Benjamin D. Stern
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Benjamin D. Stern has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Eric J. Hegedus
Department of Rehabilitation Sciences, School of Medicine, Tufts University, Boston, MA, USA
3 shared publicationsYing-Cheng Lai
School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA
2 shared publications- Ying-Cheng Lai
School of Electrical, Computer and Energy Engineering, Arizona State University
2 shared publications - Zheng-Meng Zhai
School of Electrical, Computer and Energy Engineering, Arizona State University 1 , Tempe, Arizona 85287
2 shared publications Amnon Lahad
1 shared publication- Angela Spontelli Gisselman
Doctor of Physical Therapy Program, Department of Public Health and Community Medicine, School of Medicine, Tufts University, Phoenix, AZ, USA
1 shared publication
Latest Publications
- 17 September 2025
- Published by Wolters Kluwer Health in Journal of Physical Therapy Education
- Vol. 40 (2) , 204
AI-Powered Case-Based Approach for Real-World Experiences of Student Interaction and Assessment of Interview Skills
This EduGraphic showcases AI-Powered Case-Based Approach for Real-World Experience (AI-CARE) simulating physical therapy patient interviews and assessing student communication skills. It addresses role-playing limitations using AI virtual patients. The process includes extracting patient data, setting patient personalities, conducting interviews, and receiving automated feedback based on ECHOWS, a validated interviewing assessment tool. The case demonstrates how an AI patient engages students, highlights effective communication behaviors, and identifies improvement areas. This provides unlimited practice opportunities and immediate feedback in a safe environment. AI-CARE aligns with health education trends, supported by studies showing improved performance.
- 17 September 2025
- Published by Wolters Kluwer Health in Journal of Physical Therapy Education
- Vol. 40 (2) , 204
AI-Powered Case-Based Approach for Real-World Experiences of Student Interaction and Assessment of Interview Skills
This EduGraphic showcases AI-Powered Case-Based Approach for Real-World Experience (AI-CARE) simulating physical therapy patient interviews and assessing student communication skills. It addresses role-playing limitations using AI virtual patients. The process includes extracting patient data, setting patient personalities, conducting interviews, and receiving automated feedback based on ECHOWS, a validated interviewing assessment tool. The case demonstrates how an AI patient engages students, highlights effective communication behaviors, and identifies improvement areas. This provides unlimited practice opportunities and immediate feedback in a safe environment. AI-CARE aligns with health education trends, supported by studies showing improved performance.
- Open Access
- 28 August 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Bridging known and unknown dynamics by transformer-based machine-learning inference from sparse observations
In applications, an anticipated issue is where the system of interest has never been encountered before and sparse observations can be made only once. Can the dynamics be faithfully reconstructed? We address this challenge by developing a hybrid transformer and reservoir-computing scheme. The transformer is trained without using data from the target system, but with essentially unlimited synthetic data from known chaotic systems. The trained transformer is then tested with the sparse data from the target system, and its output is further fed into a reservoir computer for predicting its long-term dynamics or the attractor. The proposed hybrid machine-learning framework is tested using various prototypical nonlinear systems, demonstrating that the dynamics can be faithfully reconstructed from reasonably sparse data. The framework provides a paradigm of reconstructing complex and nonlinear dynamics in the situation where training data do not exist and the observations are random and sparse.
- 28 August 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-12
Open AccessBridging known and unknown dynamics by transformer-based machine-learning inference from sparse observations
In applications, an anticipated issue is where the system of interest has never been encountered before and sparse observations can be made only once. Can the dynamics be faithfully reconstructed? We address this challenge by developing a hybrid transformer and reservoir-computing scheme. The transformer is trained without using data from the target system, but with essentially unlimited synthetic data from known chaotic systems. The trained transformer is then tested with the sparse data from the target system, and its output is further fed into a reservoir computer for predicting its long-term dynamics or the attractor. The proposed hybrid machine-learning framework is tested using various prototypical nonlinear systems, demonstrating that the dynamics can be faithfully reconstructed from reasonably sparse data. The framework provides a paradigm of reconstructing complex and nonlinear dynamics in the situation where training data do not exist and the observations are random and sparse.
- Open Access
- 3 February 2025
- Published by Springer Nature in Research Square
Bridging Known and Unknown Dynamics: Machine Learning Inference From Sparse Observations
In applications, an anticipated issue is where the system of interest has never been encountered before and sparse observations can be made only once. Can the dynamics be faithfully reconstructed? We address this challenge by developing a hybrid transformer and reservoir-computing scheme. The transformer is trained without using data from the target system, but with essentially unlimited synthetic data from known chaotic systems. The trained transformer is then tested with the sparse data from the target system, and its output is further fed into a reservoir computer for predicting its long-term dynamics or the attractor. The power of the proposed hybrid machine-learning framework is demonstrated using various prototypical nonlinear systems, where the dynamics can be faithfully reconstructed even with 80% sparsity. The framework provides a paradigm of reconstructing complex and nonlinear dynamics in the extreme situation where training data do not exist and the observations are random and sparse.
- 3 February 2025
- Published by Springer Nature in Research Square
Open AccessBridging Known and Unknown Dynamics: Machine Learning Inference From Sparse Observations
In applications, an anticipated issue is where the system of interest has never been encountered before and sparse observations can be made only once. Can the dynamics be faithfully reconstructed? We address this challenge by developing a hybrid transformer and reservoir-computing scheme. The transformer is trained without using data from the target system, but with essentially unlimited synthetic data from known chaotic systems. The trained transformer is then tested with the sparse data from the target system, and its output is further fed into a reservoir computer for predicting its long-term dynamics or the attractor. The power of the proposed hybrid machine-learning framework is demonstrated using various prototypical nonlinear systems, where the dynamics can be faithfully reconstructed even with 80% sparsity. The framework provides a paradigm of reconstructing complex and nonlinear dynamics in the extreme situation where training data do not exist and the observations are random and sparse.
- 1 October 2024
- Published by Human Kinetics in International Journal of Sports Physiology and Performance
- Vol. 19 (10) , 1030-1040
Stress Drives Soccer Athletes’ Wellness and Movement: Using Convergent Cross-Mapping to Identify Causal Relationships in a Dynamic Environment
Purpose: Prediction of athlete wellness is difficult—or, many sports-medicine practitioners and scientists would argue, impossible. Instead, one settles for correlational relationships of variables gathered at fixed moments in time. The issue may be an inherent mismatch between usual methods of data collection and analysis and the complex nature of the variables governing athlete wellness. Variables such as external load, stress, muscle soreness, and sleep quality may affect each other and wellness in a dynamic, nonlinear, way over time. In such an environment, traditional data-collection methods and statistics will fail to capture causal effects. If we are to move this area of sport science forward, a different approach is required. Methods: We analyzed data from 2 different soccer teams that showed no significance between player load and wellness or among individual measures of wellness. Our analysis used methods of attractor reconstruction to examine possible causal relationships between GPS/accelerometer-measured external training load and wellness variables. Results: Our analysis showed that player self-rated stress, a component of wellness, seems a fundamental driving variable. The influence of stress is so great that stress can predict other components of athlete wellness, and, in turn, self-rated stress can be predicted by observing a player’s load data. Conclusion: We demonstrate the ability of nonlinear methods to identify interactions between and among variables to predict future athlete stress. These relationships are indicative of the causal relationships playing out in athlete wellness over the course of a soccer season.
- 1 October 2024
- Published by Human Kinetics in International Journal of Sports Physiology and Performance
- Vol. 19 (10) , 1030-1040
Stress Drives Soccer Athletes’ Wellness and Movement: Using Convergent Cross-Mapping to Identify Causal Relationships in a Dynamic Environment
Purpose: Prediction of athlete wellness is difficult—or, many sports-medicine practitioners and scientists would argue, impossible. Instead, one settles for correlational relationships of variables gathered at fixed moments in time. The issue may be an inherent mismatch between usual methods of data collection and analysis and the complex nature of the variables governing athlete wellness. Variables such as external load, stress, muscle soreness, and sleep quality may affect each other and wellness in a dynamic, nonlinear, way over time. In such an environment, traditional data-collection methods and statistics will fail to capture causal effects. If we are to move this area of sport science forward, a different approach is required. Methods: We analyzed data from 2 different soccer teams that showed no significance between player load and wellness or among individual measures of wellness. Our analysis used methods of attractor reconstruction to examine possible causal relationships between GPS/accelerometer-measured external training load and wellness variables. Results: Our analysis showed that player self-rated stress, a component of wellness, seems a fundamental driving variable. The influence of stress is so great that stress can predict other components of athlete wellness, and, in turn, self-rated stress can be predicted by observing a player’s load data. Conclusion: We demonstrate the ability of nonlinear methods to identify interactions between and among variables to predict future athlete stress. These relationships are indicative of the causal relationships playing out in athlete wellness over the course of a soccer season.
- 4 January 2023
- Published by Springer Nature in Sports Medicine
- Vol. 53 (6) , 1117-1124
How Advancement in Bone Science Should Inform the Examination and Treatment of Femoral Shaft Bone Stress Injuries in Running Athletes
Stress fractures likely have a 1–2% incidence in athletes in general. In runners, a more vulnerable population, incidence rates likely range between 3.2 and 21% with female runners having greater susceptibility. The incidence of femoral shaft stress fractures is less well known. New basic and translational science research may impact the way clinicians diagnose and treat femoral stress fractures. By using a fictitious case study, this paper applies bone science to suggest new approaches to evaluating and treating femoral shaft stress fractures in the running population.
- 4 January 2023
- Published by Springer Nature in Sports Medicine
- Vol. 53 (6) , 1117-1124
How Advancement in Bone Science Should Inform the Examination and Treatment of Femoral Shaft Bone Stress Injuries in Running Athletes
Stress fractures likely have a 1–2% incidence in athletes in general. In runners, a more vulnerable population, incidence rates likely range between 3.2 and 21% with female runners having greater susceptibility. The incidence of femoral shaft stress fractures is less well known. New basic and translational science research may impact the way clinicians diagnose and treat femoral stress fractures. By using a fictitious case study, this paper applies bone science to suggest new approaches to evaluating and treating femoral shaft stress fractures in the running population.
- 1 May 2021
- Published by Elsevier in Physical Therapy in Sport
- Vol. 49, 8-14
State dependence: Does a prior injury predict a future injury?
- 1 May 2021
- Published by Elsevier in Physical Therapy in Sport
- Vol. 49, 8-14
State dependence: Does a prior injury predict a future injury?
- 1 January 2020
- Published by Elsevier in Physical Therapy in Sport
- Vol. 41, 43-48
Injury prediction as a non-linear system
- 1 January 2020
- Published by Elsevier in Physical Therapy in Sport
- Vol. 41, 43-48
Injury prediction as a non-linear system
- 1 February 2007
- Published by Wolters Kluwer Health in Spine
- Vol. 32 (4) , 471-480
Variation in Reported Safety of Lumbar Interbody Fusion
Systematic review. To quantify variability in undesirable outcomes among studies of lumbar interbody fusion using stand-alone cage devices, and to determine whether author conflicts of interest contribute to variability. Promising early studies of lumbar fusion with stand-alone cage devices led to rapid uptake of the technique, but some surgeons later expressed reservations regarding efficacy and safety. We systematically identified studies of lumbar interbody fusion with stand-alone cage devices that reported at least one undesirable outcome among 10 or more adult subjects. We performed meta-analyses of rates of 7 prespecified outcomes (nonunion, reoperation, major vessel injury, retrograde ejaculation, neurologic injury, dural injury, and infection). Heterogeneity in outcome rates was quantified as I2 (the proportion of variance due to differences among studies rather than random variation). Random-effects meta-regression identified sources of observed heterogeneity, including potential conflicts of interest. We identified 30 eligible studies, including a total of 3228 subjects. A potential conflict of interest was identified in 18 (60%). We observed marked heterogeneity in rates of nonunion, reoperation, and neurologic injury (I2 > 85%; P < 0.001), and substantial heterogeneity in rates of dural injury (I2 = 63%; P < 0.01) and major vessel injury (I2 = 38%; P = 0.09). Among 24 studies reporting fusion status after 6 months of follow-up, nonunion rates ranged from 2.3% to 83.3% (median, 8.3%) and exceeded 45% in 4 studies. Potential author conflict of interest was associated with significantly lower rates of nonunion (P = 0.001). Heterogeneity in rates of other undesirable outcomes was not significantly associated with author conflicts of interest or other study characteristics. We quantified substantial unexplained variation in reported complication rates of undesirable outcomes of lumbar interbody fusion with stand-alone cage devices. Authors with potential conflicts of interest, however, reported significantly lower rates of nonunion.
- 1 February 2007
- Published by Wolters Kluwer Health in Spine
- Vol. 32 (4) , 471-480
Variation in Reported Safety of Lumbar Interbody Fusion
Systematic review. To quantify variability in undesirable outcomes among studies of lumbar interbody fusion using stand-alone cage devices, and to determine whether author conflicts of interest contribute to variability. Promising early studies of lumbar fusion with stand-alone cage devices led to rapid uptake of the technique, but some surgeons later expressed reservations regarding efficacy and safety. We systematically identified studies of lumbar interbody fusion with stand-alone cage devices that reported at least one undesirable outcome among 10 or more adult subjects. We performed meta-analyses of rates of 7 prespecified outcomes (nonunion, reoperation, major vessel injury, retrograde ejaculation, neurologic injury, dural injury, and infection). Heterogeneity in outcome rates was quantified as I2 (the proportion of variance due to differences among studies rather than random variation). Random-effects meta-regression identified sources of observed heterogeneity, including potential conflicts of interest. We identified 30 eligible studies, including a total of 3228 subjects. A potential conflict of interest was identified in 18 (60%). We observed marked heterogeneity in rates of nonunion, reoperation, and neurologic injury (I2 > 85%; P < 0.001), and substantial heterogeneity in rates of dural injury (I2 = 63%; P < 0.01) and major vessel injury (I2 = 38%; P = 0.09). Among 24 studies reporting fusion status after 6 months of follow-up, nonunion rates ranged from 2.3% to 83.3% (median, 8.3%) and exceeded 45% in 4 studies. Potential author conflict of interest was associated with significantly lower rates of nonunion (P = 0.001). Heterogeneity in rates of other undesirable outcomes was not significantly associated with author conflicts of interest or other study characteristics. We quantified substantial unexplained variation in reported complication rates of undesirable outcomes of lumbar interbody fusion with stand-alone cage devices. Authors with potential conflicts of interest, however, reported significantly lower rates of nonunion.