Every year, pharmaceutical companies like Merck discard inventory due to temperature excursions, which results in lost sales, in addition to logistics and resupply costs. In order to preserve the potency of sensitive biological products such as vaccines and biologics, proper temperatures must be maintained during storage, handling, and shipping. These products are shipped in special containers using thermal-protection systems along with temperature-recording sensor devices. This temperature-controlled supply chain is called the cold chain.
Nitin Kaul and Richard Baumgartner offer an overview of the cold chain analytics project within Merck, which identifies the importance of various factors (origin, destination, shipment route, external weather, products, logistics providers, etc.) that highly contribute to product temperature excursions and subsequently develop and use models in order to provide predicted probability of excursion for future shipments and inform supply chain strategy to mitigate future product temperature excursions.
Revolution R (Microsoft R Server) integrated with secure Hadoop cluster is enabling Merck to perform scale out data analytics, leveraging distributed computing capabilities of Hadoop and advanced analytics capabilities for Revolution R while being in alignment with existing security, data access, and data governance policies on top of Hadoop. Nitin and Richard demonstrate how Merck applies descriptive, predictive, and prescriptive analytics leveraging parallel distributed libraries and the predictive modeling capabilities of Revolution R deployed on a secure Hadoop cluster to identify the various factors for product temperature excursions and predict and prevent future temperature excursions in product shipments.
Nitin Kaul works as an innovation lead on the Applied Technology team at Merck, where he manages projects to evaluate and apply innovative new information technologies to unmet needs and interacts with external collaborators, academic research groups, technology vendors, and commercial startups. He also serves as a project/solutions manager, solution architect, and technical lead for innovation proof of concept projects and oversees knowledge capture and transfer of the new technology into Merck for any internal engineering groups in collaboration with Internal and external SMEs. Nitin’s areas of focus include the Hadoop ecosystem, data science initiatives, open compute, distributed scale-out storage, OpenStack, microservices architecture, distributed application development, the health IT platform, and identity access management and entitlements. Nitin holds a master’s degree in computer science and a bachelor’s degree in electronics and system engineering.
Richard Baumgartner is a senior principal scientist with the biometrics research department of Biostatistics and Research Decision Sciences (BARDS) at Merck and Co. While at Merck, Richard has been supporting early clinical and preclinical studies with imaging components, including functional magnetic resonance imaging (fMRI), dynamic contrast-enhanced MRI (DCE-MRI), and positron emission tomography (PET) imaging for neuroscience, inflammation, and cardiovascular therapeutic areas. Previously, he was an associate research officer with the Institute for Biodiagnostics at the National Research Council Canada in Winnipeg, where he pioneered development of methods for exploratory data analysis of fMRI and worked on machine-learning applications to develop diagnostic biomarkers for prediction of pathogenic fungi and breast cancer.
Comments on this page are now closed.
©2016, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.