Diaceutics, Intel and Lenovo advance patient care using AI and workstations powered by Intel® Xeon® Scalable processors
March 5th, 2018
Collaboration will help to organize and categorize patient testing data using artificial intelligence
It is a revolutionary method which could help to identify new patient subsets
The aim is to further improve the diagnosis and treatment of patients
Since it was established, Diaceutics has focused on removing barriers to diagnostic test adoption and plans to use AI in its push toward democratization of precision medicine
Diaceutics, an Irish-based company helping patients to receive potentially lifesaving medicine through better diagnostic testing, has today announced a collaboration with Lenovo and Intel. The collaboration will enable Diaceutics to leverage their vast proprietary database of patient testing data in a revolutionary way. Using artificial intelligence (AI) to see whether patients can be grouped according to diagnostic test information, the company is hopeful that this data can help identify ways to improve diagnosis, treatment and outcomes for patients with similar characteristics.
The combination of Lenovo hardware and Intel® Xeon® Scalable processors for workstations delivers the compute power needed to add new machine learning capabilities on top of today’s big data analysis. This hardware solution will drive our objective of getting the right medicine to the right patients at the right time by applying AI to a vast amount of complex real-world testing data from hundreds of clinical laboratories to classify individuals, disease patterns and their routes to getting diagnosed.
After a number of biomarkers covering a variety of tumors and cancer types have been inputted, the machine learning system will be able to identify similarities and patterns within the testing data and highlight what is happening among groups of patients. Essentially, the organization of this information could mean that at-risk patients can be identified, accurately diagnosed and treated much faster.
An estimated 78,000 cancer patients are not properly tested each year in the United States alone and are possibly not getting access to potentially lifesaving medications1. This collaboration could further transform the area of personalized medicine. Diaceutics, has facilitated more than half a million patient’s access to receive improved treatment through better testing. We will share initial findings from this collaboration at a series of conferences throughout this year.
Juliesta Sylvester, Managing Director Global Data, Diaceutics said: “The technology will help to analyze the data in a new way. Rather than taking merely a quantitative view of real world diagnostic data, we will be able to look more broadly across the patients’ entire diagnostic path to treatment. This means we can identify future opportunities for intervention with better testing, which revolutionizes treatment outcomes and delivers better on the promise of precision medicine.
“In the US alone, a substantial proportion of patients who could be on a precision, and potentially lifesaving, therapy miss that opportunity. Our mission is essentially to turn the odds in favor of patients, and this collaboration helps us to do that.”
“The need for AI is growing quickly; and the benefits of AI within the healthcare industry are irrefutable,” says Rob Herman, General Manager, Lenovo Workstations. “To partner with Diaceutics in exploring what’s possible and improving the lives of so many is a very worthy and exciting endeavor. Artificial Intelligence requires extreme power to crunch the mass amounts of data within; that’s why we are proud to provide the professional-caliber hardware in the form of the ThinkStation P920 tower workstation with dual Intel Xeon processors. We are eager to see the impact of this technology in the field of personalized medicine.”
This use case provides an innovative application of advanced analytics to solve real problems with the growing volume of healthcare data. Intel and Lenovo are deeply active in working with the global healthcare ecosystem to enable better utilization of data through the application of leading edge machine learning techniques. More and more we are seeing organizations add traditional machine learning or deep learning as a standard workload. Having the flexibility of Intel Xeon Scalable processor-based workstations to support these next-gen use cases alongside today’s business critical applications improves their technical and business agility.
Intel’s portfolio of hardware and software solutions for AI offers businesses the most performance-and cost-optimized path to AI today – whether in the cloud, at the edge, or within datacenters. The latest Intel Xeon Scalable processors enable exciting new capabilities for artificial intelligence, including both deep learning and machine learning, atop the same architecture already trusted for your big data analytics. The Intel Xeon Scalable processor delivers up to 2.2X higher deep learning training and inference performance than the prior generation of Intel Xeon processors(2). These gains can be extended by utilizing Intel-optimized software frameworks (e.g. Caffe or Tensorflow), which can result in up-to 113X deep learning training performance gains compared with non-optimized three-year-old servers(2), providing a solid foundational architecture for AI workloads. For more information, please review our earlier post, “New Intel Xeon Processors for Workstations – Designed for Professional Creators”.
“Advances in high performance computing and artificial intelligence hold the power to improve the lives of everyone,” said Trish Damkroger, Vice President of Technical Computing at Intel. “Innovative companies like Diaceutics, supported by world class infrastructure from Lenovo, show how new approaches can be used to improve health care outcomes with faster, better diagnostics than has ever been possible before.”
Be sure to stop by Lenovo Booth #2443, Tuesday March 6th at 2pm, for a presentation that will provide more info on the Diaceutics, Lenovo and Intel collaboration and learn more about this amazing new technology.
Diaceutics is transforming an industry model by enabling pharmaceutical companies to optimize the integration of diagnostic tests with new targeted therapies by helping them to revolutionize patient testing. It does this by providing insights generated from its real-time testing data from its worldwide laboratory network, helping Pharma to understand and leverage the diagnostic landscape and deploy initiatives that aid patient diagnosis. The company leads the top 10 global markets with a 60% market share and experience of more than 300 precision medicine projects. Twenty-nine out of the world’s top 30 pharmaceutical companies are clients. The company employs a leading global group of experts from the laboratory, diagnostic and pharmaceutical industries. www.pmconnective.org
Steve Vitale, Managing Director, Diaceutics
Intel and Xeon are trademarks or registered trademarks of Intel Corporation in the United States and other countries.
The benchmark results reported above may need to be revised as additional testing is conducted. The results depend on the specific platform configurations and workloads utilized in the testing, and may not be applicable to any particular user’s components, computer system or workloads. The results are not necessarily representative of other benchmarks and other benchmark results may show greater or lesser impact from mitigations.
Benchmark results were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as “Spectre” and “Meltdown.” Implementation of these updates may make these results inapplicable to your device or system.
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products.
(1) Clark, J., Smart D., & Keeling, P. (2017) Patients lost to precision treatment due to suboptimal testing: US and EU real world evidence. European Alliance of Personalized Medicine 1st Congress, Belfast, UK, November 2017.