Prediction of Breast Cancer Treatment\textendashInduced Fatigue by Machine Learning Using Genome-Wide Association Data

Sangkyu Lee (1, 2, 3) , Joseph O Deasy (1) , Jung Hun Oh (1) , Antonio Di Meglio (2, 3) , Agnès Dumas (4, 2) , Gwenn Menvielle (5) , Cecile Charles (2, 3) , Sandrine Boyault (6) , Marina Rousseau (6) , Celine Besse (7, 8, 9) , Emilie Thomas (6) , Anne Boland (7, 8, 9) , Paul Cottu (10) , Olivier Tredan (6) , Christelle Levy (11) , Anne-Laure Martin (12) , Sibille Everhard (12) , Patricia A Ganz (13) , Ann H Partridge (14) , Stefan Michiels (4, 2) , Jean-François Deleuze (7, 15, 9, 8) , Fabrice Andre (3, 2) , Ines Vaz-Luis (3, 2)

1 MSKCC - Memorial Sloan Kettering Cancer Center
2 IGR - Institut Gustave Roussy
3 PMNCO - Prédicteurs moléculaires et nouvelles cibles en oncologie
4 CESP - Centre de recherche en épidémiologie et santé des populations
5 iPLESP - Institut Pierre Louis d'Epidémiologie et de Santé Publique
6 Centre Léon Bérard [Lyon]
7 CNRGH - Centre National de Recherche en Génomique Humaine
8 JACOB - Institut de Biologie François JACOB
9 Fondation Synergie Lyon Cancer [Lyon]
10 Institut Curie [Paris]
11 UNICANCER/CRLC - Centre Régional de Lutte contre le Cancer François Baclesse [Caen]
12 UNICANCER
13 UCLA - University of California [Los Angeles]
14 Dana-Farber Cancer Institute [Boston]
15 CEPH - Centre d'Etude du Polymorphisme Humain

Background We aimed at predicting fatigue after breast cancer treatment using machine learning on clinical covariates and germline genome-wide data. Methods We accessed germline genome-wide data of 2799 early-stage breast cancer patients from the Cancer Toxicity study (NCT01993498). The primary endpoint was defined as scoring zero at diagnosis and higher than quartile 3 at 1\,year after primary treatment completion on European Organization for Research and Treatment of Cancer quality-of-life questionnaires for Overall Fatigue and on the multidimensional questionnaire for Physical, Emotional, and Cognitive fatigue. First, we tested univariate associations of each endpoint with clinical variables and genome-wide variants. Then, using preselected clinical (false discovery rate < 0.05) and genomic (P\,<\,.001) variables, a multivariable preconditioned random-forest regression model was built and validated on a hold-out subset to predict fatigue. Gene set enrichment analysis identified key biological correlates (MetaCore). All statistical tests were 2-sided. Results Statistically significant clinical associations were found only with Emotional and Cognitive Fatigue, including receipt of chemotherapy, anxiety, and pain. Some single nucleotide polymorphisms had some degree of association (P\,<\,.001) with the different fatigue endpoints, although there were no genome-wide statistically significant (P\,<\,5.00 \texttimes 10-8) associations. Only for Cognitive Fatigue, the predictive ability of the genomic multivariable model was statistically significantly better than random (area under the curve = 0.59, P\,=\,.01) and marginally improved with clinical variables (area under the curve\,=\,0.60, P\,=\,.005). Single nucleotide polymorphisms found to be associated (P\,<\,.001) with Cognitive Fatigue belonged to genes linked to inflammation (false discovery rate adjusted P\,=\,.03), cognitive disorders (P\,=\,1.51 \texttimes 10-12), and synaptic transmission (P\,=\,6.28 \texttimes 10-8). Conclusions Genomic analyses in this large cohort of breast cancer survivors suggest a possible genetic role for severe Cognitive Fatigue that warrants further exploration.

Domaines: Sciences du Vivant [q-bio]

Sangkyu Lee, Joseph O Deasy, Jung Hun Oh, Antonio Di Meglio, Agnès Dumas, et al.. Prediction of Breast Cancer Treatment\textendashInduced Fatigue by Machine Learning Using Genome-Wide Association Data. JNCI Cancer Spectrum, 2020, 4 (5), pkaa039. ⟨10.1093/jncics/pkaa039⟩. ⟨hal-03833310⟩