Search for: All records

Problem: Given the United States’ urgency for systemic-level improvements to care, advancing systems-based practice (SBP) competency among future physicians is crucial. However, SBP education is inadequate, lacks a unifying framework and faculty confidence in its teaching, and is taught late in the medical education journey. Approach: The Oklahoma State University Center for Health Systems Innovation (CHSI) created an SBP program relying on Lean Health Care for a framework and targeted medical students before their second year began. Lean curricula were developed (lecture and simulation) and a partnership with a hospital was secured for work-based practice. The CHSI developed a skills assessment tool for preliminary evaluation of the program. In June 2022, 9 undergraduate medical students responded to a Lean Health Care Internship (LHCI) presentation. Outcomes: Student SBP skills increased after training and again after work-based practice. All 9 students reported that their conceptualization of problems in health care changed “extraordinarily,” and they were “extraordinarily” confident in their ability to approach another health care problem by applying the Lean method. The LHCI fostered an awareness of physicians as interdependent systems citizens, a key goal of SBP competency. After the internship concluded, the Lean team recommendations generated a resident-led quality assurance performance improvement initiative for bed throughput. Next Steps: The LHCI was effective in engaging students and building SBP skills among undergraduate medical education students. The levels of student enthusiasm and skill acquisition exceeded the Lean trainers’ expectations. The researchers will continue to measure LHCI’s effect on students’ rotation experiences to better evaluate the long-term benefit of introducing SBP concepts earlier in medical education. The program’s success has spurred enthusiasm for continued collaboration with hospital and residency programs. Program administrators are exploring how to broaden access. 

This paper presents an attention-based, deep learning framework that converts robot camera frames with dynamic content into static frames to more easily apply simultaneous localization and mapping (SLAM) algorithms. The vast majority of SLAM methods have difficulty in the presence of dynamic objects appearing in the environment and occluding the area being captured by the camera. Despite past attempts to deal with dynamic objects, challenges remain to reconstruct large, occluded areas with complex backgrounds. Our proposed Dynamic-GAN framework employs a generative adversarial network to remove dynamic objects from a scene and inpaint a static image free of dynamic objects. The Dynamic-GAN framework utilizes spatial-temporal transformers, and a novel spatial-temporal loss function. The evaluation of Dynamic-GAN was comprehensively conducted both quantitatively and qualitatively by testing it on benchmark datasets, and on a mobile robot in indoor navigation environments. As people appeared dynamically in close proximity to the robot, results showed that large, feature-rich occluded areas can be accurately reconstructed with our attention-based deep learning framework for dynamic object removal. Through experiments we demonstrate that our proposed algorithm has up to 25% better performance on average as compared to the standard benchmark algorithms. 

Despite advances in deep learning methods for song recommendation, most existing methods do not take advantage of the sequential nature of song content. In addition, there is a lack of methods that can explain their predictions using the content of recommended songs and only a few approaches can handle the item cold start problem. In this work, we propose a hybrid deep learning model that uses collaborative filtering (CF) and deep learning sequence models on the Musical Instrument Digital Interface (MIDI) content of songs to provide accurate recommendations, while also being able to generate a relevant, personalized explanation for each recommended song. Compared to state-of-the-art methods, our validation experiments showed that in addition to generating explainable recommendations, our model stood out among the top performers in terms of recommendation accuracy and the ability to handle the item cold start problem. Moreover, validation shows that our personalized explanations capture properties that are in accordance with the user’s preferences.