PROJECTS

PMMA Device for Droplet-based Complete Blood Count

PI: Kelvin Gregory, Civil & Environmental Engineering, kelvin@cmu.edu
Website: http://faculty.ce.cmu.edu/gregory/

Executive Summary: Blood chemistry analysis is time and labor intensive and delays patient care. The project aims to develop an inexpensive, rapid, low volume complete blood count test. The PI developed a device to separate particles based on size using a tilted acoustic wave field in a microfluidic channel in a PMMA prism. With the PMMA prism device he demonstrated the separation of particles by size and the feasibility of separating red and white blood cells. Theory predicts that this technology can be expanded to separate cells or particles based on compressibility, density, or shape as well as size, so we will develop the PMMA prism device to rapidly separate whole blood. Sensors can be used to count separated cells as they flow past specific locations in this continuous flow device to provide a complete blood count. The project proposes to develop this technology for use with a low blood volume to enable a pointof-care CBC, and provide timely access to the diagnostic information. As a secondary goal, the same research into cell separation in this device will enable the development of a rapid blood typing test to reduce the need for O-negative blood in emergency patients with undetermined blood type.


A Novel Approach to Improve the Delivery and Reduce the Toxic Side Effects of Anticancer Nanodrugs by Treatment with Intralipid

PI: Chien Ho, Ph.D., Department of Biological Sciences, chienho@andrew.cmu.edu
Website: http://www.cmu.edu/bio/faculty/ho.html

Executive Summary: Nanotechnology-based drug delivery systems can specifically target tumors, providing new therapeutic approaches to cancer. A major challenge for translating nanodrugs to clinical applications is their rapid clearance by the reticuloendothelial system (RES), thus reducing their efficacy and increasing their toxic side effects. In preliminary studies, Dr. Ho and his team have found that, in rats, treatment with Intralipid, an FDA approved nutritional supplement, can reduce RES uptake ~50% and increase blood half-life ~3-fold of nanoparticles. The purpose of this project is to optimize the conditions for the use of Intralipid to improve the delivery and reduce the side effects of anticancer nanodrugs. Intralipid has been used for over 40 years as a safe source of parenteral nutrition for patients, so would readily translate to clinical use. The outcome of this study has the potential to decrease the toxic side effects of anticancer drugs, and therefore to reduce human suffering. Also, increasing efficacy could lead to reduction of the dosage of these expensive drugs: the average cost per dose is US$4,000-6,000. Thus, Dr. Ho’s work for the use of Intralipid with nanodrugs can also lead to reduction of healthcare costs. These findings are an example that an “old drug” can have new applications.


Raspberry-Derived Therapeutic for Inflammatory Bowel Disease

PI: Kathryn Whitehead, Chemical Engineering and Biomedical Engineering, kawhite@cmu.edu
Website: http://whitehead.cheme.cmu.edu/

Executive Summary: The goal of this research is use bioactive raspberry extract, which is uniquely able to reduce GI permeability, to develop an inexpensive IBD therapeutic that lacks the side effects of conventional drugs. Inflammatory bowel disease (IBD) is a chronic, debilitating autoimmune disease of the gastrointestinal tract with no cure. Together, the two main variants of IBD (Crohn’s™s disease and ulcerative colitis) affect 1.6 million Americans, with 70,000 new cases reported each year. Therapeutic options are limited, and the most effective of these (e.g. anti-TNF alpha antibodies) are prone to side effects and loss of efficacy. There is an urgent need for new therapies that efficiently disrupt the IBD inflammatory cycle, facilitating swifter healing and longer periods of remission. In particular, a major opportunity exists to create a therapy that reduces the permeability of the intestine, which will reduce bacterial transport and inflammation. Through this work, we will determine the optimal mode of raspberry extract delivery to the colon of mice and use it to improve disease outcomes in acute and chronic mouse models of DSS-induced colitis.


Search-Assisted Early Melanoma Detection Library

PI: Mahadev Satyanarayanan, Computer Science, satya@cs.cmu.edu
Website: https://www.cs.cmu.edu/~satya/

Executive Summary: Early detection is a crucial aspect of improved melanoma survival. There is an unmet need for improved detection of early stage melanoma lesions by PCPs. The goal of this project is to create a cheap, easy to use software tool called DermShare that will assist PCPs in more accurately detecting melanoma. DermShare will be easily integrated into the regular patient care workflow of a PCP, simplifying its regular use in clinical practice. To make DermShare as low cost and widely distributable as possible, the team will strongly leverage open-source technologies. DermShare is already effective as a search tool for skin lesions.


Antibacterial Perfluorocarbon Ventilation To Increase Ventilator Free Days and Reduce Hospitalization Following Lower Respiratory Infection

PI: Keith E. Cook, PhD, Biomedical Engineering, keicook@andrew.cmu
Website: http://www.bme.cmu.edu/people/faculty1.html#Cook

Executive Summary: Improved treatments are needed for patients with lower respiratory bacterial infections and impaired respiratory function requiring mechanical ventilation. In this situation, mechanical ventilation hampers infection treatment while the infection hampers respiratory function. To overcome this, we propose using antibacterial perfluorocarbon ventilation (APV), in which the means of enhancing gas exchange is also antibacterial. During APV, the lungs are first filled with a perfluorocarbon (PFC) emulsion containing emulsified antibiotics. The PFC emulsion washes infected mucus from the lungs, enhances gas exchange, and delivers antibiotics directly to the infection. The bulk of the PFC evaporates within hours. The patient then receives nebulized PFC. This continues to enhance gas exchange while hastening extubation and transition to bilevel positive airway pressure ventilation (BiPAP). During BiPAP, we will continue to deliver nebulized PFC or PFC emulsion when antibiotic delivery is required. This technique should reduce the ICU stay, overall hospitalization, and medical costs. Our preliminary studies demonstrate that PFC emulsions provide respiratory support, mobilize respiratory mucus during a bacterial infection, and are bactericidal. We now propose to perform a clinically relevant 4-day treatment in a rabbit Pseudomonas aeruginosa infection model to examine the ability of the emulsion to treat the infection and enhance gas exchange.


Wearable Pulse Oximetry & Motion Sensing with 3D Printed Soft Electronics

PI: Carmel Majidi, Mechanical Engineering, cmajidi@andrew.cmu.edu
Adam Feinberg, Biomedical Engineering, feinberg@andrew.cmu.edu
Website: Majidi: https://www.cmu.edu/me/people/majidi.html
Feinberg: https://www.cmu.edu/engineering/materials/people/faculty/bios/feinberg.html

Executive Summary: Diabetics are at high risk for circulatory disorders that can interfere with wound healing and lead to cardiovascular diseases and neuropathies.Early detection and prevention can be dramatically improved with the aid of continuous, real-time monitoring of vitals like pulse rate and oxygenation.However, existing portable technologies for pulse oximetry are bulky and cannot be comfortably worn during sleep and daily activities. To enable 24/7 monitoring, the team will introduce a soft, lightweight pulse oximetric sensor that is custom-fitted to the foot and integrated into a compression sock with sensors for monitoring leg motion and a Bluetooth module for wireless connectivity.The sensing elements will be produced with a novel 3-D printer developed by the Regenerative Biomaterials & Therapeutics Group (PI: Feinberg) and incorporate stretchable circuit architectures pioneered by the Soft Machines Lab (PI: Majidi). Microfluidic wires or conductive fabrics will be used to connect the sensing nodes to a rigid body-mounted module that contains a microcontroller, wireless transceiver, antenna and battery.


Programmable Device for Optimal Non-Invasive Subcutaneous 2-D and 3-D Imaging

PI: Srinivas Narasimhan, Robotics Institute, srinivas@andrew.cmu.edu
Artur Dubrawski, Robotics Institute, awd@cs.cmu.edu
Website: Narasimhan: http://www.cs.cmu.edu/~srinivas/
Dubrawski: http://www.autonlab.org/autonweb/10223.html

Executive Summary: Existing commercial systems for subcutaneous imaging produce poor quality images, limiting their value in medical diagnosis and patient care.In this project, a prototype of a high quality non-invasive optical imaging device is being built to capture subcutaneous structures.Researchers are utilizing adaptive optics that dynamically modulate illumination and sensing to produce images and 3-D volumes with high contrast.Algorithms have been developed that optimize the lighting and imaging dynamically for every subject based on the individual’s anatomy (tissue thickness and properties, micro-vascular structure, etc.)


Intelligent Delivery of In-Home Hospice and Palliative Healthcare

PI: Zachary B. Rubinstein, Robotics Institute, zbr@cs.cmu.edu
Stephen F. Smith, Robotics Institute, sfs@cs.cmu.edu
Website: Rubinstein: http://www.cs.cmu.edu/~zbr/
Smith: http://www.cs.cmu.edu/~sfs/

Executive Summary: IDSHealthcare is working to provide real-time decision-support and scheduling for the efficient delivery of in-home hospice and palliative healthcare. The system is being designed to leverage dynamic scheduling technology together with two-way communication between the healthcare providers and the patients to provide efficient, cost-effective allocation of resources to patients and empower them throughout their case process. The project team is working to implement IDSHealthcare and integrate it into the communication and user-interface infrastructure of Celtic Healthcare, and will demonstrate the system’s feasibility and benefits by conducting a pilot at Celtic Healthcare to assist in the scheduling and management of care delivery for actual patients in Southwestern Pennsylvania.


Combining External and Implantable Sensors with Machine Learning to Detect Changes in the Health Status in Patients with Systolic Heart Failure

PI: Asim Smailagic, ICES, asim@cs.cmu.edu
Website: http://www.cs.cmu.edu/~./asim/

Executive Summary: Congestive heart failure is a leading cause of mortality, morbidity and hospitalization in the United States. The project team is developing and pilot testing instrumentation and data analysis software that alerts clinicians to patient decline well before the point that hospitalization is called for. The system will use external and implantable sensors to sample patient health parameters much more frequently than is possible during episodic patient-clinician encounters, and will apply modern analytics with predictive power to the resulting data streams. Clinician-facing data management and visualization interfaces will be well matched to clinical work-flow and thought processes.


Wearable Pulse Oximetry & Motion Sensing with 3D Printed Soft Electronics

PI: Carmel Majidi, Mechanical Engineering, cmajidi@andrew.cmu.edu
Adam Feinberg, Biomedical Engineering, feinberg@andrew.cmu.edu
Website: Majidi: https://www.cmu.edu/me/people/majidi.html
Feinberg: https://www.cmu.edu/engineering/materials/people/faculty/bios/feinberg.html

Executive Summary: Diabetics are at high risk for circulatory disorders that can interfere with wound healing and lead to cardiovascular diseases and neuropathies.Early detection and prevention can be dramatically improved with the aid of continuous, real-time monitoring of vitals like pulse rate and oxygenation.However, existing portable technologies for pulse oximetry are bulky and cannot be comfortably worn during sleep and daily activities. To enable 24/7 monitoring, the team will introduce a soft, lightweight pulse oximetric sensor that is custom-fitted to the foot and integrated into a compression sock with sensors for monitoring leg motion and a Bluetooth module for wireless connectivity.The sensing elements will be produced with a novel 3-D printer developed by the Regenerative Biomaterials & Therapeutics Group (PI: Feinberg) and incorporate stretchable circuit architectures pioneered by the Soft Machines Lab (PI: Majidi). Microfluidic wires or conductive fabrics will be used to connect the sensing nodes to a rigid body-mounted module that contains a microcontroller, wireless transceiver, antenna and battery.


Programmable Device for Optimal Non-Invasive Subcutaneous 2-D and 3-D Imaging

PI: Srinivas Narasimhan, Robotics Institute, srinivas@andrew.cmu.edu
Artur Dubrawski, Robotics Institute, awd@cs.cmu.edu
Website: Narasimhan: http://www.cs.cmu.edu/~srinivas/
Dubrawski: http://www.autonlab.org/autonweb/10223.html

Executive Summary: Existing commercial systems for subcutaneous imaging produce poor quality images, limiting their value in medical diagnosis and patient care.In this project, a prototype of a high quality non-invasive optical imaging device is being built to capture subcutaneous structures.Researchers are utilizing adaptive optics that dynamically modulate illumination and sensing to produce images and 3-D volumes with high contrast.Algorithms have been developed that optimize the lighting and imaging dynamically for every subject based on the individual’s anatomy (tissue thickness and properties, micro-vascular structure, etc.)


Intelligent Delivery of In-Home Hospice and Palliative Healthcare

PI: Zachary B. Rubinstein, Robotics Institute, zbr@cs.cmu.edu
Stephen F. Smith, Robotics Institute, sfs@cs.cmu.edu
Website: Rubinstein: http://www.cs.cmu.edu/~zbr/
Smith: http://www.cs.cmu.edu/~sfs/

Executive Summary: IDSHealthcare is working to provide real-time decision-support and scheduling for the efficient delivery of in-home hospice and palliative healthcare. The system is being designed to leverage dynamic scheduling technology together with two-way communication between the healthcare providers and the patients to provide efficient, cost-effective allocation of resources to patients and empower them throughout their case process. The project team is working to implement IDSHealthcare and integrate it into the communication and user-interface infrastructure of Celtic Healthcare, and will demonstrate the system’s feasibility and benefits by conducting a pilot at Celtic Healthcare to assist in the scheduling and management of care delivery for actual patients in Southwestern Pennsylvania.


Combining External and Implantable Sensors with Machine Learning to Detect Changes in the Health Status in Patients with Systolic Heart Failure

PI: Asim Smailagic, ICES, asim@cs.cmu.edu
Website: http://www.cs.cmu.edu/~./asim/

Executive Summary: Congestive heart failure is a leading cause of mortality, morbidity and hospitalization in the United States. The project team is developing and pilot testing instrumentation and data analysis software that alerts clinicians to patient decline well before the point that hospitalization is called for. The system will use external and implantable sensors to sample patient health parameters much more frequently than is possible during episodic patient-clinician encounters, and will apply modern analytics with predictive power to the resulting data streams. Clinician-facing data management and visualization interfaces will be well matched to clinical work-flow and thought processes.


A Novel Approach to Improve the Delivery and Reduce the Toxic Side Effects of Anticancer Nanodrugs by Treatment with Intralipid

PI: Chien Ho, Ph.D., Department of Biological Sciences, chienho@andrew.cmu.edu
Website: http://www.cmu.edu/bio/faculty/ho.html

Executive Summary: Nanotechnology-based drug delivery systems can specifically target tumors, providing new therapeutic approaches to cancer. A major challenge for translating nanodrugs to clinical applications is their rapid clearance by the reticuloendothelial system (RES), thus reducing their efficacy and increasing their toxic side effects. In preliminary studies, Dr. Ho and his team have found that, in rats, treatment with Intralipid, an FDA approved nutritional supplement, can reduce RES uptake ~50% and increase blood half-life ~3-fold of nanoparticles. The purpose of this project is to optimize the conditions for the use of Intralipid to improve the delivery and reduce the side effects of anticancer nanodrugs. Intralipid has been used for over 40 years as a safe source of parenteral nutrition for patients, so would readily translate to clinical use. The outcome of this study has the potential to decrease the toxic side effects of anticancer drugs, and therefore to reduce human suffering. Also, increasing efficacy could lead to reduction of the dosage of these expensive drugs: the average cost per dose is US$4,000-6,000. Thus, Dr. Ho’s work for the use of Intralipid with nanodrugs can also lead to reduction of healthcare costs. These findings are an example that an “old drug” can have new applications.


Secure Micro-RFID Validation of Medicines

PI: Larry Richard (Rick) Carley, carley@ece.cmu.edu
Electrical and Computer Engineering
Website: http://www.ece.cmu.edu/directory/department/faculty/C/Rick_Carley_22.html

Executive Summary: The need to prevent counterfeit drugs from being introduced into the legitimate supply chain is acute. The World Health Organization has said that counterfeit drugs represent more than 10 percent of global sales, and they are responsible for some thousands of deaths each year. Dr. Carley’s work will develop a microscopic RFID device that can be incorporated into drugs and that can be interrogated using RF signals to securely identify the drug, its production date, and its manufacturer. In addition, the RFID will be able to validate that the drug was not subjected to temperature extremes.


Search-assisted Early Melanoma Detection

PI: Mahadev Satyanarayanan, Computer Science, satya@cs.cmu.edu
Website: http://www.cs.cmu.edu/~satya/

Executive Summary: Early detection is a crucial aspect of improved melanoma survival. There is an unmet need for improved detection of early stage melanoma lesions by PCPs. Our goal is to create a cheap, easy to use software tool called DermShare that will assist PCPs in more accurately detecting melanoma. An early version of DermShare has been implemented. It is a web-based tool that can be run on a standard desktop, laptop or tablet with Internet connectivity in a physician’s office. Dr. Satya’s goal is to make DermShare easily integrated into the regular patient care workflow of a PCP, thus simplifying its regular use in clinical practice. To make DermShare as low-cost as possible, and as widely distributable as possible he has strongly leveraged open-source technologies. To date, nearly 100 person years of effort have been invested over a decade in the foundational open-source search technologies upon which DermShare rests. DermShare is already effective as a search tool for skin lesions. The proposed work will improve the user interface, search accuracy, and functionality, and lead towards a production-quality tool for clinical use.


Monitoring and Coaching to Promote Proper Asthma Inhaler Technique

PI: Alexander Hauptmann, School of Computer Science, alex+@cs.cmu.edu
Website: http://www.cs.cmu.edu/~alex/

Executive Summary: It is well documented that more than half of asthma patients have poor control, and studies show no improvements in asthma outcomes over a recent 10-year span. The main reasons for poor control include the failure to follow asthma treatment guidelines. Many physicians are unfamiliar with asthma treatment guidelines, and do not have sufficient time during an office visit to educate patients about the proper use of asthma medications. A key element in controlling asthma is good inhaler technique and many patients do not have sufficiently good technique to insure adequate lung delivery. This project proposes to develop automated methods to observe and monitor patients using metered dose inhalers, and coach them in proper inhaler use if appropriate. Observation will take place using an automated RGB+Depth camera system that identifies incorrect actions. Other camera systems, including smart phones will also be evaluated. Coaching is performed by an interactive system with friendly personal reminders and corrections to reinforce good treatment outcomes. If successful, these efforts will result in improvement in asthma control and a reduction of costs associated with asthma and other chronic obstructive pulmonary diseases.


Multi-Modal Impedance Detection of Orthopedic Implant Loosening and Biofilm Formation

PI: Jeffrey Weldon, CMU, jweldon@andrew.cmu.edu
Phil Campbell, CMU, philc@andrew.cmu.edu
Gary Fedder, CMU, fedder@andrew.cmu.edu
Lee Weiss, CMU, lew@andrew.cmu.edu

Website: Weldon: http://www.ece.cmu.edu/directory/department/faculty/W/Jeffrey_Weldon_5442.html
Campbell: http://www.ices.cmu.edu/phil-campbell.asp
Fedder: http://users.ece.cmu.edu/~fedder/
Weiss: http://www.ri.cmu.edu/person.html?person_id=336

Executive Summary: This project seeks to develop a multi-modal sensing technique to non-invasively detect biofilm formation on medical implants and/or implant loosening. The proposed solution measures both the mechanical and electrical impedances to sense changes at the interface between the implant and bone. The Centers for Disease Control and Prevention estimate that preventable infections cost approximately $40 billion annually with a significant fraction of this cost due to biofilms. Sequelae from orthopedic biofilm infections in knee and hip implants include poor patient outcomes and high health care costs. Early detection of infection and/or implant loosening can potentially ameliorate these effects. However, to date, early detection has proven to be a difficult problem. Multi-modal impedance analysis will be investigated as a method of early detection. Mechanical impedance will be analyzed with piezoelectric transducers and electrical impedance will use conventional electrodes. Preliminary studies indicate that a rigid bone/implant interface will present a significantly different mechanical impedance as compared to an interface intercalated with biofilm or a loose implant. A test device will be fabricated and a rat animal model will be used to investigate the utility of impedance measurements to detect biofilm formation and implant loosening.


Ortho Robotic Table

PI: Eric Meyhofer, NREC, meyhofer@nrec.ri.cmu.edu
Website: http://www.ri.cmu.edu/person.html?person_id=1637

Executive Summary: Engineers from National Robotics Engineering Center have been observing orthopedic procedures performed by surgeons Sotereanos, DeMeo, and Christoforetti from Allegheny Health Network at AGH and West Penn Hospitals. With the number of orthopedic surgeries increasing steadily, our goals were to identify ideas where robotics technologies can be applied into the orthopedic space to address problems of high costs and risk to patient safety. Manipulation and position-holding of the patient leg or arm remains a challenge during the orthopedic procedures. Existing tables and limb-support tools require multiple people to operate, have limited or no feedback display, and do not offer the speed and flexibility desired during surgery. NREC proposes the creation of a novel operating room manipulator arm that allows low effort positioning of the patient leg during orthopedic surgery. The robotic manipulator will be able support the patient leg at desirable positions and the surgeon will be able to move the leg to new positions with minimal effort. With the ability to hold the leg in desired position indefinitely, the clinicians will be able to focus on surgical activities. The manipulator will be instrumented to offer angle and force information relevant to the joint being operated upon.


Pre-Clinical Readiness Testing of Breast Palpation Aid for Home and Primary Care

PI: James F. Antaki, Biomedical Engineering, antaki@cmu.edu
Website: https://www.andrew.cmu.edu/user/antaki/

Executive Summary: Based on current incidence rates, one out of every eight women born in the United States today will develop breast cancer at some time during their lives). Despite advances in imaging technologies and clinical practice, breast cancer screening has shown an inconsistent impact in decreasing breast cancer-associated deaths while accumulating nearly $8bn in associated annual costs. This project aims to address the shortcomings in breast self-examination and mammographic screening practices by enhancing the roles of patient and primary care physicians in the breast screening process. We propose a cost-effective, sensitive, easy-to-use palpation aid, PalpAidTM, that visually differentiates healthy from diseased tissue based on mechanical stiffness. The proposed scope of work builds upon preliminary progress with a first-generation device to further develop a prototype suitable for clinical testing. The specific aims include: SA1: optimization of the PalpAid lens; SA2: a pilot clinical trial. Subsequent commercialization of PalpAidTM will target both clinical and home settings: both for initial screening and subsequent monitoring of palpable breast lesions. Successful employment of the PalpAidTM device would help educate and empower patients and reduce over-treatment of breast lesions through cost-effective monitoring in the home.



2014 Seed Funded Projects

Interactive Documentation of Clinical Evaluation and Management Visits

PI: Florian Metze, Computer Science, fmetze@cs.cmu.edu
Website: http://www.cs.cmu.edu/~fmetze/interACT/Home.html

Cloud-based Expert System for Personalized Pathogen Multidrug Treatment Using Combinations of Antibiotics, Probiotics, and Quorum Sensing Inhibitors

PI: Radu Marculescu, radum@ece.cmu.edu
Website: http://www.ece.cmu.edu/directory/department/faculty/M/Radu_Marculescu_109.html

Real-time 3D Position Tracking of Ultrasound Transducer and Arthroscopic Surgery Instrument for Rotator Cuff Tear Diagnosis and Repair

PI: Kenji Shimada, Mechanical Engineering, shimada@cmu.edu
Website: http://www.andrew.cmu.edu/user/shimada/

From Germ Theory to Germ Therapy in Chronic Wounds: Silver Dressing, Designer Synbiotics while Utilizing a SMarT Ecologically Safe Strategy

PI: Luisa Hiller, Biological Sciences, lhiller@andrew.cmu.edu
Website: http://www.cmu.edu/bio/faculty/hiller.html

Increasing Optimal Decision Making in End-of-Life Contexts via Targeted, Science-based Communication

PI: Baruch Fischhoff, Environment & Public Policy / Social & Decision Sciences, baruch@cmu.edu
Website: http://www.cmu.edu/dietrich/sds/people/faculty/baruch-fischhoff.html

Quick and accurate carbohydrate intake measurement for diabetes management using depth and color cameras

PI: Sebastian Scherer, Robotics Institute, basti@cmu.edu
Website: http://www.ri.cmu.edu/person.html?person_id=1397

Sustained Antibiotic Release Hydrogels for Revision Arthroplasty

PI: Richard Koepsel, ICES, rkoepsel@andrew.cmu.edu
Website: http://www.zoominfo.com/p/Richard-Koepsel/597307707

Discovering Anomalous Patterns of Care to Improve Health Outcomes and Reduce Costs

PI: Daniel B. Neill, Associate Professor of Information Systems, and Director of the Event and Pattern Detection Laboratory, H.J. Heinz III College, neill@cs.cmu.edu
Website: http://www.cs.cmu.edu/~./neill/


Enhanced Colonoscopy

PI: Yang Cai ycai@cmu.edu, CyLab
Visual Intelligence Studio
College of Engineering

Website: http://www.andrew.cmu.edu/user/ycai/index.html

Executive Summary: Colonoscopies should have the potential to dramatically reduce colon cancer rates and associated deaths. However, observed reductions in cancer rates do not fit with expectations and people who receive colonoscopies may still get colon cancer. Studies show that there are high polyp miss rates. The objective of this project is to develop video analytics software for standardizing the colonoscopy procedures and aid practitioners with real-time feedback during the procedure. Our approach includes digitizing, storing, and streaming video output from colonoscopies and developing Quality of Exam (QoE) matrices and algorithms, as well as the visualization algorithms to highlight polyps for improving detection during procedures. Dr. Yang Cai expects results will result in improvement in the exam quality, resulting in fewer expenses put toward colon cancer treatments. The tools developed from this project will potentially be deployed through a healthcare network. The technology could also be used to assist lower-level providers trained in colonoscopy.


Next Generation ECG and Machine Learning Software

PI: David Stager, NREC cop@cmu.edu
Eric Meyhofer, NREC meyhofer@rec.ri.cmu.edu
Neil Stegal, NREC nfs@cmu.edu
School of Computer Science

Website: Stager: http://www.ri.cmu.edu/person.html?person_id=296
Meyhofer: http://www.ri.cmu.edu/person.html?person_id=1637
Stegall: http://www.ri.cmu.edu/person.html?person_id=1848

Executive Summary: David Stager and Eric Meyhofer of National Robotics Engineering Center (NREC/CMU) will collaborate with Dr. Emerson Liu and Dr. Amit Thosani of Allegheny General Hospital (AGH) to develop the NextGen ECG: a portable ECG platform which employs high-resolution/high fidelity signal acquisition and modern signal processing techniques to better identify abnormal cardiac substrates, quantify presence of cardiac electrical instability, classify arrhythmias and risk-stratify for SCD. Dr. Stager’s group has enumerated various improvements into separate areas of development to include 1) extending the frequency band to include higher frequency data logging and analysis 2) increasing the number of electrodes for simultaneous beat-to-beat data sampling and 3) applying machine learning algorithms for automated detection and diagnosis of heart problems.


Anomaly and Pattern Detection in Medical Claims Data

PI: Jeff Schneider jeff.schneider@cs.cmu.edu
Robotics/School of Computer Science

Website: http://www.cs.cmu.edu/~schneide/

Executive Summary: Medical claims data is filled with mistakes, both intentional and unintentional, as well as opportunities to improve cost and reimbursement both by recognizing trends and causing changes. Dr. Schneider proposes to develop and apply machine learning algorithms to identify these phenomena. The algorithms will need to be statistically efficient because the number of hypotheses tested will be large but the tolerance for false positives will be limited. They will also need to be computationally efficient in order to sift through billions of records.

The research will proceed in three stages. First, methods of identifying anomalous mistakes and trends will be developed. Second, methods of assessing the utility of real and hypothetical changes will be developed to aid the prioritization of discoveries. Finally, supervised learning methods will be developed that take feedback from the user in order to learn and flag re-occurring patterns.

Dr. Schneider and his team will build on past expertise and experience in developing and deploying learning algorithms in disease surveillance and fleet health monitoring. If successful this effort will lead directly to commercialization in claims monitoring and can be extended to analysis of medical treatment practices.


Development of anti-biofilm surface coatings based on long-wavelength photosensitizers

PI: Aaron Mitchell, Biological Sciences, apm1@cmu.edu
Luisa Hiller, Biological Sciences, lhiller@andrew.cmu.edu
Frederick Lanni, Biological Sciences, lanni@andrew.cmu.edu

Website: Mitchell: http://www.cmu.edu/bio/faculty/mitchell.html
Hiller: http://www.cmu.edu/bio/faculty/hiller.html
Lanni: http://www.cmu.edu/bio/faculty/lanni.html

Executive Summary: Microbial biofilm growth on implanted medical hardware is a source of persistent infection in postoperative patients. For many reasons, biofilm cells are not cleared by the immune system or systemic antibiotics in these patients. This project focuses on suppression of the initial step of biofilm formation as it would occur in the post-op patient – the growth of adherent microbes on the surfaces of newly implanted medical hardware. The team’s approach is to develop a surface coating for implantable objects that contains a long-wavelength photosensitizer dye in non-releasable form. The photosensitizer is activated by light to generate toxic oxygen derivatives, and a single coating may be activated repeatedly by exposure to light. Dr. Mitchell and his team focus on photosensitizers that are excited by far-red light, because far-red light is capable of penetrating skin and musculoskeletal tissue. In practice in an immediate post-op setting, transdermal illumination will be used to activate the dye coating. However, because reactive oxygen generated by the photosensitizer is short-lived, toxic effects will be restricted to the interface region between hardware and tissue, precisely where biofilm initiation occurs. The proposed work will test the key features of photosensitized-surface biofilm suppression in culture conditions and in a biofilm infection model.


A Wearable System For Home-monitoring of Chronic Movement Disorders: Cost-effective Solution to Frequent Clinic Visits

PI: Jessica K. Hodgins, jkh@cs.cmu.edu
Fernando de la Torre, ftorre@cs.cmu.edu
Computer Science

Website: Hodgins: http://www.cs.cmu.edu/~jkh/
De La Torre: http://www.cs.cmu.edu/~ftorre/index.html

Executive Summary: There has been a large volume of research directed towards improving and building wearable technologies for assessing movement disorders. Most of them involve body-worn motion sensors like accelerometers. However, these cyber-physical systems are generally blind in the sense that they lack awareness of the context in which they are being used. In some cases, the motion profile of ordinary daily activities might match to those of major clinical symptoms (e.g, motion of hands while brushing teeth is similar to some involuntary movements in Parkinson’s Disease). An understanding of the semantic and functional context (what was the patient doing and what object he was interacting with) is required to differentiate between the two. The goal of Dr. Hodgins’ work is to couple ongoing advancements in wearable systems and statistical machine learning with state-of-the-art context based reasoning approaches. By advancing these areas of research and leveraging their complementary strengths, the team anticipates being able to construct robust systems for monitoring of patients with a variety of conditions. They believe that understanding context will provide the necessary clues for analyzing motion data and greatly simplify the task of reconstructing from sparse and noisy signals from sensors such as accelerometers. Conversely, those noisy signals will make reconstruction of the context easier.

This project is an attempt to marry computer vision and audio processing with learning-based human motion sensing systems. It aims improves the state-of-the-art of home monitoring systems and proposes to utilize multiple types of sensors (audio, video and motion) for context-aware processing. Dr. Hodgins’ team proposes to integrate wearable IMU based systems together with context reasoning algorithms to make them more effective for clinical purposes. The monitoring system, consisting of audio-visual and motion sensors will utilize novel modeling and machine learning algorithms for segmentation and activity classification/analysis. In order to address the uncontrolled nature of the daily living environments, they plan to develop novel weakly supervised learning algorithms that will learn visuomotor patterns from insufficient ground truth information.


Novel Therapy Targeting Food/Water Poisoning

PI: Adam Linstedt, linstedt@andrew.cmu.edu
Biological Sciences

Website: http://www.cmu.edu/bio/faculty/linstedt.html

Executive Summary: Enteric disease & diarrhea are globally significant health problems. A major fraction of this disease comes from food and waterborne disease caused by contaminating bacteria producing proteinaceous toxins. Indeed, Shiga Toxin (STx) producing bacteria of the Shigella genus and enterohemorrhagic E. coli (EHEC) species infect over 150 million individuals each year, cause over a million deaths and represent a global public health problem. The economic impact is also significant given that even the 100,000 EHEC cases diagnosed annually in the United States cost over $500 million. A recent outbreak of 3816 cases (including 54 deaths) in Germany originated from contaminated sprouts and resulted in 845 cases of costly and deadly hemolytic–uremic syndrome. Even a single bacterium infecting an individual can cause the disease. Currently, there is no definitive medical treatment for STx infections. The only recourse is rehydration therapy to support patients as they suffer chronic and bloody diarrhea often leading to fatal kidney failure. Antidotes for the toxin are not available and treatment of the bacteria with antibiotics is contraindicated because it is known to increase STx release and the development of lethal kidney disease.

Dr. Linstedt’s group will work to provide a therapy to combat Shiga toxicosis using the well-known metal ion manganese (Mn) either alone or in conjunction with antibiotics. Manganese is an essential nutrient and the fourth most widely available metal on earth. Its toxicology is well studied and, as a nutritional supplement, it is already approved for oral and intravenous use. The low cost and wide availability of Mn makes it amenable for use in developing countries where >95% of STx infections occur. Prolonged over-exposure to Mn can also cause health problems, but, as described in the next paragraph, we have shown that acute, non-toxic doses of Mn yield complete protection in cellular and mouse models against lethal STx challenges.



2013 Seed Funded Projects

Retinal Prosthesis for the Blind: Preclinical Electrical and Thermal Modeling

PI: Shawn K. Kelly, Institute for Complex Engineered Systems, skkelly@andrew.cmu.edu
Website: http://www.ices.cmu.edu/shawn-kelly.asp

Therapeutic Polymer Dressings for Chronic Wound Healing

PI: Kathryn Whitehead, Chemical Engineering & Biomedical Engineering, kawhite@cmu.edu
Website: http://www.cmu.edu/cheme/people/faculty/kathryn-a-whitehead.html

Drug Eluting Coils for Improved Treatment of Brain Aneurysms

PI: Christopher J Bettinger, Biomedical Engineering, cbetting@andrew.cmu.edu
Website: http://www.materials.cmu.edu/people/bettinger.html

Office-centered Three-dimensional Ultrasonic Imaging of Rotator Cuff Tears

PI: Kenji Shimada, Mechanical Engineering, shimada@cmu.edu
Website: http://www.andrew.cmu.edu/user/shimada/

Conformable Ultrasound Transducer for Diagnosis of Deep Vein Thrombosis

PI: David Greve, Electrical and Computer Engineering, dg07@andrew.cmu.edu
Website: http://users.ece.cmu.edu/~dwg/

Monitoring and Coaching to Promote Proper Inhaler Technique

PI: Alexander Hauptmann, Computer Science Department and Language Technologies Institute, alex@cs.cmu.edu
Website: http://www.cs.cmu.edu/~alex/

System for Semi-automated Minimally Invasive Myocardial Gene Transfer

PI: Cameron Riviere, Robotics Institute, camr@ri.cmu.edu
Website: http://www.ri.cmu.edu/person.html?person_id=248

Development of a rapid diagnostic tool for the detection and characterization of infections during surgery

PI: Marcel Bruchez, Biological Sciences, bruchez@cmu.edu
Website: http://www.cmu.edu/bio/faculty/bruchez.html

 


 







Contact Us

  Phone: 412-268-6920
  Email: Lynn M. Banaszak