Combining random forest and 2D correlation analysis to identify serum spectral signatures for neuro-oncology

Distinguishing IDH mutation status in gliomas using FTIR-ATR spectra of peripheral blood plasma indicating clear traces of protein amyloid aggregation

BACKGROUND

Glioma is a primary brain tumor and the assessment of its molecular profile in a minimally invasive manner is important in determining treatment strategies. Among the molecular abnormalities of gliomas, mutations in the isocitrate dehydrogenase (IDH) gene are strong predictors of treatment sensitivity and prognosis. In this study, we attempted to non-invasively diagnose glioma development and the presence of IDH mutations using multivariate analysis of the plasma mid-infrared absorption spectra for a comprehensive and sensitive view of changes in blood components associated with the disease and genetic mutations. These component changes are discussed in terms of absorption wavenumbers that contribute to differentiation.

METHODS

Plasma samples were collected at our institutes from 84 patients with glioma (13 oligodendrogliomas, 17 IDH-mutant astrocytoma, 7 IDH wild-type diffuse glioma, and 47 glioblastomas) before treatment initiation and 72 healthy participants. FTIR-ATR spectra were obtained for each plasma sample, and PLS discriminant analysis was performed using the absorbance of each wavenumber in the fingerprint region of biomolecules as the explanatory variable. This data was used to distinguish patients with glioma from healthy participants and diagnose the presence of IDH mutations.

RESULTS

The derived classification algorithm distinguished the patients with glioma from healthy participants with 83% accuracy (area under the curve (AUC) in receiver operating characteristic (ROC) = 0.908) and diagnosed the presence of IDH mutation with 75% accuracy (AUC = 0.752 in ROC) in cross-validation using 30% of the total test data. The characteristic changes in the absorption spectra suggest an increase in the ratio of β-sheet structures in the conformational composition of blood proteins of patients with glioma. Furthermore, these changes were more pronounced in patients with IDH-mutant gliomas.

CONCLUSIONS

The plasma infrared absorption spectra could be used to diagnose gliomas and the presence of IDH mutations in gliomas with a high degree of accuracy. The spectral shape of the protein absorption band showed that the ratio of β-sheet structures in blood proteins was significantly higher in patients with glioma than in healthy participants, and protein aggregation was a distinct feature in patients with glioma with IDH mutations.

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.

Global serum profiling: an opportunity for earlier cancer detection

The advances in cancer research achieved in the last 50 years have been remarkable and have provided a deeper knowledge of this disease in many of its conceptual and biochemical aspects. From viewing a tumor as a 'simple' aggregate of mutant cells and focusing on detecting key cell changes leading to the tumorigenesis, the understanding of cancer has broadened to consider it as a complex organ interacting with its close and far surroundings through tumor and non-tumor cells, metabolic mechanisms, and immune processes. Metabolism and the immune system have been linked to tumorigenesis and malignancy progression along with cancer-specific genetic mutations. However, most technologies developed to overcome the barriers to earlier detection are focused solely on genetic information. The concept of cancer as a complex organ has led to research on other analytical techniques, with the quest of finding a more sensitive and cost-effective comprehensive approach. Furthermore, artificial intelligence has gained broader consensus in the oncology community as a powerful tool with the potential to revolutionize cancer diagnosis for physicians. We herein explore the relevance of the concept of cancer as a complex organ interacting with the bodily surroundings, and focus on promising emerging technologies seeking to diagnose cancer earlier, such as liquid biopsies. We highlight the importance of a comprehensive approach to encompass all the tumor and non-tumor derived information salient to earlier cancer detection.

Metric-based analysis of FTIR data to discriminate tissue types in oral cancer

A machine learning algorithm (MLA) has predicted the prognosis of oral potentially malignant lesions and discriminated between lymph node tissue and metastatic oral squamous cell carcinoma (OSCC). The MLA analyses metrics, which are ratios of Fourier transform infrared absorbances, and identifies key wavenumbers that can be associated with molecular biomarkers. The wider efficacy of the MLA is now shown in the more complex primary OSCC tumour setting, where it is able to identify seven types of tissue. Three epithelial and four non-epithelial tissue types were discriminated from each other with sensitivities between 82% and 96% and specificities between 90% and 99%. The wavenumbers involved in the five best discriminating metrics for each tissue type were tightly grouped, indicating that small changes in the spectral profiles of the different tissue types are important. The number of samples used in this study was small, but the information will provide a basis for further, larger investigations.

Investigating centrifugal filtration of serum-based FTIR spectroscopy for the stratification of brain tumours

Discrimination of brain cancer versus non-cancer patients using serum-based attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy diagnostics was first developed by Hands et al with a reported sensitivity of 92.8% and specificity of 91.5%. Cameron et al. then went on to stratifying between specific brain tumour types: glioblastoma multiforme (GBM) vs. primary cerebral lymphoma with a sensitivity of 90.1% and specificity of 86.3%. Expanding on these studies, 30 GBM, 30 lymphoma and 30 non-cancer patients were selected to investigate the influence on test performance by focusing on specific molecular weight regions of the patient serum. Membrane filters with molecular weight cut offs of 100 kDa, 50 kDa, 30 kDa, 10 kDa and 3 kDa were purchased in order to remove the most abundant high molecular weight components. Three groups were classified using both partial least squares-discriminate analysis (PLS-DA) and random forest (RF) machine learning algorithms; GBM versus non-cancer, lymphoma versus non-cancer and GBM versus lymphoma. For all groups, once the serum was filtered the sensitivity, specificity and overall balanced accuracies decreased. This illustrates that the high molecular weight components are required for discrimination between cancer and non-cancer as well as between tumour types. From a clinical application point of view, this is preferable as less sample preparation is required.

2D-IR spectroscopy of proteins in H2O-A Perspective

The form of the amide I infrared absorption band provides a sensitive probe of the secondary structure and dynamics of proteins in the solution phase. However, the frequency coincidence of the amide I band with the bending vibrational mode of H₂O has necessitated the widespread use of deuterated solvents. Recently, it has been demonstrated that ultrafast 2D-IR spectroscopy allows the detection of the protein amide I band in H₂O-based fluids, meaning that IR methods can now be applied to study proteins in physiologically relevant solvents. In this perspective, we describe the basis of the 2D-IR method for observing the protein amide I band in H₂O and show how this development has the potential to impact areas ranging from our fundamental appreciation of protein structural dynamics to new applications for 2D-IR spectroscopy in the analytical and biomedical sciences. In addition, we discuss how the spectral response of water, rather than being a hindrance, now provides a basis for new approaches to data pre-processing, standardization of 2D-IR data collection, and signal quantification. Ultimately, we visualize a direction of travel toward the creation of 2D-IR spectral libraries that can be linked to advanced computational methods for use in high-throughput protein screening and disease 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.

Fast and Deep Diagnosis Using Blood-Based ATR-FTIR Spectroscopy for Digestive Tract Cancers

Attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) of liquid biofluids enables the probing of biomolecular markers for disease diagnosis, characterized as a time and cost-effective approach. It remains poorly understood for fast and deep diagnosis of digestive tract cancers (DTC) to detect abundant changes and select specific markers in a broad spectrum of molecular species. Here, we present a diagnostic protocol of DTC in which the in-situ blood-based ATR-FTIR spectroscopic data mining pathway was designed for the identification of DTC triages in 252 blood serum samples, divided into the following groups: liver cancer (LC), gastric cancer (GC), colorectal cancer (CC), and their different three stages respectively. The infrared molecular fingerprints (IMFs) of DTC were measured and used to build a 2-dimensional second derivative spectrum (2D-SD-IR) feature dataset for classification, including absorbance and wavenumber shifts of FTIR vibration peaks. By comparison, the Partial Least-Squares Discriminant Analysis (PLS-DA) and backpropagation (BP) neural networks are suitable to differentiate DTCs and pathological stages with a high sensitivity and specificity of 100% and averaged more than 95%. Furthermore, the measured IMF data was mutually validated via clinical blood biochemistry testing, which indicated that the proposed 2D-SD-IR-based machine learning protocol greatly improved DTC classification performance.

Liquid Biopsy for Pancreatic Cancer Detection Using Infrared Spectroscopy

Pancreatic cancer claims over 460,000 victims per year. The carbohydrate antigen (CA) 19-9 test is the blood test used for pancreatic cancer's detection; however, its levels can be raised in symptomatic patients with other non-malignant diseases, or with other tumors in the surrounding area. Attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy has demonstrated exceptional potential in cancer diagnostics, and its clinical implementation could represent a significant step towards early detection. This proof-of-concept study, investigating the use of ATR-FTIR spectroscopy on dried blood serum, focused on the discrimination of both cancer versus healthy control samples, and cancer versus symptomatic non-malignant control samples, as a novel liquid biopsy approach for pancreatic cancer diagnosis. Machine learning algorithms were applied, achieving results of up to 92% sensitivity and 88% specificity when discriminating between cancers (n = 100) and healthy controls (n = 100). An area under the curve (AUC) of 0.95 was obtained through receiver operating characteristic (ROC) analysis. Balanced sensitivity and specificity over 75%, with an AUC of 0.83, were achieved with cancers (n = 35) versus symptomatic controls (n = 35). Herein, we present these results as demonstration that our liquid biopsy approach could become a simple, minimally invasive, and reliable diagnostic test for pancreatic cancer detection.

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.

Raman, Infrared and Brillouin Spectroscopies of Biofluids for Medical Diagnostics and for Detection of Biomarkers

This review surveys Infrared, Raman/SERS and Brillouin spectroscopies for medical diagnostics and detection of biomarkers in biofluids, that include urine, blood, saliva and other biofluids. These optical sensing techniques are non-contact, noninvasive and relatively rapid, accurate, label-free and affordable. However, those techniques still have to overcome some challenges to be widely adopted in routine clinical diagnostics. This review summarizes and provides insights on recent advancements in research within the field of vibrational spectroscopy for medical diagnostics and its use in detection of many health conditions such as kidney injury, cancers, cardiovascular and infectious diseases. The six comprehensive tables in the review and four tables in supplementary information summarize a few dozen experimental papers in terms of such analytical parameters as limit of detection, range, diagnostic sensitivity and specificity, and other figures of merits. Critical comparison between SERS and FTIR methods of analysis reveals that on average the reported sensitivity for biomarkers in biofluids for SERS vs FTIR is about 103 to 105 times higher, since LOD SERS are lower than LOD FTIR by about this factor. High sensitivity gives SERS an edge in detection of many biomarkers present in biofluids at low concentration (nM and sub nM), which can be particularly advantageous for example in early diagnostics of cancer or viral infections.HighlightsRaman, Infrared spectroscopies use low volume of biofluidic samples, little sample preparation, fast time of analysis and relatively inexpensive instrumentation.Applications of SERS may be a bit more complicated than applications of FTIR (e.g., limited shelf life for nanoparticles and substrates, etc.), but this can be generously compensated by much higher (by several order of magnitude) sensitivity in comparison to FTIR.High sensitivity makes SERS a noninvasive analytical method of choice for detection, quantification and diagnostics of many health conditions, metabolites, and drugs, particularly in diagnostics of cancer, including diagnostics of its early stages.FTIR, particularly ATR-FTIR can be a method of choice for efficient sensing of many biomarkers, present in urine, blood and other biofluids at sufficiently high concentrations (mM and even a few µM)Brillouin scattering spectroscopy detecting visco-elastic properties of probed liquid medium, may also find application in clinical analysis of some biofluids, such as cerebrospinal fluid and urine.

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.

Rapid Spectroscopic Liquid Biopsy for the Universal Detection of Brain Tumours

Simple Summary

Due to the non-specific symptoms of brain cancer (e.g., headaches or memory changes), gliomas will often remain undetected until they are larger or at a higher grade, reducing the patient’s likelihood of a good clinical outcome. Earlier detection and diagnosis of brain tumours is vital to improve patient outcomes, leading to safer surgeries and earlier treatments. A liquid biopsy for brain tumour would prove revolutionary however in order to detect disease earlier the liquid biopsy needs to be able to detect smaller tumours; and current liquid biopsies perform worse when detecting smaller or earlier stage tumours. Here, for the first time, we confirm the applicability of a validated spectroscopic liquid biopsy approach to detect both small and low-grade gliomas proving that the spectroscopic liquid biopsy approach is insensitive to tumour volume unlike other liquid biopsies.

Abstract

Background: To support the early detection and diagnosis of brain tumours we have developed a rapid, cost-effective and easy to use spectroscopic liquid biopsy based on the absorbance of infrared radiation. We have previously reported highly sensitive results of our approach which can discriminate patients with a recent brain tumour diagnosis and asymptomatic controls. Other liquid biopsy approaches (e.g., based on tumour genetic material) report a lower classification accuracy for early-stage tumours. In this manuscript we present an investigation into the link between brain tumour volume and liquid biopsy test performance. Methods: In a cohort of 177 patients (90 patients with high-grade glioma (glioblastoma (GBM) or anaplastic astrocytoma), or low-grade glioma (astrocytoma, oligoastrocytoma and oligodendroglioma)) tumour volumes were calculated from magnetic resonance imaging (MRI) investigations and patients were split into two groups depending on MRI parameters (T1 with contrast enhancement or T2/FLAIR (fluid-attenuated inversion recovery)). Using attenuated total reflection (ATR)-Fourier transform infrared (FTIR) spectroscopy coupled with supervised learning methods and machine learning algorithms, 90 tumour patients were stratified against 87 control patients who displayed no symptomatic indications of cancer, and were classified as either glioma or non-glioma. Results: Sensitivities, specificities and balanced accuracies were all greater than 88%, the area under the curve (AUC) was 0.98, and cancer patients with tumour volumes as small as 0.2 cm³ were correctly identified. Conclusions: Our spectroscopic liquid biopsy approach can identify gliomas that are both small and low-grade showing great promise for deployment of this technique for early detection and diagnosis.

Insight into metastatic oral cancer tissue from novel analyses using FTIR spectroscopy and aperture IR-SNOM

A novel machine learning algorithm is shown to accurately discriminate between oral squamous cell carcinoma (OSCC) nodal metastases and surrounding lymphoid tissue on the basis of a single metric, the ratio of Fourier transform infrared (FTIR) absorption intensities at 1252 cm⁻¹ and 1285 cm⁻¹. The metric yields discriminating sensitivities, specificities and precision of 98.8 ± 0.1%, 99.89 ± 0.01% and 99.78 ± 0.02% respectively, and an area under receiver operator characteristic (AUC) of 0.9935 ± 0.0006. The delineation of the OSCC and lymphoid tissue revealed by the image formed from the metric is in better agreement with an immunohistochemistry (IHC) stained image than are either of the FTIR images obtained at the individual wavenumbers. Scanning near-field optical microscopy (SNOM) images of the tissue obtained at a number of key wavenumbers, with high spatial resolution, show variations in the chemical structure of the tissue with a feature size down to ∼4 μm. The image formed from the ratio of the SNOM images obtained at 1252 cm⁻¹ and 1285 cm⁻¹ shows more contrast than the SNOM images obtained at these or a number of other individual wavenumbers. The discrimination between the two tissue types is dominated by the contribution from the 1252 cm⁻¹ signal, which is representative of nucleic acids, and this shows the OSCC tissue to be accompanied by two wide arcs of tissue which are particularly low in nucleic acids. Haematoxylin and eosin (H&E) staining shows the tumour core in this specimen to be ∼40 μm wide and the SNOM topography shows that the core centre is raised by ∼1 μm compared to the surrounding tissue. Line profiles of the SNOM signal intensity taken through the highly keratinised core show that the increase in height correlates with an increase in the protein signal. SNOM line profiles show that the nucleic acids signal decreases at the centre of the tumour core between two peaks of higher intensity. All these nucleic acid features are ∼25 μm wide, roughly the width of two cancer cells.

A SNOM image (a) provides chemical insight into a metastatic tumour identified by H&E staining (b).

Early diagnosis of brain tumours using a novel spectroscopic liquid biopsy

Early diagnosis of brain tumours is challenging and a major unmet need. Patients with brain tumours most often present with non-specific symptoms more commonly associated with less serious diagnoses, making it difficult to determine which patients to prioritize for brain imaging. Delays in diagnosis affect timely access to treatment, with potential impacts on quality of life and survival. A test to help identify which patients with non-specific symptoms are most likely to have a brain tumour at an earlier stage would dramatically impact on patients by prioritizing demand on diagnostic imaging facilities. This clinical feasibility study of brain tumour early diagnosis was aimed at determining the accuracy of our novel spectroscopic liquid biopsy test for the triage of patients with non-specific symptoms that might be indicative of a brain tumour, for brain imaging. Patients with a suspected brain tumour based on assessment of their symptoms in primary care can be referred for open access CT scanning. Blood samples were prospectively obtained from 385 of such patients, or patients with a new brain tumour diagnosis. Samples were analysed using our spectroscopic liquid biopsy test to predict presence of disease, blinded to the brain imaging findings. The results were compared to the patient’s index brain imaging delivered as per standard care. Our test predicted the presence of glioblastoma, the most common and aggressive brain tumour, with 91% sensitivity, and all brain tumours with 81% sensitivity, and 80% specificity. Negative predictive value was 95% and positive predictive value 45%. The reported levels of diagnostic accuracy presented here have the potential to improve current symptom-based referral guidelines, and streamline assessment and diagnosis of symptomatic patients with a suspected brain tumour.

Stability of person-specific blood-based infrared molecular fingerprints opens up prospects for health monitoring

Health state transitions are reflected in characteristic changes in the molecular composition of biofluids. Detecting these changes in parallel, across a broad spectrum of molecular species, could contribute to the detection of abnormal physiologies. Fingerprinting of biofluids by infrared vibrational spectroscopy offers that capacity. Whether its potential for health monitoring can indeed be exploited critically depends on how stable infrared molecular fingerprints (IMFs) of individuals prove to be over time. Here we report a proof-of-concept study that addresses this question. Using Fourier-transform infrared spectroscopy, we have fingerprinted blood serum and plasma samples from 31 healthy, non-symptomatic individuals, who were sampled up to 13 times over a period of 7 weeks and again after 6 months. The measurements were performed directly on liquid serum and plasma samples, yielding a time- and cost-effective workflow and a high degree of reproducibility. The resulting IMFs were found to be highly stable over clinically relevant time scales. Single measurements yielded a multiplicity of person-specific spectral markers, allowing individual molecular phenotypes to be detected and followed over time. This previously unknown temporal stability of individual biochemical fingerprints forms the basis for future applications of blood-based infrared spectral fingerprinting as a multiomics-based mode of health monitoring.

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.

Rapid analysis of disease state in liquid human serum combining infrared spectroscopy and "digital drying"

In recent years, the diagnosis of brain tumors has been investigated with attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy on dried human serum samples to eliminate spectral interferences of the water component, with promising results. This research evaluates ATR-FTIR on both liquid and air-dried samples to investigate "digital drying" as an alternative approach for the analysis of spectra obtained from liquid samples. Digital drying approaches, consisting of water subtraction and least-squares method, have demonstrated a greater random forest (RF) classification performance than the air-dried spectra approach when discriminating cancer vs control samples, reaching sensitivity values higher than 93.0% and specificity values higher than 83.0%. Moreover, quantum cascade laser infrared (QCL-IR) based spectroscopic imaging is utilized on liquid samples to assess the implications of a deep-penetration light source on disease classification. The RF classification of QCL-IR data has provided sensitivity and specificity amounting to 85.1% and 75.3% respectively.

Liquid biopsy for cancer diagnosis using vibrational spectroscopy: systematic review

Background

Vibrational spectroscopy (VS) is a minimally invasive tool for analysing biological material to detect disease. This study aimed to review its application to human blood for cancer diagnosis.

Methods

A systematic review was undertaken using a keyword electronic database search (MEDLINE, Embase, PubMed, TRIP and Cochrane Library), with all original English‐language manuscripts examining the use of vibrational spectral analysis of human blood for cancer detection. Studies involving fewer than 75 patients in the cancer or control group, animal studies, or where the primary analyte was not blood were excluded.

Results

From 1446 results, six studies (published in 2010–2018) examining brain, bladder, oral, breast, oesophageal and hepatic cancer met the criteria for inclusion, with a total population of 2392 (1316 cancer, 1076 control; 1476 men, 916 women). For cancer detection, reported mean sensitivities in each included study ranged from 79·3 to 98 per cent, with specificities of 82·8–95 per cent and accuracies between 81·1 and 97·1 per cent. Heterogeneity in reporting strategies, methods and outcome measures made meta‐analysis inappropriate.

Conclusion

VS shows high potential for cancer diagnosis, but until there is agreement on uniform standard reporting methods and studies with adequate sample size for valid classification models have been performed, its value in clinical practice will remain uncertain.

Developing infrared spectroscopic detection for stratifying brain tumour patients: glioblastoma multiforme vs. lymphoma

Over a third of brain tumour patients visit their general practitioner more than five times prior to diagnosis in the UK, leading to 62% of patients being diagnosed as emergency presentations. Unfortunately, symptoms are non-specific to brain tumours, and the majority of these patients complain of headaches on multiple occasions before being referred to a neurologist. As there are currently no methods in place for the early detection of brain cancer, the affected patients' average life expectancy is reduced by 20 years. These statistics indicate that the current pathway is ineffective, and there is a vast need for a rapid diagnostic test. Attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy is sensitive to the hallmarks of cancer, as it analyses the full range of macromolecular classes. The combination of serum spectroscopy and advanced data analysis has previously been shown to rapidly and objectively distinguish brain tumour severity. Recently, a novel high-throughput ATR accessory has been developed, which could be cost-effective to the National Health Service in the UK, and valuable for clinical translation. In this study, 765 blood serum samples have been collected from healthy controls and patients diagnosed with various types of brain cancer, contributing to one of the largest spectroscopic studies to date. Three robust machine learning techniques - random forest, partial least squares-discriminant analysis and support vector machine - have all provided promising results. The novel high-throughput technology has been validated by separating brain cancer and non-cancer with balanced accuracies of 90% which is comparable to the traditional fixed diamond crystal methodology. Furthermore, the differentiation of brain tumour type could be useful for neurologists, as some are difficult to distinguish through medical imaging alone. For example, the highly aggressive glioblastoma multiforme and primary cerebral lymphoma can appear similar on magnetic resonance imaging (MRI) scans, thus are often misdiagnosed. Here, we report the ability of infrared spectroscopy to distinguish between glioblastoma and lymphoma patients, at a sensitivity and specificity of 90.1% and 86.3%, respectively. A reliable serum diagnostic test could avoid the need for surgery and speed up time to definitive chemotherapy and radiotherapy.

Salivary molecular spectroscopy: A sustainable, rapid and non-invasive monitoring tool for diabetes mellitus during insulin treatment

Monitoring of blood glucose is an invasive, painful and costly practice in diabetes. Consequently, the search for a more cost-effective (reagent-free), non-invasive and specific diabetes monitoring method is of great interest. Attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy has been used in diagnosis of several diseases, however, applications in the monitoring of diabetic treatment are just beginning to emerge. Here, we used ATR-FTIR spectroscopy to evaluate saliva of non-diabetic (ND), diabetic (D) and insulin-treated diabetic (D+I) rats to identify potential salivary biomarkers related to glucose monitoring. The spectrum of saliva of ND, D and D+I rats displayed several unique vibrational modes and from these, two vibrational modes were pre-validated as potential diagnostic biomarkers by ROC curve analysis with significant correlation with glycemia. Compared to the ND and D+I rats, classification of D rats was achieved with a sensitivity of 100%, and an average specificity of 93.33% and 100% using bands 1452 cm^-1 and 836 cm^-1, respectively. Moreover, 1452 cm^-1 and 836 cm^-1 spectral bands proved to be robust spectral biomarkers and highly correlated with glycemia (R² of 0.801 and 0.788, P < 0.01, respectively). Both PCA-LDA and HCA classifications achieved an accuracy of 95.2%. Spectral salivary biomarkers discovered using univariate and multivariate analysis may provide a novel robust alternative for diabetes monitoring using a non-invasive and green technology.

Development of high-throughput ATR-FTIR technology for rapid triage of brain cancer

Non-specific symptoms, as well as the lack of a cost-effective test to triage patients in primary care, has resulted in increased time-to-diagnosis and a poor prognosis for brain cancer patients. A rapid, cost-effective, triage test could significantly improve this patient pathway. A blood test using attenuated total reflection (ATR)-Fourier transform infrared (FTIR) spectroscopy for the detection of brain cancer, alongside machine learning technology, is advancing towards clinical translation. However, whilst the methodology is simple and does not require extensive sample preparation, the throughput of such an approach is limited. Here we describe the development of instrumentation for the analysis of serum that is able to differentiate cancer and control patients at a sensitivity and specificity of 93.2% and 92.8%. Furthermore, preliminary data from the first prospective clinical validation study of its kind are presented, demonstrating how this innovative technology can triage patients and allow rapid access to imaging.

Fourier transform infrared spectroscopic imaging of colon tissues: evaluating the significance of amide I and C-H stretching bands in diagnostic applications with machine learning

Fourier transform infrared (FTIR) spectroscopic imaging of colon biopsy tissues in transmission combined with machine learning for the classification of different stages of colon malignancy was carried out in this study. Two different approaches, an optical and a computational one, were applied for the elimination of the scattering background during the measurements and compared with the results of the machine learning model without correction for the scattering. Several different data processing pathways were implemented in order to obtain a high accuracy of the prediction model. This study demonstrates, for the first time, that C-H stretching and amide I bands are of little to no significance in the classification of the colon malignancy, based on the Gini importance values by random forest (RF). The best prediction outcome is found when supervised RF classification was carried out in the fingerprint region of the spectral data between 1500 and 1000 cm^-1 (excluding the contribution of amide I and II bands). An overall prediction accuracy higher than 90% is achieved through the RF. The results also show that dysplastic and hyperplastic tissues are well distinguished. This leads to the insight that the important differences between hyperplastic and dysplastic colon tissues lie within the fingerprint region of FTIR spectra. In this study, computational correction performed better than optical correction, but the findings show that the disease states of colon biopsies can be distinguished effectively without elimination of Mie scattering effect. Graphical abstract.

Biochemical detection of fatal hypothermia and hyperthermia in affected rat hypothalamus tissues by Fourier transform infrared spectroscopy

It is difficult to determinate the cause of death from exposure to fatal hypothermia and hyperthermia in forensic casework. Here, we present a state-of-the-art study that employs Fourier-transform infrared (FTIR) spectroscopy to investigate the hypothalamus tissues of fatal hypothermic, fatal hyperthermic and normothermic rats to determine forensically significant biomarkers related to fatal hypothermia and hyperthermia. Our results revealed that the spectral variations in the lipid, protein, carbohydrate and nucleic acid components are highly different for hypothalamuses after exposure to fatal hypothermic, fatal hyperthermic and normothermic conditions. In comparison with the normothermia group, the fatal hypothermia and hyperthermia groups contained higher total lipid amounts but were lower in unsaturated lipids. Additionally, their cell membranes were found to have less motional freedom. Among these three groups, the fatal hyperthermia group contained the lowest total proteins and carbohydrates and the highest aggregated and dysfunctional proteins, while the fatal hypothermia group contained the highest level of nucleic acids. In conclusion, this study demonstrates that FTIR spectroscopy has the potential to become a reliable method for the biochemical characterization of fatal hypothermia and hyperthermia hypothalamus tissues, and this could be used as a postmortem diagnostic feature in fatal hypothermia and hyperthermia deaths.

Optimised spectral pre-processing for discrimination of biofluids via ATR-FTIR spectroscopy

Pre-processing is an essential step in the analysis of spectral data. Mid-IR spectroscopy of biological samples is often subject to instrumental and sample specific variances which may often conceal valuable biological information. Whilst pre-processing can effectively reduce this unwanted variance, the plethora of possible processing steps has resulted in a lack of consensus in the field, often meaning that analysis outputs are not comparable. As pre-processing is specific to the sample under investigation, here we present a systematic approach for defining the optimum pre-processing protocol for biofluid ATR-FTIR spectroscopy. Using a trial-and-error based approach and a clinically relevant dataset describing control and brain cancer patients, the effects of pre-processing permutations on subsequent classification algorithms were observed, by assessing key diagnostic performance parameters, including sensitivity and specificity. It was found that optimum diagnostic performance correlated with the use of minimal binning and baseline correction, with derivative functions improving diagnostic performance most significantly. If smoothing is required, a Sovitzky-Golay approach was the preferred option in this investigation. Heavy binning appeared to reduce classification most significantly, alongside wavelet noise reduction (filter length ≥6), resulting in the lowest diagnostic performances of all pre-processing permutations tested.

SVM Optimization for Brain Tumor Identification Using Infrared Spectroscopic Samples

The work presented in this paper is focused on the use of spectroscopy to identify the type of tissue of human brain samples employing support vector machine classifiers. Two different spectrometers were used to acquire infrared spectroscopic signatures in the wavenumber range between 1200⁻3500 cm^-1. An extensive analysis was performed to find the optimal configuration for a support vector machine classifier and determine the most relevant regions of the spectra for this particular application. The results demonstrate that the developed algorithm is robust enough to classify the infrared spectroscopic data of human brain tissue at three different discrimination levels.

Health economic evaluation of a serum-based blood test for brain tumour diagnosis: exploration of two clinical scenarios

OBJECTIVES

To determine the potential costs and health benefits of a serum-based spectroscopic triage tool for brain tumours, which could be developed to reduce diagnostic delays in the current clinical pathway.

DESIGN

A model-based health pre-trial economic assessment. Decision tree models were constructed based on simplified diagnostic pathways. Models were populated with parameters identified from rapid reviews of the literature and clinical expert opinion.

SETTING

Explored as a test in both primary and secondary care (neuroimaging) in the UK health service, as well as application to the USA.

PARTICIPANTS

Calculations based on an initial cohort of 10 000 patients. In primary care, it is estimated that the volume of tests would approach 75 000 per annum. The volume of tests in secondary care is estimated at 53 000 per annum.

MAIN OUTCOME MEASURES

The primary outcome measure was quality-adjusted life-years (QALY), which were employed to derive incremental cost-effectiveness ratios (ICER) in a cost-effectiveness analysis.

RESULTS

Results indicate that using a blood-based spectroscopic test in both scenarios has the potential to be highly cost-effective in a health technology assessment agency decision-making process, as ICERs were well below standard threshold values of £20 000-£30 000 per QALY. This test may be cost-effective in both scenarios with test sensitivities and specificities as low as 80%; however, the price of the test would need to be lower (less than approximately £40).

CONCLUSION

Use of this test as triage tool in primary care has the potential to be both more effective and cost saving for the health service. In secondary care, this test would also be deemed more effective than the current diagnostic pathway.

Biofluid spectroscopic disease diagnostics: A review on the processes and spectral impact of drying

The complex patterns observed from evaporated liquid drops have been examined extensively over the last 20 years. Complete understanding of drop deposition is vital in many medical processes, and one which is essential to the translation of biofluid spectroscopic disease diagnostics. The promising use of spectroscopy in disease diagnosis has been hindered by the complicated patterns left by dried biological fluids which may inhibit the clinical translation of this technology. Coffee-ring formation, cracking and gelation patterns have all been observed in biofluid drops, and with surface homogeneity being a key element to many spectroscopic techniques, experimental issues have been found to arise. A better understanding of the fundamental processes involved in a drying droplet could allow efficient progression in this research field, and ultimately benefit the population with the development of a reliable cancer diagnostic.

Identification of Pulmonary Edema in Forensic Autopsy Cases of Sudden Cardiac Death Using Fourier Transform Infrared Microspectroscopy: A Pilot Study

Many studies have proven the usefulness of biofluid-based infrared spectroscopy in the clinical domain for diagnosis and monitoring the progression of diseases. Here we present a state-of-the-art study in the forensic field that employed Fourier transform infrared microspectroscopy for postmortem diagnosis of sudden cardiac death (SCD) by in situ biochemical investigation of alveolar edema fluid in lung tissue sections. The results of amide-related spectral absorbance analysis demonstrated that the pulmonary edema fluid of the SCD group was richer in protein components than that of the neurologic catastrophe (NC) and lethal multiple injuries (LMI) groups. The complementary results of unsupervised principle component analysis (PCA) and genetic algorithm-guided partial least-squares discriminant analysis (GA-PLS-DA) further indicated different global spectral band patterns of pulmonary edema fluids between these three groups. Ultimately, a random forest (RF) classification model for postmortem diagnosis of SCD was built and achieved good sensitivity and specificity scores of 97.3% and 95.5%, respectively. Classification predictions of unknown pulmonary edema fluid collected from 16 cases were also performed by the model, resulting in 100% correct discrimination. This pilot study demonstrates that FTIR microspectroscopy in combination with chemometrics has the potential to be an effective aid for postmortem diagnosis of SCD.