Dr. Amit Sheth
Amit P. Sheth
Founding Director, AI Institute@UofSC
NCR Chair and Professor, Computer Science & Engineering
Key Outcomes in HCLS

Key Outcomes in HCLS

My efforts in developing and applying technologies to empower real world outcomes in biomedical research and clinical practices

A Low-Cost Web-Based Tool for Pediatric Echocardiographic Consultation (with Echocardiologists at Medical college of Georgia) [1998-2000]

Connecticut State-wide Immunization Tracking, Eligibility Referral, Neonatal Clinical Pathways, GeneFlow [1996 – 2003]. Connecticut State-wide Immunization Tracking in more detail.

Collaborative TeleConsulting for HealthCare (CaTCH) [1997 – 1999]

IntelliGEN: A Distributed Workflow System for Discovering Protein-Protein Interactions [2000-2003]

Semantic Technologies

Biomedical and translational research as well as clinical practice are increasingly data driven. Activities routinely involve large number of devices, data and people, resulting in the challenges associated with volume, velocity (change), variety (heterogeneity) and veracity (provenance, quality). Equally important is to realize the challenge of serving the needs of broader ecosystems of people and organizations, extending traditional stakeholders like drug makers, clinicians and policy makers, to increasingly technology savvy and information empowered patients. With a wide variety of collaborators in informatics and in application domains, I have used semantics as the centerpiece of informatics solutions that convert data into meaningful, contextually relevant information and insights that lead to optimal decisions for translational research and 360 degree health, fitness and well-being.

Following are some snapshots of efforts in which semantic approach and technology is the key enabler. These are chosen to highlight real-world and in-use projects, technologies and systems, involving significant collaborations between my team and biomedical researchers or practicing clinicians.

  • Active Semantic Electronic Medical Record (ASEMR: demo,paper): This system deployed at Athens Heart Center and its partners since 2006 uses automatic semantic annotation with respect to three ontologies, and rule-based EMR quality and error alert system, leading to higher quality EMRs, fewer errors and time saving in clinical practice.
  • Semantics and Services enabled Problem Solving Environment for T.cruzi (SPSE): Development of open source ontologies, extraction and annotation using ontologies, domain-specific (semantic) provenance and their application to identification of interventional targets. In collaboration with Center for Tropical and Emerging Global Diseases at UGA, and NCBO.
  • Data Mining of Cardiology data: Data driven knowledge acquisition for domain knowledge enrichment leading to comprehensive cardiology ontology development, its use in finding and correcting NLP processing errors of EMRs, and development of a commercial semantic search engine in collaboration with ezDI supporting core measures and other key challenges and opportunities related to the Affordable Healthcare Act.
  • Semantic Search, Browsing and Literature Based Discovery: A semantic search and browsing technology embodied in Cuebee, Doozer, SCOONER and iExplore tools provide ability to harvest and utilize extensive background knowledge for semantic search and contextual browsing to provide insights from scientific literature. SCOONER was used by AFRL biomedical researchers in human performance and cognition. A recent work with NLM has demonstrated recovering and decomposing Swanson's Raynaud Syndrome-Fish Oil Hypothesis semi-automatically.
  • PREscription Drug abuse Online Surveillance and Epidemiology (PREDOSE): development of semantic techniques and tools for analyzing user generated content on social media related to the illicit use of pharmaceutical opioids, that recently led to discovery of Extra-Medical Use of Loperamid. In collaboration with Center for Interventions, Treatment and Addictions Research (CITAR) at WSU.
  • kHealth: development of a knowledge-enhanced sensing and mobile computing applications (using low cost sensors and smartphone), along with ability to convert low level observations into clinically relevant abstractions or actionable information that include risk and vulnerability measures. Ongoing research and evaluations are in educing preventable ADHF readmissions (in collaboration with Ohio State Wexner Medical Center), proactive asthma in children (with Dayton Children's Hospital), reducing readmission of GI surgery patients (VA hospital) and predictive preventive and personalized care of dementia patients (with Dept. of Geriatrics, WSU Boonsoft School of Medicine).

Healthcare innovations at Kno.e.sis from Amit Sheth
"This talk summarizes some of my projects at Kno.e.sis on clinical and healthcare applications, and health informatics including consumer health behavior and social media use in healthcare."

Amit Sheth, "Semantic technology empowering real world outcomes in biomedical research and clinical practices", invited talk at Case Western Reserve University, November 26, 2012.

Ora Lassila and Amit Sheth, "Semantic Web for 360-degree Health: State-of-the-Art & Vision for Better Interoperability", Invited Talk at ONC-HHS Invitational Workshop on Next Generation Interoperability for Health, Washington DC, January 19-20, 2011.

Amit Sheth, "Semantic Web for Health Care and Biomedical Informatics," Keynote at NSF Biomed Web Workshop, Corbett, Oregon, December 4-5, 2007.

Amit Sheth's Keynote at Semantic Web Technologies for Science and Engineering Workshop (held in conjunction with ISWC2003), Sanibel Island, FL, October 20, 2003.
Professor Amit P. Sheth
Artificial Intelligence Institute
Department of Computer Science & Engineering
University of South Carolina