Discrimination between human and animal blood by attenuated total reflection Fourier transform-infrared spectroscopy

Screening of malaria infections in human blood samples with varying parasite densities and anaemic conditions using AI-Powered mid-infrared spectroscopy

BACKGROUND

Effective testing for malaria, including the detection of infections at very low densities, is vital for the successful elimination of the disease. Unfortunately, existing methods are either inexpensive but poorly sensitive or sensitive but costly. Recent studies have shown that mid-infrared spectroscopy coupled with machine learning (MIRs-ML) has potential for rapidly detecting malaria infections but requires further evaluation on diverse samples representative of natural infections in endemic areas. The aim of this study was, therefore, to demonstrate a simple AI-powered, reagent-free, and user-friendly approach that uses mid-infrared spectra from dried blood spots to accurately detect malaria infections across varying parasite densities and anaemic conditions.

METHODS

Plasmodium falciparum strains NF54 and FCR3 were cultured and mixed with blood from 70 malaria-free individuals to create various malaria parasitaemia and anaemic conditions. Blood dilutions produced three haematocrit ratios (50%, 25%, 12.5%) and five parasitaemia levels (6%, 0.1%, 0.002%, 0.00003%, 0%). Dried blood spots were prepared on Whatman™ filter papers and scanned using attenuated total reflection-Fourier Transform Infrared (ATR-FTIR) for machine-learning analysis. Three classifiers were trained on an 80%/20% split of 4655 spectra: (I) high contrast (6% parasitaemia vs. negative), (II) low contrast (0.00003% vs. negative) and (III) all concentrations (all positive levels vs. negative). The classifiers were validated with unseen datasets to detect malaria at various parasitaemia levels and anaemic conditions. Additionally, these classifiers were tested on samples from a population survey in malaria-endemic villages of southeastern Tanzania.

RESULTS

The AI classifiers attained over 90% accuracy in detecting malaria infections as low as one parasite per microlitre of blood, a sensitivity unattainable by conventional RDTs and microscopy. These laboratory-developed classifiers seamlessly transitioned to field applicability, achieving over 80% accuracy in predicting natural P. falciparum infections in blood samples collected during the field survey. Crucially, the performance remained unaffected by various levels of anaemia, a common complication in malaria patients.

CONCLUSION

These findings suggest that the AI-driven mid-infrared spectroscopy approach holds promise as a simplified, sensitive and cost-effective method for malaria screening, consistently performing well despite variations in parasite densities and anaemic conditions. The technique simply involves scanning dried blood spots with a desktop mid-infrared scanner and analysing the spectra using pre-trained AI classifiers, making it readily adaptable to field conditions in low-resource settings. In this study, the approach was successfully adapted to field use, effectively predicting natural malaria infections in blood samples from a population-level survey in Tanzania. With additional field trials and validation, this technique could significantly enhance malaria surveillance and contribute to accelerating malaria elimination efforts.

The Evaluation of Artificial Intelligence Technology for the Differentiation of Fresh Human Blood Cells From Other Species' Blood in the Investigation of Crime Scenes

OBJECTIVES

The current study used the deep machine learning approach to differentiate human blood specimens from cow, goat, and chicken blood stains based on cell morphology.

METHODS

A total of 1,955 known Giemsa-stained digitized images were acquired from the blood of humans, cows, goats, and chickens. To train the deep learning models, the well-known VGG16, Resnet18, and Resnet34 algorithms were used. Based on the image analysis, confusion matrices were generated.

RESULTS

Findings showed that the F1 score for the chicken, cow, goat, and human classes were all equal to 1.0 for each of the three algorithms. The Matthews correlation coefficient (MCC) was 1 for chickens, cows, and humans in all three algorithms, while the MCC score was 0.989 for goats by ResNet18, and it was 0.994 for both ResNet34 and VGG16 algorithms. The three algorithms showed 100% sensitivity, specificity, and positive and negative predictive values for the human, cow, and chicken cells. For the goat cells, the data showed 100% sensitivity and negative predictive values with specificity and positive predictive values ranging from 98.5% to 99.6%.

CONCLUSION

These data showed the importance of deep learning as a potential tool for the differentiation of the species of origin of fresh crime scene blood stains.

Enhancing forensic investigations: Identifying bloodstains on various substrates through ATR-FTIR spectroscopy combined with machine learning algorithms

The forensic analysis of bloodstains on various substrates plays a crucial role in criminal investigations. This study presents a novel approach for analyzing bloodstains using Attenuated Total Reflectance Fourier Transform Infrared spectroscopy (ATR-FTIR) in combination with machine learning. ATR-FTIR offers non-destructive and non-invasive advantages, requiring minimal sample preparation. By detecting specific chemical bonds in blood components, it enables the differentiation of various body fluids. However, the subjective interpretation of the spectra poses challenges in distinguishing different fluids. To address this, we employ machine learning techniques. Machine learning is extensively used in chemometrics to analyze chemical data, build models, and extract useful information. This includes both unsupervised learning and supervised learning methods, which provide objective characterization and differentiation. The focus of this study was to identify human and porcine blood on substrates using ATR-FTIR spectroscopy. The substrates included paper, plastic, cloth, and wood. Data preprocessing was performed using Principal Component Analysis (PCA) to reduce dimensionality and analyze latent variables. Subsequently, six machine learning algorithms were used to build classification models and compare their performance. These algorithms comprise Partial Least Squares Discriminant Analysis (PLS-DA), Decision Trees (DT), Logistic Regression (LR), Naive Bayes Classifier (NBC), Support Vector Machine (SVM), and Neural Network (NN). The results indicate that the PCA-NN model provides the optimal solution on most substrates. Although ATR-FTIR spectroscopy combined with machine learning effectively identifies bloodstains on substrates, the performance of different identification models still varies based on the type of substrate. The integration of these disciplines enables researchers to harness the power of data-driven approaches for solving complex forensic problems. The objective differentiation of bloodstains using machine learning holds significant implications for criminal investigations. This technique offers a non-destructive, simple, selective, and rapid approach for forensic analysis, thereby assisting forensic scientists and investigators in determining crucial evidence related to bloodstains.

Forensic analysis of biological fluid stains on substrates by spectroscopic approaches and chemometrics: A review

BACKGROUND

Bodily fluid stains are one of the most relevant evidence that can be found at the crime scene as it provides a wealth of information to the investigators. They help to report on the individuals involved in the crime, to check alibis, or to determine the type of crime that has been committed. They appear as stains in different types of substrates, some of them porous, which can interfere in the analysis. The spectroscopy techniques combined with chemometrics are showing increasing potential for their use in the analysis of such samples due to them being fast, sensitive, and non-destructive.

FINDINGS

This is a comprehensive review of the studies that used different spectroscopic techniques followed by chemometrics for analysing biological fluid stains on several surfaces, and under various conditions. It focuses on the bodily fluid stains and the most suitable spectroscopic techniques to study forensic scientific problems such as the substrate's characteristics, the influence of ambient conditions, the aging process of the bodily fluids, the presence of animal bodily fluids and non-biological fluids (interfering substances), and the bodily fluid mixtures. The most widely used techniques were Raman spectroscopy and attenuated total reflection Fourier transform infrared spectroscopy (ATR FTIR). Nonetheless, other non-destructive techniques have been also used, like near infrared hyperspectral imaging (HSI-NIR) or surface enhanced Raman spectroscopy (SERS), among others. This work provides the criteria for the selection of the most promising non-destructive techniques for the effective in situ detection of biological fluid stains at crime scene investigations.

SIGNIFICANCE AND NOVELTY

The use of the proper spectroscopic and chemometric approaches on the crime scene is expected to improve the support of forensic sciences to criminal investigations. Evidence may be analysed in a non-destructive manner and kept intact for further analysis. They will also speed up forensic investigations by allowing the selection of relevant samples from occupational ones.

Scattering correction for samples with cylindrical domains measured with polarized infrared spectroscopy

Scattering artifacts are one of the most common effects distorting transmission spectra in Fourier-Transform Infrared spectroscopy. Their increased impact, strongly diminishing the quantitative and qualitative power of IR spectroscopy, is especially observed for structures with a size comparable to the radiation wavelength. To tackle this problem, a wide range of preprocessing techniques based on the Extended Multiplicative Scattering Correction method was developed, using physical properties to remove scattering presence in the spectra. However, until recently those algorithms were mostly focused on spherically shaped samples, for example, cells. Here, an algorithm for samples with cylindrical domains is described, with additional implementation of a linearly polarized light case, which is crucial for the growing field of polarized IR imaging and spectroscopy. An open-source code with GPU based implementation is provided, with a calculation time of several seconds per spectrum. Optimizations done to improve the throughput of this algorithm allow the application of this method into the standard preprocessing pipeline of small datasets.

Attenuated Total Reflection Fourier Transform Infrared Spectroscopy for Forensic Screening of Long-Term Alcohol Consumption from Human Nails

Fourier transform infrared (FT-IR) spectroscopy is used throughout forensic laboratories for many applications. FT-IR spectroscopy can be useful with ATR accessories in forensic analysis for several reasons. It provides excellent data quality combined with high reproducibility, with minimal user-induced variations and no sample preparation. Spectra from heterogeneous biological systems, including the integumentary system, can be associated with hundreds or thousands of biomolecules. The nail matrix of keratin possesses a complicated structure with captured circulating metabolites whose presence may vary in space and time depending on context and history. We developed a new approach by using machine-learning (ML) tools to leverage the potential and enhance the selectivity of the instrument, create classification models, and provide invaluable information saved in human nails with statistical confidence. Here, we report chemometric analysis of ATR FT-IR spectra for the classification and prediction of long-term alcohol consumption from nail clippings in 63 donors. A partial least squares discriminant analysis (PLS-DA) was used to create a classification model that was validated against an independent data set which resulted in 91% correctly classified spectra. However, when considering the prediction results at the donor level, 100% accuracy was achieved, and all donors were correctly classified. To the best of our knowledge, this proof-of-concept study demonstrates for the first time the ability of ATR FT-IR spectroscopy to discriminate donors who do not drink alcohol from those who drink alcohol on a regular basis.

Differentiation of blood and environmental interfering stains on substrates by Chemometrics-Assisted ATR FTIR spectroscopy

Blood is the most common and relevant bodily fluid that can be found in crime scenes. It is critical to correctly identify it, and to be able to differentiate it from other substances that may also appear at the crime scene. In this work, several stains of blood, chocolate, ketchup, and tomato sauce on five different substrates (plywood, metal, gauze, denim, and glass) were analysed by ATR FTIR spectroscopy assisted with orthogonal partial least square-discriminant analysis (OPLS-DA) models. It was possible to differentiate blood from the environmental interfering substances independently of the substrate they were on, and to differentiate bloodstains according to the substrate they were deposited on. These results represent a proof-of-concept that open new horizons to differentiate bloodstains from other interfering substances on common substrates present in crime scenes.

Molecular breast cancer subtype identification using photoacoustic spectral analysis and machine learning at the biomacromolecular level

Breast cancer threatens the health of women worldwide, and its molecular subtypes largely determine the therapy and prognosis of patients. However, an uncomplicated and accurate method to identify subtypes is currently lacking. This study utilized photoacoustic spectral analysis (PASA) based on the partial least squares discriminant algorithm (PLS-DA) to identify molecular breast cancer subtypes at the biomacromolecular level in vivo. The area of power spectrum density (APSD) was extracted to semi-quantify the biomacromolecule content. The feature wavelengths were obtained via the variable importance in projection (VIP) score and the selectivity ratio (Sratio), to identify the biomarkers. The PASA achieved an accuracy of 84%. Most of the feature wavelengths fell into the collagen-dominated absorption waveband, which was consistent with the histopathological results. This paper proposes a successful method for identifying molecular breast cancer subtypes and proves that collagen can be treated as a biomarker for molecular breast cancer subtyping.

Overcoming obstacles: Analysis of blood and semen stains washed with different chemicals with ATR-FTIR

INTRODUCTION

Blood and semen stains are the most common biological stains encountered at crime scenes. The washing of biological stains is a common application that perpetrators use to spoil the crime scene. With a structured experiment approach, this study aims to investigate the effects of washing with various chemicals on the ATR-FTIR detection of blood and semen stains on cotton.

MATERIALS AND METHODS

On cotton pieces, a total of 78 blood and 78 semen stains were applied, and each group of six stains was immersed or mechanically cleaned in water, 40% methanol, 5% sodium hypochlorite solution, 5% hypochlorous acid solution, 5 g/L soap dissolved pure water, and 5 g/L dishwashing detergent dissolved water. ATR-FTIR spectra gathered from all stains and analyzed with chemometric tools.

RESULTS AND DISCUSSION

According to performance parameters of developed models, PLS-DA is a powerful tool for discrimination of washing chemical for both washed blood and semen stains. Results from this study show that FTIR is promising for use in detecting blood and semen stains that have become invisible to the naked eye due to washing of the findings.

CONCLUSION

Our approach allows blood and semen to be detected on cotton pieces using FTIR combined with chemometrics, even though it is not visible to the naked eye. Washing chemicals also can be distinguished via FTIR spectra of stains.

Identification of blood species based on surface-enhanced Raman scattering spectroscopy and convolutional neural network

The identification of blood species is of great significance in many aspects such as forensic science, wildlife protection, and customs security and quarantine. Conventional Raman spectroscopy combined with chemometrics is an established method for identification of blood species. However, the Raman spectrum of trace amount of blood could hardly be obtained due to the very small cross-section of Raman scattering. In order to overcome this limitation, surface-enhanced Raman scattering (SERS) was adopted to analyze trace amount of blood. The 785 nm laser was selected as the optimal laser to acquire the SERS spectra, and the blood SERS spectra of 19 species were measured. The convolutional neural network (CNN) was used to distinguish the blood of 19 species including human. The recognition accuracy of the blood species was obtained with 98.79%. Our study provides an effective and reliable method for identification and classification of trace amount of blood.

Determination of blood species using echelle Raman spectrometer and surface enhanced Raman spectroscopy

Blood species identification of human and animals has attracted much attention in the areas of customs inspection and forensic science. The combination of vibrational spectroscopy and machine learning has been proven to be feasible and effective for this purpose. However, the popularization of this technology needs instrument which is compact, robust and more suitable for field application. Besides the quantity of the blood sample should be as little as possible. In this study, we proposed a system using echelle Raman spectrometer combined with surface enhanced Raman spectroscopy (SERS), which protocol combines the advantages of broadband and high resolution of echelle Raman spectrometer with the advantages of high SERS spectral sensitivity. The SERS spectra of 26 species including human were collected with echelle Raman spectrometer, and the convolutional neural network was used for species identification, with an accuracy rate of over 94%. The feasibility, validity and reliability of the combination of echelle Raman spectrometer and SERS for blood species identification were realized.

Analysis and comparison of machine learning methods for blood identification using single-cell laser tweezer Raman spectroscopy

Raman spectroscopy, a "fingerprint" spectrum of substances, can be used to characterize various biological and chemical samples. To allow for blood classification using single-cell Raman spectroscopy, several machine learning algorithms were implemented and compared. A single-cell laser optical tweezer Raman spectroscopy system was established to obtain the Raman spectra of red blood cells. The Boruta algorithm extracted the spectral feature frequency shift, reduced the spectral dimension, and determined the essential features that affect classification. Next, seven machine learning classification models are analyzed and compared based on the classification accuracy, precision, and recall indicators. The results show that support vector machines and artificial neural networks are the two most appropriate machine learning algorithms for single-cell Raman spectrum blood classification, and this finding provides essential guidance for future research studies.

Attenuated total reflection-Fourier transform infrared spectroscopy: a universal analytical technique with promising applications in forensic analyses

Contemporary criminal investigations are based on the statements made by the victim and the eyewitnesses. They also rely on the physical evidences found in the crime scene. These evidences, and more particularly biological ones, have a great judicial value in the courtroom. They are usually used to revoke the suspect’s allegations and confirm or refute the statements made by the victim and the witnesses. Stains of body fluids are biological evidences highly sought by forensic investigators. In many criminal cases, the success of the investigation relies on the correct identification and classification of these stains. Therefore, the adoption of reliable and accurate forensic analytical methods seems to be of vital importance to attain this objective. Attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) is a modern and universal analytical technique capable of fingerprint recognition of the analyte using minimal amount of the test sample. The current systematic review aims to through light on the fundamentals of this technique and to illustrate its wide range of applications in forensic investigations. ATR-FTIR is a nondestructive technique which has demonstrated an exceptional efficiency in detecting, identifying and discriminating between stains of various types of body fluids usually encountered in crime scenes. The ATR-FTIR spectral data generated from bloodstains can be used to deduce a wealth of information related to the donor species, age, gender, and race. These data can also be exploited to discriminate between stains of different types of bloods including menstrual and peripheral bloods. In addition, ATR-FTIR has a great utility in the postmortem investigations. More particularly, in estimating the postmortem interval and diagnosing death caused by extreme weather conditions. It is also useful in diagnosing some ambiguous death causes such as fatal anaphylactic shock and diabetic ketoacidosis.

Detection and identification of drug traces in latent fingermarks using Raman spectroscopy

Recent advancements in analytical techniques have greatly contributed to the analysis of latent fingermarks' (LFMs) "touch chemistry" and identification of materials that a suspect might have come into contact with. This type of information about the FM donor is valuable for criminal investigations because it narrows the pool of suspects. It is estimated that at least 30 million people around the world take over-the-counter and prescription nonsteroidal anti-inflammatory drugs (NSAIDs) for pain relief, headaches and arthritis every day. The daily use of such drugs can lead to an increased risk of their abuse. In the present study, Raman spectroscopy combined with multivariate statistical analysis was used for the detection and identification of drug traces in LFMs when NSAID tablets of aspirin, ibuprofen, diclofenac, ketoprofen and naproxen have been touched. Partial least squares discriminant analysis of Raman spectra showed an excellent separation between natural FMs and all NSAID-contaminated FMs. The developed classification model was externally validated using FMs deposited by a new donor and showed 100% accuracy on a FM level. This proof-of-concept study demonstrated the great potential of Raman spectroscopy in the chemical analysis of LFMs and the detection and identification of drug traces in particular.

Hierarchical classification models and Handheld NIR spectrometer to human blood stains identification on different floor tiles

One of the most important types of evidence in certain criminal investigations is traces of human blood. For a detailed investigation, blood samples must be identified and collected at the crime scene. The present study aimed to evaluate the potential of the identification of human blood in stains deposited on different types of floor tiles (five types of ceramics and four types of porcelain tiles) using a portable NIR instrument. Hierarchical models were developed by combining multivariate analysis techniques capable of identifying traces of human blood (HB), animal blood (AB) and common false positives (CFP). The spectra of the dried stains were obtained using a portable MicroNIR spectrometer (Viavi). The hierarchical models used two decision rules, the first to separate CFP and the second to discriminate HB from AB. The first decision rule, used to separate the CFP, was based on the Q-Residual criterion considering a PCA model. For the second rule, used to discriminate HB and AB, the Q-Residual criterion were tested as obtained from a PCA model, a One-Class SIMCA model, and a PLS-DA model. The best results of sensitivity and specificity, both equal to 100%, were obtained when a PLS-DA model was employed as the second decision rule. The hierarchical classification models built for these same training sets using a PCA or SIMCA model also obtained excellent sensitivity results for HB classification, with values above 94% and 78% of specificity. No CFP samples were misclassified. Hierarchical models represent a significant advance as a methodology for the identification of human blood stains at crime scenes.

Recent advances of vibrational spectroscopy and chemometrics for forensic biological analysis

Biological materials found at a crime scene are crucially important evidence for forensic investigation because they provide contextual information about a crime and can be linked to the donor-individuals through combination with DNA analysis. Applications of vibrational spectroscopy to forensic biological analysis have been emerging because of its advantageous characteristics such as the non-destructivity, rapid measurement, and quantitative evaluation, compared to most current methods based on histological observation or biochemical techniques. This review presents an overview of recent developments in vibrational spectroscopy for forensic biological analysis. We also emphasize chemometric techniques, which can elicit reliable and advanced analytical outputs from highly complex spectral data from forensic biological materials. The analytical subjects addressed herein include body fluids, hair, soft tissue, bones, and bioagents. Promising applications for various analytical purposes in forensic biology are presented. Simultaneously, future avenues of study requiring further investigation are discussed.

On the discrimination between facial creams of different brands using Raman Spectroscopy and partial least squares discriminant analysis for forensic application

Determining the origin of cosmetic traces is an important aspect of forensic investigations, that helps linking a suspect to a crime. Such type of evidence can help further narrow down the undergoing investigations. This paper reports the first use of Raman Spectroscopy (RS) coupled with the exploratory principal component analysis (PCA) and supervised partial least squares-discriminant analysis (PLS-DA) in facial creams. 40 facial cream samples of 8 different brands were studied in this work. Preliminary assessments through visual inspection of their Raman spectra revealed the presence of oxides, titanium dioxide, castor seed oil, and beeswax. Also, the peaks of alkyne groups were indicative of the presence of talc or mica compounds. The exploratory PCA correctly segregated the samples into 8 clusters and the supervised PLS-DA model correctly classified them into 8 classes. Further evaluation of the performance of the trained PLS-DA model resulted in perfect classification shown by the receiver operating characteristic (ROC) curves. The PLS-DA model also resulted in 100% accuracy of correctly assigning the brand on the face wipes on each of the five substrates viz. cotton, dry and wet tissue paper, nylon substrate, and polyester. This validation was done treating these samples as unknowns. The study has a potential for use under actual forensic casework conditions.

Surface enhanced Raman scattering specificity for detection and identification of dried bloodstains

Surface enhanced Raman spectroscopy (SERS) provides highly specific vibrational signatures identifying dried blood for a variety of forensic applications. SERS spectra on Au nanoparticle substrates excited at 785 nm are found to identify dried stains of human and nonhuman blood from seven animals, and distinguish stains due to menstrual and peripheral blood. In addition, the unique SERS bloodstain spectrum is distinct from the SERS spectra of thirty red-brown stains of potential household substances that could be visually mistaken for bloodstains and from food stains that have been shown to give positive results with presumptive colorimetric blood tests. Finally, a SERS swab procedure has been developed and demonstrates that the substrates that a blood sample dried on does not offer any Raman or fluorescence interference for the SERS identification of dried blood. Such bloodstains on porous and nonporous materials are all identical and exclusively due to the heme moiety of hemoglobin. Optimized selection of the extraction solvent is found to control the chemical composition of molecular components appearing in the SERS spectrum of complex, multicomponent biological mixtures, such as body fluids.

Discrimination of menstrual and peripheral blood traces using attenuated total reflection Fourier transform-infrared (ATR FT-IR) spectroscopy and chemometrics for forensic purposes

Body fluid traces can provide highly valuable clues in forensic investigations. In particular, bloodstains are a common occurrence in criminal investigation, and the discrimination of menstrual and peripheral blood is a crucial step for casework involving rape and sexual assault. Most of the current protocols require the detection of characteristic menstrual blood components using sophisticated procedures that need to be performed in a laboratory. The present study uses attenuated total reflection Fourier transform-infrared (ATR FT-IR) spectroscopy as a nondestructive technique for discriminating menstrual and peripheral blood traces. This method incorporates statistical analysis and was evaluated by internal and external validation testing. A partial least squares discriminant analysis (PLSDA) classification model was created for differentiating the two types of blood in a binary manner. Excellent separation between menstrual and peripheral blood samples was achieved during internal validation. External validation resulted in 100% accuracy for predicting a sample as peripheral or menstrual blood. This study demonstrates that ATR FT-IR spectroscopy combined with chemometrics is a reliable approach for rapid and nondestructive discrimination of menstrual and peripheral bloodstains. It offers a significant advantage to forensic science due to the availability of portable instruments and the potential for bloodstain analysis at a crime scene. Graphical abstract.