncol Educ Book2013; 33: 46–51.
50.
SteiningerC. Clinical relevance of cytomegalovirus infection in patients with disorders of the immune system. Clin Microbiol Infect2007; 13: 953–963.
51.
KellyMGWinklerSSLentzSS, et al.Serum calcium and serum albumin are biomarkers that can discriminate malignant from benign pelvic masses. Cancer Epidemiol Biomarkers Prev2015; 24: 1593–1598.
52.
YangZZhengYWuZ, et al.Association between pre-diagnostic serum albumin and cancer risk: results from a prospective population-based study. Cancer Med2021; 10: 4054–4065.
53.
BenazzoASchwarzSFrommletF, et al.Twenty-year experience with extracorporeal life support as bridge to lung transplantation. J Thor Cardiovasc Surg2019; 157: 2515–2525.e2510.
54.
EngelsEAPfeifferRMFraumeniJF, et al.Spectrum of cancer risk among US solid organ transplant recipients. Jama2011; 306: 1891–1901.
55.
NijlandMLKerstenMJPalsST, et al.Epstein-barr virus–positive posttransplant lymphoproliferative disease after solid organ transplantation: Pathogenesis, clinical manifestations, diagnosis, and management. Transplant Direct2016; 2: e48.
56.
HughesR. Patient safety and quality: An evidence-based handbook for nurses. 2008.
57.
HansenRSeifeldinRNoeL. Medication adherence in chronic disease: issues in posttransplant immunosuppression. Transplant Proc2007; 39: 1287–1300.
ShtraichmanOAhyaVN. Malignancy after lung transplantation. Ann Transl Med2020; 8: 416.
60.
WhiteMCHolmanDMBoehmJE, et al.Age and cancer risk: a potentially modifiable relationship. Am J Prevent Med2014; 46: S7–S15.
61.
AlzayerMA. The influence of deceased kidney donor blood urea nitrogen (BUN) level on graft and patient survival time. New Jersey: Rutgers University-School of Health Professions, 2017.
62.
SunYLiJQuZ, et al.Causal associations between serum urea and cancer: a Mendelian randomization study. Genes2021; 12: 498.
63.
WangCSunHLiuJ. BUN Level is associated with cancer prevalence. Eur J Med Res2023; 28: 1–9.
64.
LingjunZKeshengWXingguangL. Use of diplotypes–matched haplotype pairs from homologous chromosomes–in gene-disease association studies. Shanghai Arch Psychiatry2014; 26: 165.
65.
MosaadY. Clinical role of human leukocyte antigen in health and disease. Scand J Immunol2015; 82: 283–306.
66.
NakamuraTShirouzuTNakataK, et al.The role of major histocompatibility complex in organ transplantation-donor specific anti-major histocompatibility complex antibodies analysis goes to the next stage. Int J Mol Sci2019; 20: 4544.
67.
ShiinaTHosomichiKInokoH,et al.The HLA genomic loci map: expression, interaction, diversity and disease. J Hum Genet2009; 54: 15–39.
68.
ChenYCicciarelliJPravicaV,et al.Long-range linkage on chromosome 6p of VEGF, FKBP5, HLA and TNF alleles associated with transplant rejection. Mol Immunol2009; 47: 96–100.
69.
FerreraAOlivoAAlaezC, et al.HLA DQA1 and DQB1 loci in Honduran women with cervical dysplasia and invasive cervical carcinoma and their relationship to human papillomavirus infection. Hum Biol1999; 1: 367–379.
70.
SabbatinoFLiguoriLPolcaroG, et al.Role of human leukocyte antigen system as a predictive biomarker for checkpoint-based immunotherapy in cancer patients. Int J Mol Sci2020; 21: 7295.
