Feasibility and Safety of Oral Risperidone to Treat Prehospital Agitation.

OBJECTIVE: Agitation is a common prehospital problem and frequently presents without a clear etiology. Given the dynamic environment of the prehospital setting, there has historically been a varied approach to treating agitation with a heavy reliance on parenteral medications. Newer best practice guidelines recommend the incorporation of oral medications to treat patients experiencing agitation. Therefore, we evaluated the use of oral risperidone in a single system after a change in protocol occurred. METHODS: This was conducted as a retrospective chart review of an urban/suburban Emergency Medical Services system over the period of 8 months. The first day this medication was implemented throughout the service was included. Charts were included for selection if they included risperidone oral dissolving tablet (ODT) as a charted medication. The primary outcome was administration of additional medications to treat agitation. Exploratory outcome measures included acceptance of medication, documented injury to paramedics, documented injuries to patients, scene times, and adverse events that could possibly be linked to the medication. RESULTS: A total of 552 records were screened for inclusion. Risperidone was offered to 530 patients and accepted by 512 (96.6%). Of these 512 patients, the median age of included patients was 39 years old (IQR 29-52 years old) with a range of 18-89 years old. Rescue or additional medications for agitation were required in 9 (1.8%) cases. There were a total of 4 (0.8%) potential complications following administration of risperidone. There were no reported assaults with subsequent injuries to prehospital personnel or injuries sustained by patients reported in this study. CONCLUSIONS: Risperidone ODT was found to be a safe and effective medication to treat mild agitation in a large urban and suburban EMS system. The need for additional medications to treat agitation was rare, and there were no documented injuries to either patients or paramedics.

Inferring Metabolic States from Single Cell Transcriptomic Data via Geometric Deep Learning.

The ability to measure gene expression at single-cell resolution has elevated our understanding of how biological features emerge from complex and interdependent networks at molecular, cellular, and tissue scales. As technologies have evolved that complement scRNAseq measurements with things like single-cell proteomic, epigenomic, and genomic information, it becomes increasingly apparent how much biology exists as a product of multimodal regulation. Biological processes such as transcription, translation, and post-translational or epigenetic modification impose both energetic and specific molecular demands on a cell and are therefore implicitly constrained by the metabolic state of the cell. While metabolomics is crucial for defining a holistic model of any biological process, the chemical heterogeneity of the metabolome makes it particularly difficult to measure, and technologies capable of doing this at single-cell resolution are far behind other multiomics modalities. To address these challenges, we present GEFMAP (Gene Expression-based Flux Mapping and Metabolic Pathway Prediction), a method based on geometric deep learning for predicting flux through reactions in a global metabolic network using transcriptomics data, which we ultimately apply to scRNAseq. GEFMAP leverages the natural graph structure of metabolic networks to learn both a biological objective for each cell and estimate a mass-balanced relative flux rate for each reaction in each cell using novel deep learning models.

Bilateral nephrolithiasis following ingestion of guaifenesin and dextromethorphan.

Both guaifenesin and dextromethorphan are routinely available nonprescription medications that are also common drugs of abuse amongst young adults. We describe a presentation of guaifenesin and dextromethorphan misuse resulting in acute renal failure due to bilateral nephrolithiasis. The patient underwent placement of bilateral ureteral stents but again formed small renal stones bilaterally. While most renal calculi are not drug-induced, this case highlights the potential for nephrolithiasis after guaifenesin and dextromethorphan ingestion. It suggests that in this combination ingestion multiple mechanisms lead to a prolonged period of nephrolith formation.

Prehospital Treatment of Benzodiazepine-Resistant Pediatric Status Epilepticus with Parenteral Ketamine: A Case Series.

We report the initial six pediatric patients treated with ketamine for benzodiazepine-resistant status epilepticus in an urban, ground-based emergency medical services (EMS) system. Evidence for ketamine as a second-line agent for both adult and pediatric refractory seizure activity in the hospital setting has increased over the past decade. The availability of an inexpensive and familiar second-line prehospital anti-epileptic drug option is extremely desirable. We believe these initial data demonstrate promising seizure control effects without significant respiratory depression, indicating a potential role for ketamine in the EMS treatment of pediatric benzodiazepine-refractory seizures.

SCATTERING STATISTICS OF GENERALIZED SPATIAL POISSON POINT PROCESSES.

We present a machine learning model for the analysis of randomly generated discrete signals, modeled as the points of an inhomogeneous, compound Poisson point process. Like the wavelet scattering transform introduced by Mallat, our construction is naturally invariant to translations and reflections, but it decouples the roles of scale and frequency, replacing wavelets with Gabor-type measurements. We show that, with suitable nonlinearities, our measurements distinguish Poisson point processes from common self-similar processes, and separate different types of Poisson point processes.

Prehospital Drug Assisted Airway Management: An NAEMSP Position Statement and Resource Document.

Airway management is a critical intervention for patients with airway compromise, respiratory failure, and cardiac arrest. Many EMS agencies use drug-assisted airway management (DAAM) - the administration of sedatives alone or in combination with neuromuscular blockers - to facilitate advanced airway placement in patients with airway compromise or impending respiratory failure who also have altered mental status, agitation, or intact protective airway reflexes. While DAAM provides several benefits including improving laryngoscopy and making insertion of endotracheal tubes and supraglottic airways easier, DAAM also carries important risks. NAEMSP recommends:DAAM is an appropriate tool for EMS clinicians in systems with clear guidelines, sufficient training, and close EMS physician oversight. DAAM should not be used in settings without adequate resources.EMS physicians should develop clinical guidelines informed by evidence and oversee the training and credentialing for safe and effective DAAM.DAAM programs should include best practices of airway management including patient selection, assessmenct and positioning, preoxygenation strategies including apneic oxygenation, monitoring and management of physiologic abnormalities, selection of medications, post-intubation analgesia and sedation, equipment selection, airway confirmation and monitoring, and rescue airway techniques.Post-DAAM airway placement must be confirmed and continually monitored with waveform capnography.EMS clinicians must have the necessary equipment and training to manage patients with failed DAAM, including bag mask ventilation, supraglottic airway devices and surgical airway approaches.Continuous quality improvement for DAAM must include assessment of individual and aggregate performance metrics. Where available for review, continuous physiologic recordings (vital signs, pulse oximetry, and capnography), audio and video recordings, and assessment of patient outcomes should be part of DAAM continuous quality improvement.

The Manifold Scattering Transform for High-Dimensional Point Cloud Data.

The manifold scattering transform is a deep feature extractor for data defined on a Riemannian manifold. It is one of the first examples of extending convolutional neural network-like operators to general manifolds. The initial work on this model focused primarily on its theoretical stability and invariance properties but did not provide methods for its numerical implementation except in the case of two-dimensional surfaces with predefined meshes. In this work, we present practical schemes, based on the theory of diffusion maps, for implementing the manifold scattering transform to datasets arising in naturalistic systems, such as single cell genetics, where the data is a high-dimensional point cloud modeled as lying on a low-dimensional manifold. We show that our methods are effective for signal classification and manifold classification tasks.

A simple improvised prehospital method to warm intravenous fluid.

STUDY OBJECTIVE: Use of warmed intravenous fluid by emergency medical services (EMS) for prehospital injured patients is recommended to avoid iatrogenic hypothermia. We hypothesized that an improvised heating method would significantly increase the temperature of an intravenous fluid bag in a simulated prehospital environment. METHODS: The change from baseline in the temperature of a 1-L intravenous fluid bag positioned above the vehicle windshield defroster vent was measured for 30 minutes using a thermocouple probe. Temperature changes were compared with a control fluid bag positioned on the vehicle console armrest. A total of 10 independent experiments were performed. RESULTS: The defroster vent method increased intravenous fluid bag temperature from a mean starting temperature of 19.4°C (95% confidence interval [CI], 17.4°C-21.4°C) to a mean end temperature of 32.6°C (95% CI, 30.6°C-34.6°C) after 30 minutes. The temperature of a control intravenous fluid bag (mean starting temperature of 20.1°C; 95% CI, 19.0°C-21.2°C) exposed to a warmed (mean 33.2°C) passenger compartment changed little during the same time period (mean end temperature of 22.3°C; 95% CI, 19.4°C-25.2°C). CONCLUSIONS: Convective warming of an intravenous fluid bag using the dashboard defroster vent significantly raised the fluid temperature. Such a method should be readily available to EMS or first responders.

Emergency cricothyrotomy in morbid obesity: comparing the bougie-guided and traditional techniques in a live animal model.

BACKGROUND: Cricothyrotomy is a rare, time sensitive procedure that is more challenging to perform when anatomical landmarks are not easily palpated before the initial incision. There is a paucity of literature describing the optimal technique for cricothyrotomy in patients with impalpable airway structures, such as in morbid obesity. In this study, we used a live sheep model of morbid obesity to compare the effectiveness of two common cricothyrotomy techniques. METHODS: We randomly assigned emergency medicine residents to perform one of two cricothyrotomy techniques on a live anesthetized sheep. To simulate the anterior soft tissue neck thickness of an adult with morbid obesity we injected 120 mL of a mixture of autologous blood and saline into the anterior neck of the sheep. The traditional technique (as described in the New England Journal Video titled "Cricothyroidotomy") used a Shiley tracheostomy tube and no bougie, and the bougie-guided technique used a bougie and a standard endotracheal tube. The primary outcome was the total procedure time; the secondary outcome was first attempt success. RESULTS: 23 residents were included, 11 assigned to the bougie-guided technique and 12 to the traditional technique. After injection of blood and saline, the median depth from skin to cricothyroid membrane was 3.0 cm (IQR 2.5-3.4 cm). The median time for the bougie technique was 118 s (IQR 77-200 s) compared to 183 s (IQR 134-270 s) for the traditional technique (median difference 62 s, 95% CI 10-144 s). Success on the first attempt occurred in 7/11 (64%) in the bougie group and 6/12 (50%) in the traditional technique group. CONCLUSION: In this study, which simulated morbid obesity on a living animal model complete with active hemorrhage and time pressure caused by extubation before the procedure, the bougie-guided technique was faster than the traditional technique using a tracheostomy tube without a bougie.

MagNet: A Neural Network for Directed Graphs.

The prevalence of graph-based data has spurred the rapid development of graph neural networks (GNNs) and related machine learning algorithms. Yet, despite the many datasets naturally modeled as directed graphs, including citation, website, and traffic networks, the vast majority of this research focuses on undirected graphs. In this paper, we propose MagNet, a GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian. This matrix encodes undirected geometric structure in the magnitude of its entries and directional information in their phase. A "charge" parameter attunes spectral information to variation among directed cycles. We apply our network to a variety of directed graph node classification and link prediction tasks showing that MagNet performs well on all tasks and that its performance exceeds all other methods on a majority of such tasks. The underlying principles of MagNet are such that it can be adapted to other GNN architectures.

A Hybrid Scattering Transform for Signals with Isolated Singularities.

The scattering transform is a wavelet-based model of Convolutional Neural Networks originally introduced by S. Mallat. Mallat's analysis shows that this network has desirable stability and invariance guarantees and therefore helps explain the observation that the filters learned by early layers of a Convolutional Neural Network typically resemble wavelets. Our aim is to understand what sort of filters should be used in the later layers of the network. Towards this end, we propose a two-layer hybrid scattering transform. In our first layer, we convolve the input signal with a wavelet filter transform to promote sparsity, and, in the second layer, we convolve with a Gabor filter to leverage the sparsity created by the first layer. We show that these measurements characterize information about signals with isolated singularities. We also show that the Gabor measurements used in the second layer can be used to synthesize sparse signals such as those produced by the first layer.

Prehospital Treatment of Acute Pulmonary Edema with Intravenous Bolus and Infusion Nitroglycerin.

OBJECTIVE: The study describes the implementation of a prehospital treatment algorithm that included intravenous (IV) bolus (IVB) nitroglycerin (NTG) followed by maintenance infusion for the treatment of acute pulmonary edema (APE) in a single, high-volume Emergency Medical Services (EMS) system. METHODS: This is a retrospective chart review of patients who received IVB NTG for APE in a large EMS system in Minnesota and Wisconsin (USA). Inclusion criteria for treatment included a diagnosis of APE, systolic blood pressure ≥120mmHg, and oxygen saturation (SpO2) ≤93% following 800mcg of sublingual NTG. Patients received a 400mcg IVB of NTG, repeated every two minutes as needed, and subsequent infusion at 80mcg/min for transport times ≥10 minutes. RESULTS: Forty-four patients were treated with IVB NTG. The median total bolus dose was 400mcg. Twenty patients were treated with NTG infusion following IVB NTG. The median infusion rate was 80mcg/min. For all patients, the initial median blood pressure was 191/113mmHg. Five minutes following IVB NTG, it was 160/94mmHg, and on arrival to the emergency department (ED) it was 152/90mmHg. Five minutes after the initial dose of IVB NTG, median SpO2 increased to 92% from an initial reading of 88% and was 94% at hospital arrival. One episode of transient hypotension occurred during EMS transport. CONCLUSION: Patients treated with IVB NTG for APE had reduction in blood pressure and improvement in SpO2 compared to their original presentation. Prehospital treatment of APE with IVB appears to be feasible and safe. A randomized trial is needed to confirm these findings.

Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds.

The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional neural networks to manifold and graph-structured domains, we define a geometric scattering transform on manifolds. Similar to the Euclidean scattering transform, the geometric scattering transform is based on a cascade of wavelet filters and pointwise nonlinearities. It is invariant to local isometries and stable to certain types of diffeomorphisms. Empirical results demonstrate its utility on several geometric learning tasks. Our results generalize the deformation stability and local translation invariance of Euclidean scattering, and demonstrate the importance of linking the used filter structures to the underlying geometry of the data.

Alternatives to Rapid Sequence Intubation: Contemporary Airway Management with Ketamine.

Endotracheal intubation (ETI) is a high-risk procedure commonly performed in emergency medicine, critical care, and the prehospital setting. Traditional rapid sequence intubation (RSI), the simultaneous administration of an induction agent and muscle relaxant, is more likely to harm patients who do not allow appropriate preparation and preoxygenation, have concerning airway anatomy, or severe hypoxia, acidemia, or hypotension. Ketamine, a dissociative anesthetic, can be used to facilitate two alternatives to RSI to augment airway safety in these scenarios: delayed sequence intubation - the use of ketamine to allow airway preparation and preoxygenation in the agitated patient; and ketamine-only breathing intubation, in which ketamine is used without a paralytic to facilitate ETI as the patient continues to breathe spontaneously. Ketamine may also provide hemodynamic benefits during standard RSI and is a valuable agent for post-intubation analgesia and sedation. When RSI is not an optimal airway management strategy, ketamine's unique pharmacology can be harnessed to facilitate alternative approaches that may increase patient safety.