Conventional Learning Methods Research Articles

Classification and detection of dental images using meta-learning

Meta-learning of dental X-rays is a machine learning technique that can be used to train models to perform new tasks quickly and with minimal input. Instead of just memorizing a task, this is accomplished through teaching a model how to learn. Algorithms for meta-learning are typically trained on a collection of training problems, each of which has a limited number of labelled instances. Multiple X-ray classification tasks, including the detection of pneumonia, coronavirus disease 2019, and other disorders, have demonstrated the effectiveness of meta-learning. Meta-learning has the benefit of allowing models to be trained on dental X-ray datasets that are too few for more conventional machine learning methods. Due to the high cost and lengthy collection process associated with dental imaging datasets, this is significant for dental X-ray classification jobs. The ability to train models that are more resistant to fresh input is another benefit of meta-learning.

The effect of REACT model implementation on learning outcomes and critical thinking skills of students of SMAN 9 KENDARI

Quality human resources will be formed if education focuses on improving students’ skills. Of course, the foundation of education must be quality. Qualified human resources will later be responsible for making Indonesia a good country in all fields. This study aims to examine the effect of applying the REACT learning model (Relating, Experiencing, Applying, Cooperating, Transferring) on learning outcomes and critical thinking skills of students of SMAN 9 KENDARI. Quantitative research method with experimental research type. The research design used was post experimental control design. The research location was at SMAN 9 KENDARI. The instruments used include learning outcomes test and critical thinking skills test. The data obtained were explained using statistical tests to see the differences between the experimental group and the control group in chemistry subjects. The results showed that the application of REACT model significantly improved students’ learning outcomes and critical thinking skills compared to conventional learning methods in chemistry subjects. The findings indicated that the REACT model was effective in improving the quality of learning and developing critical thinking skills of students of SMAN 9 KENDARI, especially in chemistry learning.

PENGEMBANGAN MEDIA PEMBELAJARAN VIDEO INTERAKTIF UNTUK MENINGKATKAN HASIL BELAJAR SISWA

Conventional learning methods that are still applied by teachers experience several obstacles, including many students who cannot understand the material being taught. Students tend to be passive and do not respond to the material presented, this affects the learning outcomes of students who do not meet the minimum completeness criteria. The purpose of this study was to determine the development of interactive video learning media in improving student learning outcomes. The method used in this study is the research and development method or Research and Development (R & D). The model used in this study is the development of the 4-D (Four D) model. The results of this study indicate that the assessment of the feasibility of interactive video learning media by material experts is very valid with a percentage of 93%, and the results of the feasibility of interactive video language based on learning aspects have been valid with a percentage of 90%. The results of the feasibility of interactive video media based on material editing aspects have been valid with a percentage of 83%. The response of students to the interactive learning video individual test was 80.35% (practical) while in the field test it reached 93.68% (very practical) while student learning outcomes based on validation reached 85.77%. The effectiveness of interactive learning videos is marked by student learning completion with an average of 90%. From this, it can be concluded that interactive learning videos can improve student learning outcomes.

Classification of EEG evoked in 2D and 3D virtual reality: traditional machine learning versus deep learning

Backgrounds. Virtual reality (VR) simulates real-life events and scenarios and is widely utilized in education, entertainment, and medicine. VR can be presented in two dimensions (2D) or three dimensions (3D), with 3D VR offering a more realistic and immersive experience. Previous research has shown that electroencephalogram (EEG) profiles induced by 3D VR differ from those of 2D VR in various aspects, including brain rhythm power, activation, and functional connectivity. However, studies focused on classifying EEG in 2D and 3D VR contexts remain limited.Methods. A 56-channel EEG was recorded while visual stimuli were presented in 2D and 3D VR. The recorded EEG signals were classified using two machine learning approaches: traditional machine learning and deep learning. In the traditional approach, features such as power spectral density (PSD) and common spatial patterns (CSP) were extracted, and three classifiers-support vector machines (SVM), K-nearest neighbors (KNN), and random forests (RF)-were used. For the deep learning approach, a specialized convolutional neural network, EEGNet, was employed. The classification performance of these methods was then compared.Results. In terms of accuracy, precision, recall, and F1-score, the deep learning method outperformed traditional machine learning approaches. Specifically, the classification accuracy using the EEGNet deep learning model reached up to 97.86%.Conclusions. EEGNet-based deep learning significantly outperforms conventional machine learning methods in classifying EEG signals induced by 2D and 3D VR. Given EEGNet's design for EEG-based brain-computer interfaces (BCI), this superior classification performance suggests that it can enhance the application of 3D VR in BCI systems.

Socio-Cultural Approach through Digital Teaching Modules: A Solution to Improve Beginning Reading Skills in Elementary Schools

The low level of early reading skills among primary school students in Indonesia is one of the significant challenges in education. International evaluations such as PISA show that Indonesian students' basic literacy skills are still below average, affecting their overall academic development. One of the contributing factors to these low results is learning that is less relevant to students' socio-cultural context. Therefore, this study aims to investigate the effect of a socio-cultural-based digital teaching module on primary school students' beginning reading skills. This study used a quasi-experimental design with a sample of 200 grade 1 students divided into experimental and control groups. The experimental group learned using socio-cultural-based digital teaching modules, while the control group applied conventional learning methods. The instrument used was a beginning reading test with 20 questions that measured the ability to recognize letter symbols, distinguish words based on the same initial letter or syllable, and compose syllables into words. Independent Sample T-Test analyzing an independent sample, ensuring that the ty and homogeneity tests were met. The results revealed significant differences between the experimental and control groups, with the experimental group showing more significant improvement in all indicators of beginning reading ability. Further discussion showed that the socio-cultural-based approach in this module made learning more relevant, exciting and interactive for students, ultimately improving their reading comprehension and motivation. In addition, integrating digital technology in this module supports flexibility and continuity of learning, allowing students to learn according to their pace and needs. This research has important implications, namely the need for broader implementation of Socio-Cultural Based Digital Teaching Modules in primary schools to improve basic literacy. However, to ensure its successful implementation, adequate technological infrastructure support and teacher training are needed to optimize this digital-based learning in the classroom.

Developing Videos Through Project-Based Learning: Improving Aviation Cadets’ Basic Airport Civil Engineering

This study aimed to explain project-based learning (PjBL) in the context of making airside and landside learning videos for aviation cadets and measure the effectiveness of the learning videos in improving their understanding of basic airport civil engineering material. This study used ADDIE development method to develop learning videos integrated in a project-based learning process with a quantitative approach. There were 48 cadets included in this study selected using a purposive sampling technique. A total of 24 cadets joined the control class taught using conventional learning method and a total of 24 cadets participated in the experimental class taught using PjBL by developing learning videos. Data were collected using needs analysis questionnaire, rating scale for understanding basic airport civil engineering material, and validation sheet. The obtained data were analyzed using descriptive statistics and t-test to address the research questions. Results showed that the cadets were able to develop valid learning videos through ADDIE procedure and they could increase their understanding on basic airport civil engineering significantly (F = 3.533; t = .969; p = .000).

ECGWiz: a unified and generalizable AI model for comprehensive ECG diagnosis

Abstract Background Deep learning has demonstrated diagnostic performance in electrocardiogram (ECG) analysis comparable to that of clinicians. However, existing models primarily excel in diagnosing common conditions such as arrhythmias and heart blocks, which are easily identifiable using standard predictor variables. Conversely, models aiming to uncover novel insights, such as detecting structural changes or the presence of myocardial scar, often lack generalizability due to insufficient data, model architecture limitations, and other factors. Moreover, these models frequently encounter challenges, such as a decline in performance when applied to external datasets. To address these issues comprehensively, we propose the ECGWiz — a unified model capable of tackling diverse ECG-related problems with consistently high performance. Objective To develop a generalizable Foundation AI model for ECG diagnosis capable of detecting diverse cardiac abnormalities and diseases using few training samples. Methods We utilized publicly available datasets like PTB-XL, CPSC, etc. To build our model, totaling approximately 80,000 ECGs. These 12 lead ECGs are scaled and filtered before using them for training. The AI model is pretrained using Self Supervised Learning and Contrastive Learning strategies. Further, the model undergoes supervised training using a hierarchy of labels that increase in granularity, encompassing arrhythmias, heart blocks, other cardiac abnormalities, heart failure, sudden cardiac death and more. Lastly, the model is prepared for Few-Shot Learning — where the model learns from a minimal set of samples (5 to 10 ECGs) of the target disease. For testing the model, we are using unique datasets like PROSE which consists of non-ischemic cardiomyopathy patients with and without myocardial scaring detected using cardiac MRI imaging at the Johns Hopkins University. Results Our model, trained on a dataset of only 5 ECG recordings, demonstrated a 74% accuracy in identifying myocardial scarring as detected by LGE MRI, utilizing a standard 12-lead ECG. This performance is comparable to that of conventional deep learning methods, which necessitate datasets containing upwards of 120 ECG recordings. Conclusion Our model represents a promising stride in creating a unified and adaptable foundation AI model for comprehensive ECG-based diagnosis. Its capacity to learn from a minimal set of examples signifies a robust framework that can evolve and adapt to new challenges in ECG diagnosis. Ongoing improvements, particularly through dataset expansion, underscore its potential to enhance cardiovascular diagnostics, offering precise and efficient patient care.

The Effect of Project-Based Learning (PBL) Method on Improving Students' Writing Ability

Education plays a crucial role in shaping intelligent, moral and responsible individuals. The project-based learning (PBL) model emerges as an innovative approach that focuses not only on knowledge transfer, but also the development of students' critical skills, creativity and collaboration. This study aims to analyze the effect of PBL on students' writing ability compared to conventional learning methods. Through a literature study, the data sources obtained show that PBL increases students' engagement, confidence, and in-depth understanding of the material. Students are actively involved in project planning and implementation, which allows them to apply knowledge in a real context, resulting in a more meaningful learning experience. The findings confirm the importance of PBL as an effective method in improving students' writing skills, as well as providing recommendations for educators to integrate PBL in the educational curriculum to create a generation that is ready to face global challenges.

PENGARUH PENGGUNAAN MEDIA AJAR BERBASIS TEKNOLOGI ANIMAKER PADA MATA PELAJARAN IPAS TERHADAP MINAT BELAJAR PADA SISWA SEKOLAH DASAR

: The effect of using technology-based learning media on science subjects. So you can see how strong the influence of technology-based learning media is on increasing students' interest in learning in the learning process. The aim of this research is to determine the effect of using Animaker technology-based teaching media on class 4 students' interest in learning. This type of research uses a quantitative approach with experimental research methods. The method used to find the effect of treatment on the thing being researched. Therefore, in this experimental method there will be special treatment to determine whether or not there is an influence in the research. The method used by researchers is Quasi Experimental design. hypothesis testing, the results of the independent t test show that there are significant differences between the two groups. Levene's Test shows that the variance of the two groups is considered the same (Sig. 0.804). The t-test results show a t-statistic value of 5.298 with 54 degrees of freedom and a significance value of 0.000. The mean difference between the experimental and control groups was 8.964 with a 95% confidence interval ranging from 5.572 to 12.356. These results indicate that the use of Animaker teaching media significantly increases students' interest in learning compared to conventional learning methods. It is concluded that there is a significant influence from the use of Animaker technology-based teaching media on students' interest in learning in science and science subjects in class 4 at SDN Grogol Utara 09. Analysis statistics show that there is a significant difference in the post-test results between the experimental group using Animaker and the control group using conventional methods. With the experimental group's average post-test results being slightly higher, this difference is statistically large enough to be declared a significant difference.

Pengaruh Model Problem Based Learning Berbantuan Media Assemblr Edu terhadap Kemampuan Pemecahan Masalah Siswa Kelas V

Problem-solving skills are essential competencies that need to be developed in elementary school students. The application of innovative learning models, such as Problem-Based Learning supported by interactive technology media like Assemblr Edu, can be an effective solution for enhancing these skills. This study aims to analyze the impact of the Problem-Based Learning (PBL) model supported by Assemblr Edu media on the problem-solving abilities of fifth-grade students. The research method used is an experimental method with a Pre-test Post-test Non-Equivalent Control Group Design. The results of the study showed that the use of the PBL model supported by Assemblr Edu significantly improved students' problem-solving abilities compared to conventional learning methods. This can be seen from the significant difference in the N-Gain scores, with the experimental class reaching 0.7 (moderate category) and the control class only 0.2 (low category). These findings suggest that interactive technology media like Assemblr Edu can be an effective tool in enhancing students' critical and analytical thinking skills.

DIGITAL TEACHING MATERIAL OF SUSTAINABLE LIFESTYLE THEME WITH ETHNO-PJBL TO PROMOTE STUDENTS’ KNOWLEDGE AND CREATIVE THINKING ABILITIES

Purpose: This study aims to analyze the effects of digital teaching materials on the theme of sustainable lifestyle integrated with Ethno-PjBL on knowledge and creative thinking skills in learning in the Merdeka Curriculum. Theoretical Framework: The idea behind the development of digital learning materials on the theme of sustainable lifestyle is to promote awareness and practice of sustainability among students through the integration of technology in learning. By combining a project-based learning model enriched by local cultural values (Ethno-PjBL), students are not only invited to understand the concept of sustainable lifestyle, but also how to apply it in their cultural context. Method: This study used a quasi-experimental method with a posttest only control group design. The sample of this study was grade X students at SMAN Kota Jambi, with the experimental class using integrated digital teaching materials ethno-PjBL and the control class using conventional learning methods. Data were analyzed using descriptive statistical tests, Kolmogorov-Smirnov normality tests, and Mann-Whitney tests. Results and Discussion: Digital teaching materials on sustainable lifestyle themes integrated with ethno-PjBL have a positive impact on students' knowledge and creative thinking skills. The experimental class using the digital teaching materials showed better results compared to the control class using conventional learning methods. Research Implications: The results of this study support the integration of sustainable lifestyle-themed digital teaching materials with the Ethno-PjBL approach, which not only strengthens students' academic knowledge, but also fosters creative thinking skills and awareness of local cultural values. The findings of this study can encourage educators and policy makers to further adopt and develop contextual and relevant digital teaching materials, especially those that focus on global issues such as sustainability, but are still integrated with local wisdom. The implications of this study also open up opportunities for further research to explore the potential of digital teaching materials in other subjects or at different levels of education.

Ranking and Combining Latent Structured Predictive Scores without Labeled Data

Combining multiple predictors obtained from distributed data sources to an accurate meta-learner is promising to achieve enhanced performance in lots of prediction problems. As the accuracy of each predictor is usually unknown, integrating the predictors to achieve better performance is challenging. Conventional ensemble learning methods assess the accuracy of predictors based on extensive labeled data. In practical applications, however, the acquisition of such labeled data can prove to be an arduous task. Furthermore, the predictors under consideration may exhibit high degrees of correlation, particularly when similar data sources or machine learning algorithms were employed during their model training. In response to these challenges, this paper introduces a novel structured unsupervised ensemble learning model (SUEL) to exploit the dependency between a set of predictors with continuous predictive scores, rank the predictors without labeled data and combine them to an ensembled score with weights. Two novel correlation-based decomposition algorithms are further proposed to estimate the SUEL model, constrained quadratic optimization (SUEL.CQO) and matrix-factorization-based (SUEL.MF) approaches. The efficacy of the proposed methods is rigorously assessed through both simulation studies and real-world application of risk genes discovery. The results compellingly demonstrate that the proposed methods can efficiently integrate the dependent predictors to an ensemble model without the need of ground truth data.

LTFM: Long-tail few-shot module with loose coupling strategy for mineral spectral identification

In recent years, deep learning methods have exhibited superior performance in mineral identification when especially compared with conventional machine learning methods such as Support Vector Machine (SVM) and Partial Least Squares (PLS). Nevertheless, almost all of these deep learning methods pay more attention to improving and designing network structures, while neglecting the phenomenon of long-tail distribution in spectral data due to the inconsistency of ore distribution and the scarcity of several natural minerals. To alleviate the interference of majority categories on minority categories, we propose Long-Tail Few-shot Module (LTFM) which is inspired by rethinking the fashionable decoupling strategy that conducts primary representation learning and further classifier retrained on mineral spectral data. In particular, LTFM serves as a multi-expert mode, where these experts are respectively specialized in improving feature representation learning, mitigating the long-tail effect, and alleviating the interference of few shots. Additionally, the loose coupling learning strategy is introduced to facilitate primary representation learning and the subsequent additional experts to inherit this knowledge. Experiments on two publicly available spectral datasets show that the proposed LTFM significantly outperforms existing methods. In the end, extensive ablation studies are conducted to investigate the effectiveness, correctness, and robustness of our proposal.

Penerapan Media Pembelajaran Interaktif Quizwhizzer dengan Metode Diferensiasi Pembelajaran untuk Meningkatkan Hasil Belajar Siswa di SMK Muhammadiyah 2 Kuningan

This research aims to improve student learning outcomes in Computer Fundamentals subjects by using the learning differentiation method using quizwhizzer interactive media. This study uses the pre-experiment method with the research design used is "One Gruop Pretest-Posttest Design". The sample was 16 people consisting of 14 men and 3 women in class X Computer Engineering, Network Engineering, Data Collection Questions/Tests (Pretest-Posttest) and Quesioner (Pretest-Posttest). Data analysis was carried out on the results of the pretest and posttest which were tested using the t-test. The results of the study showed that there was a difference in the learning outcomes of students who were taught using conventional learning methods and the learning outcomes of students who were taught using quizwhizzer learning media using the differentiation method in the Computer Basics material of class X TKJ at SMK Muhammadiyah 2 Kuningan, this can be seen from the results of hypothesis testing using the t-test obtained from the results of the calculation of the hypothesis test (t-test) the posttest score was known to be the average score 60.75 while the pretest with an average of 48.37 so that it is known that the increase in the posttest learning outcome score is greater than 12.38 compared to the pretest learning outcome score. So that it can be stated that there is a significant difference in the increase in learning outcomes in the pretest and posttest

Student's Perceptions Towards Learning Arabic Language Through Digital Game

In the current age of widespread digitization, technology has become an essential aspect of our everyday existence, significantly transforming how we gain knowledge and interact with our environment. This study aims to explore students' viewpoints on acquiring the Arabic language by employing digital games. This study used a qualitative methodology and performed semi-structured interviews with a purposively selected 30 college students. Their Arabic language program exposed These students to a digital game for five weeks. The findings revealed that students responded well to learning Arabic using digital games, consistently expressing their experiences in a unique and engaging educational environment. The post-implementation semi-structured interviews indicated that students recognized the integration of digital games as a valuable and advantageous approach, providing a distinct and captivating aspect to conventional learning methods. Hence, the results indicate that incorporating digital games into language teaching improves learning and benefits teachers and students in many courses that adopt this creative method.

Non-destructive detection of male and female information in ducklings based on near-infrared spectral wavelength selection and deep learning

The technology for sex identification in ducklings can contribute to increased revenue and cost savings in modern duck farming. However, traditional manual identification techniques require high skill levels and involve significant labor intensity. In this study, a non-destructive, user-friendly, and efficient duckling sex identification technique was proposed using near-infrared spectroscopy and deep learning algorithms. Spectral data from 600 groups of newly hatched ducklings were collected. These data were divided into training, testing, and validation sets in a ratio of 7:2:1. The raw spectral data was preprocessed using the Savitzky-Golay convolution derivative method, which was employed for subsequent spectral feature wavelength extraction and modeling. The characteristic wavelengths were extracted using competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination combined with SPA (UVE-SPA). Conventional machine learning methods − support vector machine (SVM) and different deep learning models, including multilayer perceptron (MLP), mobile network version 2 (MobileNetV2), and residual neural network (ResNet), were studied and compared. The experiment showed that deep learning algorithms outperform traditional spectral analysis models in terms of classification performance. Furthermore, conducting feature wavelength extraction before constructing the classification model could reduce the model’s testing time and even improve its classification performance. Finally, the four models with better classification performance were validated using a validation set, and the combination of MobileNetV2 model UVE-SPA was selected as the optimized model for ducklings’ gender determination, with a classification accuracy of 98.3 % and an average validation time of 1.1 ms. In summary, the detection model established using near-infrared spectroscopy and MobileNetV2 can achieve non-destructive identification of the gender of ducklings. The findings can provide a preliminary research foundation and technical support for the subsequent design of related online intelligent detection systems.

Meningkatkan Prestasi Belajar PAKBP Siswa Kelas VIII Pada Materi Yesus Mewartakan Kerajaan Allah Model PBL Di SMP Negeri 2 Seluas

Catholic Religious Education (PAK) is one of the subjects taught in schools. Like every subject, Catholic Religious Education has its objectives. The aim is to build the competence of students as individuals of faith, to flourish and develop children into Christian individuals grounded in a relationship with Jesus Christ. This Catholic Religious Education subject should provide students with opportunities to be active as designed in the Independent Curriculum, which gives flexibility for educational units and teachers to develop their potential and freedom for students to learn according to their abilities and development. However, theoretical learning in Religious Education for class VIII at SMP Negeri 2 Seluas still often uses conventional learning methods. As a result, the learning outcomes of the subject have not yet reached the determined mastery target, and students' attitudes in learning are not apparent. Therefore, this study aims to (1) understand the application of the inquiry learning method, (2) improve the learning outcomes of Catholic Religious Education, and (3) enhance the religious attitude of class VIII students at SMP Negeri 2 Seluas using the Problem Based Learning method. PBL model also increases active participation and critical thinking skills of students in understanding and applying the concept of parables in the context of daily life.

Application of Project-Based Learning Model to Social Studies Learning Materials of the Independent Curriculum at SDN 01 Depok City

This research aims to obtain a clearer picture of how PBL can be implemented effectively in social studies learning in elementary schools, and can provide input for educational policy makers in formulating policies that support the implementation of innovative learning models and in accordance with dynamic curriculum demands. This research uses a quantitative approach with a quasi-experimental design. This approach was chosen because it is suitable for measuring the effectiveness of implementing the Project-Based Learning (PBL) learning model in improving student learning outcomes in Social Sciences (IPS) subjects. The research results show that the t test results show that the calculated t value (4.321) is greater than the t table (2.001) with a p-value 0.05. Meanwhile, the results of critical thinking, collaboration and creativity skills experienced a significant increase after implementing PBL, with an average increase of 16.7 to 17.9 points. This indicates that there is a statistically significant difference between the learning outcomes of students who use the PBL model and those who use conventional learning methods. Therefore, it can be concluded that the PBL learning model is more effective in improving students' social studies learning outcomes.

Intelligent Handwritten Identification Using Novel Hybrid Convolutional Neural Networks – Long-short-term Memory Architecture

Handwritten character identification finds broad applications in document analysis, digital forensics, and human-computer interaction. Conventional methods encounter challenges in accurately deciphering a range of handwriting styles and variations. Consequently, investigating intelligent system for handwriting identification becomes crucial to enhance accuracy and efficiency. This paper introduces an innovative hybrid deep learning architecture, seamlessly integrating the strengths of convolutional neural networks (CNN) and long-short term memory (LSTM) within a one single framework. The combination of these structures enables the model to effectively capture both spatial features and temporal dependencies inherent in handwritten strokes, resulting in improved recognition performance. The proposed 2DCNN-LSTM algorithm has been tested on MNIST dataset. The proposed hybrid CNN-LSTM structure has been compared to conventional intelligent machine learning methods, and the results demonstrate the superior performance of the hybrid CNN-LSTM, showcasing heightened accuracy, sensitivity, specificity, and other evaluation metrics.

PheW2P2V: a phenome-wide prediction framework with weighted patient representations using electronic health records.

Electronic health records (EHRs) provide opportunities for the development of computable predictive tools. Conventional machine learning methods and deep learning methods have been widely used for this task, with the approach of usually designing one tool for one clinical outcome. Here we developed PheW2P2V, a Phenome-Wide prediction framework using Weighted Patient Vectors. PheW2P2V conducts tailored predictions for phenome-wide phenotypes using numeric representations of patients' past medical records weighted based on their similarities with individual phenotypes. PheW2P2V defines clinical disease phenotypes using Phecode mapping based on International Classification of Disease codes, which reduces redundancy and case-control misclassification in real-life EHR datasets. Through upweighting medical records of patients that are more relevant to a phenotype of interest in calculating patient vectors, PheW2P2V achieves tailored incidence risk prediction of a phenotype. The calculation of weighted patient vectors is computationally efficient, and the weighting mechanism ensures tailored predictions across the phenome. We evaluated prediction performance of PheW2P2V and baseline methods with simulation studies and clinical applications using the MIMIC-III database. Across 942 phenome-wide predictions using the MIMIC-III database, PheW2P2V has median area under the receiver operating characteristic curve (AUC-ROC) 0.74 (baseline methods have values ≤0.72), median max F1-score 0.20 (baseline methods have values ≤0.19), and median area under the precision-recall curve (AUC-PR) 0.10 (baseline methods have values ≤0.10). PheW2P2V can predict phenotypes efficiently by using medical concept embeddings and upweighting relevant past medical histories. By leveraging both labeled and unlabeled data, PheW2P2V reduces overfitting and improves predictions for rare phenotypes, making it a useful screening tool for early diagnosis of high-risk conditions, though further research is needed to assess the transferability of embeddings across different databases. PheW2P2V is fast, flexible, and has superior prediction performance for many clinical disease phenotypes across the phenome of the MIMIC-III database compared to that of several popular baseline methods.