More Like this

1. In Search of a Feedback Signal for Closed-Loop Deep Brain Stimulation: Stimulation of the Subthalamic Nucleus Reveals Altered Glutamate Dynamics in the Globus Pallidus in Anesthetized, 6-Hydroxydopamine-Treated Rats

   https://doi.org/10.3390/bios13040480  

   Chernov, Mykyta M. ; Swan, Christina B. ; Leiter, James C. ( April 2023 , Biosensors)

   Deep Brain Stimulation (DBS) of the subthalamic nucleus (STN) is a surgical procedure for alleviating motor symptoms of Parkinson’s Disease (PD). The pattern of DBS (e.g., the electrode pairs used and the intensity of stimulation) is usually optimized by trial and error based on a subjective evaluation of motor function. We tested the hypotheses that DBS releases glutamate in selected basal ganglia nuclei and that the creation of 6-hydroxydopamine (6-OHDA)-induced nigrostriatal lesions alters glutamate release during DBS in those basal ganglia nuclei. We studied the relationship between a pseudo-random binary sequence of DBS and glutamate levels in the STN itself or in the globus pallidus (GP) in anesthetized, control, and 6-OHDA-treated rats. We characterized the stimulus–response relationships between DBS and glutamate levels using a transfer function estimated using System Identification. Stimulation of the STN elevated glutamate levels in the GP and in the STN. Although the 6-OHDA treatment did not affect glutamate dynamics in the STN during DBS in the STN, the transfer function between DBS in the STN and glutamate levels in the GP was significantly altered by the presence or absence of 6-OHDA-induced lesions. Thus, glutamate responses in the GP in the 6-OHDA-treated animals (but not in themore »STN) depended on dopaminergic inputs. For this reason, measuring glutamate levels in the GP may provide a useful feedback target in a closed-loop DBS device in patients with PD since the dynamics of glutamate release in the GP during DBS seem to reflect the loss of dopaminergic neurons in the SNc.« less
2. Robotics and AI for Teleoperation, Tele-Assessment, and Tele-Training for Surgery in the Era of COVID-19: Existing Challenges, and Future Vision

   https://doi.org/10.3389/frobt.2021.610677  

   Feizi, Navid ; Tavakoli, Mahdi ; Patel, Rajni V. ; Atashzar, S. Farokh ( April 2021 , Frontiers in Robotics and AI)

   The unprecedented shock caused by the COVID-19 pandemic has severely influenced the delivery of regular healthcare services. Most non-urgent medical activities, including elective surgeries, have been paused to mitigate the risk of infection and to dedicate medical resources to managing the pandemic. In this regard, not only surgeries are substantially influenced, but also pre- and post-operative assessment of patients and training for surgical procedures have been significantly impacted due to the pandemic. Many countries are planning a phased reopening, which includes the resumption of some surgical procedures. However, it is not clear how the reopening safe-practice guidelines will impact the quality of healthcare delivery. This perspective article evaluates the use of robotics and AI in 1) robotics-assisted surgery, 2) tele-examination of patients for pre- and post-surgery, and 3) tele-training for surgical procedures. Surgeons interact with a large number of staff and patients on a daily basis. Thus, the risk of infection transmission between them raises concerns. In addition, pre- and post-operative assessment also raises concerns about increasing the risk of disease transmission, in particular, since many patients may have other underlying conditions, which can increase their chances of mortality due to the virus. The pandemic has also limited the timemore »and access that trainee surgeons have for training in the OR and/or in the presence of an expert. In this article, we describe existing challenges and possible solutions and suggest future research directions that may be relevant for robotics and AI in addressing the three tasks mentioned above.« less
3. Pain and Laboratory Animals: Publication Practices for Better Data Reproducibility and Better Animal Welfare

   https://doi.org/10.1371/journal. pone.0155001  

   Larry Carbone, Jamie Austin ( May 2016 , PloS one)

   Scientists who perform major survival surgery on laboratory animals face a dual welfare and methodological challenge: how to choose surgical anesthetics and post-operative analgesics that will best control animal suffering, knowing that both pain and the drugs that manage pain can all affect research outcomes. Scientists who publish full descriptions of animal procedures allow critical and systematic reviews of data, demonstrate their adherence to animal welfare norms, and guide other scientists on how to conduct their own studies in the field. We investigated what information on animal pain management a reasonably diligent scientist might find in planning for a successful experiment. To explore how scientists in a range of fields describe their management of this ethical and methodological concern, we scored 400 scientific articles that included major animal survival surgeries as part of their experimental methods, for the completeness of information on anesthesia and analgesia. The 400 articles (250 accepted for publication pre-2011, and 150 in 2014–15, along with 174 articles they reference) included thoracotomies, craniotomies, gonadectomies, organ transplants, peripheral nerve injuries, spinal laminectomies and orthopedic procedures in dogs, primates, swine, mice, rats and other rodents. We scored articles for Publication Completeness (PC), which was any mention of use ofmore »anesthetics or analgesics; Analgesia Use (AU) which was any use of post-surgical analgesics, and Analgesia Completeness (a composite score comprising intra-operative analgesia, extended post-surgical analgesia, and use of multimodal analgesia). 338 of 400 articles were PC. 98 of these 338 were AU, with some mention of analgesia, while 240 of 338 mentioned anesthesia only but not postsurgical analgesia. Journals’ caliber, as measured by their 2013 Impact Factor, had no effect on PC or AU. We found no effect of whether a journal instructs authors to consult the ARRIVE publishing guidelines published in 2010 on PC or AC for the 150 mouse and rat articles in our 2014–15 dataset. None of the 302 articles that were silent about analgesic use included an explicit statement that analgesics were withheld, or a discussion of how pain management or untreated pain might affect results. We conclude that current scientific literature cannot be trusted to present full detail on use of animal anesthetics and analgesics. We report that publication guidelines focus more on other potential sources of bias in experimental results, under-appreciate the potential for pain and pain drugs to skew data, PLOS ONE | DOI:10.1371/journal.pone.0155001 May 12, 2016 1 / 24 a11111 OPEN ACCESS Citation: Carbone L, Austin J (2016) Pain and Laboratory Animals: Publication Practices for Better Data Reproducibility and Better Animal Welfare. PLoS ONE 11(5): e0155001. doi:10.1371/journal. pone.0155001 Editor: Chang-Qing Gao, Central South University, CHINA Received: December 29, 2015 Accepted: April 22, 2016 Published: May 12, 2016 Copyright: © 2016 Carbone, Austin. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: All relevant data are within the paper and its Supporting Information files. Authors may be contacted for further information. Funding: This study was funded by the United States National Science Foundation Division of Social and Economic Sciences. Award #1455838. The funder had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Competing Interests: The authors have declared that no competing interests exist. and thus mostly treat pain management as solely an animal welfare concern, in the jurisdiction of animal care and use committees. At the same time, animal welfare regulations do not include guidance on publishing animal data, even though publication is an integral part of the cycle of research and can affect the welfare of animals in studies building on published work, leaving it to journals and authors to voluntarily decide what details of animal use to publish. We suggest that journals, scientists and animal welfare regulators should revise current guidelines and regulations, on treatment of pain and on transparent reporting of treatment of pain, to improve this dual welfare and data-quality deficiency.« less
4. The Deep Learning Epilepsy Detection Challenge: Design, Implementation, and Test of a New Crowd-Sourced AI Challenge Ecosystem

   Kiral, Isabell ; Roy, Subhrajit ; Mummert, Todd ; Braz, Alan ; Tsay, Jason ; Tang, Jianbin ; Asif, Umar ; Schaffter, Thomas ; Mehmet, Eren ; Picone, Joseph ; et al ( April 2019 , Challenges in Machine Learning Competitions for All (CiML))

   The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert datamore »scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge.« less
5. Predicting Treatment Outcome in Spinal Cord Stimulation with EEG

   See, Kyle ; July, Rachel ; Coombes, Stephen ; Fang, Ruogu ( October 2021 , Biomedical Engineering Society Annual Meeting)

   Introduction: Back pain is one of the most common causes of pain in the United States. Spinal cord stimulation (SCS) is an intervention for patients with chronic back pain (CBP). However, SCS decreases pain in only 58% of patients and relies on self-reported pain scores as outcome measures. An SCS trial is temporarily implanted for seven days and helps to determine if a permanent SCS is needed. Patients that have a >50% reduction in pain from the trial stimulator makes them eligible for permanent implantation. However, self-reported measures reveal little on how mechanisms in the brain are altered. Other measurements of pain intensity, onset, medication, disabilities, depression, and anxiety have been used with machine learning to predict outcomes with accuracies <70%. We aim to predict long-term SCS responders at 6-months using baseline resting EEG and machine learning. Materials and Methods: We obtained 10-minutes of resting electroencephalography (EEG) and pain questionnaires from nine participants with CBP at two time points: 1) pre-trial baseline. 2) Six months after SCS permanent implant surgery. Subjects were designated as high or moderate responders based on the amount of pain relief provided by the long-term (post six months) SCS, and pain scored on a scale ofmore »0-10 with 0 being no pain and 10 intolerable. We used the resting EEG from baseline to predict long-term treatment outcome. Resting EEG data was fed through a pipeline for classification and to map dipole sources. EEG signals were preprocessed using the EEGLAB toolbox. Independent component analysis and dipole fitting were used to linearly unmix the signal and to map dipole sources from the brain. Spectral analysis was performed to obtain the frequency distribution of the signal. Each power band, delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), beta (13-30 Hz), and gamma (30-100 Hz), as well as the entire spectrum (1-100 Hz), were used for classification. Furthermore, dipole sources were ranked based on classification feature weights to determine the significance of specific regions in the brain. We used support vector machines to predict pain outcomes. Results and Discussion: We found higher frequency powerbands provide overall classification performance of 88.89%. Differences in power are seen between moderate and high responders in both the frontal and parietal regions for theta, alpha, beta, and the entire spectrum (Fig.1). This can potentially be used to predict patient response to SCS. Conclusions: We found evidence of decreased power in theta, alpha, beta, and entire spectrum in the anterior regions of the parietal cortex and posterior regions of the frontal cortex between moderate and high responders, which can be used for predicting treatment outcomes in long-term pain relief from SCS. Long-term treatment outcome prediction using baseline EEG data has the potential to contribute to decision making in terms of permanent surgery, forgo trial periods, and improve clinical efficiency by beginning to understand the mechanism of action of SCS in the human brain.« less