Yasin Fatemi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yasin Fatemi has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Haneen Ali
Mechanical and Industrial Engineering Department, Applied Science Private University, Amman 11937, Jordan
7 shared publications - Duha Ali
Industrial and Manufacturing Engineering Department, California Polytechnic State University, San Luis Obispo, CA 93407, USA
3 shared publications Haneen Ali
Department of Mechanical and Industrial Engineering, Applied Science Private University, Amman, Jordan
2 shared publications- Mohsen Nikfar
Department of Industrial and Systems Engineering, Auburn University, Auburn, AL 36849, USA
2 shared publications - Sa'D Hamasha
Binghamton University
2 shared publications - Amir Oladazimi
Department of Industrial and Systems Engineering, Auburn University, Auburn, AL 36849, USA
1 shared publication
Latest Publications
- Open Access
- 31 July 2025
- Published by Frontiers Media SA in Frontiers in Education
- Vol. 10, 1559509
ChatGPT perceptions, experiences, and uses with emphasis on academia
Introduction: With artificial intelligence technologies such as ChatGPT becoming increasingly integrated into educational environments, understanding their influence on academic stakeholders is essential. This study investigates how exposure to ChatGPT and demographic factors shape perceptions of this emerging AI tool in higher education.Methods: A cross-sectional survey was conducted at Auburn University, involving 761 participants including both faculty and students. The survey examined technology exposure, ChatGPT familiarity, demographic variables (e.g., gender), and overall perceptions of ChatGPT in academic contexts.Results: The analysis revealed significant differences in exposure and attitudes toward ChatGPT, with gender emerging as a key variable. Males reported greater exposure and more favorable perceptions of ChatGPT compared to other groups. Familiarity with AI tools was positively correlated with supportive attitudes toward their use in education.Discussion: These findings highlight the importance of AI exposure in fostering acceptance and effective utilization of tools like ChatGPT. The results suggest a need for inclusive and equitable strategies to integrate AI in academic settings, particularly for underrepresented or less-exposed groups. Further research is encouraged to guide ethical and effective AI adoption in education.
- 31 July 2025
- Published by Frontiers Media SA in Frontiers in Education
- Vol. 10, 1559509
Open AccessChatGPT perceptions, experiences, and uses with emphasis on academia
Introduction: With artificial intelligence technologies such as ChatGPT becoming increasingly integrated into educational environments, understanding their influence on academic stakeholders is essential. This study investigates how exposure to ChatGPT and demographic factors shape perceptions of this emerging AI tool in higher education.Methods: A cross-sectional survey was conducted at Auburn University, involving 761 participants including both faculty and students. The survey examined technology exposure, ChatGPT familiarity, demographic variables (e.g., gender), and overall perceptions of ChatGPT in academic contexts.Results: The analysis revealed significant differences in exposure and attitudes toward ChatGPT, with gender emerging as a key variable. Males reported greater exposure and more favorable perceptions of ChatGPT compared to other groups. Familiarity with AI tools was positively correlated with supportive attitudes toward their use in education.Discussion: These findings highlight the importance of AI exposure in fostering acceptance and effective utilization of tools like ChatGPT. The results suggest a need for inclusive and equitable strategies to integrate AI in academic settings, particularly for underrepresented or less-exposed groups. Further research is encouraged to guide ethical and effective AI adoption in education.
- Open Access
- 18 July 2025
- Published by MDPI AG in Healthcare
- Vol. 13 (14) , 1741
Assessing Stress and Shift Quality in Nursing Students: A Pre- and Post-Shift Survey Approach
Background: Nursing students often experience heightened levels of stress during clinical training due to the dual demands of academic and clinical responsibilities. These stressors, compounded by environmental and organizational factors, can adversely affect students’ well-being, academic performance, and the quality of patient care they deliver. Aim: This study aimed to identify the key stressors influencing nursing students’ perceptions of single-shift quality (SSQ) during clinical training and to examine how well students can predict the quality of their shift based on pre-shift expectations. Methodology: A cross-sectional survey design was implemented, collecting pre- and post-shift data from 325 nursing students undergoing clinical training in Alabama. The survey measured 13 domains related to workload, environmental conditions, organizational interactions, coping strategies, and overall satisfaction. Paired t tests and linear regressions were used to assess changes in perception and identify key predictors of SSQ. Results: This study found significant discrepancies between students’ pre- and post-shift evaluations across multiple domains, including internal environment, organizational interaction with clinical faculty/preceptors, and coping strategies (p < 0.001). Students also accurately predicted stable factors such as patient characteristics and external environment. Pre-shift expectations did not significantly predict post-shift experiences. Post-shift perceptions revealed that stress-coping strategies and collegiality were the strongest predictors of shift quality. Conclusion: Students enter clinical shifts with optimistic expectations that often do not align with actual experiences, particularly regarding support and stress management. The SSQ framework offers a valuable tool for identifying gaps in clinical training and guiding interventions that foster resilience and better alignment between expectations and real-world practice.
- 18 July 2025
- Published by MDPI AG in Healthcare
- Vol. 13 (14) , 1741
Open AccessAssessing Stress and Shift Quality in Nursing Students: A Pre- and Post-Shift Survey Approach
Background: Nursing students often experience heightened levels of stress during clinical training due to the dual demands of academic and clinical responsibilities. These stressors, compounded by environmental and organizational factors, can adversely affect students’ well-being, academic performance, and the quality of patient care they deliver. Aim: This study aimed to identify the key stressors influencing nursing students’ perceptions of single-shift quality (SSQ) during clinical training and to examine how well students can predict the quality of their shift based on pre-shift expectations. Methodology: A cross-sectional survey design was implemented, collecting pre- and post-shift data from 325 nursing students undergoing clinical training in Alabama. The survey measured 13 domains related to workload, environmental conditions, organizational interactions, coping strategies, and overall satisfaction. Paired t tests and linear regressions were used to assess changes in perception and identify key predictors of SSQ. Results: This study found significant discrepancies between students’ pre- and post-shift evaluations across multiple domains, including internal environment, organizational interaction with clinical faculty/preceptors, and coping strategies (p < 0.001). Students also accurately predicted stable factors such as patient characteristics and external environment. Pre-shift expectations did not significantly predict post-shift experiences. Post-shift perceptions revealed that stress-coping strategies and collegiality were the strongest predictors of shift quality. Conclusion: Students enter clinical shifts with optimistic expectations that often do not align with actual experiences, particularly regarding support and stress management. The SSQ framework offers a valuable tool for identifying gaps in clinical training and guiding interventions that foster resilience and better alignment between expectations and real-world practice.
- Open Access
- 27 June 2025
- Published by JMIR Publications Inc. in JMIR Preprints
A SHAP-Based Deep Learning Framework for Low Birth Weight Prediction: Balancing, Explainable AI, and Individualized Risk Intervention (Preprint)
BACKGROUND Low birth weight (LBW), defined as less than 2,500 grams at birth, is a persistent public health issue associated with increased risks of neonatal mortality, long-term developmental challenges, and chronic diseases. Alabama consistently reports higher-than-average LBW rates, emphasizing the need for effective early prediction and intervention strategies. OBJECTIVE This study aimed to develop an explainable machine learning (ML) framework to predict LBW using large-scale predelivery data, address class imbalance with multiple data-balancing techniques, and generate personalized risk assessments and intervention strategies. METHODS We used 514,294 Alabama birth records from 2014 to 2022, with 165 pre-delivery features. Seven balancing techniques were applied: Random OverSampling, Random UnderSampling, SMOTE, ADASYN, Tomek Links, SMOTE-Tomek, and class weight adjustment. Seven ML models were evaluated: Logistic Regression (LR), K-Nearest Neighbors (k-NN), Random Forest (RF), AdaBoost, XGBoost, and Multilayer Perceptron (MLP). Bayesian hyperparameter optimization and stratified train-test splits were used. SHAP (Shapley Additive Explanations) provided global and individual feature importance, and counterfactual sensitivity analysis simulated risk interventions. RESULTS The MLP model with Random UnderSampling achieved the best performance (recall = 0.7779). Key predictors included prenatal visits, pregnancy weight gain, pre-pregnancy weight, and gestational hypertension. Socioeconomic and behavioral variables (e.g., smoking, education, marital status), along with racial disparities, also contributed significantly to LBW risk. Individual-level SHAP and counterfactual analysis demonstrated how modifiable risk factors could lower LBW probabilities. CONCLUSIONS This framework combines predictive accuracy, interpretability, and personalization, offering a valuable tool for early, equitable LBW risk identification and intervention.
- 27 June 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA SHAP-Based Deep Learning Framework for Low Birth Weight Prediction: Balancing, Explainable AI, and Individualized Risk Intervention (Preprint)
BACKGROUND Low birth weight (LBW), defined as less than 2,500 grams at birth, is a persistent public health issue associated with increased risks of neonatal mortality, long-term developmental challenges, and chronic diseases. Alabama consistently reports higher-than-average LBW rates, emphasizing the need for effective early prediction and intervention strategies. OBJECTIVE This study aimed to develop an explainable machine learning (ML) framework to predict LBW using large-scale predelivery data, address class imbalance with multiple data-balancing techniques, and generate personalized risk assessments and intervention strategies. METHODS We used 514,294 Alabama birth records from 2014 to 2022, with 165 pre-delivery features. Seven balancing techniques were applied: Random OverSampling, Random UnderSampling, SMOTE, ADASYN, Tomek Links, SMOTE-Tomek, and class weight adjustment. Seven ML models were evaluated: Logistic Regression (LR), K-Nearest Neighbors (k-NN), Random Forest (RF), AdaBoost, XGBoost, and Multilayer Perceptron (MLP). Bayesian hyperparameter optimization and stratified train-test splits were used. SHAP (Shapley Additive Explanations) provided global and individual feature importance, and counterfactual sensitivity analysis simulated risk interventions. RESULTS The MLP model with Random UnderSampling achieved the best performance (recall = 0.7779). Key predictors included prenatal visits, pregnancy weight gain, pre-pregnancy weight, and gestational hypertension. Socioeconomic and behavioral variables (e.g., smoking, education, marital status), along with racial disparities, also contributed significantly to LBW risk. Individual-level SHAP and counterfactual analysis demonstrated how modifiable risk factors could lower LBW probabilities. CONCLUSIONS This framework combines predictive accuracy, interpretability, and personalization, offering a valuable tool for early, equitable LBW risk identification and intervention.
- 25 June 2025
- Published by Elsevier in Public Health
- Vol. 246, 105838
Impact of COVID-19 on maternal health and birth outcomes: A network analysis in Alabama
- 25 June 2025
- Published by Elsevier in Public Health
- Vol. 246, 105838
Impact of COVID-19 on maternal health and birth outcomes: A network analysis in Alabama
- Top Cited PapersOpen Access
- 14 June 2024
- Published by MDPI AG in Education Sciences
- Vol. 14 (6) , 643
ChatGPT in Teaching and Learning: A Systematic Review
The increasing use of artificial intelligence (AI) in education has raised questions about the implications of ChatGPT for teaching and learning. A systematic literature review was conducted to answer these questions, analyzing 112 scholarly articles to identify the potential benefits and challenges related to ChatGPT use in educational settings. The selection process was thorough to ensure a comprehensive analysis of the current academic discourse on AI tools in education. Our research sheds light on the significant impact of ChatGPT on improving student engagement and accessibility and the critical issues that need to be considered, including concerns about the quality and bias of generated responses, the risk of plagiarism, and the authenticity of educational content. The study aims to summarize the utilizations of ChatGPT in teaching and learning by addressing the identified benefits and challenges through targeted strategies. The authors outlined some recommendations that will ensure that the integration of ChatGPT into educational frameworks enhances learning outcomes while safeguarding academic standards.
- 14 June 2024
- Published by MDPI AG in Education Sciences
- Vol. 14 (6) , 643
Top Cited PapersOpen AccessChatGPT in Teaching and Learning: A Systematic Review
The increasing use of artificial intelligence (AI) in education has raised questions about the implications of ChatGPT for teaching and learning. A systematic literature review was conducted to answer these questions, analyzing 112 scholarly articles to identify the potential benefits and challenges related to ChatGPT use in educational settings. The selection process was thorough to ensure a comprehensive analysis of the current academic discourse on AI tools in education. Our research sheds light on the significant impact of ChatGPT on improving student engagement and accessibility and the critical issues that need to be considered, including concerns about the quality and bias of generated responses, the risk of plagiarism, and the authenticity of educational content. The study aims to summarize the utilizations of ChatGPT in teaching and learning by addressing the identified benefits and challenges through targeted strategies. The authors outlined some recommendations that will ensure that the integration of ChatGPT into educational frameworks enhances learning outcomes while safeguarding academic standards.
- Open Access
- 8 June 2024
- Published by MDPI AG in Healthcare
- Vol. 12 (12) , 1165
Machine Learning Approach for Cardiovascular Death Prediction among Nonalcoholic Steatohepatitis (NASH) Liver Transplant Recipients
Cardiovascular disease is the leading cause of mortality among nonalcoholic steatohepatitis (NASH) patients who undergo liver transplants. In the present study, machine learning algorithms were used to identify important risk factors for cardiovascular death and to develop a prediction model. The Standard Transplant Analysis and Research data were gathered from the Organ Procurement and Transplantation Network. After cleaning and preprocessing, the dataset comprised 10,871 patients and 92 features. Recursive feature elimination (RFE) and select from model (SFM) were applied to select relevant features from the dataset and avoid overfitting. Multiple machine learning algorithms, including logistic regression, random forest, decision tree, and XGBoost, were used with RFE and SFM. Additionally, prediction models were developed using a support vector machine, Gaussian naïve Bayes, K-nearest neighbors, random forest, and XGBoost algorithms. Finally, SHapley Additive exPlanations (SHAP) were used to increase interpretability. The findings showed that the best feature selection method was RFE with a random forest estimator, and the most critical features were recipient and donor blood type, body mass index, recipient and donor state of residence, serum creatinine, and year of transplantation. Furthermore, among all the outcomes, the XGBoost model had the highest performance, with an accuracy value of 0.6909 and an area under the curve value of 0.86. The findings also revealed a predictive relationship between features and cardiovascular death after liver transplant among NASH patients. These insights may assist clinical decision-makers in devising strategies to prevent cardiovascular complications in post-liver transplant NASH patients.
- 8 June 2024
- Published by MDPI AG in Healthcare
- Vol. 12 (12) , 1165
Open AccessMachine Learning Approach for Cardiovascular Death Prediction among Nonalcoholic Steatohepatitis (NASH) Liver Transplant Recipients
Cardiovascular disease is the leading cause of mortality among nonalcoholic steatohepatitis (NASH) patients who undergo liver transplants. In the present study, machine learning algorithms were used to identify important risk factors for cardiovascular death and to develop a prediction model. The Standard Transplant Analysis and Research data were gathered from the Organ Procurement and Transplantation Network. After cleaning and preprocessing, the dataset comprised 10,871 patients and 92 features. Recursive feature elimination (RFE) and select from model (SFM) were applied to select relevant features from the dataset and avoid overfitting. Multiple machine learning algorithms, including logistic regression, random forest, decision tree, and XGBoost, were used with RFE and SFM. Additionally, prediction models were developed using a support vector machine, Gaussian naïve Bayes, K-nearest neighbors, random forest, and XGBoost algorithms. Finally, SHapley Additive exPlanations (SHAP) were used to increase interpretability. The findings showed that the best feature selection method was RFE with a random forest estimator, and the most critical features were recipient and donor blood type, body mass index, recipient and donor state of residence, serum creatinine, and year of transplantation. Furthermore, among all the outcomes, the XGBoost model had the highest performance, with an accuracy value of 0.6909 and an area under the curve value of 0.86. The findings also revealed a predictive relationship between features and cardiovascular death after liver transplant among NASH patients. These insights may assist clinical decision-makers in devising strategies to prevent cardiovascular complications in post-liver transplant NASH patients.
- 9 July 2023
- Published by Springer Nature
- p. 3-9
Evaluating a Hospital Smart Notification System in a Simulated Environment: The Method
- 9 July 2023
- Published by Springer Nature
- p. 3-9
Evaluating a Hospital Smart Notification System in a Simulated Environment: The Method
- Open Access
- 1 May 2023
- Published by Taylor & Francis in Journal of Multidisciplinary Healthcare
- Vol. ume 16, 1311-1326
The Cost of Frontline Nursing: Investigating Perception of Compensation Inadequacy During the COVID-19 Pandemic
Background: Nursing professionals experienced greater levels of stress and burnout during the COVID-19 pandemic. Studies examining stress and burnout have found a relationship between compensation and burnout. However, further studies are needed to examine the relationship between the mediating effects of supervisor and community support and coping strategies and the effects of burnout on compensation. Objective: The purpose of this study is to build on previous burnout research by examining the mediation effects of supervisor and community support and coping strategies on the relationship between sources of stress and burnout on feelings of compensation inadequacy, or the desire for more compensation. Methods: Using Qualtrics survey responses from 232 nurses, this study used correlation testing and mediation analyses of indirect, direct, and total effects to explore the relationships between critical factors influencing stress, burnout, nurses’ use of coping skills, and the perception of supervisor and community support on perceived compensation inadequacy. Results: This study found that the support domain has a significant and positive direct effect on compensation, with supervisor support increasing the desire for additional compensation. Support was also found to have a significant and positive indirect effect and a significant and positive total effect on the desire for additional compensation. This study’s results also found that coping strategies had a significant, direct positive effect on the desire for additional compensation. While problem solving and avoidance increased the desire for additional compensation, transference had no significant relationship. Conclusion: This study found evidence of the mediation effect of coping strategies on the relationship between burnout and compensation.
- 1 May 2023
- Published by Taylor & Francis in Journal of Multidisciplinary Healthcare
- Vol. ume 16, 1311-1326
Open AccessThe Cost of Frontline Nursing: Investigating Perception of Compensation Inadequacy During the COVID-19 Pandemic
Background: Nursing professionals experienced greater levels of stress and burnout during the COVID-19 pandemic. Studies examining stress and burnout have found a relationship between compensation and burnout. However, further studies are needed to examine the relationship between the mediating effects of supervisor and community support and coping strategies and the effects of burnout on compensation. Objective: The purpose of this study is to build on previous burnout research by examining the mediation effects of supervisor and community support and coping strategies on the relationship between sources of stress and burnout on feelings of compensation inadequacy, or the desire for more compensation. Methods: Using Qualtrics survey responses from 232 nurses, this study used correlation testing and mediation analyses of indirect, direct, and total effects to explore the relationships between critical factors influencing stress, burnout, nurses’ use of coping skills, and the perception of supervisor and community support on perceived compensation inadequacy. Results: This study found that the support domain has a significant and positive direct effect on compensation, with supervisor support increasing the desire for additional compensation. Support was also found to have a significant and positive indirect effect and a significant and positive total effect on the desire for additional compensation. This study’s results also found that coping strategies had a significant, direct positive effect on the desire for additional compensation. While problem solving and avoidance increased the desire for additional compensation, transference had no significant relationship. Conclusion: This study found evidence of the mediation effect of coping strategies on the relationship between burnout and compensation.
- Open Access
Listening to the Voice of the Hospitalized Child: Comparing Children’s Experiences to Their Parents
Background: Pediatric patients can provide feedback about their healthcare experiences. However, most do not and are instead represented by their parents. A widely accepted notion is that pediatric patients lack the capacity, vocabulary, and preferences needed to answer meaningful questions related to their healthcare. However, because the pediatric patients’ experience can differ from the perspective of their parents, the use of proxy reporting ultimately reduces the hospital’s ability to address the concerns of pediatric patients directly. Objectives: The overall goals of this survey study were (1) to identify the key domains whereby pediatric patient and parent preferences differ and (2) to investigate the extent to which pediatric patients perceive their healthcare experiences differently from their parents. Methods: This study employed an adult version, an older child version, and a younger child version of a 47-question survey instrument divided into seven key domains: experience with the admission process, interactions with nurses, interactions with doctors, care in the hospital, hospital environment, experience before discharge, and overall score. The instrument was developed to survey children (ages 4–17) recently discharged from the hospital and their parents or guardian. Results: The findings suggest pediatric patients reported interest in engaging with their doctors about their healthcare. However, pediatric patients younger than 13 years old reported having fewer pediatric doctors ask them about their healthcare, with the youngest group reporting the worst experiences. Moreover, differences in perceptions were identified between pediatric patients and their parents regarding hospital quality and performance. Pediatric patients reported less pain and higher satisfaction regarding the cleanliness of the room and their experience in the admission process than their parents. Patient and parent responses were significantly different within each of the seven domains. Conclusion: The results speak to the larger discussion of whether current hospital settings can engage with small children at the level necessary to capture meaningful feedback about their healthcare experience. By providing additional evidence to the contrary, this survey study brings further context to misconceptions regarding pediatric patients’ involvement as crucial actors in the patient-and-family-centered care model.
Open AccessListening to the Voice of the Hospitalized Child: Comparing Children’s Experiences to Their Parents
Background: Pediatric patients can provide feedback about their healthcare experiences. However, most do not and are instead represented by their parents. A widely accepted notion is that pediatric patients lack the capacity, vocabulary, and preferences needed to answer meaningful questions related to their healthcare. However, because the pediatric patients’ experience can differ from the perspective of their parents, the use of proxy reporting ultimately reduces the hospital’s ability to address the concerns of pediatric patients directly. Objectives: The overall goals of this survey study were (1) to identify the key domains whereby pediatric patient and parent preferences differ and (2) to investigate the extent to which pediatric patients perceive their healthcare experiences differently from their parents. Methods: This study employed an adult version, an older child version, and a younger child version of a 47-question survey instrument divided into seven key domains: experience with the admission process, interactions with nurses, interactions with doctors, care in the hospital, hospital environment, experience before discharge, and overall score. The instrument was developed to survey children (ages 4–17) recently discharged from the hospital and their parents or guardian. Results: The findings suggest pediatric patients reported interest in engaging with their doctors about their healthcare. However, pediatric patients younger than 13 years old reported having fewer pediatric doctors ask them about their healthcare, with the youngest group reporting the worst experiences. Moreover, differences in perceptions were identified between pediatric patients and their parents regarding hospital quality and performance. Pediatric patients reported less pain and higher satisfaction regarding the cleanliness of the room and their experience in the admission process than their parents. Patient and parent responses were significantly different within each of the seven domains. Conclusion: The results speak to the larger discussion of whether current hospital settings can engage with small children at the level necessary to capture meaningful feedback about their healthcare experience. By providing additional evidence to the contrary, this survey study brings further context to misconceptions regarding pediatric patients’ involvement as crucial actors in the patient-and-family-centered care model.