Tanveer Syeda-Mahmood Almaden Research Center 
  Healthcare Informatics  
  Almaden Computer Science

Research Projects

AALIM (Advanced Analytics for Information Management) (2005-2009)

Diagnostic decision support is still very much an art for physicians in their practices today due to lack of quantitative tools that provide clinicians with a consistent view of the patient's history as well as comparing this history to that of other patients with similar disease profiles. By gathering consensus opinions from other physicians who looked at similar patients, clinicians can get a refined insight into the patient's diagnosis and the potential effectiveness of different treatments and outcomes.

AALIM is a new multimodal mining-based clinical decision support that brings together patient data captured in many modalities including ECG, Echocardiograms, textual reports, and structured electronic medical records to provide a holistic presentation of a patient's exam data, diseases, and medications. In addition, it offers disease-specific similarity search based on the various modalities and presents statistical reports summarizing possible diagnoses, their associated medications, and other demographic information.

Systems like AALIM can in the long run lead to improved quality of care offered to patients. They can also help flag potential discrepencies created due to diagnosis propagation errors from raw patient data to what is entered in EMR systems. Finally, they can help in cohort selection for clinical trials and epidemological studies. The AALIM system is currently undergoing clinical validation in a major Bay area healthcare provider's Cardiology department.

ODySSy (On-demand stethoscope system) (2008-2009)

With the rising cost of healthcare of chronically ill patients, more and more healthcare providers are looking for solutions in which important patient data can be collected in a remote fashion while the patients remain at home.

The type of data that can be sent remotely is usually limited to those measurements that can be taken easily by patients without training (eg. Clip on a finger, press a button on a device, etc. An important data that is not yet possible to monitor remotely is auscultation data. Auscultation, the act of listening for sounds made by internal organs through stethoscopes, is a common exam performed in physician’s offices. It is often used as a simple diagnostic procedure to listen for abnormal sounds such as heart murmurs, gallops, and fast heart beats in the circulatory system

ODySSy is an on-demand stethoscope system (ODySSY) for relay of auscultation sounds recorded by stethoscopes to remote servers through 802.11 wireless networks. The system also offers easy ingest of sound data into electronic medical record systems (EMR) and remote viewing and listening of auscultation sounds through web portals.

GEM: Gene Expression Miner tool for Bioinformatics (2002-2005)

GEM is a suite of tools for mining time-varying gene expression data. Among the mining algorithms offered in GEM are algorithms finding salient changes in time series, order-preserving clustering of time series, and for detecting functional dependencies and deviations for raising alerts.

FormPad: A camera-assisted digital notepad (2004-2005)

FormPad is a new digital notepad device for automated electronic conversion of hand-filled forms without the need for scanning. The device is a camera-assisted writing tablet that recognizes the form and recovers the necessary geometric transformations to align the tablet coordinates with corresponding entries on the electronic form. This allows for automated metadata extraction for hand-filled forms without the need for handwritten OCR. FormPad is a cheaper alternative to tabletPC for point-of-care recording of patient data and has potential applications in Physician order entry systems and routine insurance form filling in healthcare.

MineLink: Pattern discovery middleware for bioinformatics information integration (2002-2004)

Now that the human genome has been sequenced, a greater challenge faces the scientists: to extract, analyze and integrate the information being populated in genome databases world-wide for improved diagnosis and cure of diseases. With progress in Genomics, scientists have also begun to ask queries that often span more than one data source and/or one or more analytic components. To satisfactorily address the needs of scientists, an information integration framework is needed that can pull together both life sciences data and analytic applications from disparate sources.

MineLink is a novel federated information integration framework that is designed to address the data and analysis needs of the scientists. It specifies a design methodology for automatically integrating individual components, be they data sources, processors, data miners or visualization components without the need for explicit programming. It addresses both syntactic and semantic aspects of information integration through the introduction of a generalized schema as an abstract data type for communication between components and a concept connectivity graph for the specification of semantic integration of components that is learned automatically through examples. It combines state-of-the-art service composition techniques of distributed computing with active feedback on the ease-of-use from scientists in Life Sciences.

MineLink started out in bioinformatics but its applications have been found in diverse areas such as automated warehousing, automatic service composition, business process modeling, and ETL. MineLink is a general pattern discovery middleware for information integration that achieves seamless data and application integration through semantic relationship discovery between generic schemas. MineLink is described in our ISMB'03 paper.

  Privacy | Terms of Use | IBM Home | Almaden Home | Research Sites | Page Contact