Multiscale modeling meets machine learning: What can we learn?

Machine learning is increasingly recognized as a promising technology in the biological, biomedical, and behavioral sciences. There can be no argument that this technique is incredibly successful in image recognition with immediate applications in diagnostics including electrophysiology, radiology, or pathology, where we have access to massive amounts of annotated data. However, machine learning often performs poorly in prognosis, especially when dealing with sparse data. This is a field where classical physics-based simulation seems to remain irreplaceable. In this review, we identify areas in the biomedical sciences where machine learning and multiscale modeling can mutually benefit from one another: Machine learning can integrate physics-based knowledge in the form of governing equations, boundary conditions, or constraints to manage ill-posted problems and robustly handle sparse and noisy data; multiscale modeling can integrate machine learning to create surrogate models, identify system dynamics and parameters, analyze sensitivities, and quantify uncertainty to bridge the scales and understand the emergence of function. With a view towards applications in the life sciences, we discuss the state of the art of combining machine learning and multiscale modeling, identify applications and opportunities, raise open questions, and address potential challenges and limitations. We anticipate that it will stimulate discussion within the community of computational mechanics and reach out to other disciplines including mathematics, statistics, computer science, artificial intelligence, biomedicine, systems biology, and precision medicine to join forces towards creating robust and efficient models for biological systems.

NIH BRAIN Circuits Programs: An Experiment in Supporting Team Neuroscience.

The NIH BRAIN Initiative is aimed at revolutionizing our understanding of the human brain. Here, we present a discussion of support for team research in investigative neuroscience at different stages and on various scales.

Credible practice of modeling and simulation in healthcare: ten rules from a multidisciplinary perspective.

The complexities of modern biomedicine are rapidly increasing. Thus, modeling and simulation have become increasingly important as a strategy to understand and predict the trajectory of pathophysiology, disease genesis, and disease spread in support of clinical and policy decisions. In such cases, inappropriate or ill-placed trust in the model and simulation outcomes may result in negative outcomes, and hence illustrate the need to formalize the execution and communication of modeling and simulation practices. Although verification and validation have been generally accepted as significant components of a model's credibility, they cannot be assumed to equate to a holistic credible practice, which includes activities that can impact comprehension and in-depth examination inherent in the development and reuse of the models. For the past several years, the Committee on Credible Practice of Modeling and Simulation in Healthcare, an interdisciplinary group seeded from a U.S. interagency initiative, has worked to codify best practices. Here, we provide Ten Rules for credible practice of modeling and simulation in healthcare developed from a comparative analysis by the Committee's multidisciplinary membership, followed by a large stakeholder community survey. These rules establish a unified conceptual framework for modeling and simulation design, implementation, evaluation, dissemination and usage across the modeling and simulation life-cycle. While biomedical science and clinical care domains have somewhat different requirements and expectations for credible practice, our study converged on rules that would be useful across a broad swath of model types. In brief, the rules are: (1) Define context clearly. (2) Use contextually appropriate data. (3) Evaluate within context. (4) List limitations explicitly. (5) Use version control. (6) Document appropriately. (7) Disseminate broadly. (8) Get independent reviews. (9) Test competing implementations. (10) Conform to standards. Although some of these are common sense guidelines, we have found that many are often missed or misconstrued, even by seasoned practitioners. Computational models are already widely used in basic science to generate new biomedical knowledge. As they penetrate clinical care and healthcare policy, contributing to personalized and precision medicine, clinical safety will require established guidelines for the credible practice of modeling and simulation in healthcare.

Advanced technologies for intuitive control and sensation of prosthetics.

The Department of Defense, Department of Veterans Affairs and National Institutes of Health have invested significantly in advancing prosthetic technologies over the past 25 years, with the overall intent to improve the function, participation and quality of life of Service Members, Veterans, and all United States Citizens living with limb loss. These investments have contributed to substantial advancements in the control and sensory perception of prosthetic devices over the past decade. While control of motorized prosthetic devices through the use of electromyography has been widely available since the 1980s, this technology is not intuitive. Additionally, these systems do not provide stimulation for sensory perception. Recent research has made significant advancement not only in the intuitive use of electromyography for control but also in the ability to provide relevant meaningful perceptions through various stimulation approaches. While much of this previous work has traditionally focused on those with upper extremity amputation, new developments include advanced bidirectional neuroprostheses that are applicable to both the upper and lower limb amputation. The goal of this review is to examine the state-of-the-science in the areas of intuitive control and sensation of prosthetic devices and to discuss areas of exploration for the future. Current research and development efforts in external systems, implanted systems, surgical approaches, and regenerative approaches will be explored.

The State of the NIH BRAIN Initiative.

The BRAIN Initiative arose from a grand challenge to "accelerate the development and application of new technologies that will enable researchers to produce dynamic pictures of the brain that show how individual brain cells and complex neural circuits interact at the speed of thought." The BRAIN Initiative is a public-private effort focused on the development and use of powerful tools for acquiring fundamental insights about how information processing occurs in the central nervous system (CNS). As the Initiative enters its fifth year, NIH has supported >500 principal investigators, who have answered the Initiative's challenge via hundreds of publications describing novel tools, methods, and discoveries that address the Initiative's seven scientific priorities. We describe scientific advances produced by individual laboratories, multi-investigator teams, and entire consortia that, over the coming decades, will produce more comprehensive and dynamic maps of the brain, deepen our understanding of how circuit activity can produce a rich tapestry of behaviors, and lay the foundation for understanding how its circuitry is disrupted in brain disorders. Much more work remains to bring this vision to fruition, and the National Institutes of Health continues to look to the diverse scientific community, from mathematics, to physics, chemistry, engineering, neuroethics, and neuroscience, to ensure that the greatest scientific benefit arises from this unique research Initiative.

Simulation Research in Gastrointestinal and Urologic Care-Challenges and Opportunities: Summary of a National Institute of Diabetes and Digestive and Kidney Diseases and National Institute of Biomedical Imaging and Bioengineering Workshop.

: A workshop on "Simulation Research in Gastrointestinal and Urologic Care: Challenges and Opportunities" was held at the National Institutes of Health in June 2016. The purpose of the workshop was to examine the extent to which simulation approaches have been used by skilled proceduralists (not trainees) caring for patients with gastrointestinal and urologic diseases. The current status of research findings in the use and effectiveness of simulation applications was reviewed, and numerous knowledge gaps and research needs were identified by the faculty and the attendees. The paradigm of "deliberate practice," rather than mere repetition, and the value of coaching by experts was stressed by those who have adopted simulation in music and sports. Models that are most useful for the adoption of simulation by expert clinicians have yet to be fully validated. Initial studies on the impact of simulation on safety and error reduction have demonstrated its value in the training domain, but the role of simulation as a strategy for increased procedural safety remains uncertain in the world of the expert practitioner. Although the basic requirements for experienced physicians to acquire new skills have been explored, the widespread availability of such resources is an unrealized goal, and there is a need for well-designed outcome studies to establish the role of simulation in improving the quality of health care.

Perspectives on Sharing Models and Related Resources in Computational Biomechanics Research.

The role of computational modeling for biomechanics research and related clinical care will be increasingly prominent. The biomechanics community has been developing computational models routinely for exploration of the mechanics and mechanobiology of diverse biological structures. As a result, a large array of models, data, and discipline-specific simulation software has emerged to support endeavors in computational biomechanics. Sharing computational models and related data and simulation software has first become a utilitarian interest, and now, it is a necessity. Exchange of models, in support of knowledge exchange provided by scholarly publishing, has important implications. Specifically, model sharing can facilitate assessment of reproducibility in computational biomechanics and can provide an opportunity for repurposing and reuse, and a venue for medical training. The community's desire to investigate biological and biomechanical phenomena crossing multiple systems, scales, and physical domains, also motivates sharing of modeling resources as blending of models developed by domain experts will be a required step for comprehensive simulation studies as well as the enhancement of their rigor and reproducibility. The goal of this paper is to understand current perspectives in the biomechanics community for the sharing of computational models and related resources. Opinions on opportunities, challenges, and pathways to model sharing, particularly as part of the scholarly publishing workflow, were sought. A group of journal editors and a handful of investigators active in computational biomechanics were approached to collect short opinion pieces as a part of a larger effort of the IEEE EMBS Computational Biology and the Physiome Technical Committee to address model reproducibility through publications. A synthesis of these opinion pieces indicates that the community recognizes the necessity and usefulness of model sharing. There is a strong will to facilitate model sharing, and there are corresponding initiatives by the scientific journals. Outside the publishing enterprise, infrastructure to facilitate model sharing in biomechanics exists, and simulation software developers are interested in accommodating the community's needs for sharing of modeling resources. Encouragement for the use of standardized markups, concerns related to quality assurance, acknowledgement of increased burden, and importance of stewardship of resources are noted. In the short-term, it is advisable that the community builds upon recent strategies and experiments with new pathways for continued demonstration of model sharing, its promotion, and its utility. Nonetheless, the need for a long-term strategy to unify approaches in sharing computational models and related resources is acknowledged. Development of a sustainable platform supported by a culture of open model sharing will likely evolve through continued and inclusive discussions bringing all stakeholders at the table, e.g., by possibly establishing a consortium.

Simulation Research in Gastrointestinal and Urologic Care-Challenges and Opportunities: Summary of a National Institute of Diabetes and Digestive and Kidney Diseases and National Institute of Biomedical Imaging and Bioengineering Workshop.

A workshop on ''Simulation Research in Gastrointestinal and Urologic Care: Challenges and Opportunities'' was held at the National Institutes of Health in June 2016. The purpose of the workshop was to examine the extent to which simulation approaches have been used by skilled proceduralists (not trainees) caring for patients with gastrointestinal and urologic diseases. The current status of research findings in the use and effectiveness of simulation applications was reviewed, and numerous knowledge gaps and research needs were identified by the faculty and the attendees. The paradigm of ''deliberate practice,'' rather than mere repetition, and the value of coaching by experts was stressed by those who have adopted simulation in music and sports. Models that are most useful for the adoption of simulation by expert clinicians have yet to be fully validated. Initial studies on the impact of simulation on safety and error reduction have demonstrated its value in the training domain, but the role of simulation as a strategy for increased procedural safety remains uncertain in the world of the expert practitioner. Although the basic requirements for experienced physicians to acquire new skills have been explored, the widespread availability of such resources is an unrealized goal, and there is a need for well-designed outcome studies to establish the role of simulation in improving the quality of health care.

National Institutes of Health Research Plan on Rehabilitation: NIH Medical Rehabilitation Coordinating Committee.

One in five Americans experiences disability that affects their daily function because of impairments in mobility, cognitive function, sensory impairment, or communication impairment. The need for rehabilitation strategies to optimize function and reduce disability is a clear priority for research to address this public health challenge. The National Institutes of Health (NIH) recently published a Research Plan on Rehabilitation that provides a set of priorities to guide the field over the next 5 years. The plan was developed with input from multiple Institutes and Centers within the NIH, the National Advisory Board for Medical Rehabilitation Research, and the public. This article provides an overview of the need for this research plan, an outline of its development, and a listing of six priority areas for research. The NIH is committed to working with all stakeholder communities engaged in rehabilitation research to track progress made on these priorities and to work to advance the science of medical rehabilitation.This article is being published almost simultaneously in the following six journals: American Journal of Occupational Therapy, American Journal of Physical Medicine and Rehabilitation, Archives of Physical Medicine and Rehabilitation, Neurorehabilitation and Neural Repair, Physical Therapy, and Rehabilitation Psychology. Citation information is as follows: NIH Medical Rehabilitation Coordinating Committee. Am J Phys Med Rehabil. 2017;97(4):404-407.

Epidural Spinal Stimulation to Improve Bladder, Bowel, and Sexual Function in Individuals With Spinal Cord Injuries: A Framework for Clinical Research.

While some recent studies that apply epidural spinal cord stimulation (SCS) have demonstrated a breakthrough in improvement of the health and quality of the life of persons with spinal cord injury (SCI), the numbers of people who have received SCS are small. This is in sharp contrast to the thousands of persons worldwide living with SCI who have no practical recourse or hope of recovery of lost functions. Thus, the vision is to understand the full potential of this new intervention and to determine if it is safe and effective in a larger cohort, and if it is scalable so that it can be made available to all those who might benefit. To achieve this vision, the National Institute of Biomedical Imaging and Bioengineering called for and organized a consortium of multiple stakeholder groups: foundations addressing paralysis, federal and public agencies, industrial partners, academicians, and researchers, all interested in the same goal. Based on input from consortium participants, we have reasoned that a first step is to define a scalable SCS approach that is effective in restoring lost autonomic physiology, specifically bladder, bowel, and sexual function. These functions are most critical for improving the quality of life of persons living with SCI. This report outlines a framework for conducting the research needed to define such an effective SCS procedure that might seek Food and Drug Administration approval and be implemented at the population level.

Moving Toward Model Reproducibility and Reusability.

This paper provides a brief history of the U.S. funding initiatives associated with promoting multiscale modeling of the physiome since 2003. An effort led in the United States is the Interagency Modeling and Analysis Group (IMAG) Multiscale Modeling (MSM) Consortium. Though IMAG and the MSM Consortium have generated much interest in developing MSM models of the physiome, challenges associated with model and data sharing in biomedical, biological, and behavioral systems still exist. Since 2013, the IEEE EMBS Technical Committee on Computational Biology and the Physiome (CBaP TC) has supported discussions on promoting model reproducibility through publications. This special issue on model sharing and reproducibility is a realization of the CBaP TC discussions. Though open questions remain on how we can further facilitate model reproducibility, accessibility, and reuse by the worldwide community for different biomedical domain applications, this special issue provides a unique demonstration of both the challenges and opportunities for publishing reproducible computational models.

Grand challenges in interfacing engineering with life sciences and medicine.

This paper summarizes the discussions held during the First IEEE Life Sciences Grand Challenges Conference, held on October 4-5, 2012, at the National Academy of Sciences, Washington, DC, and the grand challenges identified by the conference participants. Despite tremendous efforts to develop the knowledge and ability that are essential in addressing biomedical and health problems using engineering methodologies, the optimization of this approach toward engineering the life sciences and healthcare remains a grand challenge. The conference was aimed at high-level discussions by participants representing various sectors, including academia, government, and industry. Grand challenges were identified by the conference participants in five areas including engineering the brain and nervous system; engineering the cardiovascular system; engineering of cancer diagnostics, therapeutics, and prevention; translation of discoveries to clinical applications; and education and training. A number of these challenges are identified and summarized in this paper.

Telehealth innovations in health education and training.

Telehealth applications are increasingly important in many areas of health education and training. In addition, they will play a vital role in biomedical research and research training by facilitating remote collaborations and providing access to expensive/remote instrumentation. In order to fulfill their true potential to leverage education, training, and research activities, innovations in telehealth applications should be fostered across a range of technology fronts, including online, on-demand computational models for simulation; simplified interfaces for software and hardware; software frameworks for simulations; portable telepresence systems; artificial intelligence applications to be applied when simulated human patients are not options; and the development of more simulator applications. This article presents the results of discussion on potential areas of future development, barries to overcome, and suggestions to translate the promise of telehealth applications into a transformed environment of training, education, and research in the health sciences.

Gaze position corrective eye movements in normal subjects and in patients with vestibular deficits.

Eye movements in response to high-acceleration head rotations (thrusts) in the horizontal plane from patients with unilateral (UVD) or bilateral vestibular loss (BVD) were recorded. The rapid, gaze-position corrections (GPCs) that appeared when vestibulo-ocular reflex (VOR) slow phases were undercompensatory were characterized. For comparison, eye movements from normal subjects who were asked to generate saccades in the direction opposite head rotation (in the same direction as slow phases) were recorded. This normal-subject model produced responses with spatial and temporal characteristics similar to those from GPCs in patients as follows: When head rotations were generated actively, compared with passively, gaze-position errors and corresponding GPCs were smaller and occurred earlier. During passively generated head thrusts, GPCs still occurred when head rotations were made in total darkness, though their accuracy decreased as the requirement for maintaining gaze on a specific location in space was relaxed. Time of onset of GPCs was not rigidly tied to head kinematics (peak velocity or peak acceleration). Speeds of GPCs, however, were lower than speeds of similar-sized, head-fixed saccades. Finally, during passive and active head thrusts in patients, sustained, high-frequency (20 to 30 Hz) oscillations that appeared as tiny saccades were occasionally observed, one immediately following the other, resembling a compensatory slow-phase response. Taken together, the results suggest that one strategy for overcoming a VOR deficit is to enlist the saccadic system to produce an oculomotor response that is required to compensate for head rotation. This response may come in the form of high-velocity GPCs or smaller-amplitude oscillations.