The focus of my research has been to develop new technologies that expand
the scope of medicine and increase the diagnostic capabilities of physicians
at the point of care. My specific research
interests include clinical decision support systems, clinical data mining,
clinical image processing, emergency preparedness, and personalized medicine.
Students and Post-Docs Who Want to Work in My Research Group
Great! I would love to see how we can work
together. Please contact me if you are already a
student, resident, or
facutly at the University of Maryland School of Medicine, UMB, UMBC,
College Park, or elsewhere in the University of Maryland system.
However, if you are not currently a student or post-bacc, and are
looking for an appointment at the University of Maryland, I
unfortunately can't help you, and have no information about paid or
volunteer positions. Instead, please follow the admissions process at
the University of Maryland.
Miguel Ossandon, 2009, PhD Student, visual sensory
Xianshu Zhu, 2009, MS Student, clinical image processing
Dashana Dalvi, 2009-2010, MS Student, clinical image
- David Chapman, 2010, PhD Student, clinical image processing with semantic
metadata in cell biology
- Justin martineua, 2010-2011, PhD Student, clinical image processing with
semantic metadata in cell biology
Ronil Mokashi, 2009-2011, MS Student, clinical image
processing with semantic metadata in cell biology
Ashwini Lahane, 2010-2011, MS Student, Thesis Committee,
clinical image processing
Ronil Mokashi, 2011, MS Student, Thesis Committee,
clinical image processing
Dashana Dalvi, 2011, MS Student, Thesis Committee,
genomic prediction of type 2 diabetes
Aniket Bochare, 2011-2012, MS Student, Thesis Committee,
domain knowledge and genomic prediction
Ronil Mokashi, 2011-2012, MS Student, Thesis Committee,
genomic association and machine learning
Zachary Kurtz, 2012, MS Student, Thesis Committee,
simultaneous feature and cost estimation
Eduardo Llamas, 2012, MS Student, Thesis Committee,
extraction of drug-gene relationships
Soma Das, 2011-2012, MS Student, Thesis Advisor, genomic
prediction of coronary artery disease
Matthew Gately, 2011-2012, MS Student, Thesis Advisor,
Isaac Mativo, 2012, Thesis Advisor, personalized medicine
Current Research Projects
Personalized Medicine and Big Data Applied to Clinial Decision Support.
Although intuitive, the addition of genetic information to increase the
accuracy of disease prediction remains an unproven hypothesis. We are
experimenting with supervised learning methods, which combine clinical and
gentic information, in order to increase the accuracy of disease-predition
algorithms. We recently developed new disease prediction algorithms using
machine learning techniques that combine clinical and genomic data. We are
leading a four-campus research team, which is applying these new algorithms to
several large clinical and genomic repositories, including data from VINCI,
GENEVA, and the Million Veteran Project. Specifically, we are looking at
factors that predict coronary artery disease and type 2 diabetes in
pre-symptomatic individuals, predict critical events associated with these
conditions, and predict the efficacy of various treatment options. This type
of research will lead to personalized therapies based on an individual’s
genetic and clinical characteristics.
Syndromic surveillance is a process used for the early detection and
monitoring of disease outbreaks attributable to biologic terrorism or natural
causes. We are developing a new approach to syndromic surveillance by applying
machine learning algorithms to both clinical data and social media.
Image Classification with Semantic Metadata in Cell Biology
Computational image classification is growing in importance in various
fields, including cell biology. We propose to develop a database that can
store images along with computer-extracted image features, and correlate these
features to metadata that captures biological or clinical characteristics. Our
initial focus is on the actin and myosin cytoskeleton. We are developing an
image classifier using a support vector machine to map image features to
biological characteristics. We are using the Oracle Relational Database
platform to leverage its ability to handle both multimedia and semantic data
efficiently. We are using a W3C semantic web approach to develop the ontology
for the biological characteristics.
Video Summarization for Laparoscopic Surgery
Laparoscopic surgery is a minimally
invasive technique that is the method of choice for a number of surgical
procedures. Patients who undergo laparoscopic surgery have smaller
scars, reduced pain, and a quicker recovery. The laparoscopic approach,
however, is more technical challenging and has more demanding training
requirements. Our overall goal is to develop a software tool to assist
with video-based assessment of surgical trainees. We are developing an
image classifier using machine learning approach to segment surgical
videos into their basic steps, perform time and motion
analysis, and provide a set of tools for review and
Wireless capsule endoscopy is used to directly visualize parts of the small
intestine previously unreachable by colonoscopy or upper endoscopy. As the
capsule travels through the digestive system, it collects in excess of 50,000
images, which must be reviewed by a gastroenterologist. We are developing machine learning
and image classification techniques to detect common lesions found in capsule
Intelligent Software Agents for Disaster Management
An agent framework is being developed for the Department of Homeland Security to
support a peer-to-peer network of disaster responders using the
Unified Incident Command and Decision Support (UICDS) platform. This is a
middleware foundation that enables commercial and government incident management
technologies to share information and support decisions for the National
Response Framework and National Incident Management to prevent, protect,
respond, and recover from natural, technological, and terrorist events.
Virtual Reality Simulation for Medical Education
environments such as Second Life are known to influence behavior. Learners
become immersed in their own education through three-dimensional realism,
role-play, and community interaction. We are using this approach to educate
people about specific medical issues and to virtually experience the benefits
and consequences of their behaviors. The educational areas we are working on
include diabetes and cancer prevention.
Personal Health Records
Personal Health Records (PHR) are health
records that are initiated and maintained by individuals. Examples of web-based
records include Google Health and Microsoft HealthVault. Issues related to PHRs
include trust, privacy, security, portability, mobility, medical identify theft,
fidelity and completeness of the medical record, and the ability to interface
with hospital-based and other clinical systems.
Past Research Projects
A Computerized Approach to Glycemic Control
Lessons learned from prior efforts were used to design an optimal approach
to computerize insulin protocols for critical care and general medicine
patients that better fits into the existing physician workflow.
Identification and Analysis of a TSH-Associated SNP
An analysis of a TSH-associated SNP was performed to help identify which
gene/variant was the most likely functional unit.
- Ventricular Assist Devices and Gastrointestinal Bleeding
A retrospective analysis of consecutive VAD recipients found that age was
the only independent predictor of gastrointestinal bleeding, and that
nonpulsatile VADs were not associated with an increase in gastrointestinal
bleeding versus there pulsatile counterparts.
Efforts to Minimize Adverse Events by Cross-Covering Physicians
An analysis of process improvement efforts regarding on the transfer or
care was performed, and a software framework was developed to increase the
accuracy and safety of this process.
Medical Response to Terrorist Attacks and Other Disasters
A redundant communication framework was developed to mobilize medical
personnel and transfer information during a medical disaster.
- Clinical Trials Data Collection Using Palm Computers
A handheld data collection system was developed to update and validate
clinical information obtained at the bedside or in the field.
- Voice-Driven Pathology Data Management System
A voice-driven system was developed to collect clinical data in hands-busy
and eyes-busy environments.