Integrating classifiers across datasets improves consistency of biomarker predictions for sepsis

详细信息    查看全文

• 作者：Joã ; o Pedro Saraiva¹ ; ² ; Marcus Oswald¹ ; ² ; Antje Biering¹ ; ² ; Cora Assmann³ ; Tilman Klassert³ ; Markus Blaess² ; Kristin Czakai⁴ ; Ralf Claus² ; Jü ; rgen L&ouml ; ffler⁴ ; Hortense Slevogt³ ; Rainer K&ouml ; nig¹ ; ² ; ^{rainerkoenig@uni-jena.de}
• 关键词：Machine Learning ; Consistency ; Biomarker ; Feature Selection ; Sepsis ; Infection
• 刊名：IFAC-PapersOnLine
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：49
• 期：26
• 页码：95-102
• 全文大小：623 K
• 卷排序：49

文摘

Systemic infection can cause multiple organ failure leading to severe sepsis and often death. Hence, early diagnosis is mandatory. Several transcriptomics studies were performed resulting in biomarker lists for diagnosis. This lists, however are very inconsistent. We developed Mixed Integer Linear Programming based classifiers (Support Vector Machines), trained them separately with different datasets, and combined them by constraining them to use the same sets of features. Strikingly, this improved the consistency of the predicted biomarkers across datasets by 42%. Our approach is generic; it enabled to integrate diverse datasets and, with this, improved the consistency of predictions.