Search

Epilepsy is a common neurological disorder characterized by recurrent epileptic seizures. These seizures have different intensities and might lead to accidents or, in the worst case, to sudden death. Therefore, being able to predict epileptic seizures would allow patients to be prepared, reducing the risk of injury. This paper focuses on epileptic seizure prediction using EEG (Electroencephalogram) signals. In contrast to the standard approach where the preictal state is assumed to have a constant duration in all the seizures of a patient, we propose a new method that labels each seizure individually exploiting clustering. Our labeling approach, which was applicable for 38% of the selected seizures, results in substantial improvements compared to the standard one. In fact, it reduces noise in the labels and improves the performance of the binary classifier used to distinguish the interictal and preictal states. Hence, our results suggest that the preictal duration is seizure-specific, not only patient-specific. Finally, we show that our method is able to predict 17 out of 18 (94%) seizures between 15 and 85 minutes, before seizure onset.

Artificial intelligence (AI) is certainly not a panacea for solving the ‘Pharma Dilemma’, in which the cost of producing new drugs continues to spiral. However, AI can be used to fundamentally change the way we perform essential steps in clinical trial design and execution, from cohort selection to patient monitoring. Merging AI and clinical expertise across engineering and medical disciplines to explore the impact of these changes on trial performance and success rates is one of the most promising leads we have for restoring efficiency and sustainability to the drug development cycle.

Background Assistive automatic seizure detection can empower human annotators to shorten patient monitoring data review times. We present a proof-of-concept for a seizure detection system that is sensitive, automated, patient-specific, and tunable to maximise sensitivity while minimizing human annotation times. The system uses custom data preparation methods, deep learning analytics and electroencephalography (EEG) data. Methods Scalp EEG data of 365 patients containing 171,745 s ictal and 2,185,864 s interictal samples obtained from clinical monitoring systems were analysed as part of a crowdsourced artificial intelligence (AI) challenge. Participants were tasked to develop an ictal/interictal classifier with high sensitivity and low false alarm rates. We built a challenge platform that prevented participants from downloading or directly accessing the data while allowing crowdsourced model development. Findings The automatic detection system achieved tunable sensitivities between 75.00% and 91.60% allowing a reduction in the amount of raw EEG data to be reviewed by a human annotator by factors between 142x, and 22x respectively. The algorithm enables instantaneous reviewer-managed optimization of the balance between sensitivity and the amount of raw EEG data to be reviewed. Interpretation This study demonstrates the utility of deep learning for patient-specific seizure detection in EEG data. Furthermore, deep learning in combination with a human reviewer can provide the basis for an assistive data labelling system lowering the time of manual review while maintaining human expert annotation performance. Funding IBM employed all IBM Research authors. Temple University employed all Temple University authors. The Icahn School of Medicine at Mount Sinai employed Eren Ahsen. The corresponding authors Stefan Harrer and Gustavo Stolovitzky declare that they had full access to all the data in the study and that they had final responsibility for the decision to submit for publication.

Wearable sensors are being used in clinical settings to monitor the condition of patients as well as in recreational environments for routine health monitoring. Some of the most advanced clinical applications include monitoring patients with Parkinson's disease through wearable inertial measuring units (IMUs) and patients with diabetes by means of wearable glucose sensors. Prominent examples of wearable sensors in routine use are fitness trackers, step-and calorie counters. Recently, wearables have evolved to being capable of running artificial intelligence algorithms in real-time at the point of sensing which allows to gain analytical insights directly from measurement data. We call such intelligent wearables with AI-at-the-edge functionality THINKables. First use cases for THINKables have emerged in both clinical and nonclinical applications: real-time seizure prediction or detection systems for epilepsy patients, or digital coaches providing real-time feedback to athletes on performance and injury risks. Technological and regulatory challenges of developing and deploying THINKables are multifold: data privacy and security of monitoring data needs to be ensured at all times, analytical AI models need to be transparent, explainable and fair, and all these features need to be implemented taking the limited computing power of point-of-sensing processors into account. In order for THINKables to become integrated into clinical workflows, all stakeholders in the Health AI ecosystem (regulators, clinicians, biomedical device technologists, pharma and biotech sectors, data scientists, and patients) need to work together to create frameworks for responsible and meaningful use.

This paper presents a novel deep learning enabled, video based analysis framework for assessing the Unified Parkinsons Disease Rating Scale (UPDRS) that can be used in the clinic or at home. We report results from comparing the performance of the framework to that of trained clinicians on a population of 32 Parkinsons disease (PD) patients. In-person clinical assessments by trained neurologists are used as the ground truth for training our framework and for comparing the performance. We find that the standard sit-to-stand activity can be used to evaluate the UPDRS sub-scores of bradykinesia (BRADY) and posture instability and gait disorders (PIGD). For BRADY we find F1-scores of 0.75 using our framework compared to 0.50 for the video based rater clinicians, while for PIGD we find 0.78 for the framework and 0.45 for the video based rater clinicians. We believe our proposed framework has potential to provide clinically acceptable end points of PD in greater granularity without imposing burdens on patients and clinicians, which empowers a variety of use cases such as passive tracking of PD progression in spaces such as nursing homes, in-home self-assessment, and enhanced tele-medicine., Comment: Accepted by CVPR Workshops 2021

Artificial intelligence (AI) technologies have advanced to a level of maturity that allows them to be employed under real-life conditions to assist human decision-makers. AI has the potential to transform key steps of clinical trial design from study preparation to execution towards improving trial success rates, thus lowering the pharma R&D burden. Suboptimal patient cohort selection and recruiting techniques, paired with the inability to monitor patients effectively during trials, are two of the main causes for high trial failure rates: only one of 10 compounds entering a clinical trial reaches the market. This session will explain in layman's terms some of the foundations of AI methodology, such as Machine Learning and Deep Learning, highlighting how recent advances can be applied at specific stages of the clinical trial design process to improve cohort composition, patient recruitment, medication compliance and patient retention. A special focus will be given to describing how patients in neurology trials could be monitored more efficiently through Digital Disease Diaries, which use wearable devices, machine learning at the edge and cloud technology to automatically detect and log disease episodes and patient adherence to trial protocols. Like all technical revolutions, this comes with challenges and risks, both technical and regulatory. In particular, we will discuss scalability, data encryption and patient privacy.

Background Seizure prediction can increase independence and allow preventative treatment for patients with epilepsy. We present a proof-of-concept for a seizure prediction system that is accurate, fully automated, patient-specific, and tunable to an individual's needs. Methods Intracranial electroencephalography (iEEG) data of ten patients obtained from a seizure advisory system were analyzed as part of a pseudoprospective seizure prediction study. First, a deep learning classifier was trained to distinguish between preictal and interictal signals. Second, classifier performance was tested on held-out iEEG data from all patients and benchmarked against the performance of a random predictor. Third, the prediction system was tuned so sensitivity or time in warning could be prioritized by the patient. Finally, a demonstration of the feasibility of deployment of the prediction system onto an ultra-low power neuromorphic chip for autonomous operation on a wearable device is provided. Results The prediction system achieved mean sensitivity of 69% and mean time in warning of 27%, significantly surpassing an equivalent random predictor for all patients by 42%. Conclusion This study demonstrates that deep learning in combination with neuromorphic hardware can provide the basis for a wearable, real-time, always-on, patient-specific seizure warning system with low power consumption and reliable long-term performance., Highlights • We use deep learning and long-term neural data to develop an automated, patient-tunable epileptic seizure prediction system. • We deploy our prediction system on a low-power neuromorphic chip to form the basis of a wearable device. Predicting and treating the debilitating seizures suffered by epileptic patients has challenged medical researchers for over fifty years. A new way forward was opened when Cook and colleagues, in 2013, collected a large longitudinal and continuous dataset recorded directly from patients' brains for one to three years. Harnessing the recent breakthroughs in deep learning techniques and in building specialized processing chips, we have demonstrated that seizures can now be predicted by a portable device. Our system automatically learns patient-specific pre-seizure signatures, and, in real time, warns of oncoming seizures.

Accurate classification of seizure types plays a crucial role in the treatment and disease management of epileptic patients. Epileptic seizure types not only impact the choice of drugs but also the range of activities a patient can safely engage in. With recent advances being made towards artificial intelligence enabled automatic seizure detection, the next frontier is the automatic classification of seizure types. On that note, in this paper, we explore the application of machine learning algorithms for multi-class seizure type classification. We used the recently released TUH EEG seizure corpus (V1.4.0 and V1.5.2) and conducted a thorough search space exploration to evaluate the performance of a combination of various pre-processing techniques, machine learning algorithms, and corresponding hyperparameters on this task. We show that our algorithms can reach a weighted $F1$ score of up to 0.901 for seizure-wise cross validation and 0.561 for patient-wise cross validation thereby setting a benchmark for scalp EEG based multi-class seizure type classification., 5 pages, 2 figure, 4 table

Neuroethics is central to the Australian Brain Initiative’s aim to sustain a thriving and responsible neurotechnology industry. Diverse and inclusive community and stakeholder engagement and a trans-disciplinary approach to neuroethics will be key to the success of the Australian Brain Initiative. Refereed/Peer-reviewed

Importance: Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. Objective: To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. Design, Setting, and Participants: In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Main Outcomes and Measurements: Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated. Results: Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. Conclusions and Relevance: While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation. CA extern

Clinical trials consume the latter half of the 10 to 15 year, 1.5–2.0 billion USD, development cycle for bringing a single new drug to market. Hence, a failed trial sinks not only the investment into the trial itself but also the preclinical development costs, rendering the loss per failed clinical trial at 800 million to 1.4 billion USD. Suboptimal patient cohort selection and recruiting techniques, paired with the inability to monitor patients effectively during trials, are two of the main causes for high trial failure rates: only one of 10 compounds entering a clinical trial reaches the market. We explain how recent advances in artificial intelligence (AI) can be used to reshape key steps of clinical trial design towards increasing trial success rates.

Brain-computer interfaces are commonly proposed to assist individuals with locked-in syndrome to interact with the world around them. In this paper, we present a pipeline to move from recorded brain signals to real-time classification on a low-power platform, such as IBM's TrueNorth Neurosynaptic System. Our results on a EEG-based hand squeeze task show that using a convolutional neural network and a time preserving signal representation strategy provides a good balance between high accuracy and feasibility in a real-time application. This pathway can be adapted to the management of a variety of conditions, including spinal cord injury, epilepsy and Parkinson's disease.

© 2019 Elsevier Inc. Neuroethics is central to the Australian Brain Initiative's aim to sustain a thriving and responsible neurotechnology industry. Diverse and inclusive community and stakeholder engagement and a trans-disciplinary approach to neuroethics will be key to the success of the Australian Brain Initiative.

The DNA-Transistor is a device designed to control the translocation of single-stranded DNA through a solid-state nanopore. Functionality of the device is enabled by three electrodes exposed to the DNA-containing electrolyte solution within the pore and the application of a dynamic electrostatic potential well between the electrodes to temporarily trap a DNA molecule. Optimizing the surface chemistry and electrochemical behavior of the device is a necessary (but by no means sufficient) step toward the development of a functional device. In particular, effects to be eliminated are (i) electrochemically induced surface alteration through corrosion or reduction of the electrode surface and (ii) formation of hydrogen or oxygen bubbles inside the pore through water decomposition. Even though our motivation is to solve problems encountered in DNA transistor technology, in this paper we report on generic surface chemistry results. We investigated a variety of electrode-electrolyte-solvent systems with respect to their capability of suppressing water decomposition and maintaining surface integrity. We employed cyclic voltammetry and long-term amperometry as electrochemical test schemes, X-ray photoelectron spectroscopy, atomic force microscopy, and scanning, as well as transmission electron microscopy as analytical tools. Characterized electrode materials include thin films of Ru, Pt, nonstoichiometric TiN, and nonstoichiometric TiN carrying a custom-developed titanium oxide layer, as well as custom-oxidized nonstoichiometric TiN coated with a monolayer of hexadecylphosphonic acid (HDPA). We used distilled water as well as aqueous solutions of poly(ethylene glycol) (PEG-300) and glycerol as solvents. One millimolar KCl was employed as electrolyte in all solutions. Our results show that the HDPA-coated custom-developed titanium oxide layer effectively passivates the underlying TiN layer, eliminating any surface alterations through corrosion or reduction within a voltage window from -2 V to +2 V. Furthermore, we demonstrated that, by coating the custom-oxidized TiN samples with HDPA and increasing the concentration of PEG-300 or glycerol in aqueous 1 mM KCl solutions, water decomposition was suppressed within the same voltage window. Water dissociation was not detected when combining custom-oxidized HDPA-coated TiN electrodes with an aqueous 1 mM KCl-glycerol solution at a glycerol concentration of at least 90%. These results are applicable to any system that requires nanoelectrodes placed in aqueous solution at voltages that can activate electrochemical processes.

We report novel strategies to integrate block copolymer self-assembly with 193 nm water immersion lithography. These strategies employ commercially available positive tone chemically amplified photoresists to spatially encode directing information into precise topographical or chemical prepatterns for the directed self-assembly of block copolymers. Each of these methods exploits the advantageous solubility and thermal properties of polarity-switched positive tone photoresist materials. Precisely registered, sublithographic self-assembled structures are fabricated using these versatile integration schemes which are fully compatible with current optical lithography patterning materials, processes, and tooling.

We have demonstrated direct nanoscale transfer printing (nTP) of PdAu lines from a hard mold onto a hard substrate at room temperature without employing any flexible buffer layers or organic adhesion promoters or release agent layers. PdAu was evaporated onto the mold surface, and a Ti layer was deposited on top of the PdAu layer. By pressing the mold against a Si/SiO2 substrate, the PdAu/Ti sandwich structure was directly transferred onto the SiO2 surface. The molds used in these experiments were GaAs/AlGaAs sandwich structures fabricated by molecular beam epitaxy that we cleaved and selectively etched afterwards in order to generate 3-D grating structures with nanometer resolution on their edges. We fabricated positive multiline molds with different aspect ratios, linewidths between 15 and 100 nm, and spacings between lines ranging from 5 to 70 nm. We also fabricated negative single-line molds with a positive supporting structure comprising a single 16-nm-wide groove feature. The experiments revealed that direct hard-on-hard transfer of nanoscale structures from a mold onto a substrate can be used to fabricate PdAu gaps with widths down to 9 nm. We also performed electronic measurements on transfer patterns and demonstrated that transferred structures can be used as electrodes, which are electrically isolated by these gaps. Since isolation characteristics of gaps improved with decreasing gap length, we partitioned longer gap segments into multiple shorter ones by focused ion beam lithography and conventional optical lithography in combination with wet chemical or plasma etching of the mold or the substrate, respectively. In this paper, we give a detailed description of all technological aspects of the developed direct nTP technique, including mold preparation, patterning efficiency, short reduction techniques, and yield.