Diagnosing brain tumours by routine blood tests using machine learning

• Published in: Scientific reports Vol. 9; no. 1; pp. 14481 - 7
• Main Authors: Podnar, Simon, Kukar, Matjaž, Gunčar, Gregor, Notar, Mateja, Gošnjak, Nina, Notar, Marko
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 09.10.2019; Nature Publishing Group
• Subjects: 692/53/2421; 692/617/375/1922; Adolescent; Adult; Aged; Aged, 80 and over; Algorithms; Artificial intelligence; Blood; Blood tests; Brain cancer; Brain Neoplasms - blood; Brain Neoplasms - diagnosis; Brain tumors; Case-Control Studies; Diagnosis; Diagnosis, Computer-Assisted; Female; Hematologic Tests - statistics & numerical data; Humanities and Social Sciences; Humans; Learning algorithms; Machine Learning; Male; Middle Aged; multidisciplinary; Neuroimaging; Neurological diseases; Prediction models; Retrospective Studies; Science; Science (multidisciplinary); Sensitivity and Specificity; Tumors; Young Adult
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-019-51147-3

Routine blood test results are assumed to contain much more information than is usually recognised even by the most experienced clinicians. Using routine blood tests from 15,176 neurological patients we built a machine learning predictive model for the diagnosis of brain tumours. We validated the model by retrospective analysis of 68 consecutive brain tumour and 215 control patients presenting to the neurological emergency service. Only patients with head imaging and routine blood test data were included in the validation sample. The sensitivity and specificity of the adapted tumour model in the validation group were 96% and 74%, respectively. Our data demonstrate the feasibility of brain tumour diagnosis from routine blood tests using machine learning. The reported diagnostic accuracy is comparable and possibly complementary to that of imaging studies. The presented machine learning approach opens a completely new avenue in the diagnosis of these grave neurological diseases and demonstrates the utility of valuable information obtained from routine blood tests.