Machine Learning Enhanced Optical Spectroscopy for Disease Detection

Machine learning-driven Raman spectroscopy: A novel approach to lipid profiling in diabetic kidney disease

Diabetes mellitus is a chronic metabolic disease that increasingly affects people every year. It is known that with its progression and poor management, metabolic changes can lead to organ dysfunctions, including kidneys. The study aimed to combine Raman spectroscopy and biochemical lipid profiling, complemented by machine learning (ML) techniques to evaluate chemical composition changes in kidneys induced by Type 2 Diabetes mellitus (T2DM). Raman spectroscopy identified significant differences in lipid content and specific molecular vibrations, with the 1777 cm-1 band emerging as a potential spectroscopic marker for diabetic kidney damage. The integration of ML algorithms improved the analysis, providing high accuracy, selectivity, and specificity in detecting these changes. Moreover, lipids metabolic profiling revealed distinct variations in the concentration of 11 phosphatydylocholines and 9 acyl-alkylphosphatidylcholines glycerophospholipids. Importantly, the correlation between Raman data and lipids metabolic profiling differed for control and T2DM groups. This study underscores the combined power of Raman spectroscopy and ML in offering a low-cost, fast, precise, and comprehensive approach to diagnosing and monitoring diabetic nephropathy, paving the way for improved clinical interventions. However, taking into account small number of data related to ethical committee approvals, the study should be verified on a larger number of cases.

Rapid diagnosis of latent and active pulmonary tuberculosis by autofluorescence spectroscopy of blood plasma combined with artificial neural network algorithm

The existing clinical diagnostic methods of pulmonary tuberculosis (TB) usually have some of the following limitations, such as time-consuming, invasive, radioactive, insufficiently sensitive and accurate. This study demonstrates the possibility of using blood plasma autofluorescence spectroscopy and Artificial Neural Network (ANN) algorithm for the rapid and accurate diagnosis of latent and active pulmonary TB from healthy subjects. The fluorescence spectra of blood plasma from 18 healthy volunteers, 12 individuals with latent TB infections and 80 active TB patients are measured and analyzed. By optimizing the ANN structure and activation functions, the ANN three-classification model achieves average classification accuracy of 96.3 %, and the accuracy of healthy persons, latent TB infections and active TB patients are 100 %, 83.3 % and 97.5 %, respectively, which is much better than the results of traditional Principal component analysis (PCA) and Linear discriminant analysis (LDA) method. To the best of our knowledge, this is the first research work of differentiating latent, active pulmonary TB cases from healthy samples with autofluorescence spectroscopy. As a rapid, accurate, safe, label-free, non-invasive and cost-effective technique, it can be developed as a promising diagnostic tool for the screening of pulmonary TB disease in the early stage.

Ensemble learning prediction framework for EGFR amplification status of glioma based on terahertz spectral features

Epidermal growth factor receptor (EGFR) plays a pivotal role in the initiation and progression of gliomas. In particular, in glioblastoma, EGFR amplification emerges as a catalyst for invasion, proliferation, and resistance to radiotherapy and chemotherapy. Current approaches are not capable of providing rapid diagnostic results of molecular pathology. In this study, we propose a terahertz spectroscopic approach for predicting the EGFR amplification status of gliomas for the first time. A machine learning model was constructed using the terahertz response of the measured glioma tissues, including the absorption coefficient, refractive index, and dielectric loss tangent. The novelty of our model is the integration of three classical base classifiers, i.e., support vector machine, random forest, and extreme gradient boosting. The ensemble learning method combines the advantages of various base classifiers, this model has more generalization ability. The effectiveness of the proposed method was validated by applying an individual test set. The optimal performance of the integrated algorithm was verified with an area under the curve (AUC) maximum of 85.8 %. This signifies a significant stride toward more effective and rapid diagnostic tools for guiding postoperative therapy in gliomas.

Revolutionary approaches for cancer diagnosis by terahertz-based spectroscopy and imaging

Most tumors are easily missed and misdiagnosed due to the lack of specific clinical signs and symptoms in the early stage. Thus, an accurate, rapid and reliable early tumor detection method is highly desirable. The application of terahertz (THz) spectroscopy and imaging in biomedicine has made remarkable progress in the past two decades, which addresses the shortcomings of existing technologies and provides an alternative for early tumor diagnosis. Although issues such as size mismatch and strong absorption of THz waves by water have set hurdles for cancer diagnosis by THz technology, innovative materials and biosensors in recent years have led to possibilities for new THz biosensing and imaging methods. In this article, we reviewed the issues that need to be solved before THz technology is used for tumor-related biological sample detection and clinical auxiliary diagnosis. We focused on the recent research progress of THz technology, with an emphasis on biosensing and imaging. Finally, the application of THz spectroscopy and imaging for tumor diagnosis in clinical practice and the main challenges in this process were also mentioned. Collectively, THz-based spectroscopy and imaging reviewed here is envisioned as a cutting-edge approach for cancer diagnosis.

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

Surface-enhanced Raman spectroscopy/scattering (SERS) has evolved into a popular tool for applications in biology and medicine owing to its ease-of-use, non-destructive, and label-free approach. Advances in plasmonics and instrumentation have enabled the realization of SERS's full potential for the trace detection of biomolecules, disease diagnostics, and monitoring. We provide a brief review on the recent developments in the SERS technique for biosensing applications, with a particular focus on machine learning techniques used for the same. Initially, the article discusses the need for plasmonic sensors in biology and the advantage of SERS over existing techniques. In the later sections, the applications are organized as SERS-based biosensing for disease diagnosis focusing on cancer identification and respiratory diseases, including the recent SARS-CoV-2 detection. We then discuss progress in sensing microorganisms, such as bacteria, with a particular focus on plasmonic sensors for detecting biohazardous materials in view of homeland security. At the end of the article, we focus on machine learning techniques for the (a) identification, (b) classification, and (c) quantification in SERS for biology applications. The review covers the work from 2010 onwards, and the language is simplified to suit the needs of the interdisciplinary audience.