Tyler O'Neal, Staff Editor AEROSPACE

UH prof Liaw develops AI system that predicts patients at more increased risk for diabetes complications

Dr. Winston Liaw is the principal investigator of the project and chair of the Department of Health Systems and Population Health Sciences at the Tilman J. Fertitta Family College of Medicine. University of Houston researchers aim to prevent poor health outcomes before they occur

More than 37 million people in the United States have diabetes but many don’t receive timely care which can lead to costly, even deadly complications. While effective treatments are available in primary care settings, clinicians lack the tools necessary to identify those at the highest risk. To prevent poor health outcomes before they occur, researchers at the University of Houston are developing Primary Care Forecast. This clinical decision support system uses deep learning to predict which patients are more likely to experience complications.

The first tool to be developed within the innovative AI system is the Diabetes Complication Severity Index (DCSI) Progression Tool, which, in addition to a patient’s health history, considers how their social and environmental circumstances – employment status, living arrangement, education level, food security – could increase their risk for complications. Research shows these societal factors can affect disease progression.

Funded by the American Board of Family Medicine, the tool will provide clinicians with timely, actionable insights so they can intervene early, reduce the percentage of individuals with diabetes who have complications, and lower the number of difficulties affecting each patient.

“Our long-term goal is to help clinicians become more proactive and less reactive when treating diabetes. By leveraging the capabilities of artificial intelligence and machine learning, we can more effectively connect at-risk individuals with interventions before they become sicker,” said Dr. Winston Liaw, the principal investigator of the project and chair of the Department of Health Systems and Population Health Sciences at the Tilman J. Fertitta Family College of Medicine. 

For years, insurance companies and researchers have used the DCSI to quantify patients’ complications at a single time. Still, no tools exist to predict which individuals are at the most significant risk for rising DCSI scores.

The tool will be developed in collaboration with the Humana Integrated Health System Sciences Institute at the University of Houston, and leverage unique data sets from Humana Inc. – claims, health records, and individual and community social risk factors. The tool will be tested within the PRIME Registry, a national platform that includes millions of primary care patients nationwide.

“The challenge with existing prediction tools is they provide little explanation and no guidance for subsequent action, limiting trust and implementation. The tool we are developing will inform clinicians why patients are at risk and suggest actions to reduce that risk,” said Ioannis Kakadiaris, Hugh Roy, and Lillie Cranz Cullen University Professor of Computer Science and Health Systems and Population Health Sciences.

“Humana is excited to collaborate with our partners at the University of Houston leveraging their AI and predictive analytic expertise with our extensive diabetes experience using the DCSI and health impactful social determinant solutions. This tool represents a great opportunity to put actionable information into the hands of primary care physicians at the point of service where real change in health happens,” said Dr. Todd Prewitt, corporate medical director, of clinical strategy and analytics at Humana.

Beyond diabetes, the researchers believe the tool could help predict complications associated with other conditions, such as uncontrolled hypertension or worsening depression. The tool will be especially relevant as the healthcare industry shifts to a value-based care model where doctors are rewarded for improving patients’ health instead of being paid for each visit, procedure, or test, regardless of the outcome.

The Fertitta Family College of Medicine, founded in 2019 on a social mission to improve health and health care in underserved urban and rural communities across Texas, emphasizes primary care education and research.

“As primary care doctors, we need an efficient way to leverage the massive amounts of information we receive to improve the quality of life of our patients. The number of complications a patient experiences is strongly associated with death or hospitalization, so developing this AI tool is critical,” said Liaw.

German scientists build a model for supercomputing the matter in neutron star collisions

Tyler O'Neal, Staff Editor AEROSPACE

Illustration of the new method: the researchers use five-dimensional black holes (right) to calculate the phase diagram of strongly coupled matter (middle), enabling simulations of neutron star mergers and the produced gravitational waves (left).Except for black holes, neutron stars are the densest objects in our universe. As their name suggests, neutron stars are mainly made of neutrons. However, our knowledge of the matter produced during the collision of two neutron stars is still limited. Scientists from Goethe University Frankfurt and the Asia Pacific Center for Theoretical Physics in Pohang have now developed a new model that gives insights into the matter under such extreme conditions.

After a massive star has burned its fuel and explodes as a supernova, an extremely compact object, called a neutron star, can be formed. Neutron stars are extraordinarily dense: To reach the density inside them, one would need to squeeze a massive body like our sun down to the size of a city like Frankfurt. In 2017, gravitational waves, the small ripples in spacetime that are produced during a collision of two neutron stars, could be directly measured here on earth for the first time. However, the composition of the resulting hot and dense merger product is not known precisely. It is still an open question, for instance, whether quarks, which are otherwise trapped in neutrons, can appear in free form after the collision.

Dr. Christian Ecker from the Institute for Theoretical Physics of Goethe University Frankfurt, Germany, and Dr. Matti Järvinen and Dr. Tuna Demircik from the Asia Pacific Center for Theoretical Physics in Pohang, South Korea, have now developed a new model that allows them to get one step closer to answering this question. In their work, they extend models from nuclear physics, which are not applicable at high densities, with a method used in string theory to describe the transition to dense and hot quark matter.

“Our method uses a mathematical relationship found in string theory, namely the correspondence between five-dimensional black holes and strongly interacting matter, to describe the phase transition between dense nuclear and quark matter”, explains Dr. Demircik and Dr. Järvinen. ”We have already used the new model in computer simulations to calculate the gravitational-wave signal from these collisions and show that both hot and cold quark matter can be produced”, adds Dr. Ecker, who implemented these simulations in collaboration with Samuel Tootle and Konrad Topolski from the working group of Prof. Luciano Rezzolla at Goethe University in Frankfurt.

Next, the researchers hope to be able to compare their supercomputer simulations with future gravitational waves measured from space in order to gain further insights into quark matter in neutron star collisions.

Russian mathematicians boost the performance of blockchain system by 1.5x

Tyler O'Neal, Staff Editor AEROSPACE

image 7 7643fRUDN University mathematicians have improved the performance of the blockchain system. The researchers managed to increase the throughput of the system by almost 1.5 times and reduce the delay time. The results are published in Computers & Industrial Engineering.

Blockchain technology is considered a promising system that will be widely used in banking to medicine. It is based on a special way of transferring and storing data between member elements. Information is stored as a chain of blocks. Violation in one block is immediately noticeable to the entire system. Despite a large number of possible applications, several drawbacks make it difficult to scale up. For example, the calculation of each block can take a long time. As a result, the throughput of the system decreases and the delay time increases. RUDN mathematicians built a model in which they combined blockchain technology with optimization methods and improved the system performance by almost one and a half times.

“Blockchain technology has revolutionized the processing and storage of data in terms of reliability and security. Blockchain made it possible to transfer processing to a decentralized secure platform. It is rightfully considered an efficient technology of the future that will benefit various industries. The problem that becomes a “bottleneck” for blockchain applications is limited bandwidth,” said Ammar Muthanna, Ph.D., Junior Researcher at the Scientific Center for Modeling High-tech Systems and Info communication Modeling at RUDN University.

Mathematicians have created a system with intelligent traffic control. For this, a hybrid model is used that combines optimization using the so-called particle swarm method and fuzzy logic. The particle swarm method is needed to find the optimal delay time, send rate, and the number of transactions. Fuzzy logic is used to automate traffic control. RUDN University mathematicians tested the model on the service for clinical trials and then compared the results with other options.

The system for clinical trials, which was used by RUDN University mathematicians, consists of five participants - a patient, a research doctor, a coordinator, a researcher, and a chief physician. Each has its own set of functions and data that it must exchange with other participants. The processing of clinical data passes through the blockchain network. The new approach increased network bandwidth and minimized delays. Transaction throughput increased by 38.5% and latency decreased by 40.5%. The scope is not limited to the considered service. This model can be applied to other tools that use blockchain technology.

“Latency and throughput are considered the main performance metrics that speak to the efficiency of an information system. The proposed model improved the network by maximizing throughput and minimizing latency. It can be easily integrated into other existing blockchain-based platforms to increase productivity,” said Ammar Muthanna, Ph.D., Junior Researcher at the Scientific Center for Modeling High-tech Systems and Info communication Modeling at RUDN University.