University of Michigan

Virginia Commonwealth University

The Ohio State University

Other

Biotrack, LLC

Kevin R Ward

Kayvan Najarian

Sardar Ansari

Rao R Ivatury

Christopher Elliot Gillies

Mark A Burns

Roger R Dzwonczyk

Bruce D Spiess

Charles G Brown

Ashwin Belle

Daniel Taylor

Mark J Licata

Jeffrey Stephen Plott

Gary L Bowlin

Kenn Oldham

Marcus E Carr

Rodney C Daniels

Mary Jo Grap

Curtis N Sessler

Laurence J DiNardo

Richard C Medlin

Frederick Korley

Robert F Diegelmann

Martin Patrick De Beer

Maryanne M Collinson

Yunzi Li

Mohamad Hakam Tiba

Cindy Munro

Alyse D Krausz

Lu Wang

Fadi Islim

Michael W Sjoding

Sarah Elizabeth Mena

Nicholas Alexander Kotov

Gary E Wnek

Martin K Safo

Albert J Shih

Martin L Lenhardt

Marcus E Carr, Jr

Richmond E Danso-Danquah

Gary S Huvard

Hasan B Alam

Martin J Mangino

Bogdan I Epureanu

Richard P Imbruce

Brahmajee Kartik Nallamothu

Robert Mitchell Baldwin, Ii

Jurgen Venitz

Parag G Patil

Mohini Ghatge

Sayedmohammadreza Soroushmehr

Kelman I Cohen

Jianping Fu

James M Blum

R Wayne Barbee

James Terner

Fred Hawkridge

Thuan Doan

Himanshu Saxena

Mahmut Mert Egilmez

James A Arrowood

Daniel Slavin

Zida Li

Martin M Lenhardt

Xiang Li

Kyle Gunnerson

Hamid Ghanbari

Wenan Chen

Harm Derksen

Jie Wu

Rosalyn Hobson Hargraves

Cindy Muare

Jeremy Scott VanEpps

Sharad Shandilya

Rosalyn Stacy Hobson

Sumeyra Ummuhan Demir Kanik

Nazanin Mirshahi

Soo-Yeon Ji

Roya Hakimzadeh

Simina Vasilache

Rebecca Smith

Wayne Barbee

Robert W Barbee

Gary Lee Bowlin

A method includes receiving raw input signals, analyzing the raw signals using a trained coding architecture including an encoding layer; and displaying an output. A computing system includes a processor and a memory storing instructions that when executed by the processor, cause the computing system to receive raw input signals, analyzing the raw signals using a trained coding architecture and display an output. A non-transitory computer readable medium includes program instructions that when executed cause a computer to receive raw input signals, analyze the raw signals using a trained coding architecture and display an output.

Coding architectures for automatic analysis of waveforms

A junctional hemorrhage control device includes a strap and a base operably connected to the strap. A strap carriage is operably connected to, and linearly translatable relative to, the base. A screw assembly is rotatably attached to the base. The screw assembly moves the strap carriage away from the base when the screw assembly is operated in one direction and towards the base when the screw assembly is operated in an opposite direction. A removable pressure plate is attached to the base to apply occlusion pressure to a hemorrhage location.

Junctional hemorrhage occlusion device

A computing system includes a processor; and a memory having stored thereon an adjustment application comprising computer-executable instructions that, when executed, cause the computing system to: display a graphical user interface including a digital medical image of a patient; superimpose a bounding box; receive an adjustment of an area of interest; and provide an adjusted digital medical image. A non-transitory computer-readable medium includes computer-executable instructions that, when executed via one or more processors, cause a computer to: display a graphical user interface including a digital medical image of a patient; superimpose a bounding box; receive an adjustment of an area of interest; and provide an adjusted digital medical image. A computer-implemented method includes: displaying a graphical user interface including a digital medical image of a patient; superimposing a bounding box; receiving an adjustment of an area of interest; and providing an adjusted digital medical image.

Computer vision technologies for rapid detection

An anti-hemorrhage device, and an anti-hemorrhage kit, includes a rigid platform and a compression device adjustably secured to the rigid platform. The kit also includes a gastroesophageal aortic occlusion device.

Anti-hemorrhage device with rigid back plate

A method includes receiving patient health data; determining a score using a trained machine learning model; determining a threshold value using an adaptive threshold tuning learning model; comparing the score to the threshold value; and generating an alarm. A computing system includes a processor; and a memory having stored thereon instructions that, when executed by the processor, cause the computing system to: receive patient health data; determine a score using a trained machine learning model; determine a threshold value using an adaptive threshold tuning learning model; compare the score to the threshold value; and generate an alarm. A non-transitory computer readable medium includes program instructions that when executed, cause a computer to: receive patient health data; determine a score using a trained machine learning model; determine a threshold value using an adaptive threshold tuning learning model; compare the score to the threshold value; and generate an alarm.

Predicting intensive care transfers and other unforeseen events using machine learning

A microfluidic device system includes a channel having an entrance and an exit, a height at the entrance being greater than a height at the exit. The height of the channel may decrease continuously from the height at the entrance to the height at the exit. Cells or particles or beads traveling through the channel become trapped based on their size and/or deformability. A visual sensor captures images of the trapped cells or particles or beads, and image software analyzes the captured images to provide size and/or deformability and/or fluorescence information. A method of fabricating such a microfluidic device includes introducing a glass wafer to an etching solution at a specific rate such that a first end of the glass wafer is etched longer than other portions of the glass wafer.

Microfluidic device for size and deformability measurements and applications thereof

A droplet-based microfluidic rheometer system and method of use for real-time viscosity monitoring of blood coagulation is disclosed. Droplets of blood samples are generated in a microfluidic rheometer, and the size of the droplets is highly correlated to the sample viscosity. The size of the droplets can be determined optically using an inverted light microscope and a camera or using electrodes. The microfluidic rheometer systems provides viscosity measurements in less than a second and consumes less than 1 μl blood or plasma over an hour period. The viscosity measurements may be displayed and transmitted to the Internet or cloud storage.

Droplet-based microfluidic rheometer system

Devices and techniques for continuously monitoring pressure and simultaneously monitoring changes in blood flow, vascular resistance, and/or vascular behavior are provided. The techniques are employed in measuring intracranial pressure (ICP), while simultaneously measuring cerebral blood flow and/or cerebrovascular resistance or behavior. A sensor device includes an optical and piezoelectric sensing assembly integrated into a deployable ICP monitoring device.

Multi-sensor intracranial pressure monitor for cerebral hemodynamic monitoring

A computer-implemented method includes preprocessing a variable dimension medical image, identifying one or more areas of interest in the medical image; and analyzing the one or more areas of interest using a deep learning model. A computing system includes one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to preprocess a variable dimension medical image, identify one or more areas of interest in the medical image; and analyze the one or more areas of interest using a deep learning model. A non-transitory computer readable medium contains program instructions that when executed, cause a computer to preprocess a variable dimension medical image, identify one or more areas of interest in the medical image, and analyze the one or more areas of interest using a deep learning model.

A method of predicting patient deterioration includes receiving an electronic health record data set of the patient, determining a risk score corresponding to the patient by analyzing the electronic health record data set of the patient using a trained machine learning model, determining a threshold value using an online/reinforcement learning model, comparing the risk score to the threshold value, and when the risk score exceeds the threshold value, generating an alarm. A non-transitory computer readable medium includes program instructions that when executed, cause the computer to receive a list of patients, display selectable patient information corresponding to each of the list of patients according to an ordering established by a feature importance algorithm, receive a selection, retrieve vital sign information corresponding to the selection, and display the vital sign information.

A method includes disposing a plurality of actuators about a subject, each actuator being configured to generate a respective vibration signal, each vibration signal applying a normal force to the subject, and controlling the plurality of actuators such that the respective vibration signal of each actuator of the plurality has a respective vibration characteristic. Each actuator is oriented such that the respective vibration signal propagates along a longitudinal axis of the subject for stimulation of the subject remote from the plurality of actuators.

Multiple actuator vibration therapy

Methods and systems monitor and assess brain bioimpedance through the use of an ocular window that assesses dynamic changes in cerebral blood volume (CBV). That ocular window is implemented through an ocular bioimpedance device that, in a non-invasive manner, measures numerous different brain health indicators using the bioimpedance measurements collected through the regions around the eyes. The ocular bioimpedance device may be goggles with localized measurement electrodes that include cathodes and anodes.

Ocular impedance-based system for brain health monitoring

Provided herein are compositions, systems, and methods for detecting microorganisms. In particular, provided herein are compositions, systems, and methods for rapid, multiplex detection of microorganism in unpurified biological samples.

Compositions and methods for detection of microorganisms

A blood clot retraction assay device and methods of measuring whole-blood clot retractive forces during coagulation are described. When placed in proximity to a micro-beam, a blood droplet attaches thereto, applying a force to the micro-beam during clot formation. Using Piezoresistive micro-beams or other Piezoresistive components disposed upon such micro-beams, the device measures retractive force of a blood droplet based upon changes in resistance. The sensitivity of such measurements allows use of small quantities of blood for measurement, between 15 microliters and 300 microliters. The device further permits continuous measurement of coagulation, allowing measurement of distinct reaction, contraction development, and fibrinolysis phases for each blood sample.

Microscale whole blood coagulation assay platform

Growing community of inventors

Superior Township, MI, United States of America

Kevin R Ward