Software Applications
Error Detection for Emergency Department
PI: Robert F. Kelly
EEDS (Error Detection for the Emergency Department System) is a system for the identification and prevention of errors in the Emergency Room. The system captures patient clinical data, through data entry or electronic feeds from other hospital systems, and then processes the data, using a collection or clinical rules. The clinical rules are stored as XML documents and are parsed to obtain rule objects. If a rule object identifies a potential error, the physician is alerted, along with other identified medical and administrative personnel. Corrective action is recommended, and the physician can remove the alert through a variety of actions. Prevented errors are stored and analyzed to help in the development of improvements to clinical processes. XML rules are also provided for the identification of patients suitable for clinical trials.
In this case, rules are supplemented with a questionnaire to further refine the inclusion and exclusion criteria. Identified patients are given the option of enrolling in the clinical trial. Clinical data is captured through interfaces with hospital systems and real-time monitors. The system includes a capability for a wireless connection to a medical monitor for capture of patient vital signs data. The research is supported by grants from the Emergency Medicine Foundation and from the US Department of Health and Human Services and the New York State Office of Science, Technology and Academic Research (NYSTAR).
Marine Science Data Capture and Display
PI: Robert Wilson
The project primarily provides for the selection and display of marine science data through a Web interface. Typical data includes water temperature, air temperature, solar radiation, and plankton levels and the regions covered include the Long Island Sound, Atlantic Ocean, Mediterranean Sea, Caspian Sea, and Aral Sea. Real-time data for the Long Island Sound is captured by sensors on a ferry crossing the Sound. Sensor data are transmitted via a wireless link to a ground station, for inclusion in the sensor database. Data display includes automatic generation of map data with integrated data display as well as date/time selection and data downloads. (NY Sea Grant, NSF)
Content-Driven Techniques for Non-Visual Web Access
PI: Y. Annie Liu
The World Wide Web has evolved into an indispensable medium for dissemination of information, entertainment, commerce and education. However, the graphical nature of most browsing software as well as the diversity and complexity of web content has limited access to this technology for an entire community of persons with visual disabilities. Existing audio browsers that are based on text-to-speech conversion (e.g. screen readers) are not capable of describing the conceptual organization of a document's content or of letting a user select parts of a document to listen to. As a result, persons with visual disabilities can find it difficult to understand the organization of documents (such as being able to distinguish topics, correlate similar items, etc.), and waste considerable time and attention listening to irrelevant information. This project is developing HearSay, a system that will bring the browsing experience of persons with visual disabilities closer to that of sighted people. HearSay will be based on automated techniques for structuring the content of web documents into labeled partitions consisting of logically related items. By enabling interactive speech-driven guided exploration, in which the system presents the document's labeled content, and the user selects which parts of the content to listen to and when to navigate to a new page, HearSay will make non-visual browsing far less cumbersome. Furthermore for repetitive browsing tasks, HearSay will let users create and retrieve personalized content in different ways, ranging from content-based voicemarking of selected partitions in a page to powerful personal information assistants that gather and present user-defined information at the user's command. The ability to browse the Web using alternative modalities as will be facilitated by HearSay, will offer significant benefits not only to users with disabilities, but also to mobile users of hand-held devices. (NSF)
Ad Hoc Command, Control, and Communication Networks for Homeland Security
PIs: Y. Annie Liu and Alex Mohr
Homeland security requires that military, law enforcement, emergency services, and other similar organizations be capable of coming together in an immediate and ad hoc manner to perform the necessary operational analysis, develop a common mission, and coordinate their common operational maneuvers and short-term logistic support. These requirements mandate that a joint tactical information technology (IT) infrastructure be available. This project aims to develop an information technology infrastructure that is able to integrate disparate and dispersed personnel, material and information resources in a robust, efficient and effective manner by means of ad hoc command, control and communication (C3) networks; and further to make it a framework into which legacy systems can be readily absorbed in order to maximize both its operational and economic measures of effectiveness. (Convergent Technologies Consortium)
Toxin Knowledge Base: Discovering Bioengineered Threats
PIs: Dr. Swaminathan Subramanyam, M. Kifer, I.V. Ramakrishnan
The technological developments in the recombinant DNA techniques have made it possible to produce pathogens, bioengineered pathogens and their products easily in large scales. The National Institutes of Health has prioritized select agents, which are the main targets for counter terrorism. But the possibility of producing genetically engineered pathogens or toxins present a different kind of problem for emerging threats. These may be chimeric protein molecules or benign molecules transformed into virulent proteins or toxin molecules, which could escape notice or detection. If these are used as biowarfare agents or as general bioterrorism agents, they will pose a threat to the Armed Forces and the general public. Is it possible to identify such bioengineered toxins? Is it possible to determine whether a given toxin or its active site could be incorporated into another protein which is otherwise non-toxic but homologous to biowarfare agents? Our proposal addresses this problem and will help in identifying potential and emerging threats and will provide tools to discover such threats. The long-range goal of this proposal is to develop and establish the present Toxin Knowledge Base (TKB) which will be a National resource and use it in conjunction with other available bioinformatics tools to identify homologs of toxins, and structural motifs of toxins and virulent factors in other proteins. (NIH)
LanguageMate – Language Interpretation Application for PDA and Tablet PC
PI: Rong Zhao
This is a joint project through the SPIR program with Transcendent International, a New York City-based startup company providing language services to government, healthcare, and social service agencies. For 14 million Americans who have limited English proficiency (LEP), obtaining adequate access to health care is a constant struggle. In New York City, by conservative estimate, about 200,000 school days are missed every year because children have to accompany their parents to hospitals and serve as interpreters. Hospitals, on the other hand, face a host of problems including legal liabilities, community and political pressures, and increased operating costs due to their inability to provide linguistically and culturally accessible care. The objective of this project is to design and develop a language interpretation software to bridge the language gap and we believe such a system will have positive impact on LEP persons, their families, and the healthcare system as a whole . This application will enable doctors and non-English speaking patients to communicate with each other in the absence of medical interpreters. To maximize the portability of the application, the design and implementation will ensure that the system can be deployed on various PDA platforms, including Palm and Pocket PC, as well as Table PC environment. This project is funded in part by the National Institutes of Health (NIH), and supported by several public and private hospitals in New York City. (Transcendent International / SPIR)
Wi-RAN Service Upgrades and User Interface Implementation
PI: Rong Zhao
This is a joint project with Best Mobile Computing, a local startup company focusing on developing wireless software products, through the SPIR program. Wi-RAN is a communication hub that has been deployed on several Hampton Jitney motorcoaches that run between New York and the east end of Long Island. Currently the Wi-RAN service provides paid internet access to Hampton Jitney passengers with a wireless laptop or a PDA. This communication hub has a wide range of potential uses for data communication to a moving vehicle. This project involves the design and development of the following functionalities:
a) vehicle tracking using real-time GPS coordinates;
b) video and security monitoring;
c) improvements in the data connection including transport efficiency and robustness of the connection; and
d) user interface improvements for the wireless users.
(Best Mobile Computing / SPIR)
Content Management Software Application Architecture Design and Development
PI: Rong Zhao
This is a joint project with FatWire Software, a leading-edge Long Island software vendor, through the SPIR program. This project involves helping FatWire Software to refactor their J2EE application infrastructure which is used by Fortune 500 corporations around the world for managing Web content, documents, and digital assets. The software contains a rules engine for dynamically delivering personalized content for sophisticated corporate Web sites. FatWire is planning an architectural overhaul of key application components ranging from database abstraction layer, programming library, database model, to user interface. The technology is based on J2EE and stores content in major third party relational databases such as Oracle, DB2 and Microsoft SQL Server. The goal of the project is to improve performance, usability and portability to multiple platforms. (FatWire Software / SPIR)
Workflow Design and Implementation for Automated Document Generation and Management
PI: Rong Zhao
This is a joint project with ZyDoc.com, a local technology company, through the SPIR program. ZyDoc performs medical transcription using handheld digital recorders, secure Internet transmission of voice and text files and a workflow including speech recognition and editing. In order to store, route, track and archive jobs, the company intends to design an information infrastructure that will interface with a workflow system for routing, tracking and management of the work. The scalable workflow system will be used to organize the data and direct files to and from the authors, speech recognition engines, editors and quality assurance workers and systems. The system securely routes and tracks the voice input from a variety of sources, such as telephone, in different formats. During the voice-to-text conversion process, the workflow interface tools to be developed in this project will allow control of many processes including the conversion of audio file formats, cleaning of audio signals, feeding them through speech recognition engines, routing them to secure FTP servers, and routing the resultant word processing reports. The workflow also incorporates version control and life cycle management of the voice and text data with reporting functions. (ZyDoc.com / SPIR)
Design and Development of Partner Online Enterprise
PI: Rong Zhao
This is a joint project with AppliedE, a local software development company, through the SPIR program. This project involves the architecture design and development of PartnerOnline Enterprise which creates a searchable archive of all forms of electronic communications such as emails, browsed Web contents, electronic forms, documents on desktops and handheld devices, instant messages, and RSS feeds. Assisted by its highly portable structure and automated, secure, and customizable archiving and searching mechanisms, this system can manage and ensure compliance with a wide range of regulations governing proprietary or protected information, such as Sarbanes-Oxley, HIPAA, and Patriot Act, with greater certainty and substantially less cost, time, and effort. This system also addresses another major issue with broad social and economic impact - data security. With over 85% of all corporate fraud originating from inside the corporation and identity theft on the rise, enforcing data security procedures and preventing data leakage has never been a higher priority. This system will be able to monitor and track access to sensitive data and issue warnings should inappropriate access, sharing, or removal of sensitive data occur. (AppliedE / SPIR)
VRM—Video Resource Management
PI: Rong Zhao
This is a joint project with Expedite VCS, a local video conferencing service provider and corporate partner of CEWIT, through the SPIR program. The primary goal of this project is to provide configuration, deployment, and management capabilities for video conferencing services. Once installed, it will enable small to medium business owners to manage their video conferencing systems without the need of any other software such as Web servers or database servers. The software is being designed using design patterns, component frameworks, point-to-point technology, and various cutting-edge software development methodologies. A full version and a light version will be developed to target different application domains. (Expedite VCS / SPIR)
Portable Forms Enhancement
PI: Rong Zhao
This is a joint project with Rovenet, a local wireless software development company and corporate partner of CEWIT, through the SPIR program. The primary goal is to enhance Portable Forms, Rovenet’s core product, which is a mobile Web service application which operates in a variety of modes including a client/server environment with thick clients on mobile devices including Palm and Pocket PC. In this project a new version of Portable Forms will be
developed for Blackberry handheld computers and other J2ME-based mobile cellular devices. (Rovenet / SPIR)
Automated Stereo Imaging System
PI: Rong Zhao
This is a joint project with inGenious Targeting Laboratory, a biotech company in the Long Island High Technology Incubator, through the SPIR program. This project involves research and development of a stereo image processing system for automatic monitoring and analysis of animal locomotion behavior phenotype. The focus of this project is the development of the post-processing module, which analyzes and identifies animal locomotion behavior by applying various data mining and pattern recognition techniques. (inGenious Targeting Laboratory / SPIR)
Information Technology Projects
PI: Wei Zhu
Information Technology is a broad subject, with applications and effects throughout the sciences, engineering, education, medicine, economy, the humanities, and society in general. IT deals with how we develop and use information, how we make sense of it, how we compute, and how we communicate and make decisions. In many cases, the scale and scope of opportunities and challenges require research approaches that cover many parts of the IT field and other areas. The research group has been striving to advance bioinformatics and their applications in biomedical research and services with the following on-going efforts. (Various)
1) Proteomics – We have been developing proteoExplorerTM, a comprehensive spectrum analysis software platform that will achieve thorough analysis, visualization and comparison of proteomic mass spectra (e.g. serum protein spectra) from several populations (e.g. diseased and disease-free subjects). Our system will identify the optimal or near optimal subset of biomarkers that can achieve maximum separation between the groups. These biomarkers are candidates for the subsequent biological examination that could potentially reveal protein-disease pathways, and for disease diagnosis and treatment evaluations. (SUNY)
2) Genetics – We have been developing ViStaMSTM, a comprehensive genetics data analysis software platform that will achieve thorough analysis and visualization of SAGE and microarray data from several subpopulations and/or different disease/treatment stages. Our system will identify the presence or absence of certain genes/tags, perform patient/disease/treatment profiling and, correlation analysis between microarray data and SAGE data. Our software aim to discover gene-disease pathways and determine the effectiveness of the treatments. The ultimate goal is to help establish the individualized treatment regime according to each patient’s physique/genetic profile. (Foster Foundation)
3) Optimal Designs – We are establishing a website (http://ptolemy.ams.sunysb.edu/doe) containing resources for generating all types of optimal designs for lots of useful models in biomedical studies and clinical trials. There will be FAQ, pointers and online assistance to guide visitors throughout the design process. Our site also provides links to other websites, where design software related to optimal design issues is available. For instance, sites that have on-line software for power and sample size calculations
(www.statsol.ie/nquery/nquery.htm) & (www.stat.uiowa.edu/~rlenth/Power/)We also plan to include a module which allows users to simulate data based on different designs and to investigate how different designs perform in a simulation. This will provide a direct link between the design and the subsequent data analysis. (NIH)
4) Brain Pathway Analysis – The ultimate goal of brain connectivity studies is to propose, test, modify, and compare certain directional brain pathways. With funding from the Brookhaven National Laboratory, we have been developing a novel unified SEM/GLM method, for the analysis of effective brain connectivity. This method enables the unified structural equation modeling (SEM) of multi-subject, multivariate time-series functional magnetic resonance imaging (fMRI) data with subject level covariates. Specifically, this is done by modeling the longitudinal and the contemporaneous relations in the same SEM, analyzing this unified SEM for each subject separately and then merging the resulting individual path parameters with other subject-level covariates such as gender, age, IQ, and education etc. for the final general linear model (GLM) analysis to examine the influence of these covariates on the path model. An additional merit of our approach is that researchers can now use any of the widely available traditional SEM software such as LISREL, EQS and SAS to analyze autocorrelated brain functional data — a task not tenable previously. This in turn, will boost the brain pathway analysis activities tremendously among the entire brain research community. (BNL)
5) Web-Based Database – We are establishing a web-based database for the NYU Silberstein Alzheimer’s Disease Center (ADC). Such website will not only enhance the information exchange between NYU and the other thirty NIH-funded ADC’s throughout the country, but also help educate the entire community on the disease and its treatment. We will post up-to-date summary statistics and other data analysis results and findings from our database so our current/future patients, their families, and the entire community can have easy access to such information. The community can also provide their feedbacks through a web-based discussion forum. (NIH)
Continuous Medical Monitoring with Wireless Sensor Networks
PI: Ki Chon, Co-PIs: Samir Das, Himanshu Gupta & CR Ramakrishnan
In this project, faculty from Biomedical Engineering and Computer Science collaborate on continuous medical monitoring of patients using wireless-equipped micro-sensors. The goal is to develop platforms so that such monitoring can be done in an unobtrusive fashion in any setting – in hospitals, nursing homes, elderly care centers, medical triages, or even at homes. Our work will be particularly useful for people suffering from chronic conditions where continuous, low-cost monitoring is desired without affecting daily routines significantly. Regardless of the setting, the goal is to generate medically meaningful alerts for impending medical emergencies without requiring continuous attention of trained medical professionals.
Our medical monitoring system consists of four main components:
1) sensors
2) wireless motes with a small processor that can gather samples, perform any preliminary processing and communicate the samples
3) a real-time streaming database with long-term storage capabilities
4) a signal processing system with inference engine
In the basic form, the sensors sample physiological data (e.g., EKG, EEG, pulse oximetry, respiration, etc) from a subject and send it to attached motes with wireless communication ability. Other than physiological sensors, we will also use sensors that detect movements, pose, etc anticipating that they can provide useful information about the subject’s functions that can correlate with certain medical conditions. The motes relay the data to the central database to be used by the signal processing system and inference engine. The data to be relayed could be the raw samples or semi-processed or compressed data depending on the characteristics of the signal and available bandwidth in the motes.
The sensors and a set of motes will be worn by the subject. Due to battery power limitations, the motes have short radio ranges. Thus, multihop relaying in an “ad hoc network” will be necessary to route the data to the database/inference engine. Such motes will be pre-deployed to cover the area the subject may move around. Wide-area wireless links (e.g., using a cellular telecom system or even a wi-fi-based system) will be used possible when such coverage may not be available.
The following 4 research directions will be pursued in an inter-disciplinary context.
1) Wireless communication/networking
2) Collaborative sampling
3) Signal Processing/Inference Engine
4) Streaming Database
(NIH)