Celiac Disease (CD) is an autoimmune digestive system disorder characterized by impaired fat digestion or absorption, resulting in the excretion of substantial amounts of fat and giving stools a milky appearance [1]. Under normal circumstances, the digestive system efficiently breaks down fats, allowing for absorption and transportation into the body. However, in CD patients, this process is disrupted, preventing adequate fat absorption. The presence of large amounts of unabsorbed fats in the intestines can lead to irritation, potentially causing diarrhea. Additionally, the loss of essential nutrients such as fats, proteins, and fat-soluble vitamins may result in malnutrition, leading to various health issues [2]. CD can impact growth and development and compromise the immune system, increasing the risk of infections and other diseases. Individuals with CD commonly experience gastrointestinal symptoms such as diarrhea, abdominal pain, and bloating, significantly affecting their quality of life [3].
Research indicates that early diagnosis and treatment of the disease can effectively slow down its progression. Therefore, establishing a rapid and accurate diagnostic method is of paramount importance for achieving early detection of CD and reducing associated damages [4]. Currently, the diagnosis and classification of CD depend on factors such as patient medical history, physical examinations, laboratory findings, and radiological evidence [5]. Diagnostic methods often involve examining fecal fat content [6] and conducting blood and intestinal mucosal biopsies [7]. However, diagnosing CD remains challenging due to its symptoms being subtle or mistaken for other gastrointestinal issues. The most common reasons for CD screening include abdominal bloating and diarrhea, but these symptoms may not always be evident. This difficulty in diagnosis can lead to delayed or incorrect treatment, exacerbated by significant variations in the course of CD among patients. Some may exhibit mild symptoms, while others experience noticeable clinical manifestations, adding complexity to accurate diagnosis [8][36]. Early detection of CD is crucial, as timely intervention and treatment can significantly improve patients' quality of life and slow down disease progression.
As a rapid spectral analysis technique, Raman spectroscopy (RS) can measure various biomolecules present in plasma samples, including proteins, nucleic acids, carbohydrates, and lipids [9]. Intensity differences between Raman peaks are primarily attributed to nucleic acids, amino acids, and lipids, which play crucial roles in biochemical reactions such as biological transformations, immune process monitoring, signal transduction, and nutrient metabolism. Raman spectroscopy's ability to capture a wealth of information from multiple peaks, each representing specific substances and their intensities and positions, makes it the "biological fingerprint" region of sample Raman spectra [10].
Despite the significant achievements of Raman spectroscopy combined with machine learning models in disease diagnosis [11], the technique has limitations, such as a low signal-to-noise ratio [10]. This limitation may hinder the intuitive identification of differences between spectra, potentially resulting in lower diagnostic performance. Therefore, exploring spectral differences through intelligent methods holds substantial significance.
Various chemometric techniques, including Principal Component Analysis (PCA), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), have been extensively applied in spectral analysis [14–15]. However, for extracting more features and achieving diagnostic requirements, more complex deep learning models are needed. Convolutional Neural Network (CNN) is one of the most popular foundational deep learning frameworks, reducing parameter numbers and improving feature extraction quality through local connections and parameter sharing. Traditional CNN models have demonstrated high performance and robustness in processing raw spectral data.
Studies by Yang et al. [16] and Wu et al. [17] showcase the effectiveness of one-dimensional CNNs in accurately classifying plasma lesions of tongue squamous cell carcinoma and rapidly diagnosing sparganosis using plasma Raman spectra, achieving accuracies of 94.90%. However, traditional CNN models can only extract local features at one scale, and the spectral measurement process is often susceptible to strong noise interference, making high-quality feature extraction more challenging. Additionally, differences arising from noise between training and testing sets may decrease spectral classification accuracy.
To address these challenges, this study constructs and adopts four different neural network models: CNN, Multi-Scale Convolutional Neural Network (MCNN), Residual Network (ResNet), and Deep Residual Shrinkage Network (DRSN). These models are trained end-to-end, eliminating the tedious process of manually extracting features. The models can automatically learn critical features from spectral data, enhancing generalization capabilities. By extracting features at different scales, the models effectively capture local information within the spectra, crucial for diagnosing celiac disease. Moreover, these models reduce noise interference during spectral measurement, further enhancing the neural network models' generalization capabilities and diagnostic accuracy for celiac disease.