Unlocking Preclinical Alzheimer's: A Multi-Year Label-Free In Vitro Raman Spectroscopy Study Empowered by Chemometrics.

Alzheimer's disease is a progressive neurodegenerative disorder, the early detection of which is crucial for timely intervention and enrollment in clinical trials. However, the preclinical diagnosis of Alzheimer's encounters difficulties with gold-standard methods. The current definitive diagnosis of Alzheimer's still relies on expensive instrumentation and post-mortem histological examinations. Here, we explore label-free Raman spectroscopy with machine learning as an alternative to preclinical Alzheimer's diagnosis. A special feature of this study is the inclusion of patient samples from different cohorts, sampled and measured in different years. To develop reliable classification models, partial least squares discriminant analysis in combination with variable selection methods identified discriminative molecules, including nucleic acids, amino acids, proteins, and carbohydrates such as taurine/hypotaurine and guanine, when applied to Raman spectra taken from dried samples of cerebrospinal fluid. The robustness of the model is remarkable, as the discriminative molecules could be identified in different cohorts and years. A unified model notably classifies preclinical Alzheimer's, which is particularly surprising because of Raman spectroscopy's high sensitivity regarding different measurement conditions. The presented results demonstrate the capability of Raman spectroscopy to detect preclinical Alzheimer's disease for the first time and offer invaluable opportunities for future clinical applications and diagnostic methods.

Gaussian Beam Shaping and Multivariate Analysis in Plasmonic Sensing.

This work demonstrates a novel strategy to improve the sensing performance of a prism-coupled surface plasmon resonance system by Gaussian beam shaping and multivariate data analysis. The propagation of the beam along the optical system has been studied using the Gaussian beam approximation to design the incident beam such that the beam waist is aligned precisely and that stability is assured at the metal-dielectric interface. This renders a collimated incident beam, hence least angular dispersion, yielding a stronger and sharper plasmonic resonance. Moreover, we use the multivariate analysis method partial least squares that combines multiple features of the surface plasmon resonance curve and allows for a more precise analysis of the plasmonic response. Compared to univariate analysis, partial least squares improves typical sensing performance parameters remarkably. The combination of both aspects, beam shaping and multivariate analysis, overcomes current limitations of plasmonic detection systems. Thereby, we improve analytical sensitivity by a factor of 16, decrease the prediction error of the concentration of an unknown analyte by a factor of 11, and enhance resolution to the order of 5 × 10-7 RIU in angular interrogation.

Optical Single Cell Resolution Cytotoxicity Biosensor Based on Single Cell Adhesion Dot Arrays.

Low cost, easy to use cell viability tests are needed in the pharmaceutical, biomaterial, and environmental industries to measure adverse cellular effects. We present a new methodology to track cell death with high resolution. Adherent cells commonly detach from the surface when they die, but some toxic compounds promote cell adhesion. A methodology that enables both dynamic detachment monitoring but also rapid detection of toxic effects of compounds that promote cell adhesion would constitute a step forward toward high-throughput cytotoxicity measurements. We achieved dynamic digital quantification of cell viability by simple optical imaging using "single cell adhesion dot arrays" (SCADA), fibronectin (FN) dot arrays designed to accommodate a single cell on each fibronectin dot. For cytotoxicity measurements, cell-filled SCADA substrates were exposed to K2CrO4, HgSO4 salts, and dimethyl sulfoxide (DMSO). The toxic effect of DMSO and K2CrO4 was dynamically monitored by measuring the cell detachment rate during more than 30 h by quantifying the number of occupied dots in the SCADA array. HgSO4 inhibited cellular detachment from the surface, and cytotoxicity was monitored using the trypan blue life/death assay directly on the surface. In all cases, the cytotoxicity effects were easily monitored with single cell resolution, and the results were comparable to previous reports. SCADA enabled dynamic measurements at the highest resolution due to the digital measuring in this method. The integration of SCADA substrates into microfluidic platforms will provide a practical tool that will extend to fundamental research and commercial applications.

Amplifying Sensing Capabilities: Combining Plasmonic Resonances and Fresnel Reflections through Multivariate Analysis.

Multivariate analysis applied in biosensing greatly improves analytical performance by extracting relevant information or bypassing confounding factors such as nonlinear responses or experimental errors and noise. Plasmonic sensors based on various light coupling mechanisms have shown impressive performance in biosensing by detecting dielectric changes with high sensitivity. In this study, gold nanodiscs are used as metasurface in a Kretschmann setup, and a variety of features from the reflectance curve are used by machine learning to improve sensing performance. The nanostructures of the metasurface generate new plasmonic features, apart from the typical resonance that occurs in the classical Kretschmann mode of a gold thin film, related to the evanescent field beyond total internal reflection. When the engineered metasurface is integrated into a microfluidic chamber, the device provides additional spectral features generated by Fresnel reflections at all dielectric interfaces. The increased number of features results in greatly improved detection. Here, multivariate analysis enhances analytical sensitivity and sensor resolution by 200% and more than 20%, respectively, and reduces prediction errors by almost 40% compared to a standard plasmonic sensor. The combination of plasmonic metasurfaces and Fresnel reflections thus offers the possibility of improving sensing capabilities even in commonly available setups.

The importance of choosing a proper validation strategy in predictive models. A tutorial with real examples.

Machine learning is the art of combining a set of measurement data and predictive variables to forecast future events. Every day, new model approaches (with high levels of sophistication) can be found in the literature. However, less importance is given to the crucial stage of validation. Validation is the assessment that the model reliably links the measurements and the predictive variables. Nevertheless, there are many ways in which a model can be validated and cross-validated reliably, but still, it may be a model that wrongly reflects the real nature of the data and cannot be used to predict external samples. This manuscript shows in a didactical manner how important the data structure is when a model is constructed and how easy it is to obtain models that look promising with wrong-designed cross-validation and external validation strategies. A comprehensive overview of the main validation strategies is shown, exemplified by three different scenarios, all of them focused on classification.