A recent study used visible-near-infrared spectroscopy (vis-NIR) to improve quantification of white blood cells.
The accurate quantification of white blood cells is important because it is an indicator how well humans and animals can fight off bacterial infections and other illnesses.
Hematologists are highly specialized healthcare providers that study blood and blood disorders (2). Along with studying blood and blood components, they also can study bone marrow and bone marrow cells (2). Generally, hematologists are the ones that diagnose patients with blood-clotting disorders. Some of the tests that hematologists run on their patients includes white blood cell count (WBC), red blood cell count (RBC), platelet count, and hemoglobin concentration, which is the oxygen-carrying protein in red blood cells (2).
A background depicting white blood cells in action, symbolizing immune defense, with a palette of white, soft blues, and pale greens. Clinical look. Generated with AI. | Image Credit: © png-jpeg-vector - stock.adobe.com
Quantifying WBC count is an indicator of how organisms can defend against invading organisms (3). Recently, a team of researchers from institutions from Portugal, led by Rui Costa Martins, proposed a novel approach to the accurate quantification of WBCs in blood samples using advanced spectral analysis techniques (1).
Martins and the team introduced a technology that leverages spectral point-of-care methods that are both reagentless and capable of real-time analysis with minimal sample volumes of less than 10 μL (1). One of the issues in hematology is the lack of spectral information of white blood cells in blood. Despite their relatively low concentration, WBCs can account for between 0.5% and 22.5% of the spectral information because of their scattering and absorbance characteristics (1).
By hybridizing 94 real-world blood samples into 300 synthetic data samples, the research team was able to expand the spectral information available for analysis. Using this approach allowed them to unscramble the specific spectral signatures of WBCs from the composite blood spectra (1). The synthetic data samples proved to be highly representative of real-world conditions, facilitating detailed spectral analysis and achieving correlations (Pearson correlation [R]) between 0.7975 and 0.8397, with a mean absolute error ranging from 32.25% to 34.13% (1).
The researchers also showed how efficient their method was. They achieved a diagnostic efficiency accuracy level between 83–100% within the reference interval of 5.5 to 19.5 × 109 cells/L (1). In cases with extremely high white blood cell counts, the diagnostic efficiency remained robust at 85.11% (1). Compared to current hematology analyzers used in veterinary medicine, the results achieved in this study either match or exceed what current analyzers can deliver (1).
The unique aspect to this study is how WBCs were quantified. In their study, the research team used covariance mode (CovM) levels between RBCs and WBCs to do so. By utilizing orthogonal information on RBCs, the researchers maximized the sensitivity and specificity of WBC detection, avoiding the pitfalls of non-specific natural correlations present in the data set (1). This approach significantly enhanced the specificity of WBC spectral information, making the quantification process more accurate (1).
The development of high-specificity, reagentless spectral point-of-care (POC) technology could revolutionize hematology diagnostics in veterinary medicine (1). The miniaturized nature of the technology makes it suitable for POC settings, enabling rapid and accurate diagnostics without the need for extensive laboratory infrastructure (1).
By overcoming the challenges associated with the non-dominance of WBCs in blood samples and leveraging innovative data augmentation techniques, the team has developed a highly specific and accurate spectral point-of-care technology, which can potentially improve diagnostic capabilities in veterinary medicine and improve the health and well-being of animals.
(1) Barroso, T. G.; Quieros, C.; Monteiro-Silva, F.; et al. Reagentless Vis-NIR Spectroscopy Point-of-Care for Feline Total White Blood Cell Counts. Biosensors 2024, 14 (1), 53. DOI: 10.3390/bios14010053
(2) Johns Hopkins Medicine, Hematology. Hopkins Medicine. Available at: https://www.hopkinsmedicine.org/health/treatment-tests-and-therapies/hematology (accessed 2024-07-24).
(3) Cotter, S. M. White Blood Cells in Animals. Merck Veterinary Manual. Available at: https://www.merckvetmanual.com/circulatory-system/hematopoietic-system-introduction/white-blood-cells-in-animals (accessed 2024-07-24).
Best of the Week: AI, Rapid Food Analysis, Agriculture Analysis, and Soil Property Prediction
September 6th 2024Top articles published this week include a review article on the latest research in agriculture analysis, a peer-reviewed article on near-infrared (NIR) spectroscopy, and an interview about using fluorescence spectroscopy in cheese ripening.
AI-Powered Spectroscopy Faces Hurdles in Rapid Food Analysis
September 4th 2024A recent study reveals on the challenges and limitations of AI-driven spectroscopy methods for rapid food analysis. Despite the promise of these technologies, issues like small sample sizes, misuse of advanced modeling techniques, and validation problems hinder their effectiveness. The authors suggest guidelines for improving accuracy and reliability in both research and industrial settings.
Non-Linear Memory-Based Learning Advances Soil Property Prediction Using vis-NIR Spectral Data
September 3rd 2024Researchers from Zhejiang University have developed a new non-linear memory-based learning (N-MBL) model that enhances the prediction accuracy of soil properties using visible near-infrared (vis-NIR) spectroscopy. By comparing N-MBL with traditional machine learning and local modeling methods, the study reveals its superior performance, particularly in predicting soil organic matter and total nitrogen.
Measuring Muscle Oxidation in Athletes with Near-Infrared Spectroscopy
September 2nd 2024A recent article authored by scientists from the Institute of Sport and Preventive Medicine, part of the University of Saarland (Saarbrücken, Germany), discusses their investigation of the absolute and relative test-retest reliability of the Moxy Monitor, as well as their investigations into side differences of oxygen saturation at the vastus lateralis muscle of both legs in male cyclists.