Translating Biospectroscopy Techniques to Clinical Settings: A New Paradigm in Point-of-Care Screening and/or Diagnostics

Vibrational spectroscopy coupled with machine learning sheds light on the cellular effects induced by rationally designed TLR4 agonists

In this work, we present the potential of Fourier transform infrared (FTIR) microspectroscopy to compare on whole cells, in an unbiased and untargeted way, the capacity of bacterial lipopolysaccharide (LPS) and two rationally designed molecules (FP20 and FP20Rha) to activate molecular circuits of innate immunity. These compounds are important drug hits in the development of vaccine adjuvants and tumor immunotherapeutics. The biological assays indicated that FP20Rha was more potent than FP20 in inducing cytokine production in cells and in stimulating IgG antibody production post-vaccination in mice. Accordingly, the overall significant IR spectral changes induced by the treatment with LPS and FP20Rha were similar, lipids and glycans signals being the most diagnostic, while the effect of the less potent molecule FP20 on cells resulted to be closer to control untreated cells. We propose here the use of FTIR spectroscopy supported by artificial intelligence (AI) to achieve a more holistic understanding of the cell response to new drug candidates while screening them in cells.

Near-Infrared Spectroscopy with Supervised Machine Learning as a Screening Tool for Neutropenia

The use of non-invasive tools in conjunction with artificial intelligence (AI) to detect diseases has the potential to revolutionize healthcare. Near-infrared spectroscopy (NIR) is a technology that can be used to analyze biological samples in a non-invasive manner. This study evaluated the use of NIR spectroscopy in the fingertip to detect neutropenia in solid-tumor oncologic patients. A total of 75 patients were enrolled in the study. Fingertip NIR spectra and complete blood counts were collected from each patient. The NIR spectra were pre-processed using Savitzky-Golay smoothing and outlier detection. The pre-processed data were split into training/validation and test sets using the Kennard-Stone method. A toolbox of supervised machine learning classification algorithms was applied to the training/validation set using a stratified 5-fold cross-validation regimen. The algorithms included linear discriminant analysis (LDA), logistic regression (LR), random forest (RF), multilayer perceptron (MLP), and support vector machines (SVMs). The SVM model performed best in the validation step, with 85% sensitivity, 89% negative predictive value (NPV), and 64% accuracy. The SVM model showed 67% sensitivity, 82% NPV, and 57% accuracy on the test set. These results suggest that NIR spectroscopy in the fingertip, combined with machine learning methods, can be used to detect neutropenia in solid-tumor oncology patients in a non-invasive and timely manner. This approach could help reduce exposure to invasive tests and prevent neutropenic patients from inadvertently undergoing chemotherapy.