Non-linear machine learning with sample perturbation augments leukemia relapse prognostics from single-cell proteomics measurements

• Published in: Advances in computational intelligence Vol. 4; no. 4; p. 11
• Main Author: Lo, Yu-Chen
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.12.2024; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Blood; Classification; Computational Intelligence; Data augmentation; Datasets; Engineering; Leukemia; Leukocytes; Linearity; Machine Learning; Medical prognosis; Original Article; Patients; Perturbation; Physiology; Proteomics; Regression analysis; Single-cell analysis; Leukemia; Machine learning
• ISSN: 2730-7794; 2730-7808
• DOI: 10.1007/s43674-024-00078-2

Developing accurate and robust prognostic prediction for classifying the risks of acute lymphoblastic leukemia (ALL) relapse is critical for patient treatment management and survival. However, the lack of clinical samples and linearity assumption remains a significant clinical challenge for achieving high accuracy for single-cell prognostics. Here, we explore the use of non-linear machine learning models with ex vivo sample perturbation as a data augmentation strategy to improve ALL relapse prediction. We hypothesize that treating each sample with ex vivo perturbation can be viewed as independent measurements, thus increasing the number of available observations for machine learning. We show that ex vivo sample stimulation combined with non-linear machine learning significantly improves the performance of ALL risk stratification from limited single-cell proteomic data.