Sondra R. Renly

Information technology for healthcare transformation

Rising costs, decreasing quality of care, diminishing productivity, and increasing complexity have all contributed to the present state of the healthcare industry. The interactions between payers (e.g., insurance companies and health plans) and providers (e.g., hospitals and laboratories) are growing and are becoming more complicated. The constant upsurge in and enhanced complexity of diagnostic and treatment information has made the clinical decision-making process more difficult. Medical transaction charges are greater than ever. Population-specific financial requirements are increasing the economic burden on the entire system. Medical insurance and identity theft frauds are on the rise. The current lack of comparative cost analytics hampers systematic efficiency. Redundant and unnecessary interventions add to medical expenditures that add no value. Contemporary payment models are antithetic to outcome-driven medicine. The rate of medical errors and mistakes is high. Slow inefficient processes and the lack of best practice support for care delivery do not create productive settings. Information technology has an important role to play in approaching these problems. This paper describes IBM Researchs approach to helping address these issues, i.e., the evidence-based healthcare platform.

Public health affinity domain: a standards-based surveillance system solution

The negative impact of infectious disease on contemporary society has the potential to be considerably greater than in decades past due to the growing interdependence among nations of the world. In the absence of worldwide public health standards-based networks, the ability to monitor and respond quickly to such outbreaks is limited. In order to tackle such threats, IBM Haifa Research Lab and IBM Almaden Research Lab developed a PHAD implementation which consists of an information technology infrastructure for the public health community leveraging the Integrating the Healthcare Enterprise (IHE) initiative and important standards. This system enables sharing of data generated at clinical and public health institutions across proprietary systems and political borders. The ability to share public health data electronically paves the way for sophisticated and advanced analysis tools to visualize the population health, detect outbreaks, determine the effectiveness of policy, and perform forecast modeling.

Accelerating investigation of food-borne disease outbreaks using pro-active geospatial modeling of food supply chains

Over the last decades the globalization of trade has significantly altered the topology of food supply chains. Even though food-borne illness has been consistently on the decline, the hazardous impact of contamination events is larger [1-3]. Possible contaminants include pathogenic bacteria, viruses, parasites, toxins or chemicals. Contamination can occur accidentally, e.g. due to improper handling, preparation, or storage, or intentionally as the melamine milk crisis proved. To identify the source of a food-borne disease it is often necessary to reconstruct the food distribution networks spanning different distribution channels or product groups. The time needed to trace back the contamination source ranges from days to weeks and significantly influences the economic and public health impact of a disease outbreak. In this paper we describe a model-based approach designed to speed up the identification of a food-borne disease outbreak source. Further, we exploit the geospatial information of wholesaler-retailer food distribution networks limited to a given food type and apply a gravity model for food distribution from retailer to consumer. We present a likelihood framework that allows determining the likelihood of wholesale source(s) distributing contaminated food based on geo-coded case reports. The developed method is independent of the underlying food distribution kernel and thus particularly applicable to empirical distributions of food acquisition.

Improving disease surveillance capabilities through a public health information affinity domain

In March 2009, deaths from influenza like illness began to mount in Mexico and the United States. In April, the National Respiratory Disease Institute [1] reported a 100 percent increase in patients checking in for atypical pneumonia. Samples were sent to laboratories in Canada and the United States. On April 17, a national influenza alert was announced; on April 23, the new influenza virus was officially recognized [2]. In Mexico City, where a three week surge of influenza accounted for 90,000 visits in 220 health units and 20 hospitals [3], Mayor Marcelo Ebrard ordered the temporary closure of schools and commercial establishments. In response to the pandemic, IBM collaborated with the Ciudad de México Gobierno del Distrito Federal Secretaria de Salud del Distrito Federal (Secretaria de Salud of GDF) [4] on software to standardize influenza reporting and improve situational awareness [5]. Secretaria de Salud of GDF installed IBMs Public Health Information Affinity Domain (PHIAD) that uses Health Information Exchange technology and standards to enable rapid data sharing of clinical surveillance data with public health officials [6]. De-identified 2009 H1N1 positive laboratory results from the Institute of Epidemiological Reference and Diagnosis [7] were provided by the Secretaria de Salud of GDF for import into PHIAD; each record was transformed into a standard Integrating the Healthcare Enterprise XD-LAB document. The standardized data was analyzed with Spatiotemporal Epidemiological Modeler (STEM), an open source software framework for infectious disease modeling and forecasting [8, 9]. Using STEM, we made quantitative measures of the policy effects of school and commercial closures in Mexico City on the transmission rate of the 2009 H1N1 virus.