Analytics prove lifeblood of product quality

IBM SPSS software helps LifeScan gain more insight into manufacturing data to improve product quality

Published on 10-Jun-2011

Validated on 02 Dec 2013

"We use IBM SPSS analytics software to address the entire analytical process - from planning and data preparation to analysis, reporting and deployment of the insight obtained to aid decision making during the manufacturing process (...) As a result, we increased yield for the company from 92 to 97 percent, by increasing the number of batches that passed release testing. It truly is the lifeblood of product quality at LifeScan." - Scott Dickinson, Manager, Quality Lab Services at LifeScan Scotland Ltd

Customer:
LifeScan, a Johnson & Johnson Company

Industry:
Life Sciences

Deployment country:
United Kingdom

Solution:
BA - Business Analytics, BA - Predictive Analytics, Business-to-Business

Overview

LifeScan, a Johnson & Johnson Company since November 1986, is a leading maker of blood glucose monitoring systems for people with diabetes. Every day more than three million people around the world rely on LifeScan products for simple blood glucose testing and accurate results.

Business need:
LifeScan must analyse laboratory and clinic testing data to gain actionable insight into manufacturing processes, in order to produce a high volume, disposable product, which is costeffective to manufacture and yet also technically very precise and safe for the end user.

Solution:
LifeScan is using analytics software from IBM SPSS to continually assess product quality throughout the manufacturing process. This allows any defects to be identified quickly and corrected before the product is released into full production, protecting both resources and the customer.

Benefits:
• Gained ability to conduct analysis efficiently and ensure highly accurate results so that the product can be manufactured cost-effectively and also safely for the end user. • Introduced control charts within manufacturing process to provide early warnings of problems and make adjustments to the product in a timely manner, resulting in an increase in yield (number of batches that passed release testing) from 92 to 97 percent. • Provided clear, accountable data to demonstrate if the product meets or exceeds external audit specifications. • Implemented a system of data

Case Study

LifeScan, a Johnson & Johnson Company since November 1986, is a leading maker of blood glucose monitoring systems for people with diabetes. Every day more than three million people around the world rely on LifeScan products for simple blood glucose testing and accurate results. The company employs over 2,500 people and is headquartered in Milpitas, California, and also has manufacturing facilities in Puerto Rico and Scotland.

LifeScan is committed to improving the quality of life for people with diabetes and this vision has led to the development of some of the most innovative blood glucose monitoring products in the market today. LifeScan pioneered the modern era of blood glucose monitoring with the introduction of OneTouch® Technology, which brought about much quicker and simpler testing. LifeScan’s OneTouch® Systems are recommended by doctors, pharmacists and diabetes educators as a trusted brand for home and hospital use.

Accurate and actionable data analysis proves critical for product quality

Diabetes is a serious condition, which requires careful monitoring and treatment. As a provider of blood glucose monitoring systems, LifeScan must be able to ensure its products are safe, reliable and effective. Under the OneTouch brand, LifeScan manufactures everything required for blood glucose testing in one easy to use kit, including: blood glucose meters, test strips, lancing devices and diabetes management software.

The test strips are used once by the customer and then thrown away, but they play a crucial role in providing an accurate blood glucose result. Manufacturing the test strips is a complicated and challenging process.

Every year LifeScan makes approximately four billion test strips. The company must analyse the results of laboratory and clinic testing data from up to 20,000 different data points, in order to assign critical labelling information to the test strips which, in conjunction with the glucose meter, lets the user know the result of their blood test.

Every lot of strips (5,000 lots per year) has to be release-tested for accuracy, and the results are analysed to ensure the product meets LifeScan’s exacting standards and provides a precise blood glucose result. LifeScan also needs to be able to use its data to prove statistically that the product complies with strict external specifications, including USA federal regulations (FDA) and international quality standards (ISO).

In addition, LifeScan requires timely insight into data about the test strips as they are being manufactured. Any product which does not meet specifications must be rejected and the labelling information assigned to the test strips should be adjusted immediately to avoid the costly mistake of producing large volumes of inaccurate product.

In summary, LifeScan requires accurate and actionable insight into its data to avoid two potential risks: first, that a poorly performing product is released to the customer, who receives an inaccurate result from the blood glucose test and takes inappropriate action, such as injecting too much insulin; and second, that poor quality control erroneously identifies a batch (lot) of test strips is faulty and therefore will be rejected, resulting in a lost revenue opportunity.

Analytics help LifeScan achieve its objectives

LifeScan uses IBM SPSS analytics software to analyse the performance of the test strips before they are released to the customer and can therefore guarantee only the highest quality product reaches the end user. The analysis also enables LifeScan to prove statistically that the test strips meet or exceed the external specifications set by the FDA and ISO.

Using IBM SPSS software to gain deep insight into its data, LifeScan has been able to identify when changes to the manufacturing process have been necessary. For example, when the test strips are release tested for accuracy, the results are analysed using IBM SPSS to assess performance and assign a pass or fail result. The release data is monitored against specific parameters outputted from SPSS. This data is plotted and reviewed on a daily basis for change against predetermined action limits.

For instance, during the manufacture of one batch of test strips the analysis revealed high failure rates at release testing. LifeScan carried out further analysis to identify the key factors involved and formulate experimental designs. The new design was then tested and the results analysed using IBM SPSS.
This enabled LifeScan to identify the root cause of the problem and make changes to the manufacturing process to fix it. Updates were then made to the data analysis programmes to ensure continued control of the process and provide an early warning for any issues arising in the future.

As a result, LifeScan was able to increase the number of batches that passed release testing from 92 to 97 percent, which represents a significant increase in yield for the company as less test strips had to be rejected. In addition, with improved insight into problems as they occur, it typically takes only 12 hours from testing the product to making necessary adjustments during manufacture.

While the increase in yield benefits the business, the changes to the manufacturing process also resulted in a better performing product, providing the end user with a more accurate blood glucose test result and therefore better management of their conditions.

IBM SPSS is deployed across multiple manufacturing sites to drive product quality and control release of the test strips to the market. It also plays a key role in product development and is used extensively throughout the laboratory whenever there is a requirement to understand how a product is performing, analyse the results of clinical trials, and gain essential insight into whether a product is doing what it should be for the end user.

“We use IBM SPSS analytics software to address the entire analytical process - from planning and data preparation to analysis, reporting and deployment of the insight obtained to aid decision making during the manufacturing process,” said Scott Dickinson, Manager, Quality Lab Services at LifeScan Scotland Ltd. “As a result, we increased yield for the company from 92 to 97 percent, by increasing the number of batches that passed release testing. It truly is the lifeblood of product quality at LifeScan.”

About IBM Business Analytics
IBM Business Analytics software delivers actionable insights decision-makers need to achieve better business performance. IBM offers a comprehensive, unified portfolio of business intelligence, predictive and advanced analytics, financial performance and strategy management, governance, risk and compliance and analytic applications.

With IBM software, companies can spot trends, patterns and anomalies, compare “what if” scenarios, predict potential threats and opportunities, identify and manage key business risks and plan, budget and forecast resources. With these deep analytic capabilities our customers around the world can better understand, anticipate and shape business outcomes.

For more information
For further information or to reach a representative please visit ibm.com/analytics.

Request a call
To request a call or to ask a question, go to ibm.com/business-analytics/contactus. An IBM representative will respond to your enquiry within two business days.

Products and services used

IBM products and services that were used in this case study.

Software:
SPSS Statistics Standard, SPSS Statistics Base

Legal Information

© Copyright IBM Corporation 2010 IBM Corporation Route 100 Somers, NY 10589 US Government Users Restricted Rights - Use, duplication of disclosure restricted by GSA ADP Schedule Contract with IBM Corp. Produced in the United States of America May 2010 All Rights Reserved IBM, the IBM logo, ibm.com, WebSphere, InfoSphere and Cognos are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol (® or TM), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml. SPSS is a trademark of SPSS, Inc., an IBM Company, registered in many jurisdictions worldwide. Other company, product or service names may be trademarks or service marks of others.