Ensemble of Heterogeneous Machine Learning Models with Multiple Inputs for Multi-Omics Analysis
文献类型： 会议论文
第一作者： Eleftherios Trivizakis
作者： Eleftherios Trivizakis 1 ; Vassilis Koutoulidis 2 ; Lia A. Moulopoulos 2 ; Evangelos Terpos 3 ; Ioannis Ntanasis-Stathopoulos 3 ; Panagiotis Malandrakis 3 ; Panagiotis Grigoropoulos 2 ; Panagiotis Papadopoulos 2 ; Katerina Nikiforaki 1 ; Kostas Marias 1 ; Nickolas Papanikolaou 4 ;
作者机构： 1.Foundation for Research and Technology – Hellas, Heraklion, Greece
2.1st Department of Radiology, School of Medicine, Aretaieion Hospital, National Kapodistrian University of Athens, Athens, Greece
3.Department of Clinical Therapeutics, School of Medicine, National and Kapodistrian University of Athens, Athens, Greece
4.Computational Clinical Imaging Group, Centre of the Unknown, Champalimaud Foundation, Lisbon, Portugal
关键词： Biological system modeling;Transfer learning;Genomics;Medical services;Plasmas;Ensemble learning;Neoplasms
会议名称： IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology
主办单位：
页码： 187-188
摘要： Multiple myeloma is a plasma cell neoplasm with genetic complexity that originates in pre-malignant stages due to genomic alterations, leading to malignant plasma cell proliferation. The completeness of data is significantly affecting multi-omics studies since the more sources included in the analysis, the more likely it is for key data to be missing. In this study, an ensemble meta-model that uses transfer learning from multiple single-source models was developed to assess the progression of multiple myeloma by leveraging radiocytogenetics. The proposed meta-model achieved the highest performance with an AUC of 0.75±0.07 and a SP of 0.84±0.02 among other single-source and radiocytogenetic models.Clinical Relevance: This study expands the current ensemble methods by allowing the combination of pre-trained machine learning models with multiple inputs for MM radiocytogenetics.
分类号： r318-53
- 相关文献
[1]Genome sequencing of the sweetpotato whitefly Bemisia tabaci MED/Q. Yang, Zezhong,Guo, Litao,Yang, Xin,Wen, Yanan,Zeng, Yang,Liu, Yating,Xia, Jixing,Tian, Lixia,Wu, Qingjun,Wang, Shaoli,Xu, Baoyun,Zhang, Youjun,Chen, Chunhai,Wang, Dan,Chen, Ming,Huang, Jinqun,Zhao, Jinyang,Gao, Qiang,Xia, Jinquan,Yin, Ye,Zhou, Xuguo (Joe),Li, Xianchun,Brown, Judith K.,Tan, Xinqiu,Liu, Yong,Ghanim, Murad,Qiu, Baoli,Pan, Huipeng,Chu, Dong,Delatte, Helene,Maruthi, M. N.,Ge, Feng,Zhou, Xueping,Wan, Fanghao,Wang, Xiaowei,Du, Yuzhou,Du, Yuzhou,Luo, Chen,Yan, Fengming,Preisser, Evan L.,Jiao, Xiaoguo,Coates, Brad S.. 2017
作者其他论文 更多>>
-
Fully Automated Detection and Segmentation Pipeline for the Bone Marrow of the Lytic Bone of Multiple Myeloma Patients
作者：Nickolas Papanikolaou;Dimitrios I. Fotiadis;Kostas Marias;Emmanouil Koutoulakis;Eleftherios Trivizakis;Vassilis Koutoulidis;Lia A. Moulopoulos;Evangelos Terpos;Ioannis Ntanasis-Stathopoulos;Panagiotis Malandrakis;Panagiotis Grigoropoulos;Panagiotis Papadopoulos;Katerina Nikiforaki
关键词：Patient monitoring;Pipelines;Medical treatment;Bones;Robustness;Lesions;Task analysis
