A Review of Machine Learning for Near-Infrared Spectroscopy

Orthogonal signal correction assisted multivariate regression approach for the estimation of uranium and acidity in PUREX process streams

A direct UV-Visible absorbance spectrophotometric method was developed for the simultaneous determination of uranium and nitric acid concentration in the PUREX process samples. The simulated system consisted of uranium and nitric acid in concentration range corresponding to reprocessing of spent nuclear fuel discharged from nuclear reactor was prepared. The absorbance of these samples was measured in the range of 400-470 nm at a scan speed of 100 nm/s and resultant spectra were recorded. The changes in wavelength maxima of U(VI) absorption spectrum at different nitric acid concentration was utilized to determine the concentration of uranium and nitric acid in the sample by orthogonal signal correction assisted principal component regression. After the principle component regression the RMSEP for test data (Uranium: 3-21 g/L and acidity: 2-12 M) were 0.7 g/L and 0.4 M respectively. This method is superior to conventional method being followed for routine analysis of plant control samples in view of minimizing the generation of radioactive analytical waste consisting other corrosive reagents and reducing radiation exposure to operators during analysis. This method is amenable for online monitoring also.

Repairing Noise-Contaminated Low-Frequency Vibrational Spectra with an Attention U-Net

Low-frequency vibrational modes in infrared (IR) and Raman spectra, often termed molecular fingerprints, are sensitive probes of subtle structural changes and chemical interactions. However, their inherent weakness and susceptibility to environmental interference make them challenging to detect and analyze. To tackle this issue, we developed a deep learning denoising protocol based on an attention-enhanced U-net architecture. This model leverages the inherent correlations between high- and low-frequency vibrational modes within a molecule, effectively reconstructing low-frequency spectral features from their high-frequency counterparts. We demonstrate the effectiveness of this method by recovering low-frequency signals of trans-1,2-bis(4-pyridyl)ethylene (BPE) adsorbed on an Ag surface, a representative system for surface enhancement Raman spectroscopy (SERS). Notably, the trained model exhibits promising transferability to SERS spectra acquired under different surface and external field conditions. Furthermore, we applied this method to experimental IR and Raman spectra of BPE, achieving high-quality, low-frequency spectral recovery.

A comprehensive review on electromagnetic wave based non-invasive glucose monitoring in microwave frequencies

Diabetes is a chronic disease that affects millions of humans worldwide. This review article provides an analysis of the recent advancements in non-invasive blood glucose monitoring, detailing methods and techniques, with a special focus on Electromagnetic wave microwave glucose sensors. While optical, thermal, and electromagnetic techniques have been discussed, the primary emphasis is focussed on microwave frequency sensors due to their distinct advantages. Microwave sensors exhibit rapid response times, require minimal user intervention, and hold potential for continuous monitoring, renders them extremely potential for real-world applications. Additionally, their reduced susceptibility to physiological interferences further enhances their appeal. This review critically assesses the performance of microwave glucose sensors by considering factors such as accuracy, sensitivity, specificity, and user comfort. Moreover, it sheds light on the challenges and upcoming directions in the growth of microwave sensors, including the need for reduction and integration with wearable platforms. By concentrating on microwave sensors within the broader context of non-invasive glucose monitoring, this article aims to offer significant enlightenment that may drive further innovation in diabetes care.

Deep learning and feature reconstruction assisted vis-NIR calibration method for on-line monitoring of key growth indicators during kombucha production

Artificial intelligence (AI) technology is advancing the digitization and intelligence development of the food industry. A promising application is using deep learning-assisted visible near-infrared (vis-NIR) spectroscopy to monitor residual sugar and bacterial concentration in real-time, ensuring kombucha quality during production. The feature fingerprints of residual sugar and bacterial concentration were extracted by four variable selection algorithms and then reconstructed using serial and parallel processing methods. Based on these reconstructed features, Partial Least Squares (PLS) and Convolutional Neural Networks (1DCNN and 2DCNN) models were developed and compared. The experimental results showed that the 2DCNN model based on reconstruction features achieved superior performance. The RPDs of the residual sugar and bacterial concentrations models were 4.49 and 6.88, while the MAEs were 0.42 mg/mL and 0.04 (Abs), respectively. These results suggest that the proposed modeling strategy effectively supports quality control during kombucha production and provides a new perspective for spectral analysis.

A decision support tool to analyze the properties of wheat, cocoa beans and mangoes from their NIR spectra

Near infrared spectroscopy (NIRS) is an analytical technique that offers a real advantage over laboratory analysis in the food industry due to its low operating costs, rapid analysis, and non-destructive sampling technique. Numerous studies have shown the relevance of NIR spectra analysis for assessing certain food properties with the right calibration. This makes it useful in quality control and in the continuous monitoring of food processing. However, the NIR calibration process is difficult and time-consuming. Analysis methods and techniques vary according to the configuration of the NIR instrument, the sample to be analyzed and the attribute that is to be predicted. This makes calibration a challenge for many manufacturers. This paper aims to provide a data-driven methodology for developing a decision support tool based on the smart selection of NIRS wavelength to assess various food properties. The decision support tool based on the methodology has been evaluated on samples of cocoa beans, grains of wheat and mangoes. Promising results were obtained for each of the selected models for the moisture and fat content of cocoa beans (R2cv: 0.90, R2test: 0.93, RMSEP: 0.354%; R2cv: 0.73, R2test: 0.79, RMSEP: 0.913%), acidity and vitamin C content of mangoes (R2cv: 0.93, R2test: 0.97, RMSEP: 17.40%; R2cv: 0.66, R2test: 0.46, RMSEP: 0.848%), and protein content of wheat-DS2 (R2cv: 0.90, R2test:0.92, RMSEP: 0.490%) respectively. Moreover, the proposed approach allows results to be obtained that are better than benchmarks for the moisture and protein content of wheat-DS1 (R2cv: 0.90, R2test: 94, RMSEP: 0.337%; R2cv: 0.99, R2test: 0.99, RMSEP: 0.177%), respectively. PRACTICAL APPLICATION: This research introduces a practical tool aimed at determining the quality of food by identifying specific light wavelengths. However, it is important to acknowledge potential challenges, such as overfitting. Before implementation, it is crucial for further research to address and mitigate the issues to ensure the reliability and accuracy of the solution. If successfully applied, this tool could significantly enhance the accuracy of near-infrared spectroscopy in assessing food quality attributes. This advancement would provide invaluable support for decision-making in industries involved in food production, ultimately leading to better overall product quality for consumers.

A method for accurate identification of Uyghur medicinal components based on Raman spectroscopy and multi-label deep learning

Uyghur medicine is one of the four major ethnic medicines in China and is a component of traditional Chinese medicine. The intrinsic quality of Uyghur medicinal materials will directly affect the clinical efficacy of Uyghur medicinal preparations. However, in recent years, problems such as adulteration of Uyghur medicinal materials and foreign bodies with the same name still exist, so it is necessary to strengthen the quality control of Uyghur medicines to guarantee Uyghur medicinal efficacy. Identifying the components of Uyghur medicines can clarify the types of medicinal materials used, is a crucial step to realizing the quality control of Uyghur medicines, and is also an important step in screening the effective components of Uyghur medicines. Currently, the method of identifying the components of Uyghur medicines relies on manual detection, which has the problems of high toxicity of the unfolding agent, poor stability, high cost, low efficiency, etc. Therefore, this paper proposes a method based on Raman spectroscopy and multi-label deep learning model to construct a model Mix2Com for accurate identification of Uyghur medicine components. The experiments use computer-simulated mixtures as the dataset, introduce the Long Short-Term Memory Model (LSTM) and Attention mechanism to encode the Raman spectral data, use multiple parallel networks for decoding, and ultimately realize the macro parallel prediction of medicine components. The results show that the model is trained to achieve 90.76% accuracy, 99.41% precision, 95.42% recall value and 97.37% F1 score. Compared to the traditional XGBoost model, the method proposed in the experiment improves the accuracy by 49% and the recall value by 18%; compared with the DeepRaman model, the accuracy is improved by 9% and the recall value is improved by 14%. The method proposed in this paper provides a new solution for the accurate identification of Uyghur medicinal components. It helps to improve the quality standard of Uyghur medicinal materials, advance the research on screening of effective chemical components of Uyghur medicines and their action mechanisms, and then promote the modernization and development of Uyghur medicine.

Measurement of lung oxygenation by near-infrared spectroscopy in preterm infants with bronchopulmonary dysplasia

INTRODUCTION

It has recently been reported that it is possible to monitor lung oxygenation (rSO2L) by near-infrared spectroscopy (NIRS) in preterm infants with respiratory distress syndrome (RDS). Thus, our aim was to assess the possibility of monitoring rSO2L in infants with evolving and established bronchopulmonary dysplasia (BPD) and to evaluate if rSO2L correlates with BPD severity and other oxygenation indices.

METHODS

We studied 40 preterm infants with gestational age ≤30 weeks at risk for BPD. Patients were continuously studied for 2 h by NIRS at 28 ± 7 days of life and 36 weeks ± 7 days of postmenstrual age.

RESULTS

rSO2L was similar at the first and second NIRS recordings (71.8 ± 7.2 vs. 71.4 ± 4.2%) in the overall population, but it was higher in infants with mild than in those with moderate-to-severe BPD at both the first (73.3 ± 3.1 vs. 71.2 ± 3.2%, p = .042) and second (72.3 ± 2.8 vs. 70.5 ± 2.8, p = .049) NIRS recording. A rSO2L cutoff value of 71.6% in the first recording was associated with a risk for moderate-to-severe BPD with a sensitivity of 66% and a specificity of 60%. Linear regression analysis demonstrated a significant positive relationship between rSO2L and SpO2/FiO2 ratio (p = .013) and a/APO2 (p = .004).

CONCLUSIONS

Monitoring of rSO2L by NIRS in preterm infants with evolving and established BPD is feasible and safe. rSO2L was found to be higher in infants with mild BPD, and predicts the risk for developing moderate-to-severe BPD and correlates with other indices of oxygenation.

Near-Infrared Spectroscopy Analysis of the Phytic Acid Content in Fuzzy Cottonseed Based on Machine Learning Algorithms

Cottonseed is rich in oil and protein. However, its antinutritional factor content, of phytic acid (PA), has limited its utilization. Near-infrared (NIR) spectroscopy, combined with chemometrics, is an efficient and eco-friendly analytical technique for crop quality analysis. Despite its potential, there are currently no established NIR models for measuring the PA content in fuzzy cottonseeds. In this research, a total of 456 samples of fuzzy cottonseed were used as the experimental materials. Spectral pre-treatments, including first derivative (1D) and standard normal variable transformation (SNV), were applied, and the linear partial least squares (PLS), nonlinear support vector machine (SVM), and random forest (RF) methods were utilized to develop accurate calibration models for predicting the content of PA in fuzzy cottonseed. The results showed that the spectral pre-treatment significantly improved the prediction performance of the models, with the RF model exhibiting the best prediction performance. The RF model had a coefficient of determination in prediction (R2p) of 0.9114, and its residual predictive deviation (RPD) was 3.9828, which indicates its high accuracy in measuring the PA content in fuzzy cottonseed. Additionally, this method avoids the costly and time-consuming delinting and crushing of cottonseeds, making it an economical and environmentally friendly alternative.

Research on detection of potato varieties based on spectral imaging analytical algorithm

Potatoes are popular among consumers due to their high yield and delicious taste. However, due to the numerous varieties of potatoes, different varieties are suitable for different processing methods. Therefore, it is necessary to distinguish varieties after harvest to meet the needs of processing enterprises and consumers. In this study, a new visible-near-infrared spectroscopic analysis method was proposed, which can achieve detection of five potato varieties. The method measures the transmission and reflection spectra of potatoes using a spectral acquisition system, encodes one-dimensional spectra into two-dimensional images using Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), Markov Transition Field (MTF) and Recurrence Plot (RP), and improves the coordinated attention mechanism module and embeds the improved module into the ConvNeXt V2 model to build the ConvNeXt V2-CAP model for potato variety classification. The results show that compared with directly using one-dimensional classification models, image encoding of spectral data for classification greatly improves the accuracy. Among them, the best accuracy of 99.54% is achieved by using GADF image encoding of transmission spectra combined with the ConvNeXt V2-CAP model for classification, which is 16.28% higher than the highest accuracy of the one-dimensional classification model. The CAP attention mechanism module improves the performance of the model, especially when the dataset is small. When the training set is reduced to 150 images, the accuracy of the model is improved by 2.33% compared to the original model. Therefore, it is feasible to classify potato varieties using visible-near infrared spectroscopy and image encoding technology.

ResD-Net: A model for rapid prediction of antioxidant activity in gentian root using FT-IR spectroscopy

Gentian, an herb resource known for its antioxidant properties, has garnered significant attention. However, existing methods are time-consuming and destructive for assessing the antioxidant activity in gentian root samples. In this study, we propose a method for swiftly predicting the antioxidant activity of gentian root using FT-IR spectroscopy combined with chemometrics. We employed machine learning and deep learning models to establish the relationship between FT-IR spectra and DPPH free radical scavenging activity. The results of model fitting reveal that the deep learning model outperforms the machine learning model. The model's performance was enhanced by incorporating the Double-Net and residual connection strategy. The enhanced model, named ResD-Net, excels in feature extraction and also avoids gradient vanishing. The ResD-Net model achieves an R2 of 0.933, an RMSE of 0.02, and an RPD of 3.856. These results support the accuracy and applicability of this method for rapidly predicting antioxidant activity in gentian root samples.

Advancements, limitations and challenges in hyperspectral imaging for comprehensive assessment of wheat quality: An up-to-date review

The potential of hyperspectral imaging technology (HIT) for the determination of physicochemical and nutritional components, evaluation of fungal/mycotoxins contamination, wheat varieties classification, identification of non-mildew-damaged wheat kernels, as well as detection of flour adulteration is comprehensively illustrated and reviewed. The latest findings (2018-2023) of HIT in wheat quality evaluation through internal and external attributes are compared and summarized in detail. The limitations and challenges of HIT to improve assessment accuracy are clearly described. Additionally, various practical recommendations and strategies for the potential application of HIT are highlighted. The future trends and prospects of HIT in evaluating wheat quality are also mentioned. In conclusion, HIT stands as a cutting-edge technology with immense potential for revolutionizing wheat quality evaluation. As advancements in HIT continue, it will play a pivotal role in shaping the future of wheat quality assessment and contributing to a more sustainable and efficient food supply chain.

Nondestructive Determination of Epicarp Hardness of Passion Fruit Using Near-Infrared Spectroscopy during Storage

The hardness of passion fruit is a critical feature to consider when determining maturity during post-harvest storage. The capacity of near-infrared diffuse reflectance spectroscopy (NIRS) for non-destructive detection of outer and inner hardness of passion fruit epicarp was investigated in this work. The passion fruits' spectra were obtained using a near-infrared spectrometer with a wavelength range of 10,000-4000 cm-1. The hardness of passion fruit's outer epicarp (F1) and inner epicarp (F2) was then measured using a texture analyzer. Moving average (MA) and mean-centering (MC) techniques were used to preprocess the collected spectral data. Competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), and uninformative variable elimination (UVE) were used to pick feature wavelengths. Grid-search-optimized random forest (Grids-RF) models and genetic-algorithm-optimized support vector regression (GA-SVR) models were created as part of the modeling process. After MC preprocessing and CARS selection, MC-CARS-Grids-RF model with 7 feature wavelengths had the greatest prediction ability for F1. The mean square error of prediction set (RMSEP) was 0.166 gN. Similarly, following MA preprocessing, the MA-Grids-RF model displayed the greatest predictive performance for F2, with an RMSEP of 0.101 gN. When compared to models produced using the original spectra, the R2P for models formed after preprocessing and wavelength selection improved. The findings showed that near-infrared spectroscopy may predict the hardness of passion fruit epicarp, which can be used to identify quality during post-harvest storage.

Deep learning assisted XRF spectra classification

EDXRF spectrometry is a well-established and often-used analytical technique in examining materials from which cultural heritage objects are made. The analytical results are traditionally subjected to additional multivariate analysis for archaeometry studies to reduce the initial data's dimensionality based on informative features. Nowadays, artificial intelligence (AI) techniques are used more for this purpose. Different soft computing techniques are used to improve speed and accuracy. Choosing the most suitable AI method can increase the sustainability of the analytical process and postprocessing activities. An autoencoder neural network has been designed and used as a dimension reduction tool of initial [Formula: see text] data collected in the raw EDXRF spectra, containing information about the selected points' elemental composition on the canvas paintings' surface. The autoencoder network design enables the best possible reconstruction of the original EDXRF spectrum and the most informative feature extraction, which has been used for dimension reduction. Such configuration allows for efficient classification algorithms and their performances. The autoencoder neural network approach is more sustainable, especially in processing time consumption and experts' manual work.

Non-neotissue constituents as underestimated confounders in the assessment of tissue engineered constructs by near-infrared spectroscopy

Non-destructive assessments are required for the quality control of tissue-engineered constructs and the optimization of the tissue culture process. Near-infrared (NIR) spectroscopy coupled with machine learning (ML) provides a promising approach for such assessment. However, due to its nonspecific nature, each spectrum incorporates information on both neotissue and non-neotissue constituents of the construct; the effect of these constituents on the NIR-based assessments of tissue-engineered constructs has been overlooked in previous studies. This study investigates the effect of scaffolds, growth factors, and buffers on NIR-based assessments of tissue-engineered constructs. To determine if these non-neotissue constituents have a measurable effect on the NIR spectra of the constructs that can introduce bias in their assessment, nine ML algorithms were evaluated in classifying the NIR spectra of engineered cartilage according to the scaffold used to prepare the constructs, the growth factors added to the culture media, and the buffers used for storing the constructs. The effect of controlling for these constituents was also evaluated using controlled and uncontrolled NIR-based ML models for predicting tissue maturity as an example of neotissue-related properties of interest. Samples used in this study were prepared using norbornene-modified hyaluronic acid scaffolds with or without the conjugation of an N-cadherin mimetic peptide. Selected samples were supplemented with transforming growth factor-beta1 or bone morphogenetic protein-9 growth factor. Some samples were frozen in cell lysis buffer, while the remaining samples were frozen in PBS until required for NIR analysis. The ML models for classifying the spectra of the constructs according to the four constituents exhibited high to fair performances, with F1 scores ranging from 0.9 to 0.52. Moreover, controlling for the four constituents significantly improved the performance of the models for predicting tissue maturity, with improvement in F1 scores ranging from 0.09 to 0.77. In conclusion, non-neotissue constituents have measurable effects on the NIR spectra of tissue-engineered constructs that can be detected by ML algorithms and introduce bias in the assessment of the constructs by NIR spectroscopy. Therefore, controlling for these constituents is necessary for reliable NIR-based assessments of tissue-engineered constructs.

Non-Invasive Glucose Sensing Technologies and Products: A Comprehensive Review for Researchers and Clinicians

Diabetes Mellitus incidence and its negative outcomes have dramatically increased worldwide and are expected to further increase in the future due to a combination of environmental and social factors. Several methods of measuring glucose concentration in various body compartments have been described in the literature over the years. Continuous advances in technology open the road to novel measuring methods and innovative measurement sites. The aim of this comprehensive review is to report all the methods and products for non-invasive glucose measurement described in the literature over the past five years that have been tested on both human subjects/samples and tissue models. A literature review was performed in the MDPI database, with 243 articles reviewed and 124 included in a narrative summary. Different comparisons of techniques focused on the mechanism of action, measurement site, and machine learning application, outlining the main advantages and disadvantages described/expected so far. This review represents a comprehensive guide for clinicians and industrial designers to sum the most recent results in non-invasive glucose sensing techniques' research and production to aid the progress in this promising field.

Estimating the sensory-associated metabolites profiling of matcha based on PDO attributes as elucidated by NIRS and MS approaches

Matcha has been globally valued by consumers for its distinctive fragrance and flavor since ancient times. Currently, the protected designation of origin (PDO) certified matcha, characterized by unique sensory attributes, has garnered renewed interest from consumers and the industry. Given the challenges associated with assessing sensory perceptions, the origin of PDO-certified matcha samples from Guizhou was determined using NIRS and LC-MS platforms. Notably, the accuracy of our established attribute models, based on informative wavelengths selected by the CARS-PLS method, exceeds 0.9 for five sensory attributes, particularly the particle homogeneity attribute (with a validation correlation coefficient of 0.9668). Moreover, an LC-MS method was utilized to analyze non-target matcha metabolites to identify the primary flavor compounds associated with each flavor attribute and to pinpoint the key constituents responsible for variations in grade and flavor intensity. Additionally, high three-way intercorrelations between descriptive sensory attributes, metabolites, and the selected informative wavelengths were observed through network analysis, with correlation coefficients calculated to quantify these relationships. In this research, the integration of matcha chemical composition and sensory panel data was utilized to develop predictive models for assessing the flavor profile of matcha based on its chemical properties.

The diagnostic value of pulmonary near-infrared spectroscopy in the early distinction of neonatal pneumonia from transient tachypnea of the newborn

AIM

Pulmonary near-infrared spectroscopy (NIRS) is a new and promising tool for diagnosis of neonatal respiratory diseases (RD). The study aimed to determine the role of pulmonary regional oxygen saturation (pRSO2 ) values obtained by NIRS in the early distinction of neonatal pneumonia (NP) from transient tachypnea of the newborn (TTN).

METHODS

This prospective, observational, double-blind study was conducted in neonatal intensive care unit (NICU) between 2020 and 2021. Late preterm and term newborns hospitalized in the NICU due to the diagnosis of TTN and NP were included. Cerebral RSO2 and pRSO2 values were measured during the 1st, 24th, 48th, and 72nd hours of hospitalization, using NIRS.

RESULTS

Of the eligible 40 infants, 65% (n: 26) were diagnosed as TTN and 35% (n: 16) as NP. The pRSO2 values were significantly higher in the TTN group than the NP group for both apexes (75.3 ± 8.7 vs. 69 ± 5.4, p: .018, respectively) and lateral lung (77.8 ± 6 vs. 72.7 ± 6.2, p: .016, respectively) in the 1st hour of hospitalization. There were significant differences in pRSO2 apex and pRSO2 lateral values between the 1st and 24th hours of hospitalization and the 24th and 48th hours in the NP group (p2 : .001 for both). The optimal pRSO2 apex cut-off value was >72% to predict the diagnosis of NP with a sensitivity of 78.6% and a specificity of 69.2%.

CONCLUSION

Pulmonary NIRS may be considered as a feasible and promising diagnostic tool in late preterm and term infants with RD. It may also be helpful for the early differentiation of NP from TTN and the courses of these diseases.

Rapid and Green Classification Method of Bacteria Using Machine Learning and NIR Spectroscopy

Green Chemistry is a vital and crucial instrument in achieving pollution control, and it plays an important role in helping society reach the Sustainable Development Goals (SDGs). NIR (near-infrared spectroscopy) has been utilized as an alternate technique for molecular identification, making the process faster and less expensive. Near-infrared diffuse reflectance spectroscopy and Machine Learning (ML) algorithms were utilized in this study to construct identification and classification models of bacteria such as Escherichia coli, Salmonella enteritidis, Enterococcus faecalis and Listeria monocytogenes. Furthermore, divide these bacteria into Gram-negative and Gram-positive groups. The green and quick approach was created by combining NIR spectroscopy with a diffuse reflectance accessory. Using infrared spectral data and ML techniques such as principal component analysis (PCA), hierarchical cluster analysis (HCA) and K-Nearest Neighbor (KNN), It was feasible to accomplish the identification and classification of four bacteria and classify these bacteria into two groups: Gram-positive and Gram-negative, with 100% accuracy. We may conclude that our study has a high potential for bacterial identification and classification, as well as being consistent with global policies of sustainable development and green analytical chemistry.

Diagnostic and monitoring applications using Near infrared (NIR) Spectroscopy in cancer and other diseases

Early cancer diagnosis plays a critical role in improving treatment outcomes and increasing survival rates for certain cancers. NIR spectroscopy offers a rapid and cost-effective approach to evaluate the optical properties of tissues at the microvessel level and provides valuable molecular insights. The integration of NIR spectroscopy with advanced data-driven algorithms in portable instruments has made it a cutting-edge technology for medical applications. NIR spectroscopy is a simple, non-invasive and affordable analytical tool that complements expensive imaging modalities such as functional magnetic resonance imaging, positron emission tomography and computed tomography. By examining tissue absorption, scattering, and concentrations of oxygen, water, and lipids, NIR spectroscopy can reveal inherent differences between tumor and normal tissue, often revealing specific patterns that help stratify disease. In addition, the ability of NIR spectroscopy to assess tumor blood flow, oxygenation, and oxygen metabolism provides a key paradigm for its application in cancer diagnosis. This review evaluates the effectiveness of NIR spectroscopy in the detection and characterization of disease, particularly in cancer, with or without the incorporation of chemometrics and machine learning algorithms. The report highlights the potential of NIR spectroscopy technology to significantly improve discrimination between benign and malignant tumors and accurately predict treatment outcomes. In addition, as more medical applications are studied in large patient cohorts, consistent advances in clinical implementation can be expected, making NIR spectroscopy a valuable adjunct technology for cancer therapy management. Ultimately, the integration of NIR spectroscopy into cancer diagnostics promises to improve prognosis by providing critical new insights into cancer patterns and physiology.