Predictive Analytics to Support Clinical Trials Get Healthier

Predictive Analytics to Support Clinical Trials Get Healthier

Ankit Lodha (University of Redlands, USA) and Anvita Karara (Carnegie Mellon University, USA)
Copyright: © 2018 |Pages: 18
DOI: 10.4018/978-1-5225-2947-7.ch016
OnDemand PDF Download:
No Current Special Offers


The concept of clinical big data analytics is simply the joining of two or more previously disparate sources of information, structured in such a way that insights are prescribed from examination of the new expanded data set. The combination with Internet of Things (IoT), can provide multivariate data, if healthcare organizations build the infrastructure to accept it. Many providers are able to integrate financial and utilization data to create a portrait of organizational operations, but these sources do not give a clear idea of what patients do on their own time. Embracing the centrality of the IoT would relinquish the idea that provider is the only pillar around which healthcare revolves. This chapter provides deeper insights into the four major challenges: costly protocol amendments, increasing protocol complexity and investigator site burden. It also provides recommendations for streamlining clinical trials by following a two dimension approach-optimization at a program level (clinical development plan) as well as at the individual trial candidate level.
Chapter Preview


The Rapid Growth in Clinical Development

The number of clinical trials underway each year has been increasing steadily, worldwide. In the last five years alone, over 75,000 federally and privately supported trials have been registered with the National Institute of Health’s Clinical Trials registry with a growing trend in trials being conducted in Brazil, Russia, India, and China (Lodha, 2016).

With a broad range of study designs, varying data collection methods and time points, efficient data analysis in clinical development has become more important than ever. The more effectively study data are managed, the faster the data can be extracted and analyzed. The analysis of the data is important for each trial stage as valuable insights can be gained. For example, during the early stages of a clinical trial, access to data is vital not only for patient safety, but for solving problems while they are still manageable and before they become costly (Tibco, 2011).

Complete Chapter List

Search this Book: