Liquid biopsy for cancer diagnosis using vibrational spectroscopy: systematic review

Plasma infrared fingerprinting with machine learning enables single-measurement multi-phenotype health screening

Infrared spectroscopy is a powerful technique for probing the molecular profiles of complex biofluids, offering a promising avenue for high-throughput in vitro diagnostics. While several studies showcased its potential in detecting health conditions, a large-scale analysis of a naturally heterogeneous potential patient population has not been attempted. Using a population-based cohort, here we analyze 5,184 blood plasma samples from 3,169 individuals using Fourier transform infrared (FTIR) spectroscopy. Applying a multi-task classification to distinguish between dyslipidemia, hypertension, prediabetes, type 2 diabetes, and healthy states, we find that the approach can accurately single out healthy individuals and characterize chronic multimorbid states. We further identify the capacity to forecast the development of metabolic syndrome years in advance of onset. Dataset-independent testing confirms the robustness of infrared signatures against variations in sample handling, storage time, and measurement regimes. This study provides the framework that establishes infrared molecular fingerprinting as an efficient modality for populational health diagnostics.

Near-infrared spectroscopy as a novel method of ex vivo bladder cancer tissue characterisation

OBJECTIVE

To evaluate near-infrared (NIR) spectroscopy in differentiating between benign and malignant bladder pathologies ex vivo immediately after resection, including the grade and stage of malignancy.

PATIENTS AND METHODS

A total of 355 spectra were measured on 71 bladder specimens from patients undergoing transurethral resection of bladder tumour (TURBT) between April and August 2022. Scan time was 5 s, undertaken using a portable NIR spectrometer within 10 min from excision. Specimens were then sent for routine histopathological correlation. Machine learning models were applied to the spectral dataset to construct diagnostic algorithms; these were then tested for their ability to predict the histological diagnosis of each sample using its NIR spectrum.

RESULTS

A two-group algorithm comparing low- vs high-grade urothelial cancer demonstrated 97% sensitivity, 99% specificity, and the area under the receiver operating characteristic curve (AUC) was 0.997. A three-group algorithm predicting stages Ta vs T1 vs T2 achieved 97% sensitivity, 92% specificity, and the AUC was 0.996.

CONCLUSIONS

This first study evaluating the diagnostic potential of NIR spectroscopy in urothelial cancer shows that it can be accurately used to assess tissue in an ex vivo setting immediately after TURBT. This offers point-of-care assessment of bladder pathology, with potential to influence the extent of resection, reducing both the need for re-resection where invasive disease may be suspected, and also the potential for complications where extent of diagnostic resection can be limited. Further studies utilising fibre-optic probes offer the potential for in vivo assessment.

Cervical Squamous Cell Carcinoma Diagnosis by FTIR Microspectroscopy

Cervical cancer was considered the fourth most common cancer worldwide in 2020. In order to reduce mortality, an early diagnosis of the tumor is required. Currently, this type of cancer occurs mostly in developing countries due to the lack of vaccination and screening against the Human Papillomavirus. Thus, there is an urgent clinical need for new methods aiming at a reliable screening and an early diagnosis of precancerous and cancerous cervical lesions. Vibrational spectroscopy has provided very good results regarding the diagnosis of various tumors, particularly using Fourier transform infrared microspectroscopy, which has proved to be a promising complement to the currently used histopathological methods of cancer diagnosis. This spectroscopic technique was applied to the analysis of cryopreserved human cervical tissue samples, both squamous cell carcinoma (SCC) and non-cancer samples. A dedicated Support Vector Machine classification model was constructed in order to categorize the samples into either normal or malignant and was subsequently validated by cross-validation, with an accuracy higher than 90%.

Predicting the Likelihood of Colorectal Cancer with Artificial Intelligence Tools Using Fourier Transform Infrared Signals Obtained from Tumor Samples

The early and accurate detection of colorectal cancer (CRC) significantly affects its prognosis and clinical management. However, current standard diagnostic procedures for CRC often lack sensitivity and specificity since most rely on visual examination. Hence, there is a need to develop more accurate methods for its diagnosis. Support vector machine (SVM) and feedforward neural network (FNN) models were designed using the Fourier transform infrared (FT-IR) spectral data of several colorectal tissues that were unanimously identified as either benign or malignant by different unrelated pathologists. The set of samples in which the pathologists had discordant readings were then analyzed using the AI models described above. Between the SVM and NN models, the NN model was able to outperform the SVM model based on their prediction confidence scores. Using the spectral data of the concordant samples as training set, the FNN was able to predict the histologically diagnosed malignant tissues (n = 118) at 59.9-99.9% confidence (average = 93.5%). Of the 118 samples, 84 (71.18%) were classified with an above average confidence score, 34 (28.81%) classified below the average confidence score, and none was misclassified. Moreover, it was able to correctly identify the histologically confirmed benign samples (n = 83) at 51.5-99.7% confidence (average = 91.64%). Of the 83 samples, 60 (72.29%) were classified with an above average confidence score, 22 (26.51%) classified below the average confidence score, and only 1 sample (1.20%) was misclassified. The study provides additional proof of the ability of attenuated total reflection (ATR) FT-IR enhanced by AI tools to predict the likelihood of CRC without dependence on morphological changes in tissues.

Extracellular polymeric substances from marine actinobacterium of Micromonospora sp. and their antioxidant activity

Actinobacteria, Gram-positive bacteria are the largest phyla among the major species in the bacteria domain. Micromonospora sp. is one of the secondary metabolite-producing Actinobacteria, and it has a comprehensive spectrum of antibacterial, antifungal, antitumor, antiviral, antiparasitic, diabetogenic anti-inflammatory, insecticidal, inhibitory of enzyme, antioxidant, and other biological activities. The objective of the study is to assess the antioxidant activity of the Actinobacterium Micromonospora sp. producing extracellular polymeric substances (EPSs). Enumeration and isolation of Actinobacteria from sediment samples are done. The marine Actinobacteria, Micromonospora sp. are identified by melanoid pigments and other chemotaxonomical characteristics. EPS is produced from the potential marine Actinobacteria and their components are estimated. The total antioxidant value is found for the EPS. The antioxidant activity of the ascorbic acid equivalent which was 142.65 μg/ml was equivalent to 150 μg/ml of the total antioxidant activity of the EPS produced. The role of different antioxidants and the action in different diseases were challenged since they could act as many mechanisms such as reducing power, providing hydrogen to radicals, and scavenging activity (free radical). To conclude, the potent antioxidant activity was obtained from Actinobacteria Micromonospora sp. producing extracellular substances. These extracts might bear anticancer metabolites and are considered a potent anticancer drug.

Breast-cancer detection using blood-based infrared molecular fingerprints

BACKGROUND

Breast cancer screening is currently predominantly based on mammography, tainted with the occurrence of both false positivity and false negativity, urging for innovative strategies, as effective detection of early-stage breast cancer bears the potential to reduce mortality. Here we report the results of a prospective pilot study on breast cancer detection using blood plasma analyzed by Fourier-transform infrared (FTIR) spectroscopy - a rapid, cost-effective technique with minimal sample volume requirements and potential to aid biomedical diagnostics. FTIR has the capacity to probe health phenotypes via the investigation of the full repertoire of molecular species within a sample at once, within a single measurement in a high-throughput manner. In this study, we take advantage of cross-molecular fingerprinting to probe for breast cancer detection.

METHODS

We compare two groups: 26 patients diagnosed with breast cancer to a same-sized group of age-matched healthy, asymptomatic female participants. Training with support-vector machines (SVM), we derive classification models that we test in a repeated 10-fold cross-validation over 10 times. In addition, we investigate spectral information responsible for BC identification using statistical significance testing.

RESULTS

Our models to detect breast cancer achieve an average overall performance of 0.79 in terms of area under the curve (AUC) of the receiver operating characteristic (ROC). In addition, we uncover a relationship between the effect size of the measured infrared fingerprints and the tumor progression.

CONCLUSION

This pilot study provides the foundation for further extending and evaluating blood-based infrared probing approach as a possible cross-molecular fingerprinting modality to tackle breast cancer detection and thus possibly contribute to the future of cancer screening.

Vibrational Spectroscopy: A Valuable Screening and Diagnostic Tool for Obstetric Disorders?

Preeclampsia (PE) is a common obstetric disorder typically affecting 2–8% of all pregnancies and can lead to several adverse obstetric outcomes for both mother and fetus with the greatest burden of severe outcomes in low middle-income countries (LMICs), therefore, screening for PE is vital. Globally, screening is based on maternal characteristics and medical history which are nonspecific for the disorder. In 2004, the World Health Organization acknowledged that no clinically useful test was able to predict the onset of PE, which prompted a universal search for alternative means of screening. Over the past decade or so, emphasis has been placed on the use of maternal characteristics in conjunction with biomarkers of disease combined into predictive algorithms, however these are yet to transition into the clinic and are cost prohibitive in LMICs. As a result, the screening paradigm for PE remains unchanged. It is evident that novel approaches are needed. Vibrational spectroscopy, specifically Raman spectroscopy and Fourier-transform infrared spectroscopy (FTIR), could provide better alternatives suited for implementation in low resource settings as no specialized reagents are required for conventional approaches and there is a drive to portable platforms usable in both urban and rual community settings. These techniques are based on light scattering and absorption, respectively, allowing detailed molecular analysis of samples to produce a unique molecular fingerprint of diseased states. The specificity of vibrational spectroscopy might well make it suited for application in other obstetric disorders such as gestational diabetes mellitus and obstetric cholestasis. In this review, we summarize current approaches sought as alternatives to current screening methodologies and introduce how vibrational spectroscopy could offer superior screening and diagnostic paradigms in obstetric care. Additionally, we propose a real benefit of such tools in LMICs where limited resources battle the higher prevalence of obstetric disorders.

Infrared molecular fingerprinting of blood-based liquid biopsies for the detection of cancer

Recent omics analyses of human biofluids provide opportunities to probe selected species of biomolecules for disease diagnostics. Fourier-transform infrared (FTIR) spectroscopy investigates the full repertoire of molecular species within a sample at once. Here, we present a multi-institutional study in which we analysed infrared fingerprints of plasma and serum samples from 1639 individuals with different solid tumours and carefully matched symptomatic and non-symptomatic reference individuals. Focusing on breast, bladder, prostate, and lung cancer, we find that infrared molecular fingerprinting is capable of detecting cancer: training a support vector machine algorithm allowed us to obtain binary classification performance in the range of 0.78-0.89 (area under the receiver operating characteristic curve [AUC]), with a clear correlation between AUC and tumour load. Intriguingly, we find that the spectral signatures differ between different cancer types. This study lays the foundation for high-throughput onco-IR-phenotyping of four common cancers, providing a cost-effective, complementary analytical tool for disease recognition.