Machine learning models based on routinely sampled blood tests can predict the presence of malignancy amongst patients with suspected musculoskeletal malignancy

Bentick, Kieran; Runevic, Joel; Akula, Sriram; Kyriacou, Theocharis; Cool, Paul; Andras, Peter

Abstract

This study explores the possibility of using routinely taken blood tests in the diagnosis and triage of patients with suspected musculoskeletal malignancy. A retrospective study was performed on results of patients who had presented for assessment to a regional musculoskeletal tumour unit. Blood results of patients with a histologically confirmed diagnosis between 2010 and 2020 were retrieved. 33 distinct blood tests were available for model forming. Results were standardised by calculating z-scores. Data were split into a training set (70%) and a test set (30%). The training set was balanced by resampling underrepresented classes. The random forest algorithm performed best and was selected for model forming. Receiver operating characteristic curves were used to find the optimum threshold. Models were calibrated and performance metrics evaluated with confusion tables. 2371 patients formed the study population. 1080 had a malignant diagnosis in one of three categories: sarcoma, metastasis, or haematological malignancy. 1291 had a benign condition. Metastasis could be predicted with an accuracy of 79% (AUC 87%, sensitivity 79%, specificity 80% NPV 91%). Haematological malignancy accuracy 79% (AUC 81%, sensitivity 77%, specificity 79%, NPV 97%). Sarcoma accuracy 64% (AUC 73%, sensitivity 76%, specificity 61%, NPV 88%) and all malignancy accuracy 74% (AUC 80%, sensitivity 72%, specificity 75%, NPV 76%). Routinely performed blood tests can be useful in triage of musculoskeletal tumours and can be used to predict presence of musculoskeletal malignancy. [Abstract copyright: Copyright © 2023 The Author(s). Published by Elsevier Inc. All rights reserved.]

Citation

Bentick, K., Runevic, J., Akula, S., Kyriacou, T., Cool, P., & Andras, P. (2023). Machine learning models based on routinely sampled blood tests can predict the presence of malignancy amongst patients with suspected musculoskeletal malignancy. Methods, 220, 55-60. https://doi.org/10.1016/j.ymeth.2023.10.012

• Journal Article Type: Article
• Acceptance Date: Oct 26, 2023
• Online Publication Date: Nov 10, 2023
• Publication Date: 2023-12
• Deposit Date: Dec 4, 2023
• Publicly Available Date: Dec 4, 2023
• Journal: Methods
• Print ISSN: 1046-2023
• Electronic ISSN: 1095-9130
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 220
• Pages: 55-60
• DOI: https://doi.org/10.1016/j.ymeth.2023.10.012
• Keywords: Diagnosis, Machine Learning, Muscluloskeletal, Blood tests, Cancer