Stratifying Brain Tumour Histological Sub-Types: The Application of ATR-FTIR Serum Spectroscopy in Secondary Care

Machine learning assisted rapid approach for quantitative prediction of biochemical parameters of blood serum with FTIR spectroscopy

This study develops regression models for predicting blood biochemical data using Fourier-transform infrared spectroscopy (FTIR) analysis. Absorption at specific wavelengths of blood serum is revealed to have strong correlations with biochemical parameters, such as ALT, amylase, AST, protein, bilirubin, Gamma-GT, iron, calcium, uric acid, triglycerides, phosphatase and cholesterol, were shown. The results consistently demonstrate that Random Forest Regression outperforms other models, delivering impressive outcomes for the majority of the analyzed parameters. For some parameters we obtained a coefficient of determination of 0.95 and more (amylase, AST, iron, calcium, protein, uric acid and cholesterol), which makes this approach to be applicable in clinical diagnostics. These findings highlight the potential of FTIR analysis combined with regression models for precise assessment of blood biochemistry.

Decoding myasthenia gravis: advanced diagnosis with infrared spectroscopy and machine learning

Myasthenia Gravis (MG) is a rare neurological disease. Although there are intensive efforts, the underlying mechanism of MG still has not been fully elucidated, and early diagnosis is still a question mark. Diagnostic paraclinical tests are also time-consuming, burden patients financially, and sometimes all test results can be negative. Therefore, rapid, cost-effective novel methods are essential for the early accurate diagnosis of MG. Here, we aimed to determine MG-induced spectral biomarkers from blood serum using infrared spectroscopy. Furthermore, infrared spectroscopy coupled with multivariate analysis methods e.g., principal component analysis (PCA), support vector machine (SVM), discriminant analysis and Neural Network Classifier were used for rapid MG diagnosis. The detailed spectral characterization studies revealed significant increases in lipid peroxidation; saturated lipid, protein, and DNA concentrations; protein phosphorylation; PO2-asym + sym /protein and PO2-sym/lipid ratios; as well as structural changes in protein with a significant decrease in lipid dynamics. All these spectral parameters can be used as biomarkers for MG diagnosis and also in MG therapy. Furthermore, MG was diagnosed with 100% accuracy, sensitivity and specificity values by infrared spectroscopy coupled with multivariate analysis methods. In conclusion, FTIR spectroscopy coupled with machine learning technology is advancing towards clinical translation as a rapid, low-cost, sensitive novel approach for MG diagnosis.

OralEpitheliumDB: A Dataset for Oral Epithelial Dysplasia Image Segmentation and Classification

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia, is the most reliable way to prevent oral cancer. Computational algorithms have been used as an auxiliary tool to aid specialists in this process. Usually, experiments are performed on private data, making it difficult to reproduce the results. There are several public datasets of histological images, but studies focused on oral dysplasia images use inaccessible datasets. This prevents the improvement of algorithms aimed at this lesion. This study introduces an annotated public dataset of oral epithelial dysplasia tissue images. The dataset includes 456 images acquired from 30 mouse tongues. The images were categorized among the lesion grades, with nuclear structures manually marked by a trained specialist and validated by a pathologist. Also, experiments were carried out in order to illustrate the potential of the proposed dataset in classification and segmentation processes commonly explored in the literature. Convolutional neural network (CNN) models for semantic and instance segmentation were employed on the images, which were pre-processed with stain normalization methods. Then, the segmented and non-segmented images were classified with CNN architectures and machine learning algorithms. The data obtained through these processes is available in the dataset. The segmentation stage showed the F1-score value of 0.83, obtained with the U-Net model using the ResNet-50 as a backbone. At the classification stage, the most expressive result was achieved with the Random Forest method, with an accuracy value of 94.22%. The results show that the segmentation contributed to the classification results, but studies are needed for the improvement of these stages of automated diagnosis. The original, gold standard, normalized, and segmented images are publicly available and may be used for the improvement of clinical applications of CAD methods on oral epithelial dysplasia tissue images.

Innovation in Non-Invasive Diagnosis and Disease Monitoring for Meningiomas

Meningiomas are tumors of the central nervous system that vary in their presentation, ranging from benign and slow-growing to highly aggressive. The standard method for diagnosing and classifying meningiomas involves invasive surgery and can fail to provide accurate prognostic information. Liquid biopsy methods, which exploit circulating tumor biomarkers such as DNA, extracellular vesicles, micro-RNA, proteins, and more, offer a non-invasive and dynamic approach for tumor classification, prognostication, and evaluating treatment response. Currently, a clinically approved liquid biopsy test for meningiomas does not exist. This review provides a discussion of current research and the challenges of implementing liquid biopsy techniques for advancing meningioma patient care.

Complete characterization of RNA biomarker fingerprints using a multi-modal ATR-FTIR and SERS approach for label-free early breast cancer diagnosis

Breast cancer is a prevalent form of cancer worldwide, and the current standard screening method, mammography, often requires invasive biopsy procedures for further assessment. Recent research has explored microRNAs (miRNAs) in circulating blood as potential biomarkers for early breast cancer diagnosis. In this study, we employed a multi-modal spectroscopy approach, combining attenuated total reflection Fourier transform infrared (ATR-FTIR) and surface-enhanced Raman scattering (SERS) to comprehensively characterize the full-spectrum fingerprints of RNA biomarkers in the blood serum of breast cancer patients. The sensitivity of conventional FTIR and Raman spectroscopy was enhanced by ATR-FTIR and SERS through the utilization of a diamond ATR crystal and silver-coated silicon nanopillars, respectively. Moreover, a wider measurement wavelength range was achieved with the multi-modal approach than with a single spectroscopic method alone. We have shown the results on 91 clinical samples, which comprised 44 malignant and 47 benign cases. Principal component analysis (PCA) was performed on the ATR-FTIR, SERS, and multi-modal data. From the peak analysis, we gained insights into biomolecular absorption and scattering-related features, which aid in the differentiation of malignant and benign samples. Applying 32 machine learning algorithms to the PCA results, we identified key molecular fingerprints and demonstrated that the multi-modal approach outperforms individual techniques, achieving higher average validation accuracy (95.1%), blind test accuracy (91.6%), specificity (94.7%), sensitivity (95.5%), and F-score (94.8%). The support vector machine (SVM) model showed the best area under the curve (AUC) characterization value of 0.9979, indicating excellent performance. These findings highlight the potential of the multi-modal spectroscopy approach as an accurate, reliable, and rapid method for distinguishing between malignant and benign breast tumors in women. Such a label-free approach holds promise for improving early breast cancer diagnosis and patient outcomes.

Providing potential solutions by using FT-IR spectroscopy for biofluid analysis: Clinical impact of optical screening and diagnostic tests

BACKGROUND

Currently, the potential of FT-IR spectroscopy for rapid diagnosis of many pathologies has been demonstrated by numerous research studies including those targeting COVID-19 detection. However, the number of clinicians aware of this potential and who are willing to use spectroscopy in their clinics and hospitals is still negligible. In addition, lack of awareness creates a huge gap between clinicians and researchers involved in clinical translation of current FT-IR technology hence hindering initiatives to bring basic and applied research together for the direct benefit of patients.

METHODS

Knowledge and medical training on FT-IR on the side of clinicians should be one of the first steps to be able to integrate it into the list of complementary exams which may be requested by health professionals. Countless FT-IR applications could have a life-changing impact on patients' lives, especially screening and diagnostic tests involving biofluids such as blood, saliva and urine which are routinely non-invasively or minimally-invasively.

RESULTS

Blood may be the most difficult to obtain by the invasive method of collection, but much can be evaluated in its components, and areas such as hematology, infectiology, oncology and endocrinology can be directly benefited. Urine with a relatively simple collection method can provide pertinent information from the entire urinary system, including the actual condition of the kidneys. Saliva collection can be simpler for the patient and can provide information on diseases affecting the mouth and digestive system and can be used to diagnose diseases such as oral cancer in its early-stages. An unavoidable second step is the active involvement of industries to design robust and portable instruments for specific purposes, as the medical community requires user-friendly instruments of advanced computational algorithms. A third step resides in the legal situation involving the global use of the technique as a new diagnostic modality.

CONCLUSIONS

It is important to note that decentralized funds for variety of technologies hinders the training of clinical and medical professionals for the use of newly arising technologies and affect the engagement of these professionals with technology developers. As a result of decentralized funding, research efforts are spread out over a range of technologies which take a long time to get validated and translated to the clinic. Partnership over similar groups of technologies and efforts to test the same technologies while overcoming barriers posed to technology validation in different areas around the globe may benefit the clinical/medical, research and industry community globally.

Infrared Spectroscopy: A New Frontier in Hematological Disease Diagnosis

Hematological diseases, due to their complex nature and diverse manifestations, pose significant diagnostic challenges in healthcare. The pressing need for early and accurate diagnosis has driven the exploration of novel diagnostic techniques. Infrared (IR) spectroscopy, renowned for its noninvasive, rapid, and cost-effective characteristics, has emerged as a promising adjunct in hematological diagnostics. This review delves into the transformative role of IR spectroscopy and highlights its applications in detecting and diagnosing various blood-related ailments. We discuss groundbreaking research findings and real-world applications while providing a balanced view of the potential and limitations of the technique. By integrating advanced technology with clinical needs, we offer insights into how IR spectroscopy may herald a new era of hematological disease diagnosis.

Exploring the Steps of Infrared (IR) Spectral Analysis: Pre-Processing, (Classical) Data Modelling, and Deep Learning

Infrared (IR) spectroscopy has greatly improved the ability to study biomedical samples because IR spectroscopy measures how molecules interact with infrared light, providing a measurement of the vibrational states of the molecules. Therefore, the resulting IR spectrum provides a unique vibrational fingerprint of the sample. This characteristic makes IR spectroscopy an invaluable and versatile technology for detecting a wide variety of chemicals and is widely used in biological, chemical, and medical scenarios. These include, but are not limited to, micro-organism identification, clinical diagnosis, and explosive detection. However, IR spectroscopy is susceptible to various interfering factors such as scattering, reflection, and interference, which manifest themselves as baseline, band distortion, and intensity changes in the measured IR spectra. Combined with the absorption information of the molecules of interest, these interferences prevent direct data interpretation based on the Beer-Lambert law. Instead, more advanced data analysis approaches, particularly artificial intelligence (AI)-based algorithms, are required to remove the interfering contributions and, more importantly, to translate the spectral signals into high-level biological/chemical information. This leads to the tasks of spectral pre-processing and data modeling, the main topics of this review. In particular, we will discuss recent developments in both tasks from the perspectives of classical machine learning and deep learning.

Attenuated Total Reflection Fourier-Transform Infrared Spectral Discrimination in Human Tissue of Oesophageal Transformation to Adenocarcinoma

This study presents ATR-FTIR (attenuated total reflectance Fourier-transform infrared) spectral analysis of ex vivo oesophageal tissue including all classifications to oesophageal adenocarcinoma (OAC). The article adds further validation to previous human tissue studies identifying the potential for ATR-FTIR spectroscopy in differentiating among all classes of oesophageal transformation to OAC. Tissue spectral analysis used principal component analysis quadratic discriminant analysis (PCA-QDA), successive projection algorithm quadratic discriminant analysis (SPA-QDA), and genetic algorithm quadratic discriminant analysis (GA-QDA) algorithms for variable selection and classification. The variables selected by SPA-QDA and GA-QDA discriminated tissue samples from Barrett's oesophagus (BO) to OAC with 100% accuracy on the basis of unique spectral "fingerprints" of their biochemical composition. Accuracy test results including sensitivity and specificity were determined. The best results were obtained with PCA-QDA, where tissues ranging from normal to OAC were correctly classified with 90.9% overall accuracy (71.4-100% sensitivity and 89.5-100% specificity), including the discrimination between normal and inflammatory tissue, which failed in SPA-QDA and GA-QDA. All the models revealed excellent results for distinguishing among BO, low-grade dysplasia (LGD), high-grade dysplasia (HGD), and OAC tissues (100% sensitivities and specificities). This study highlights the need for further work identifying potential biochemical markers using ATR-FTIR in tissue that could be utilised as an adjunct to histopathological diagnosis for early detection of neoplastic changes in susceptible epithelium.

Infrared Spectroscopy as a Potential Diagnostic Tool for Medulloblastoma

INTRODUCTION

Medulloblastoma (MB) is the most common malignant tumor of the central nervous system in childhood. FTIR spectroscopy provides a holistic view of the chemical composition of biological samples, including the detection of molecules such as nucleic acids, proteins, and lipids. This study evaluated the applicability of FTIR spectroscopy as a potential diagnostic tool for MB.

MATERIALS AND METHODS

FTIR spectra of MB samples from 40 children (boys/girls: 31/9; age: median 7.8 years, range 1.5-21.5 years) treated in the Oncology Department of the Children's Memorial Health Institute in Warsaw between 2010 and 2019 were analyzed. The control group consisted of normal brain tissue taken from four children diagnosed with causes other than cancer. Formalin-fixed and paraffin-embedded tissues were sectioned and used for FTIR spectroscopic analysis. The sections were examined in the mid-infrared range (800-3500 cm^-1) by ATR-FTIR. Spectra were analysed using a combination of principal component analysis, hierarchical cluster analysis, and absorbance dynamics.

RESULTS

FTIR spectra in MB were significantly different from those of normal brain tissue. The most significant differences related to the range of nucleic acids and proteins in the region 800-1800 cm^-1. Some major differences were also revealed in the quantification of protein conformations (α-helices, β-sheets, and others) in the amide I band, as well as in the absorbance dynamics in the 1714-1716 cm^-1 range (nucleic acids). It was not, however, possible to clearly distinguish between the various histological subtypes of MB using FTIR spectroscopy.

CONCLUSIONS

MB and normal brain tissue can be distinguished from one another to some extent using FTIR spectroscopy. As a result, it may be used as a further tool to hasten and enhance histological diagnosis.

Recurrent neural networks for time domain modelling of FTIR spectra: application to brain tumour detection

A recurrent neural network trained on time domain data can accurately identify brain tumours from serum spectral data.

Identification of hepatocellular carcinoma and paracancerous tissue based on the peak area in FTIR microspectroscopy

Hepatocellular carcinoma (HCC) is one of the most common primary hepatic malignancies across the world. The annual incidence and death rates have increased at the highest rate of all cancers in recent years. Surgical resection is a potentially curative option for solitary HCC or unilobar disease without evidence of metastases or vascular invasion. This study focuses on the molecular differences between the HCC foci and paracancerous tissues and provides some valuable biomarkers based on the vibrational spectrum. Fourier transform infrared (FTIR) spectroscopy is a non-invasive and qualitative and semi-quantitative analysis technique that has been widely applied for the identification of macromolecular changes in biological tissues. In this study, the FTIR spectra of the HCC foci and the paracancerous tissues were recorded separately, and ten areas under the absorption peaks of all the specimens were calculated. The result demonstrates that the areas of protein-related absorption peaks at 1398 cm^-1, 1548 cm^-1, 1654 cm^-1 and 3070 cm^-1 may be the key indicators of the two different regions. After coupling with the classification algorithms of k-nearest neighbor (KNN), random forest (RF) and support vector machine (SVM), it was found that SVM with an RBF kernel performed best with the AUC (area under the ROC curve) reaching 0.997, and the performance was better than the feature based on the full spectrum. This reveals that the peak area-based FTIR spectra combined with the SVM algorithm may be a promising tool in identifying the HCC foci and the paracancerous tissues.

Rapid diagnosis of malignant pleural mesothelioma and its discrimination from lung cancer and benign exudative effusions using blood serum

Malignant pleural mesothelioma (MPM), an aggressive cancer associated with exposure to fibrous minerals, can only be diagnosed in the advanced stage because its early symptoms are also connected with other respiratory diseases. Hence, understanding the molecular mechanism and the discrimination of MPM from other lung diseases at an early stage is important to apply effective treatment strategies and for the increase in survival rate. This study aims to develop a new approach for characterization and diagnosis of MPM among lung diseases from serum by Fourier transform infrared spectroscopy (FTIR) coupled with multivariate analysis. The detailed spectral characterization studies indicated the changes in lipid biosynthesis and nucleic acids levels in the malignant serum samples. Furthermore, the results showed that healthy, benign exudative effusion, lung cancer, and MPM groups were successfully separated from each other by applying principal component analysis (PCA), support vector machine (SVM), and especially linear discriminant analysis (LDA) to infrared spectra.

ATR-IR Spectroscopy Application to Diagnostic Screening of Advanced Endometriosis

Endometriosis is one of the most common gynecological diseases among young women of reproductive age. Thus far, it has not been possible to define a parameter that is sensitive and specific enough to be a recognized biomarker for diagnosing this disease. Nonspecific symptoms of endometriosis and delayed diagnosis are impulses for researching noninvasive methods of differentiating endometriosis from other gynecological disorders. We compared three groups of individuals in our research: women with endometriosis (E), patients suffering from other gynecological disorders (nonendometriosis, NE), and healthy women from the control group (C). Partial least squares discriminant analysis (PLS-DA) models were developed based on selected serum biochemical parameters, specific regions of the serum’s infrared attenuated total reflectance (FTIR ATR) spectra, and combined data. Incorporating the spectral data into the models significantly improved differentiation among the three groups, with an overall accuracy of 87.5%, 97.3%, and 98.5%, respectively. This study shows that infrared spectroscopy and discriminant analysis can be used to differentiate serum samples among women with advanced endometriosis, women without this disease, i.e., healthy women, and, most importantly, also women with other benign gynecological disorders.

Clinical Spectroscopy: Lost in Translation?

This Focal Point Review paper discusses the developments of biomedical Raman and infrared spectroscopy, and the recent strive towards these technologies being regarded as reliable clinical tools. The promise of vibrational spectroscopy in the field of biomedical science, alongside the development of computational methods for spectral analysis, has driven a plethora of proof-of-concept studies which convey the potential of various spectroscopic approaches. Here we report a brief review of the literature published over the past few decades, with a focus on the current technical, clinical, and economic barriers to translation, namely the limitations of many of the early studies, and the lack of understanding of clinical pathways, health technology assessments, regulatory approval, clinical feasibility, and funding applications. The field of biomedical vibrational spectroscopy must acknowledge and overcome these hurdles in order to achieve clinical efficacy. Current prospects have been overviewed with comment on the advised future direction of spectroscopic technologies, with the aspiration that many of these innovative approaches can ultimately reach the frontier of medical diagnostics and many clinical applications.

Clinical validation of a spectroscopic liquid biopsy for earlier detection of brain cancer

Background

Diagnostic delays impact the quality of life and survival of patients with brain tumors. Earlier and expeditious diagnoses in these patients are crucial to reducing the morbidities and mortalities associated with brain tumors. A simple, rapid blood test that can be administered easily in a primary care setting to efficiently identify symptomatic patients who are most likely to have a brain tumor would enable quicker referral to brain imaging for those who need it most.

Methods

Blood serum samples from 603 patients were prospectively collected and analyzed. Patients either had non-specific symptoms that could be indicative of a brain tumor on presentation to the Emergency Department, or a new brain tumor diagnosis and referral to the neurosurgical unit, NHS Lothian, Scotland. Patient blood serum samples were analyzed using the Dxcover®Brain Cancer liquid biopsy. This technology utilizes infrared spectroscopy combined with a diagnostic algorithm to predict the presence of intracranial disease.

Results

Our liquid biopsy approach reported an area under the receiver operating characteristic curve of 0.8. The sensitivity-tuned model achieves a 96% sensitivity with 45% specificity (NPV 99.3%) and identified 100% of glioblastoma multiforme patients. When tuned for a higher specificity, the model yields sensitivity of 47% with 90% specificity (PPV 28.4%).

Conclusions

This simple, non-invasive blood test facilitates the triage and radiographic diagnosis of brain tumor patients, while providing reassurance to healthy patients. Minimizing time to diagnosis would facilitate identification of brain tumor patients at an earlier stage, enabling more effective, less morbid surgical and adjuvant care.

Grade diagnosis of human glioma using Fourier transform infrared microscopy and artificial neural network

The World Health Organization (WHO) grade diagnosis of cancer is essential for surgical outcomes and patient treatment. Traditional pathological grading diagnosis depends on dyes or other histological approaches, and the result interpretation highly relies on the pathologists, making the process time-consuming (>60 min, including the steps of dewaxing to water and H&E staining), resource-wasting, and labor-intensive. In the present study, we report an alternative workflow that combines the Fourier transform infrared (FTIR) microscopy and artificial neural network (ANN) to diagnose the grade of human glioma in a way that is faster (~20 min, including the processes of sample dewaxing, spectra acquisition and analysis), accurate (the prediction accuracy, specificity and sensitivity can reach above 99%), and without reagent. Moreover, this method is much superior to the common classification method of principal component analysis-linear discriminate analysis (PCA-LDA) (the prediction accuracy, specificity and sensitivity are only 87%, 89% and 86%, respectively). The ANN mainly learned the characteristic region of 800-1800 cm^-1 to classify the major histopathologic classes of human glioma. These results demonstrate that the grade diagnosis of human glioma by FTIR microscopy plus ANN can be streamlined, and could serve as a complementary pathway that is independent of the traditional pathology laboratory.

Synchrotron-Based Fourier-Transform Infrared Micro-Spectroscopy (SR-FTIRM) Fingerprint of the Small Anionic Molecule Cobaltabis(dicarbollide) Uptake in Glioma Stem Cells

The anionic cobaltabis (dicarbollide) [3,3'-Co(1,2-C2B9H11)2]-, [o-COSAN]-, is the most studied icosahedral metallacarborane. The sodium salts of [o-COSAN]- could be an ideal candidate for the anti-cancer treatment Boron Neutron Capture Therapy (BNCT) as it possesses the ability to readily cross biological membranes thereby producing cell cycle arrest in cancer cells. BNCT is a cancer therapy based on the potential of 10B atoms to produce α particles that cross tissues in which the 10B is accumulated without damaging the surrounding healthy tissues, after being irradiated with low energy thermal neutrons. Since Na[o-COSAN] displays a strong and characteristic ν(B-H) frequency in the infrared range 2.600-2.500 cm-1, we studied the uptake of Na[o-COSAN] followed by its interaction with biomolecules and its cellular biodistribution in two different glioma initiating cells (GICs), mesenchymal and proneural respectively, by using Synchrotron Radiation-Fourier Transform Infrared (FTIR) micro-spectroscopy (SR-FTIRM) facilities at the MIRAS Beamline of ALBA synchrotron light source. The spectroscopic data analysis from the bands in the regions of DNA, proteins, and lipids permitted to suggest that after its cellular uptake, Na[o-COSAN] strongly interacts with DNA strings, modifies proteins secondary structure and also leads to lipid saturation. The mapping suggests the nuclear localization of [o-COSAN]-, which according to reported Monte Carlo simulations may result in a more efficient cell-killing effect compared to that in a uniform distribution within the entire cell. In conclusion, we show pieces of evidence that at low doses, [o-COSAN]- translocates GIC cells' membranes and it alters the physiology of the cells, suggesting that Na[o-COSAN] is a promising agent to BNCT for glioblastoma cells.

Roadmap on Universal Photonic Biosensors for Real-Time Detection of Emerging Pathogens

The COVID-19 pandemic has made it abundantly clear that the state-of-the-art biosensors may not be adequate for providing a tool for rapid mass testing and population screening in response to newly emerging pathogens. The main limitations of the conventional techniques are their dependency on virus-specific receptors and reagents that need to be custom-developed for each recently-emerged pathogen, the time required for this development as well as for sample preparation and detection, the need for biological amplification, which can increase false positive outcomes, and the cost and size of the necessary equipment. Thus, new platform technologies that can be readily modified as soon as new pathogens are detected, sequenced, and characterized are needed to enable rapid deployment and mass distribution of biosensors. This need can be addressed by the development of adaptive, multiplexed, and affordable sensing technologies that can avoid the conventional biological amplification step, make use of the optical and/or electrical signal amplification, and shorten both the preliminary development and the point-of-care testing time frames. We provide a comparative review of the existing and emergent photonic biosensing techniques by matching them to the above criteria and capabilities of preventing the spread of the next global pandemic.

An infrared spectral biomarker accurately predicts neurodegenerative disease class in the absence of overt symptoms

Although some neurodegenerative diseases can be identified by behavioral characteristics relatively late in disease progression, we currently lack methods to predict who has developed disease before the onset of symptoms, when onset will occur, or the outcome of therapeutics. New biomarkers are needed. Here we describe spectral phenotyping, a new kind of biomarker that makes disease predictions based on chemical rather than biological endpoints in cells. Spectral phenotyping uses Fourier Transform Infrared (FTIR) spectromicroscopy to produce an absorbance signature as a rapid physiological indicator of disease state. FTIR spectromicroscopy has over the past been used in differential diagnoses of manifest disease. Here, we report that the unique FTIR chemical signature accurately predicts disease class in mouse with high probability in the absence of brain pathology. In human cells, the FTIR biomarker accurately predicts neurodegenerative disease class using fibroblasts as surrogate cells.

Identification of Aspergillus species in human blood plasma by infrared spectroscopy and machine learning

Invasive Aspergillosis is a challenging infection that requires convenient, efficient, and cost-effective diagnostics. This study addresses the potential of infrared spectroscopy to satisfy this clinical need with the aid of machine learning. Two models, based on Partial Least Squares-Discriminant Analysis (PLS-DA), have been trained by a set of infrared spectral data of 9 Aspergillus-spiked and 7 Aspergillus-free plasma samples, and a set of 200 spectral data simulated by oversampling these 16 samples. Two further models have also been trained by the same sets but with auto-scaling performed prior to PLS-DA. These models were assessed using 45 mock samples, simulating the challenging samples of patients at risk of Invasive Aspergillosis, including the presence of drugs (9 tested) and other common pathogens (5 tested) as potential confounders. The simple model shows good prediction performance, yielding a total accuracy of 84.4%, while oversampling and autoscaling improved this accuracy to 93.3%. The results of this study have shown that infrared spectroscopy can identify Aspergillus species in blood plasma even in presence of potential confounders commonly present in blood of patients at risk of Invasive Aspergillosis.

Interrogation of IDH1 Status in Gliomas by Fourier Transform Infrared Spectroscopy

Mutations in the isocitrate dehydrogenase 1 (IDH1) gene are found in a high proportion of diffuse gliomas. The presence of the IDH1 mutation is a valuable diagnostic, prognostic and predictive biomarker for the management of patients with glial tumours. Techniques involving vibrational spectroscopy, e.g., Fourier transform infrared (FTIR) spectroscopy, have previously demonstrated analytical capabilities for cancer detection, and have the potential to contribute to diagnostics. The implementation of FTIR microspectroscopy during surgical biopsy could present a fast, label-free method for molecular genetic classification. For example, the rapid determination of IDH1 status in a patient with a glioma diagnosis could inform intra-operative decision-making between alternative surgical strategies. In this study, we utilized synchrotron-based FTIR microanalysis to probe tissue microarray sections from 79 glioma patients, and distinguished the positive class (IDH1-mutated) from the IDH1-wildtype glioma, with a sensitivity and specificity of 82.4% and 83.4%, respectively. We also examined the ability of attenuated total reflection (ATR)-FTIR spectroscopy in detecting the biomolecular events and global epigenetic and metabolic changes associated with mutations in the IDH1 enzyme, in blood serum samples collected from an additional 72 brain tumour patients. Centrifugal filtration enhanced the diagnostic ability of the classification models, with balanced accuracies up to ~69%. Identification of the molecular status from blood serum prior to biopsy could further direct some patients to alternative treatment strategies.