Artificial intelligence-enhanced epileptic seizure detection by wearables.

OBJECTIVE: Wrist- or ankle-worn devices are less intrusive than the widely used electroencephalographic (EEG) systems for monitoring epileptic seizures. Using custom-developed deep-learning seizure detection models, we demonstrate the detection of a broad range of seizure types by wearable signals. METHODS: Patients admitted to the epilepsy monitoring unit were enrolled and asked to wear wearable sensors on either wrists or ankles. We collected patients' electrodermal activity, accelerometry (ACC), and photoplethysmography, from which blood volume pulse (BVP) is derived. Board-certified epileptologists determined seizure onset, offset, and types using video and EEG recordings per the International League Against Epilepsy 2017 classification. We applied three neural network models-a convolutional neural network (CNN) and a CNN-long short-term memory (LSTM)-based generalized detection model and an autoencoder-based personalized detection model-to the raw time-series sensor data to detect seizures and utilized performance measures, including sensitivity, false positive rate (the number of false alarms divided by the total number of nonseizure segments), number of false alarms per day, and detection delay. We applied a 10-fold patientwise cross-validation scheme to the multisignal biosensor data and evaluated model performance on 28 seizure types. RESULTS: We analyzed 166 patients (47.6% female, median age = 10.0 years) and 900 seizures (13 254 h of sensor data) for 28 seizure types. With a CNN-LSTM-based seizure detection model, ACC, BVP, and their fusion performed better than chance; ACC and BVP data fusion reached the best detection performance of 83.9% sensitivity and 35.3% false positive rate. Nineteen of 28 seizure types could be detected by at least one data modality with area under receiver operating characteristic curve > .8 performance. SIGNIFICANCE: Results from this in-hospital study contribute to a paradigm shift in epilepsy care that entails noninvasive seizure detection, provides time-sensitive and accurate data on additional clinical seizure types, and proposes a novel combination of an out-of-the-box monitoring algorithm with an individualized person-oriented seizure detection approach.

Dimensionality of carbon nanomaterials determines the binding and dynamics of amyloidogenic peptides: multiscale theoretical simulations.

Experimental studies have demonstrated that nanoparticles can affect the rate of protein self-assembly, possibly interfering with the development of protein misfolding diseases such as Alzheimer's, Parkinson's and prion disease caused by aggregation and fibril formation of amyloid-prone proteins. We employ classical molecular dynamics simulations and large-scale density functional theory calculations to investigate the effects of nanomaterials on the structure, dynamics and binding of an amyloidogenic peptide apoC-II(60-70). We show that the binding affinity of this peptide to carbonaceous nanomaterials such as C60, nanotubes and graphene decreases with increasing nanoparticle curvature. Strong binding is facilitated by the large contact area available for π-stacking between the aromatic residues of the peptide and the extended surfaces of graphene and the nanotube. The highly curved fullerene surface exhibits reduced efficiency for π-stacking but promotes increased peptide dynamics. We postulate that the increase in conformational dynamics of the amyloid peptide can be unfavorable for the formation of fibril competent structures. In contrast, extended fibril forming peptide conformations are promoted by the nanotube and graphene surfaces which can provide a template for fibril-growth.

Simulations of graphitic nanoparticles at air-water interfaces.

The free energy associated with transferring a set of fullerene particles through a finite water layer is calculated using explicit solvent molecular dynamic simulations. Each fullerene particle is a carbon network of one or more spheroidal shells of graphitic carbon, and include single-shell (single-wall) or nested multi-shelled (nano-onions) structures ranging from 6 to 28 Å in radius. Corresponding changes in energy suggest a stronger affinity of carbon nano-onions for water compared to their single-shelled analogues. In the case of multi-shelled structures, the free energy profiles display a global minimum only in the bulk liquid indicating a high affinity of multi-shelled fullerene for complete hydration. Single-wall particles however, display a minimum at the air-water interface and for particles larger than 2 nm this minimum is a global minimum possessing a lower energy compared to the particle's state of complete hydration. While the propensity for single-shell particles to adsorb to the air-interface may increase with increasing particle size, there is an indication based on line tension calculations that larger single-shell particles may actually exhibit enhanced wetting compared to their smaller analogues.

Size-Dependent Fullerene-Fullerene Interactions in Water: A Molecular Dynamics Study.

Nested fullerenes display a range of unique properties influenced by their size and shape. In this paper, the size- and shape-dependent aggregation of nested fullerenes in water is studied using explicit solvent molecular dynamic simulations. It is shown that water forms a layered structure near the surface of the particle, with the density of interfacial water increasing with increasing particle size. Meanwhile, water molecules near the extended facets of large nested fullerenes are unable to maintain their hydrogen bonding network, leading to a shape and size mediated structuring of surrounding waters. These distortions affect the overall association kinetics of particles in water with spherically shaped particles transitioning quickly into contact, while larger fullerenes, characterized by a lower sphericity, cluster at a much slower rate.

Designing Fluorescent Peptide Sensors with Dual Specificity for the Detection of HIV-1 Protease.

HIV-1 protease is a key enzyme in the life cycle of HIV/AIDS, as it is responsible for the formation of the mature virus particle. We demonstrate here that phage-display peptides raised against this enzyme can be used as peptide sensors for the detection of HIV-1 protease in a simple, one-pot assay. The presence of the enzyme is detected through an energy transfer between two peptide sensors when simultaneously complexed with the target protein. The multivalent nature of this assay increases the specificity of the detection by requiring all molecules to be interacting in order for there to be a FRET signal. We also perform molecular dynamics simulations to explore the interaction between the protease and the peptides in order to guide the design of these peptide sensors and to understand the mechanisms which cause these simultaneous binding events. This approach aims to facilitate the development of new assays for enzymes that are not dependent on the cleavage of a substrate and do not require multiple washing steps.