Twitter   LinkedInFacebookRSS  
Accelerating Personalized Healthcare with High Performance Computing in the Cloud

Contributed Commentary by Wolfgang Gentzsch

December 13, 2018 | Personalized healthcare has existed for more than a decade because of great advances in science and technology which have made diagnostics smarter, more targeted, and more accessible. For example, based on an intricate understanding of the biology of a disease, scientists and physicians are able to identify biomarkers: biological molecules found in body fluids or tissues that provide insight into the state of the disease, such as gene mutations or protein expressions. Employing diagnostic tests like liquid biopsy helps to find specific genetic defects in the patient’s tissue to better understand the molecular root cause of the disease. Scientists and physicians are now able to work with leading diagnostic partners to develop tests and making informed treatment decisions for the individual patients.

In the field of oncology for example, the impact of personalized healthcare is particularly evident: targeted treatments are helping cancer patients live longer, healthier and more productive lives. Since 1991, the cancer death rate is down about 20% and the five-year relative survival rate has climbed to about 68%. Over time, personalized approaches to cancer care have the potential to improve the overall survival rate across a broad range of tumor types, giving us the opportunity to change outcomes for patients on a meaningful scale.

Major factors contributing to the acceleration of personalized healthcare in recent years come from advances in high-performance computing (HPC), data analytics, machine learning, and artificial intelligence, enabling scientists now to perform the most sophisticated simulations in genomics, proteomics, and many other fields, using methods like genome analysis, molecular dynamics, and more general computer aided analysis methods widely applied and proven in other areas of scientific and engineering modeling.

We demonstrate the impact of computer simulations on personalized health care and present two research projects aiming at living heart and brain simulations.

Studying Personalized Drug-induced Arrhythmias of a Human Heart

Last year, during the Supercomputing Conference SC17 in Denver, UberCloud—together with the Stanford Living Heart Project—won the Hyperion Research Award for Innovation Excellence, elected by the HPC User Forum Steering Committee. The Living Heart Project (LHP) team consisted of researchers from the Living Matter Laboratory at Stanford University, Hewlett Packard Enterprise and Intel (the sponsors), Dassault Systemes SIMULIA (for Abaqus 2017), Advania (providing HPC Cloud resources), and the UberCloud tech team for developing the Abaqus high-performance software container and integrating all software and hardware components into one seamless solution stack.

The Living Heart Project is uniting leading cardiovascular researchers, educators, medical device developers, regulatory agencies, and practicing cardiologists around the world on a shared mission to develop and validate highly accurate personalized digital human heart models. These models will establish a unified foundation for cardiovascular in silico medicine and serve as a common technology base for education and training, medical device design, testing, clinical diagnosis and regulatory science—creating an effective path for rapidly translating current and future cutting-edge innovations directly into improved patient care. 

“The Living Heart Project community has demonstrated the profound impact computational modeling will have on personalized medicine,” said Dr. Steve Levine, Sr. Director Life Sciences, Dassault Systèmes. “HPC is essential to efficiently delivering on these benefits, as shown from the recent heart and brain simulations performed by Stanford University and the NIMHANS National Institute of Mental Health. While still at the R&D level, these projects provide a glimpse into what will be clinically possible in the near future.”

This Stanford LHP project dealt with simulating cardiac arrhythmia which can be an undesirable and potentially lethal side effect of drugs. During this condition, the electrical activity of the heart turns chaotic, decimating its pumping function, thus diminishing the circulation of blood through the body. Some kind of cardiac arrhythmia, if not treated with a defibrillator, will cause death within minutes.

Before a new drug reaches the market, pharmaceutical companies need to check for the risk of inducing arrhythmias. Currently, this process takes years and involves costly animal and human studies. In this project, the Living Matter Laboratory of Stanford University developed a new software tool enabling drug developers to quickly assess the viability of a new compound. This means better and safer drugs reaching the market to improve patients’ lives.


A computational model that is able to assess the response of new drug compounds rapidly and inexpensively is of great interest for pharmaceutical companies, doctors, and patients. Such a tool will increase the number of successful drugs that reach the market, while decreasing cost and time to develop them, thus helping hundreds of thousands of patients in the future. However, the creation of a suitable model requires taking a multiscale approach that is computationally expensive: the electrical activity of cells is modeled in high detail and resolved simultaneously in the entire heart. Due to the fast dynamics that occur in this problem, the spatial and temporal resolutions are highly demanding.


Prof. Ellen Kuhl, Head of Living Matter Laboratory at Stanford University, said of the work: The Living Heart Project has allowed us to perform virtual drug testing using realistic human heart models. For us, high-performance cloud computing and the close collaboration with UberCloud, HPE, Dassault Systèmes, and Advania, were critical to speed-up our simulations to identify the arrhythmic risk of existing and new drugs in the benefit of human health."

Personalized Non-invasive Clinical Treatment of Schizophrenia

This NIMHANS project is based on computer simulations of non-invasive transcranial electro-stimulation of the human brain in schizophrenia, a serious mental illness characterized by illogical thoughts, bizarre behavior and speech, and delusions or hallucinations. This work represents a breakthrough in demonstrating the high value of computational modeling and simulation in improving the clinical application of non-invasive electro-stimulation of the human brain in schizophrenia and the potential to apply this technology to the treatment of other neuropsychiatric disorders such as depression and Parkinson’s disease. With the addition of HPC, clinicians can now precisely and non-invasively target regions of the brain without disrupting nearby healthy brain regions!

At the Supercomputing Conference SC18 last month, UberCloud and the National Institute of Mental Health & Neuro Sciences NIMHANS in Bangalore, Dassault Systemes SIMULIA, Advania Data Centers, Hewlett Packard Enterprise and Intel, received this year’s prestigious Hyperion Research Award for Innovation Excellence for this breakthrough project.


At the core of the project is Neuromodulation which refers to the modification of neural activity via an artificial stimulus such as an electrical current or a chemical agent. Traditionally, it involves highly risky and expensive invasive implantation of electrodes close to the nerves to be stimulated. It may also be performed non-invasively using methods such as electrical stimulation wherein external electrodes induce the required neural activity changes without the need for surgical implantation. This procedure is simple, affordable, and portable, and the subject is fully conscious and experiences minimal discomfort during the procedure.


After a 3-D patient-specific head/brain model was developed, electrode placement was performed with Synopsys Simpleware ScanIP and CAD modules, and a high-resolution tetrahedral FE mesh (element size = 1mm3) was generated using the ScanIP and ScanFE modules. After specifying appropriate material properties and boundary conditions, 26 different electrical simulations were performed using UberCloud’s SIMULIA Abaqus container mentioned above—each representing a different electrode configuration based on clinical guidance—on the Advania/UberCloud HPC cluster of HPE ProLiant servers with 2x Intel Broadwell E5-2683 v4 processors and Intel OmniPath interconnect. Each job contained approximately 1.8M finite elements describing the individual’s brain geometry. On a system with 16 cores at SIMULIA’s office in India, a single run took about 75 minutes, whereas on the UberCloud/Advania cluster in Iceland a single run took about 28 minutes on 24 cores.

Now, an even bigger advantage comes from performing all 26 different electrical simulations in parallel, with an overall speedup of 26, thus reducing simulation time for all 26 simulations from previously 33 hours down to 28 minutes, a speed-up factor of 70 just by using high-performance cloud computing resources, and an even higher speed-up the more high-performance cloud servers are used.

With this achievement, the patient can now wait for the doctor’s simulations resulting in the optimal electrode configuration, and the fine-tuning of the patient’s remote control. Compared to the traditional hospital treatment which comes along with a painful, risky, and expensive operation, this novel ambulant treatment enabled by high-performance computing is non-intrusive, safe, and affordable for everybody, ready for a wider research and commercial adoption!

Wolfgang Gentzsch is co-founder and president of UberCloud, the community, marketplace, and software provider for engineers and scientists to discover, try, and buy complete hardware/software solutions in the cloud. Wolfgang is a passionate engineer and high-performance engineering computing veteran with 40 years of experience as a researcher, university professor, and serial entrepreneur. He can be reached at or on LinkedIn. Extended case studies of these examples can be downloaded from the UberCloud site.