A view from the Center

Deloitte's Life Sciences & Health Care Blog

NIH analyzes use of data analytics to improve infectious disease surveillance

The last decade has seen an explosion of health care data – from increasingly sophisticated electronic health records and the growth of digital health to connected devices and social media. Data analytics has been touted as a solution to many challenges in health care, if stakeholders can appropriately harness the right data at the right time. The National Institutes of Health (NIH) recently published an analysis of the role of data analytics in infectious disease surveillance in a series of articles in a supplement to the Journal of Infectious Disease. The analysis featured several examples of innovative surveillance models. It also cautioned that non-traditional infectious disease data may lack key demographics and information on certain populations, some sources are unstable due to funding and other issues, and all sources must be validated.

Leading authorities in epidemiology, computer science, and modeling collaborated on the series. The articles feature opportunities and challenges associated with different types of data, including medical encounter files (e.g., records from healthcare facilities and claim forms), crowdsourced data collected from volunteers who self-report symptoms in near real time, and data generated by the use of social media, the internet, and mobile phones.

Examples featured include:

  • ResistanceOpen: An open-collaboration database that serves as a global map of antimicrobial resistance based on aggregated publicly available and user submitted resistance data from laboratories, hospitals, health networks or surveillance networks. Antibiotic resistance values displayed are based on weighted averages from all resistance indices (from the most recent available year) from all sources within the region of interest. Users can type in their zip code and find stats about antibiotic resistant superbugs in their area.
  • epiDMS: A novel epidemic simulation data management system developed by researchers to collect massive amounts of information on previous epidemics into a readable format so that public health decision-makers can find and compare similar epidemics.
  • Influenzanet: A network that monitors the activity of influenza-like-illness in Europe with the help of volunteers via crowdsourcing. Volunteers self-report symptoms on a weekly basis using standardized online surveys. It is operational in eleven countries. Influenzanet collects its data directly from the population to create a fast and flexible monitoring system whose uniformity allows for direct comparison of illness rates between countries and now includes information on Zika and salmonella.

While traditional infectious disease surveillance based on laboratory tests and other data collected by public health institutions is the gold standard, this type of surveillance is not in real time, can be costly, and can make accurate monitoring challenging at the local level. In contrast, big data streams from internet queries are available in real time and can track disease activity locally. However, they can be biased. The authors say that tools that combine traditional surveillance and big data sets may provide viable solutions to advancing global infectious disease surveillance. The next step in advancing the field is to compare validated data sets in high-income countries to models in low-resource settings where traditional surveillance is sparse.

Analysis: In the US, federal, state, and local governments are continually working to improve infectious disease surveillance and management. Becoming an intelligent, responsive, and adaptable health care system calls for collaborative development of policies and updated workflows and optimization of data collection and sharing. Early warning signs of new or changing diseases come from a variety of sources, from traditional health care data sources such as clinics and facilities, to spikes in over-the-counter medication purchases, reduced public transit usage, Internet searches, weather events, and even sources such as childcare centers. Data analytics capabilities could encompass a broad range of data to give health officials a clearer sense of potential threats in the US and around the world.

Source: NIH New Releases, “NIH-led effort examines use of big data for infectious disease surveillance,” November 14, 2016

This weekly series explores innovative breakthroughs and new technologies that are driving momentum and change in the life sciences and health care industry.


Author bio

Doug leads Deloitte Consulting LLP’s Life Sciences and Health Care practice. With 24 years of experience, he works closely with multiple top health care organizations on major clinical and enterprise transformation efforts and on large-scale technology implementation projects. Doug has extensive experience in comprehensive quality and patient safety transformations, turnaround and performance improvement in academic medical centers as well as organization/workflow redesign and technology enablement. He has served as the lead on a number of enterprise transformation initiatives with some of Deloitte’s most largest and most complex clients.