Computational analysis of continuous body temperature provides early discrimination of graft-versus-host disease in mice

Blood Adv. 2019 Dec 10;3(23):3977-3981. doi: 10.1182/bloodadvances.2019000613.

Kuang He¹, Zhenke Wu^{2

3

4}, Hideaki Fujiwara¹, Steven Whitesall⁵, Cynthia K Zajac¹, Sung Won Choi⁶, Pavan Reddy¹, Muneesh Tewari^{1

7

8

9}

¹ Division of Hematology and Oncology, Department of Internal Medicine, Comprehensive Cancer Center.
² Department of Biostatistics.
³ Michigan Institute for Data Science.
⁴ Quantitative Methodology Program, Survey Research Center of Institute for Social Research.
⁵ Physiology Phenotyping Core.
⁶ Department of Pediatrics and Communicable Diseases.
⁷ Center for Computational Medicine and Bioinformatics.
⁸ Department of Biomedical Engineering, and.
⁹ Biointerfaces Institute, University of Michigan, Ann Arbor, MI.

Abstract

Unsupervised machine learning analysis of continuous body temperature data revealed early signals of aGVHD in allo-HCT mice.
Continuous measurement of body temperature is promising for early prediction of aGVHD in human allo-HCT patients.