Serum Fourier-Transform Infrared Spectroscopy with Machine Learning for Screening of Pediatric Acute Lymphoblastic...

Area of Science:

• Biochemistry
• Medical Diagnostics
• Spectroscopy

Background:

• Acute lymphoblastic leukemia (ALL) is the most common childhood cancer.
• Current diagnostic methods, such as bone marrow procedures, are invasive and costly.
• There is a need for non-invasive, rapid, and cost-effective diagnostic tools for pediatric ALL.

Purpose of the Study:

• To investigate the potential of Fourier-transform infrared (FTIR) spectroscopy for diagnosing pediatric ALL.
• To identify spectral differences in serum between ALL patients and healthy controls.
• To assess the diagnostic performance of FTIR spectroscopy in distinguishing ALL from controls.

Main Methods:

• Serum samples from 103 participants (45 ALL patients, 58 controls) were analyzed using FTIR spectroscopy.
• Spectra were preprocessed, and statistical analyses, including logistic regression and cross-validation, were performed.
• Receiver operating characteristic (ROC) and precision-recall (PR) analyses were conducted to evaluate performance.

Main Results:

• Distinct spectral alterations were observed between ALL patients and controls, particularly in amide and lipid regions.
• Logistic regression achieved an area under the curve (AUC) of approximately 0.80, with sensitivity ranging from 0.73-0.84.
• Principal component analysis (PCA) and hierarchical cluster analysis (HCA) showed partial but consistent group separation.

Conclusions:

• Serum FTIR spectroscopy demonstrates potential for distinguishing pediatric ALL from controls.
• The technique reflects disease-related metabolic changes and is rapid, label-free, and requires minimal serum.
• Further validation in larger, multi-center studies is necessary before clinical implementation.