laboratory informatics


News S


For regular news updates, please visit www.scientific-computing.com/news


Predicting life expectancy with big data


tatisticians, computer scientists and medical researchers for the UK’s University of East Anglia (UEA) are launching a project that uses big data to


predict life expectancy. This research could be used to develop more robust, personalised treatments as well as bringing practical, financial and medical benefits – such as helping people plan for retirement, and knowing how particular drugs such as statins or beta-blockers affect patients’ predicted longevity. The four-year project has been launched through £800,000 of funding from the Institute and Faculty of Actuaries (IFoA). Lead researcher Prof Elena Kulinskaya from UEA’s School of Computing Sciences said: ‘People around the world are living longer. We want to develop software tools that use big data routinely collected by healthcare providers to forecast longevity. When we talk about big data what we mean is data that is vast, complex and difficult to analyse. We want to be able to use it to see


statistical life expectancy trends, based on large- scale population-based data collected over the long term.’


While big data will largely be unstructured population-based data, computer science and statistics tools can be used to predict common responses to certain chronic illnesses and treatments – enabling healthcare professionals to develop treatments which help to promote longevity and life expectancy. ‘We want to identify and quantify the key factors affecting mortality and longevity, such as lifestyle choices, medical conditions and medical interventions’ commented Kulinskaya. ‘We are particularly interested in understanding how various chronic diseases and their treatments impact life expectancy,’ she added. Researchers from UEA’s School of Computing Sciences will work alongside medical and health scientists from Norwich Medical School, with assistance from technical experts at Aviva. The researchers will develop new statistical methods to model mortality, find trends in morbidity, and assess life expectancy,


USING AI TO MEET DATA TRANSPARENCY REQUIREMENTS


Certara, a provider of biosimulation technology, has announced that its regulatory and medical consultancy Synchrogenix has introduced an artificial intelligence enabled solution to meet the data transparency requirements of the clinical drug development market.


The aim of this new technology is to support drug companies’ need to redact and de-identify datasets in their clinical study reports, patient narratives, patient data listings, and submission documents, in order to publish their clinical study information publicly. The details of the requirements were published by the European Medicines Agency (EMA) on March 2, 2016 under Policy 70.


Kelley Kendle, Synchrogenix


president, said: ‘Disclosing clinical trial information so that researchers can build upon prior knowledge is an important step in bringing new therapies to patients, and fostering the industry’s commitment to the patients it serves.’


At the same time, we must


protect the confidential patient and personal information contained in the myriad clinical reports to be published under Policy 70, which are often hundreds of pages long. In anticipation of these regulations and concerns around protecting patient privacy, Synchrogenix has developed technology that automates the redaction of personally-identifiable


24 SCIENTIFIC COMPUTING WORLD


information, patient-protected data, and company-confidential information with 99 per cent accuracy.’ The EMA has been working with the industry for several years to develop a set of rules to make clinical trial data more public. In January 2015, the agency released new transparency and disclosure rules related to clinical study reports contained in marketing authorisation


applications submitted on or after that date. The first reports are expected to be made publicly available in September 2016. The rules that EMA published earlier this month expand the breadth and depth of the original rules, and provide detailed requirements for companies to follow. Synchrogenix’s technology is


currently the only AI-enabled solution available to the biopharmaceutical industry. Built on natural language processing and recognition, this technology is able to identify individual words, parts of speech, and word and phrasing combinations automatically to enable the software to determine context.


@scwmagazine l www.scientific-computing.com


based on big data. Kulinskaya said: ‘Pension contributions were recently freed, so now people can take their pension pots out and use them as they wish. But to be able to plan for retirement, and to understand how much you can spend, it is good to have some idea of your life expectancy. Our estimates of life expectancy will only be true on average, not at the individual level. ‘This is exactly what we are trying to do for a


THIS RESEARCH COULD BE USED TO DEVELOP MORE ROBUST, PERSONALISED TREATMENTS


number of chronic medical conditions. We also want to be able to estimate how some popular drugs, such as statins or beta-blockers, may affect longevity,’ stated Kulinskaya. The research project, entitled ‘Use of big health and actuarial data for understanding longevity and morbidity risks’ is one of three research programmes nationally to receive funding from IFoA, after proposals involving more than 100 institutions from 20 countries.


Gualtiero boffi/Shutterstock.com


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36