Deep Learning Neural Network Research Articles

The impact of body mass index on rehabilitation outcomes after lower limb amputation.

To determine the effect of obesity on physical function and clinical outcome measures in patients who received inpatient rehabilitation services for lower extremity amputation. A retrospective review was performed on patients with lower extremity amputation (n = 951). Patients were stratified into five categories adjusted for limb loss mass across different levels of healthy body mass index (BMI), overweight, and obesity. Outcomes included the Inpatient Rehabilitation Facility Patient Assessment Instrument functional scores (GG section), discharge home, length of stay (LOS), therapy time, discharge location, medical complications and acute care readmissions. Deep learning neural networks (DLNNs) were developed to learn the relationships between adjusted BMI and discharge home. The severely obese group (BMI > 40 kg/m2) demonstrated 7%-13% lower toileting hygiene functional scores at discharge compared to the remaining groups (p < .001). The severely obese group also demonstrated 8%-9% lower sit-to-lying and lying-to-sitting bed mobility scores than the other groups (both p < .001). Sit-to-stand scores were 16%-21% worse and toilet transfer scores were 12%-20% worse in the BMI > 40 kg/m2 group than the other groups (all p < .001). Walking 50 ft with two turns was most difficult for the BMI > 40 kg/m2 group, with mean scores 7%-27% lower than the other BMI groups (p = .011). Wheelchair mobility scores for propelling 150 ft were worst for the severely obese group (4.9 points vs. 5.1-5.5 points for all other groups; p = .021). The LOS was longest in the BMI > 40 group and shortest in the BMI < 25 group (15.0 days vs. 13.3 days; p = .032). Logistic regression analysis indicated that BMI > 40 kg/m2 was associated with lower odds risk (OR) of discharge-to-home (OR = 0.504 [0.281-0.904]; p < .022). DLNNs found that adjusted BMI and BMI category were ranked 11th and 12th out of 90 model variables in predicting discharge home. Patients with severe obesity (>40 kg/m2) achieved lower functional independence for several tasks and are less likely to be discharged home despite higher therapy volume than other groups. If a patient is going home, obesity will pose unique demands on the caregivers and resources can be put in place to help reintegrate the patient into life.

Using Deep Learning Techniques to Enhance Blood Cell Detection in Patients with Leukemia

Medical diagnosis plays a critical role in the early detection and treatment of diseases by examining symptoms and supporting findings through advanced laboratory testing. Early and accurate diagnosis is essential for detecting medical problems and then prescribing the most effective treatment strategies, especially in life-threatening diseases such as leukemia. Leukemia, a blood malignancy, is one of the most prevalent cancer types affecting both adults and children. It is caused by the rapid and uncontrolled growth of abnormal white blood cells in the bone marrow. This accumulation interferes with the production of normal blood cells, leading to a weakened immune deficiency, anemia, and bleeding disorders. Conventional leukemia diagnostic methods are time-consuming, manually intensive, and inefficient. This research study proposes an automatic diagnostics prediction of leukemia by analyzing blood images according to the shape of the blast cells using digital image processing and machine learning. The purpose of blood cell detection is to precisely identify and classify diverse blood cells, detecting anomalies associated with blood cancers like leukemia. This supports early diagnosis and monitoring, which leads to more effective treatments and improved results for cancer patients. To accomplish this task, we use digital image processing techniques and then apply the convolutional neural network (CNN) deep learning algorithm to blood sample images. This research employs a multi-stage methodology, including data preparation, data preprocessing, feature extraction, and then classification. While our model is built on a typical CNN architecture, we make significant advances by using preprocessing techniques and hyperparameter tuning. We have modified its layers combination to include convolutional, pooling, and fully connected layers that are optimized for image characteristics. These layers are fine-tuned for better feature extraction and classification accuracy. This study showed that blood cell detection for diagnosing acute leukemia based on images had 99% accuracy and outperformed other advanced models, including DenseNet121, ResNet-50, Incep-tionv3, MobileNet, and EfficientNet. The comprehensive analysis of the results reveals the highest accuracy of leukemia detection as compared to existing studies in the relevant literature.

Intelligent Methods for Estimating the Flood Susceptibility in the Danube Delta, Romania

Floods, along with other natural and anthropogenic disasters, profoundly disrupt both society and the environment. Populations residing in deltaic regions worldwide are particularly vulnerable to these threats. A prime example is the Danube Delta (DD), located in the Romanian sector of the Black Sea. This research paper aims to identify areas within the DD that are highly or very highly susceptible to flooding. To accomplish this, we employed a combination of multicriteria decision-making (AHP) and artificial intelligence (AI) techniques, including deep learning neural networks (DLNNs), support vector machines (SVMs), and multilayer perceptron (MLP). The input data comprised previously flooded regions alongside eight geographical factors. All models identified high or very high flood potential of over 65% of the studied area. The models’ performance was assessed using receiver operating characteristic (ROC) analysis, demonstrating excellent outcomes evaluated by the area under the curve (AUC) exceeding 0.908. This study is significant as it lays the groundwork for implementing measures against flood impacts in the DD.

The impact of Artificial Intelligence in detecting esophageal squamous cell carcinoma: advances and challenges

This review explores the transformative role of artificial intelligence (AI), especially through deep learning (DL) and convolutional neural networks (CNNs), in the early detection of esophageal squamous cell carcinoma (ESCC). ESCC presents significant diagnostic challenges due to its aggressive nature and high mortality, often diagnosed at advanced stages. Traditional endoscopic methods, while essential, suffer from limitations like interobserver variability, especially for subtle early lesions. AI-based systems have demonstrated high sensitivity in identifying these early neoplasms, reducing diagnostic discrepancies and enhancing precision. Through a bibliographic review, the article highlights recent AI advancements, particularly in utilizing CNNs to identify early-stage ESCC. These tools have shown the potential to improve diagnostic accuracy even among less experienced endoscopists and provide critical support in clinical decision-making, including biopsy guidance and lesion mapping in chromoendoscopy and narrow-band imaging (NBI). Despite promising results, challenges persist in AI’s practical application, such as the need for extensive data for training, clinical validation, and standardization across different endoscopic equipment. The study underscores the need for large-scale multicenter studies and standardization to solidify AI’s role in ESCC diagnosis. It envisions a future where AI not only serves as a diagnostic support tool but becomes integral to endoscopic practices, requiring continued technological development, ethical considerations, and regulatory frameworks to maximize clinical benefit.

A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning

Diabetes foot ulcer (DFU) is one of the common complications of diabetes patients, which may lead to infection, necrosis and even amputation. Therefore, early diagnosis, classification of severity and related treatment are crucial for the patients. Current DFU classification methods often require experienced doctors to manually classify the severity, which is time-consuming and low accuracy. The objective of the study is to propose a few-shot DFU image classification method based on deep residual neural network and transfer learning. Considering the difficulty in obtaining clinical DFU images, it is a few-shot problem. Therefore, the methods include: (1) Data augmentation of the original DFU images by using geometric transformations and random noise; (2) Deep ResNet models selection based on different convolutional layers comparative experiments; (3) DFU classification model training with transfer learning by using the selected pre-trained ResNet model and fine tuning. To verify the proposed classification method, the experiments were performed with the original and augmented datasets by separating three classifications: zero grade, mild grade, severe grade. (1) The datasets were augmented from the original 146 to 3000 image datasets and the corresponding DFU classification’s average accuracy from 0.9167 to 0.9867; (2) Comparative experiments were conducted with ResNet18, ResNet34, ResNet50, ResNet101, ResNet152 by using 3000 image datasets, and the average accuracy/loss is 0.9325/0.2927, 0.9276/0.3234, 0.9901/0.1356, 0.9865/0.1427, 0.9790/0.1583 respectively; (3) Based on the augmented 3000 image datasets, it was achieved 0.9867 average accuracy with the DFU classification model, which was trained by the pre-trained ResNet50 and hyper-parameters. The experimental results indicated that the proposed few-shot DFU image classification method based on deep ResNet and transfer learning got very high accuracy, and it is expected to be suitable for low-cost and low-computational terminal equipment, aiming at helping clinical DFU classification efficiently and auxiliary diagnosis.

Dual Multi Scale Attention Network Optimized With Archerfish Hunting Optimization Algorithm for Diabetics Prediction

ABSTRACTDiabetes is a chronic disease that occurs when the body cannot regulate blood sugar levels. Nowadays, the screening tests for diabetes are developed using multivariate regression methods. An increasing amount of data is automatically collected to provide an opportunity for creating challenging and accurate prediction modes that are updated constantly with the help of machine learning techniques. In this manuscript, a Dual Multi Scale Attention Network optimized with Archerfish Hunting Optimization Algorithm is proposed for Diabetes Prediction (DMSAN‐AHO‐DP). Here, the data is gathered through PIMA Indian Diabetes Dataset (PIDD). The collected data is fed towards the preprocessing to remove the noise of input data and improves the data quality by using Contrast Limited Adaptive Histogram Equalization Filtering (CLAHEF) method. Then the preprocessed data are fed to Multi‐Level Haar Wavelet Features Fusion Network (MHWFFN) based feature extraction. Then the extracted data is supplied to the Dual Multi Scale Attention Network (DMSAN) for diabetic or non‐diabetic classification. The hyper parameter of Dual Multi Scale Attention Network is tuned with Archerfish Hunting Optimization (AHO) algorithm, which classifies diabetic or non‐diabetic accurately. The proposed DMSAN‐AHO‐DP technique is implemented in Python. The efficacy of the DMSAN‐AHO‐DP approach is examined with some metrics, like Accuracy, F‐scores, Sensitivity, Specificity, Precision, Recall, Computational time. The DMSAN‐AHO‐DP technique achieves 23.52%, 36.12%, 31.12% higher accuracy and 16.05%, 21.14%, 31.02% lesser error rate compared with existing models: Enhanced Deep Neural Network based Model for Diabetes Prediction (EDNN‐DP), Indian PIMA Dataset using Deep Learning for Diabetes Prediction (ANN‐DP), and Enhanced Support Vector Machine with Deep Neural Network Learning strategies for Diabetes Prediction (SVM‐DNN‐DP).

Bioindication Studies of Surface Water Supported by Automatic Image Analysis Using Deep Learning Neural Network – Cyclotella Case Study

Bioindication Studies of Surface Water Supported by Automatic Image Analysis Using Deep Learning Neural Network – Cyclotella Case Study

Instability prediction under distorted inflow based on deep learning neural networks in an axial flow compressor

Traditional stall prediction methods often rely on empirical formulas and models, which have certain limitations. The deep learning model was introduced to predict stall and surge under distorted inflow conditions in an axial flow compressor, and the model can learn from the dynamic pressure data containing stall processes measured on the casing wall by use of a long short-term memory neural network. In order to enhance the model's generalization capability and prediction accuracy, the model parameters are optimized through the Northern Goshawk optimization algorithm. In the experimental validation, the stall prediction model was first trained by using the collected stalling signal. Then, a step-by-step prediction method was used to verify the accuracy of the prediction model under uniform and distorted inflow conditions. Subsequently, the recursive prediction technology is used to predict the instability under different inflow conditions in both subsonic and supersonic axial flow compressors. By comparing with the measured stalling data under uniform and distorted inflow, the model accurately and timely predicts stall and surge signal through a self-learning mechanism when inputting non-stall pressure data. Regardless of whether the instability routes are spikes and modal-wave stall or surge, the model can predict the instability at least 1 s in advance, and it leaves enough time for the anti-surge actuator to operate. This study not only significantly improves the real-time and accuracy of predictions but also demonstrates the potential application value of deep learning in the field of aero engines, contributing to enhanced safety and reliability of aircraft engines.

Sentiment-electroencephalogram fusion for efficient product review prediction using correlation-based deep learning neural network

&lt;span lang="EN-US"&gt;Various techniques have been proposed and implemented in previous work for sentiment analysis prediction. However, achieving satisfactory quality of description and fault prediction remains a challenging task. To overcome these limitations, this study proposes an efficient prediction technique that utilizes sentiment analysis of product reviews and electroencephalogram (EEG) signals using correlation-based deep learning neural network (CDNN). The study employs two types of datasets: EEG signals and Amazon product reviews. During the pre-processing phase, EEG signals undergo normalization, while Amazon product reviews undergo tokenization, stop word removal, and weighting factor application to convert unstructured data into a structured format. Subsequently, the pre-processed EEG signals and reviews are analyzed to extract features like emotion, demographic information, personality traits, and sentiment. These features are then employed in sentiment analysis via an entropy-based deep-learning neural network. The proposed CDNN utilizes the grasshopper optimization algorithm (EGOA) to optimize hyperparameters for each layer. Comparative performance assessment against established methods like convolutional neural network (CNN), &lt;a name="_Hlk167111148"&gt;&lt;/a&gt;long short-term memory (LSTM), multiclass &lt;a name="_Hlk175651957"&gt;&lt;/a&gt;support vector machine (M-SVM), and bidirectional encoder representations from transformers (BERT) is conducted, and the results are evaluated. Experimental result reveal that the proposed system outperforms traditional approaches.&lt;/span&gt;

Deep Learning Model for Prediction of Dementia Severity based on EEG Signals

This study aimed to determine variations in the electroencephalograms (EEGs) of 15 individuals who were diagnosed with mild cognitive impairment (MCI) following stroke, 5 individuals suffering from vascular dementia (VD) and 15 healthy normal control (NC) individuals who performed a working memory task. Conventional filters including notch and bandpass filters were utilised to remove noise from the EEG data. The proposed method comprises computing the estimates of the attention entropy (AttEn), bubble entropy (BubbEn) and symbolic dynamic entropy (SyDyEn) of univariate data sequence features. The long short-term memory (LSTM) deep learning neural network was used to automatically classify dementia severity through noninvasive EEG-based recordings. The LSTM classification result with AttEn exceeds an average of 88.9% than BubbEn and SyDyEn, with classification results of 69.2% and 77.7%, respectively. The analysis of the brain EEG-based dementia severity dataset suggests that AttEn could potentially serve as a biomarker for detecting dementia severity. AttEn can capture relevant patterns and features in the EEG data and may be indicative of the severity of dementia with LSTM RNN to differentiate patients with VD, patients with MCI and NC individuals.

Seismic and outcrop-based 3D characterization of fault damage zones in sandstones, Rio do Peixe Basin, Brazil

Fault damage zones, composed of sub-seismic deformation structures, are difficult to detect using seismic data. Still, they can be related to fault throw, which is widely measured in the subsurface. This research employs a multiscale approach that integrates outcrop studies with seismic reflection data to investigate the attributes of fault damage zones affecting porous sandstones. We provide an in-depth understanding of the 3D fault zone volume, investigating correlations between geometric attributes of faults (width of damage zone, frequency of subsidiaries structures, and fault termination) in the outcrop and the fault throw in the subsurface, with insights from deformation mechanisms within the fault zone. The methods encompass 1D scanlines to constrain the damage zone width on the outcrop. At the same time, the subsurface analysis uses 3D seismic data, seismic attributes, and deep learning neural network (DNN) fault volumes to interpret fault geometries and quantify fault throw at different depths. Results show that the area presents a complex fault zone with multiple fault sets, deformation bands, and fracture corridors trending mainly NE-SW, NW-SE, and E-W. The integration of surface and subsurface fault data enabled the identification of two portions in each fault set outcropping at the fault tip for E-W/ESE-WNW-striking faults and the central part of the fault for NE-SW-striking faults. Faults with the greatest length do not outcrop with the largest damage zone width since they are outcropping the tip of the fault. The parallel faults overlap their damage zones, increasing the deformation zones in the affected sandstones. Fault throw and damage zone width present a positive correlation. This relation is affected by fault segments and subsidiary faults.

Breast Cancer Prediction Using Transfer Learning-Based Classification Model

Breast cancer is currently the most prevalent type of cancer in women, with a growing number of fatalities worldwide. Different imaging methods like mammography, computed tomography, Magnetic Resonance Imaging, ultrasound, and biopsies assist in detecting breast cancer. Recent developments in deep learning have revolutionized breast cancer pathology by facilitating accurate image categorization. This study introduces a novel approach to enhance detection and classification using the Convolutional Neural Network Deep Learning method and Transfer Learning to create a high-speed, accurate image classification model. The model is trained on pre-processed data subjected to thorough analysis and augmentation to ensure the quality of inputs. The experimental results from the Breast Ultrasound Image dataset indicate that our model, with a 0.1 test size ratio, outperforms its counterparts. It achieved an accuracy of 90.12%, with a loss of 0.2641, validation accuracy of 90.15%, and validation loss of 0.31, evidencing its superior classification capability. This research introduces an innovative approach to the automated diagnosis of breast cancer. By combining CNN, Transfer Learning, and data augmentation, we have developed a desktop application that expedites the classification process and significantly improves accuracy. This advancement represents a key development in machine learning applications for breast cancer prognostics and diagnostics. Doi: 10.28991/ESJ-2024-08-06-014 Full Text: PDF

Big Data Visualization for Black Sigatoka Disease of Bananas and Pathogen–Host Interactions (PHI) of Other Plants

Black sigatoka is a leaf spot disease affecting banana plants that has caused significant yield reductions of up to 50% (Arman et al., 2023). This research presents data visualizations of 8,761 data points related to black sigatoka in banana plants, encompassing attributes such as time, canopy temperature, and relative humidity. The paper also reviews related work, including the application of data mining to plant studies, the use of deep learning neural networks for plant disease data, and the use of machine learning for predicting crop yields and detecting disease. Additionally, it presents big data visualizations for 20,952 values obtained from the web-accessible Pathogen–Host Interactions database (PHI-base), covering various plant disease categories and providing an epidemiological analysis of prevalent causative agents in specific plant diseases.

Multi-patch Isogeometric convolution hierarchical deep-learning neural network

A seamless integration of neural networks with Isogeometric Analysis (IGA) was first introduced in [1] under the name of Hierarchical Deep-learning Neural Network (HiDeNN) and has systematically evolved into Isogeometric Convolution HiDeNN (in short, C-IGA) [2]. C-IGA achieves higher order approximations without increasing the degree of freedom. Due to the Kronecker delta property of C-IGA shape functions, one can refine the mesh in the physical domain like standard finite element method (FEM) while maintaining the exact geometrical mapping of IGA. In this article, C-IGA theory is generalized for multi-CAD-patch systems with a mathematical investigation of the compatibility conditions at patch interfaces and convergence of error estimates. Two compatibility conditions (nodal compatibility and G0 (i.e., global C0) compatibility) are presented and validated through numerical examples.

PINN for solving forward and inverse problems involving integrable two-dimensional nonlocal equations

In this paper, the physics informed neural network (PINN) deep learning method is applied to solve two-dimensional nonlocal equations, including the partial reverse space y-nonlocal Mel’nikov equation, the partial reverse space-time nonlocal Mel’nikov equation and the nonlocal two-dimensional nonlinear Schrödinger (NLS) equation. By the PINN method, we successfully derive a data-driven two soliton solution, lump solution and rogue wave solution. Numerical simulation results indicate that the error range between the data-driven solution and the exact solution is relatively small, which verifies the effectiveness of the PINN deep learning method for solving high dimensional nonlocal equations. Moreover, the parameter discovery of the partial reverse space-time nonlocal Mel’nikov equation is analysed in terms of its soliton solution for the first time.

Optimized early fusion of handcrafted and deep learning descriptors for voice pathology detection and classification

This study presents an automated noninvasive voice disorder detection and classification approach using an optimized fusion of modified glottal source estimation and deep transfer learning neural network descriptors. A new set of modified descriptors based on a glottal source estimator and pre-trained Inception-ResNet-v2 convolutional neural network-based features are proposed for the speech disorder detection and classification task. The modified feature set is obtained using mel-cepstral coefficients, harmonic model, phase discrimination means, distortion deviation descriptors, conventional wavelet, and glottal source estimation features. Early descriptor-level fusion is employed in this study for performance enhancement-however, the fusion results in higher feature vector dimensionality. A nature-inspired slime mould algorithm is utilized to remove redundant and select the best discriminating features. Finally, the classification is performed using the K-nearest neighbor (KNN) classifier. The proposed algorithm was evaluated using extensive experiments with different feature combinations, with and without feature selection, and with two popular datasets: the Arabic Voice Pathology Database (AVPD) and the Saarbrucken Voice Database (SVD). We show that the proposed optimized fusion method attained an enhanced voice pathology detection accuracy of 98.46%, encompassing a wide spectrum of voice disorders on the SVD database. Furthermore, compared to traditional handcrafted and deep neural network-based techniques, the proposed method demonstrates competitive performance with fewer features.

Valuation of Emotionality and Osgood Factors in Fiction Prose using Machine-Generated Dictionaries (On the Material of the Strugatsky Brothers Trilogy about M. Kammerer)

The relevance of the work lies in the fact that Osgood factors and emotive characteristics of the text can be extrapolated from the russian fiction prose, as the most adequate type of author's and reader's expression, to the assessment of moods in society in a specifically given period. To analyse them, we need deep-learning neural networks capable of assessing positivity and other factors taking into account the context - with the help of dictionaries based on the survey of informants and machine extrapolation. From a methodological point of view, we used a dictionary with positivity ratings for russian language words CartaSlovSent, as well as data from multilingual NRC VAD, Hedonometer dictionaries to identify categories of valence, dominance and arousal in texts. To construct a series of average text positivity, all word forms contained in the selected dictionary were found and the values of their positivity ratings were averaged. The results of the study showed that in the Strugatsky brothers' trilogy about Maxim Kammerer, "The Inhabited Island" with the corresponding descriptive negative narrative related to the image of the planet Saraksh is the most indicative for positivity ratings. At the same time, throughout the trilogy, Osgood factors are spread throughout the text according to the development of plot and compositional elements. "The Beetle in the Anthill" and "Waves Extinguish the Wind" are similar in the degree of expression of Osgood factors, including due to a similar dominant chronotope.

Seismic post-stack impedance inversion using geophysics-informed deep learning neural network

Traditionally, seismic post-stack impedance inversion is implemented using linear optimization algorithms. Recently, deep learning neural networks have been successfully used to estimate the impedance from seismic data. First, we demonstrate the general workflow of seismic post-stack impedance inversion using supervised neural network (SNN). Next, we propose to compute seismic impedance using geophysics-informed neural network (GINN). Similarly with linear optimization algorithms, the inputs of GINN include real seismograms, a wavelet, and a low frequency model. The loss function of GINN is designed to minimize the difference between real seismograms and synthetic seismic seismograms that are computed from estimated impedance and input wavelet. To avoid lateral discontinuity of estimated impedance, the weights of GINN are trained using the seismograms of all seismic traces. We use synthetic and real seismic data to discuss the advantages and limitations of GINN, SNN, and traditional linear optimization algorithms. Not surprisingly, signal-to-noise ratio (SNR) of seismic data and the phase of seismic wavelet are the most important factors that affect the accuracy of impedance estimated using GINN. The accuracy and resolution of impedance estimated using GINN is higher than linear optimization and SNN if the seismic data has a high signal-to-noise ratio. The synthetic examples demonstrate that the accuracy of impedance calculated using SNN increases with the number of available training wells and linear optimization algorithms are more robust to noise than GINN and SNN.

Improving automated scoring of prosody in oral reading fluency using deep learning algorithm

Automated assessing prosody of oral reading fluency presents challenges due to the inherent difficulty of quantifying prosody. This study proposed and evaluated an approach focusing on specific prosodic features using a deep-learning neural network. The current work focuses on cross-domain performance, researching how generalizable the prosody scoring is across students and text passages. The results demonstrated that the model with selected prosodic features had better cross-domain performance with an accuracy of 62.5% compared to 57% from the previous research. Our findings also indicate that students’ reading patterns influence cross-domain performance more than specific text passage patterns. In other words, letting the student read at least one passage is more important than having others read all passage texts. The specific prosodic features had a high generalization to capture the typical prosody characteristics for achieving a satisfactorily high accuracy and classification agreement rate. This result provides valuable information for developing future automated scoring algorithms of prosody. This study is an essential demonstration of estimating the prosody score using fewer selected features, which would be more efficient and interpretable.

Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans.

The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions. We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores. The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks. The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.