Application Of Learning Model Research Articles

Implementation of Realistic Mathematics Education Learning Model to Improve Students' Mathematics Learning Outcomes

This study aims to improve student learning outcomes on triangle material by applying realistic mathematics education learning models to students. This research is a class action research which consists of two cycles. The results of the study: (1) The process of learning mathematics through the application of the resource-based learning approach at SMP Negeri 1 Sitolu Ori is good, (2) In the first cycle the results of observations of the implementation of the learning process for teacher respondents through the application of realistic mathematics education learning models reached an average value of 64.38% with a sufficient category. In the second cycle, the results of observations of the implementation of the learning process for teacher respondents through the application of realistic mathematics education learning models reached an average of 85.00% with a good category and based on the average questionnaire results 88.69% classified as excellent. In the first cycle, the implementation of the learning outcomes test obtained an average of 64.52 learning outcomes and included a sufficient category, with a percentage of completeness of 52.38% and unsuccessfulness of 47.62%. In cycle two, the implementation of the learning outcomes test obtained an average of 83.21 learning outcomes and included in the good category, with a percentage of 100% completeness and 0% unsuccessful, so that learning completeness reached the target of 75%.

Deep learning model combined with computed tomography features to preoperatively predicting the risk stratification of gastrointestinal stromal tumors

BACKGROUND Gastrointestinal stromal tumors (GIST) are prevalent neoplasm originating from the gastrointestinal mesenchyme. Approximately 50% of GIST patients experience tumor recurrence within 5 years. Thus, there is a pressing need to accurately evaluate risk stratification preoperatively. AIM To assess the application of a deep learning model (DLM) combined with computed tomography features for predicting risk stratification of GISTs. METHODS Preoperative contrast-enhanced computed tomography (CECT) images of 551 GIST patients were retrospectively analyzed. All image features were independently analyzed by two radiologists. Quantitative parameters were statistically analyzed to identify significant predictors of high-risk malignancy. Patients were randomly assigned to the training (n = 386) and validation cohorts (n = 165). A DLM and a combined DLM were established for predicting the GIST risk stratification using convolutional neural network and subsequently evaluated in the validation cohort. RESULTS Among the analyzed CECT image features, tumor size, ulceration, and enlarged feeding vessels were identified as significant risk predictors (P < 0.05). In DLM, the overall area under the receiver operating characteristic curve (AUROC) was 0.88, with the accuracy (ACC) and AUROCs for each stratification being 87% and 0.96 for low-risk, 79% and 0.74 for intermediate-risk, and 84% and 0.90 for high-risk, respectively. The overall ACC and AUROC were 84% and 0.94 in the combined model. The ACC and AUROCs for each risk stratification were 92% and 0.97 for low-risk, 87% and 0.83 for intermediate-risk, and 90% and 0.96 for high-risk, respectively. Differences in AUROCs for each risk stratification between the two models were significant (P < 0.05). CONCLUSION A combined DLM with satisfactory performance for preoperatively predicting GIST stratifications was developed using routine computed tomography data, demonstrating superiority compared to DLM.

Prediction of Nursing Need Proxies Using Vital Signs and Biomarkers Data: Application of Deep Learning Models.

To develop deep learning models to predict nursing need proxies among hospitalised patients and compare their predictive efficacy to that of a traditional regression model. This methodological study employed a cross-sectional secondary data analysis. This study used de-identified electronic health records data from 20,855 adult patients aged 20 years or older, admitted to the general wards at a tertiary hospital. The models utilised patient information covering the preceding 2 days, comprising vital signs, biomarkers and demographic data. To create nursing need proxies, we identified the six highest-workload nursing tasks. We structured the collected data sequentially to facilitate processing via recurrent neural network (RNN) and long short-term memory (LSTM) algorithms. The STROBE checklist for cross-sectional studies was used for reporting. Both the RNN and LSTM predicted nursing need proxies more effectively than the traditional regression model. However, upon testing the models using a sample case dataset, we observed a notable reduction in prediction accuracy during periods marked by rapid change. The RNN and LSTM, which enhanced predictive performance for nursing needs, were developed using iterative learning processes. The RNN and LSTM demonstrated predictive capabilities superior to the traditional multiple regression model for nursing need proxies. Applying these predictive models in clinical settings where medical care complexity and diversity are increasing could substantially mitigate the uncertainties inherent in decision-making processes. We used de-identified electronic health record data of 20,855 adult patients about vital signs, biomarkers and nursing activities. The authors state that they have adhered to relevant EQUATOR guidelines: STROBE statement for cross-sectional studies. Despite widespread adoption of deep learning algorithms in various industries, their application in nursing administration for workload distribution and staffing adequacy remains limited. This study amalgamated deep learning technology to develop a predictive model to proactively forecast nursing need proxies. Our study demonstrates that both the RNN and LSTM models outperform a traditional regression model in predicting nursing need proxies. The proactive application of deep learning methods for nursing need prediction could help facilitate timely detection of changes in patient nursing demands, enabling the effective and safe nursing services.

An Application of Machine Learning Models in Detecting Vietnamese Fake News

Nowadays, with the development of the Internet, publishing and sharing news has become very easy, and anyone can do it. Along with the increasing amount of information on the internet, besides official information, fake news continues to rise and spreads quickly across the network. Fake news has become a major societal problem, negatively impacting all aspects of economic, cultural, and social life. How to prevent the spread of fake news online is an urgent issue today. To help readers recognize whether news is trustworthy, this paper proposes using natural language processing techniques and machine learning models to detect fake news in posts on the social network Facebook in the Vietnamese language. After the training process, the resulting model can predict whether the news is real or fake. The model's evaluation results are presented according to popular machine learning metrics, and the best-performing model on the dataset used in this paper is the Light Gradient Boosting Algorithm – LGBM – with an accuracy of 88.21% compared to other models used in this paper.

Air pollution forecasting: Application of machine learning models to estimate PM2.5 index

In the context of ongoing industrialization, air pollution has become an urgent global problem, particularly severe in large cities such as Hanoi (Vietnam), Beijing (China), and others. Air pollution, especially the concentration of fine particulate matter (PM2.5), is not only harmful to human health but also has significant negative impacts on the environment, economy, and quality of life. This study aims to enhance the ability to predict air pollution levels more accurately. By using machine learning models, meteorologists can better predict air pollution levels and propose more effective mitigation solutions. The article utilizes a multivariate time series dataset, including meteorological and air pollution indices from Beijing, China, from 2010 to 2014. Machine learning models such as Lasso Regression, Support Vector Regression, Random Forest, XGBoost, and, notably, a Stack Model combining the four aforementioned models, are evaluated. The performance of these models is measured using statistical indicators such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²). Among these models, the Stack model provides the most accurate predictions for the PM2.5 index.

Integrative Machine Learning, Virtual Screening, and Molecular Modeling for BacA-Targeted Anti-Biofilm Drug Discovery Against Staphylococcal Infections

The rise in antibiotic-resistant Staphylococcal infections necessitates innovative approaches to identify new therapeutic agents. This study investigates the application of machine learning models to identify potential phytochemical inhibitors against BacA, a target related to Staphylococcal infections. Active compounds were retrieved from BindingDB while the decoy was generated from DUDE. The RDKit was utilized for feature engineering. Machine learning models such as k-nearest neighbors (KNN), the support vector machine (SVM), random forest (RF), and naive Bayes (NB) were trained on an initial dataset consisting of 226 active chemicals and 2550 inert compounds. Accompanied by an MCC of 0.93 and an accuracy of 96%, the RF performed better. Utilizing the RF model, a library of 9000 phytochemicals was screened, identifying 300 potentially active compounds, of which 192 exhibited drug-like properties and were further analyzed through molecular docking studies. Molecular docking results identified Ergotamine, Withanolide E, and DOPPA as top inhibitors of the BacA protein, accompanied by interaction affinities of −8.8, −8.1, and −7.9 kcal/mol, respectively. Molecular dynamics (MD) was applied for 100 ns to these top hits to evaluate their stability and dynamic behavior. RMSD, RMSF, SASA, and Rg analyses showed that all complexes remained stable throughout the simulation period. Binding energy calculations using MMGBSA analysis revealed that the BacA_Withanolide E complex exhibited the most favorable binding energy profile with significant van der Waals interactions and a substantial reduction in gas-phase energy. It also revealed that van der Waals interactions contributed significantly to the binding stability of Withanolide E, while electrostatic interactions played a secondary role. The integration of machine learning models with molecular docking and MD simulations proved effective in identifying promising phytochemical inhibitors, with Withanolide E emerging as a potent candidate. These findings provide a pathway for developing new antibacterial agents against Staphylococcal infections, pending further experimental validation and optimization.

Modeling Energy Access Challenges in Europe: A Neural Network Approach to Predicting Household Heating Inadequacy Using Macro-Energy Indicators

This study explores the use of machine learning models to predict the percentage of the population unable to keep their houses adequately warm in European countries. The research focuses on applying three machine learning models—ElasticNet, decision trees, and neural networks—using macro-energy indicator data from Eurostat for 27 European countries. Neural networks with Bayesian regularization (BR) achieved the best performance in terms of prediction accuracy, with a regression value of 0.98179, and the lowest root mean squared error (RMSE) of 1.8981. The results demonstrate the superior ability of the BR algorithm to generalize data, outperforming other models like ElasticNet and decision trees, which also provided valuable insights but with lower precision. The findings highlight the potential of machine learning to predict the percentage of the population unable to keep their houses adequately warm, enabling policymakers to allocate resources more efficiently and target vulnerable populations. This research is the result of the application of machine learning models to solve the problem of energy poverty.

Employing machine learning models to predict pregnancy termination among adolescent and young women aged 15–24 years in East Africa

Pregnancy termination is still a sensitive and continuing public health issue due to several political, economic, religious, and social concerns. This study assesses the applications of machine learning models in the prediction of pregnancy termination using data from eleven national datasets in East Africa. Nine machine learning models, namely: Random Forests (RF), Decision Tree, Logistic Regression, Support Vector Machine, eXtreme Gradient Boosting (XGB), AdaBoost, CatBoost, K-nearest neighbor, and feedforward neural network models were used to predict pregnancy termination, with six evaluation criteria utilized to compare their performance. The pooled prevalence of pregnancy termination in East Africa was found to be 4.56%. All machine learning models had an accuracy of at least 71.8% on average. The RF model provided accuracy, specificity, precision, and AUC of 92.9%, 0.87, 0.91, and 0.93, respectively. The most important variables for predicting pregnancy termination were marital status, age, parity, country of residence, age at first sexual activity, exposure to mass media, and educational attainment. These findings underscore the need for a tailored approach that considers socioeconomic and regional disparities in designing policy initiatives aimed at reducing the rate of pregnancy terminations among younger women in the region.

Application of deep learning models with spectral data augmentation and Denoising for predicting total phosphorus concentration in water pollution

BackgroundWith the increasing severity of global water pollution, accurate prediction models of water pollution content are critical for effective environmental management. However, traditional methods often exhibit low prediction accuracy for pollutant concentrations when data samples are limited and do not adequately address data noise. This study focuses on predicting total phosphorus (TP) concentrations in the Yangtze River Basin by integrating data augmentation and denoising methods with spectral technology and deep learning, using water samples collected from Wuhan to Anhui, China. MethodThe study utilized an improved Conditional Generative Adversarial Networks (CGAN) for data augmentation, increasing dataset diversity and training effectiveness. Adaptive threshold wavelet denoising is applied to reduce noise and improve data quality. A Convolutional Neural Network (CNN) with a coordinate attention (CA) mechanism is used to extract key spectral features linked to TP concentration prediction. Significant FindingsThis study introduces an innovative approach that combines advanced CGAN-based data augmentation, adaptive threshold wavelet denoising, and a CNN model incorporating a CA mechanism, achieving high accuracy in TP concentration prediction. The proposed model outperforms traditional methods, achieving R² = 0.9805, RMSE = 0.0019, and MAE = 0.0009. This novel method significantly enhances prediction performance, providing an effective solution particularly in scenarios with limited data samples.

Natural factor-based spatial prediction and source apportionment of typical heavy metals in Chinese surface soil: Application of machine learning models.

Predicting the natural distribution of heavy metals (HMs) in soil is important to understand the potential risk of pollution. However, suitable technologies are still lacking for wide scale due to the large spatial heterogeneity. In this study, we developed machine learning models for predicting natural contents of five typical HMs in soil, including As, Cd, Cr, Hg and Pb. It was found that the optional random forest (RF) model had the best performance with the R2 up to 0.64. Based on this model, potential distribution of the five HMs explored that elevated contents were mainly concentrated in the southwest and south central of China. Feature analysis illustrated that importance of natural factors followed the order of geological attributes > soil properties > climatic conditions > ecological functions. In particular, lithology of the parent material dominated the content of metals, with the contributions of 18 - 25%. Moreover, soil properties of pH, cation exchange capacity, profile depth of soil and vegetation coverage had different influences on HMs, due to the variability in the properties of different HMs. This study developed a mapping relationship between natural factors and soil HMs by data science method, which may provide instructive information for pollution control and planning decisions.

Application of The Discovery Learning Model with Process Differentiation to Improve Junior High School Students' Mathematics Learning Outcomes

The aim of this research was to improve mathematics learning outcomes of class VIII A students at SMPN 14 Denpasar through the application of discovery learning with process differentiation. This type of research was classroom action research with two cycles. The research subjects were 42 students. Student’s mathematics learning outcomes data were obtained using mathematics learning outcomes tests. The collected data was analysed descriptively. The results showed that the percentage of students with mathematics learning outcomes in the complete category increased in each cycle. The success criteria were that the average student mathematics learning outcome score in each cycle increased, where the average student mathematics learning outcome was at least 80 and student’s classical learning completeness was at least 75%. Subsequently, the improvement results from each cycle could be said optimal. It could be conluded that the application of the discovery learning model with process differentiation could improve junior high school students' mathematics learning outcomes.

Application of machine learning and neural network models based on experimental evaluation of dissimilar resistance spot-welded joints between grade 2 titanium alloy and AISI 304 stainless steel

Application of machine learning and neural network models based on experimental evaluation of dissimilar resistance spot-welded joints between grade 2 titanium alloy and AISI 304 stainless steel

Prediction of ROI Achievements and Potential Maximum Profit on Spot Bitcoin Rupiah Trading Using K-means Clustering and Patterned Dataset Model

Since Satoshi Nakamoto first proposed the idea of bitcoin in 2009, the cryptocurrency and prediction methods for it have grown and changed exceptionally quickly. The Patterned Dataset Model was a valuable tool in earlier studies to explain how changes in the price of Bitcoin affect the movements of other cryptocurrencies in a digital trading market. Three different kinds of datasets are generated by this model: patterned datasets under full conditions, patterned datasets under dropping prices (Crash), and patterned datasets under rising prices (Moon). The K-means approach was then used to cluster these three datasets. Specifically, each dataset was split into two clusters, and the clustering score was determined by utilizing eight unique clustering metrics. Consequently, the best clustering score was found in the patterned dataset in the crash situation. Additionally, from 2022 to 2024, the raw data from this crash-condition-patterned dataset is used to determine the possibility of reaching maximum profit and return on investment (ROI) daily and monthly. According to the calculation results, the range computed over the course of a whole month (30 to 31 days) is significantly larger than the daily range (24 hours multiplied by one month), which represents the most significant profit and ROI attained before the emergence of the first diamond crash level. This research also covers the application of a deep learning model to forecast patterned datasets for crash scenarios that may occur many days in advance. The ConvLSTM2D Model performs better in predicting pattern dataset values for the subsequent crash scenario, according to the hyperparameter comparison between the Gated Recurrent Unit (GRU) Model and the 2D Convolutional Long Short-Term Memory Model.

Effectiveness and Practicality of Islamic-oriented Cooperative Learning Model in Private and State Islamic Higher Education in South and West Sulawesi, Indonesia

Aims: The Islamic-oriented Cooperative Learning Model for Improving Islamic Education Learning Outcomes is based on a number of problems in the praxis of learning Islamic education at the Faculty of Tarbiyah and Teacher Training UIN Alauddin Makassar and STAI DDI Majene, namely student learning outcomes that are not optimal, learning motivation being, learning has not described active, creative and fun learning. Testing the effectiveness and practicality of this model through research activities aims to describe and analyze: (1) the level of effectiveness of applying the Islamic-oriented cooperative learning model through Islamic Education courses at UIN Alauddin and STAI DDI Majene; (2) the level of practicality of applying the Islamic-oriented cooperative learning model through Islamic Education courses at UIN Alauddin and STAI DDI Majene; and (3) the reality of implementing the Islamic-oriented cooperative learning model through Islamic Education courses at UIN Alauddin and STAI DDI Majene. Methodology: This research is a type of development research that examines the results of developing Islamic-oriented cooperative learning models, which are expected to improve student learning outcomes in Islamic education courses. This research was conducted at the Tarbiyah and Teacher Training Faculties of UIN Alauddin Makassar and STAI DDI Majene. The subjects of this study were 32 Class C English Education Study Program students and 35 Class A Madrasah Ibtidaiyyah Teacher Education Study Program, and 16 STAI DDI students. Data collection methods vii namely: observation, questionnaires and learning achievement tests. Data analysis technique using Percentage of Agreements and Normalized N Gain. Results: The results of the study show: (1) an analysis of the effectiveness of applying the Islamic-oriented cooperative learning model through the course of Islamic Education at UIN Alauddin and STAI DDI Majene, based on the results of the N Normalized Gain analysis is in the medium category, so that it can be seen as fulfilling the effective requirements in its application through learning Islamic education science; (2) practical analysis of the application of the Islamic-oriented cooperative learning model through Islamic Education courses at UIN Alauddin and STAI DDI Majene, based on the results of the Normalized N Gain analysis in the very good category, so that it can be seen as fulfilling practical requirements in its application through learning Islamic education; and (3) the reality of implementing the Islamic-oriented cooperative learning model through Islamic Education courses at UIN Alauddin and STAI DDI Majene, is in the very good category. Conclusion: The implications of this research show: (1) there is an increase in student learning outcomes through Islamic Education courses at UIN Alauddin and STAI DDI Majene; (2) there was a positive response from lecturers and students as the main actors of Islamic-oriented cooperative learning through Islamic Education courses at UIN Alauddin and STAI DDI Majene; and (3) the application of an Islamic-oriented cooperative learning model through Islamic Education courses at UIN Alauddin and STAI DDI Majene, which can be used in tertiary institutions, is easy and practical to use. Thus, this model can be used as an alternative choice in learning activities, especially if lecturers or students want to build activeness and success in their learning.

Hierarchical Reinforcement Learning: Structuring Decision-Making for Complex AI Tasks

Hierarchical Reinforcement Learning (abbreviated as HRL) represents a progress in the realm of artificial intelligence (AI) focusing on handling the increasing complexity of decision-making processes effectively. By breaking down tasks into smaller sub tasks that are easier to manage and comprehend; HRL plays a key role in enhancing the learning efficiency of AI models. The hierarchical system mirrors decision making approaches by breaking down complex goals into smaller achievable steps; this allows reinforcement learning agents to effectively learn and adjust to dynamic environments, with limited rewards and long-term objectives. In contrast to the limitations faced by flat reinforcement learning techniques in terms of scalability and efficiency Hierarchical Reinforcement Learning (HRL) introduces a higher-level policy that controls the series and implementation of sub tasks. This study delves into the evolution, application, and influence of reinforcement learning models in artificial intelligence. We explore HRL frameworks, such, as the Options framework and temporal adaptive models that offer a systematic decision-making method. Furthermore, the study analyzes the role HRL plays in fields including robotics, self-governing systems, and game artificial intelligence. HRL is on the brink of transforming how AI tackles challenges by shaping decision making processes in intricate settings that mimic real world scenarios. This piece explores the issue at hand along, with its solutions and applications while discussing the influence and extent of HRL in enhancing AI technologies. Keywords: Hierarchical Reinforcement Learning, AI, Reinforcement Learning, Decision-Making, Sub-tasks, Options Framework, Temporal-Adaptive Models, Robotics, Autonomous Systems, Game AI, Artificial Intelligence.

Implementation of the ASICC learning model to improve the metacognitive students' based on lesson study extracts

This research is driven by observations from the eighth-grade class at Junior High School 5 Kertosono, which revealed that lesson planning, reading comprehension, and problem-solving strategies have not been effectively utilized. Therefore, this research aims to enhance students' awareness and metacognitive skills through the application of the ASICC learning model. The focus of this study is on 18 eighth-grade students at Junior High School 5 Kertosono. This research is classroom action research based on a lesson study conducted over two cycles. The data analysis used is the scores of metacognitive awareness and skills in the first cycle compared to the second cycle, tested using N-Gain analysis. The research results reveal that metacognitive awareness in the first cycle showed that 11.1% of students were in the "medium" category, which increased to 22.2% in the second cycle. Meanwhile, metacognitive skills experienced a significant increase in the "high" category, starting from 16.7% in the first cycle and rising to 33.3% in the second cycle. The ASICC learning model can be applied to enhance students' metacognition. Another finding reveals that students with good metacognitive awareness do not always possess good metacognitive skills

The Effect of the Application of the Problem-Based Learning Model on Communication Problem Solving Ability in Students of the Communication Study Program FISIP UNAS Jakarta

Problem-based Learning (PBL) is a learning method where students are faced with problems that exist in society in real life, to then be used as a trigger in learning. PBL is seen as more effective than the conventional curriculum, which only relies on lectures and practicums. Learning activities in PBL include expert lectures, discussions in small groups, practicum in the laboratory, and clinical skills practicum. Through this activity, it is hoped that students can achieve satisfactory learning achievements, considering that the concept carried by this system is so ideal. Problembased learningg is learning with an approach oriented to a constructivistic view that contains contextual characteristics, collaborative, metacognitive thinking, and facilitates problem solving. Students are able to learn meaningfully that can develop higher-order thinking skills through problem solving. Through this learning, it is hoped that it can increase understanding of meaning, increase independence, increase the development of higher-level thinking skills, increase motivation, facilitate relationships between students and improve skills in building teamwork when solving problems and finding solutions. The design of this study uses a quantitative approach with a survey method through the distribution of questionnaires to communication students of the Communication Psychology course. The results of the research can be used as reference to universities, especially the Communication Study Program, Faculty of Social and Political Sciences, UNAS Jakarta, to implement The problem-based learning model plays an active role in the learning process, especially in this independent curriculum.

E-History Media Development of Widuri Beach Efforts to Improve New Vocabulary Writing Skills Through the Project Based Learning (PJBL) Model in High Class Students

This research aims to develop electronic-based learning media, "E-History of Widuri Beach," which functions as a tool to improve new vocabulary writing skills in elementary school students through the application of the Project-Based Learning (PjBL) model. The method used in this research is research and development (R&D) with the ADDIE (analysis, design, development, implementation, and evaluation) model. The research subjects consisted of high school elementary school students in Pemalang Regency. Research instruments include questionnaires, vocabulary writing skills tests, and observations. Data were analyzed using quantitative and qualitative descriptive analysis techniques. The results of the research show that the E-History of Widuri Beach media developed is effective in improving students' new vocabulary writing skills. Apart from that, the implementation of the PjBL model has been proven to increase students' active participation in the learning process. Keywords: E-History, vocabulary writing skills, Project Based Learning (PjBL), Widuri Beach

Analyzing Student Online Learning Behaviors and Academic Performance in Science Education Using Machine Learning Techniques

This study investigates the factors influencing student engagement and performance in online science education through the application of machine learning models, specifically Random Forests, Decision Trees, and Support Vector Machines (SVM). With the rapid growth of online education, understanding students' adaptability and learning behaviors has become increasingly critical. A systematic analysis of features such as study duration, daily study habits, and demographic factors revealed significant insights into their impact on academic achievement in science subjects. The Random Forest model outperformed others in classification accuracy, achieving an accuracy of 81%. The findings emphasize the importance of tailored educational strategies that foster consistent study practices and address the unique needs of diverse learners, ultimately enhancing learning outcomes in online science education.

Applications of AI-based deep learning models for detecting dental caries on intraoral images - a systematic review.

This systematic review aimed to assess the effectiveness of ArtificialIntelligence(AI)-based Deep Learning (DL) models in the detection of dental caries on intraoral images. This systematic review adhered to PRISMA 2020 guidelines conducting an electronic search on PubMed, Scopus, and CENTRAL databasesfor retrospective, prospective, and cross-sectional studies published till 1st June 2024. Methodological and performance metrics of clinical studies utilizing DL models were assessed. A modified QUADAS risk of bias tool was used for quality assessment. Out of 273 studies identified, a total of 23 were included with 19 studies having a low risk and 4 studies having a high risk of bias. Overall accuracy ranged from 56% to 99.1%, sensitivity ranged from 23% to 98% and specificity ranged from 65.7% to 100%. Only 3 studies utilized explainable AI (XAI) techniques for caries detection. A total of 4 studies exhibited a level 4 deployment status by developing mobile or web-based applications. AI-based DL models have demonstrated promising prospects in enhancing the detection of dental caries, especially in terms of low-resource settings. However, there is a need for future deployed studies to enhance the AI models to improve their real-world applications.