MoU Covers a Think-Tank at Khalifa University Research and Data Intelligence Support Center, Internship Programs and Research Collaboration Ěý

Khalifa University of Science and Technology and the National Health Insurance Company – Daman today announced they have signed a memorandum of understanding (MoU) to explore broad-ranging collaboration in academics and research in healthcare-related areas.

The agreement was signed by Dr. Arif Sultan Al Hammadi, Executive Vice President, Khalifa University, and Hamad Al Mehyas, Chief Executive Officer, National Health Insurance Company-Daman, in Abu Dhabi.

According to the MoU, Khalifa University will support Daman as a think-tank in areas of healthcare quality, through the Khalifa University Research and Data Intelligence Support Center and other centers/departments.

Dr. Arif Sultan Al Hammadi said: “We are delighted to enter into this partnership with the National Health Insurance Company – Daman and strengthen our roles in academic and research in healthcare economics, clinical epidemiology and health data. We are also keen to support Daman as a think-tank in healthcare quality, cost and access through our Research and Data Intelligence Support Center, and we welcome experts from Daman to our Department of Epidemiology and Public Health. Such close interaction between a key insurance sector stakeholder, and the UAE’s top-ranked university illustrates the close involvement of important institutions in the advancement of the healthcare ecosystem in the UAE and the region.”

Hamad Al Mehyas, Chief Executive Officer of the National Health Insurance Company – Daman, said: “As an Emirati led firm and a trusted government partner, Daman is committed to investing in the next generation of local talent. The signing of this MoU is further evidence of our unwavering support for research and education initiatives across the country.

The healthcare sector is a key pillar of the UAE’s diverse economy and has the potential to grow exponentially over the coming years. By signing this MoU with our esteemed colleagues at Khalifa University, we are investing in the brilliant young minds who will go on to fuel innovation and invention across our industry, helping to ensure the UAE’s position as a world leading destination for healthcare.”

The Khalifa University Department of Epidemiology and Public Health focuses on academic and programmatic collaborative work aimed at the study of and educating on the distribution and role of factors associated with health and disease. The Department also works on the implementation, through collaborations, of potential initiatives that help maintain health for all, all the time, and improve conditions for patients and health workers in clinical settings.

The Khalifa University Research and Data Intelligence Support Center (R-DISC) is a key component in the Daman MoU and it provides an unparalleled and unprecedented one-stop high-end resource that supports research initiatives, researchers and impactful collaborative work at local, national and global levels.

Clarence Michael
English Editor Specialist
23 March 2022

The post Khalifa University Signs MoU with Daman to Collaborate in Several Areas appeared first on Khalifa University.

Digital mass testing for Covid-19 could soon be possible through smartphone applications and machine learning techniques to identify patterns in sounds made by simply breathing.

Read the Arabic story here:

The sound of a person’s breathing, cough or even their voice could all be used to help diagnose patients with Covid-19, as Khalifa University researchers design an app using artificial intelligence to detect the sounds of a coronavirus infection.

The standard methods to test for Covid-19 rely on polymerase chain reaction (PCR) technologies. While highly accurate, these tests are hindered by the time taken to get results. They also require trained personnel, properly equipped test sites, and robust operational and logistical supply chains. Not to mention, PCR testing is unpleasant for the patient which can deter them from testing regularly.

Finding promising alternatives that are simple, fast and cost-effective is the goal. Plus, since Covid-19 cases continue to increase around the world, a system capable of recognizing the disease in signals recorded by portable devices, such as smartphones, is essential.

Mohanad Alkhodari, Research Associate, and Dr. Ahsan Khandoker, Associate Professor of Biomedical Engineering, investigated the use of breathing sounds and a deep learning framework to determine Covid-19 infections from healthy subjects, including asymptomatic cases. Their results were published in

“Recent studies have used new emerging algorithms in artificial intelligence to detect and classify Covid-19 infections in CT and X-ray images, averaging over 95 percent accuracy,” Alkhodari said. “While the imaging techniques aren’t feasible for frequent testing purposes, the machine learning techniques can be used in determining infection from biological respiratory signals, such as coughing and breathing sounds.”

The human body makes all sorts of noises and physicians have used them to diagnose disease—perhaps the most classic medical device is the stethoscope. Auscultation, the technique of listening to the body, can be challenging for humans to grasp accurately, but it’s a simple task for a machine. Artificial intelligence algorithms can identify features or patterns in sounds that the human ear cannot, and can also pick up noises that are beyond human hearing.

“Respiratory auscultation is a safe and non-invasive technique to diagnose the respiratory system and its associated organs,” Alkhodari said. “Clinicians can hear and record the air sound moving inside and outside the lungs while breathing or coughing, and then identify any abnormalities. This could serve as an early alert to a patient before they move on with further testing.”

Previous studies have investigated the information carried in respiratory sounds in patients who tested positive for Covid-19, forming the dataset necessary to train a machine learning algorithm. Additionally, the vocal patterns seen in patients with Covid-19 show indicative biomarkers for viral infection.

“Although the current gold standard, PCR testing has various limitations, including the high expenses involved in equipment and chemical agents, the need for experts for diagnosis, and the long wait needed for results,” Dr. Khandoker said. “A handheld deep learning model overcomes most of these limitations and allows for a better revival of the healthcare and economic sectors in several countries.”

The team focused on a dataset from India, using a total of 480 breathing sounds from a publicly available dataset. These sounds were recovered by an equal number of healthy and infected subjects using a smartphone microphone and fed into the deep learning framework.

“India is severely suffering from a new genomic variant of Covid-19,” Dr. Khandoker said. “This gives us an insight to the ability of the AI algorithms in detecting infection in patients carrying this new variant, as well as asymptomatic patients.”

The results obtained from testing the deep learning framework on the Indian dataset shows its potential for developing telemedicine and smartphone applications for Covid-19 that can provide real-time results in an efficient and timely manner. It could also be extended beyond Covid-19 to future pandemics or other respiratory diseases. For countries experiencing high infection rates, this technique would also mean isolation behaviors could be maintained, reducing further infection spread, but also provide a diagnostic test that is much cheaper for places struggling to implement the infrastructure needed for mass PCR testing.

“This study paves the way towards implementing deep learning in Covid-19 diagnostics,” Dr. Khandoker said.Ěý

Jade Sterling
Science Writer
1 March 2022

The post New Artificial Intelligence Technique Could Tell if You Have Covid-19 from the Sound of Your Breathing appeared first on Khalifa University.

Two patients with unique genetic mutations in a single gene sparked the investigation of 40 researchers into the effects of gene expression on diabetesĚý

The discovery and mapping of the complete human genome in 2003 introduced the possibility of individualized medicine to a person’s physical and genetic makeup. Increasing evidence is now demonstrating that a patient’s unique genetic profile can be used to detect a disease’s onset, prevent its progression, and optimize its treatment.

This has led to enhanced global efforts to implement precision (personalized) medicine and pharmacogenomics in clinical practice. One such area of clinical practice is the treatment of diabetes.

In contrast, the most common types of diabetes are caused by multiple genes or lifestyle factors. Most cases of monogenic diabetes are inherited.

Dr. Pierre Zalloua, Professor and Chair of the Department of Molecular Biology and Genetics, collaborated with researchers from France, Germany, Austria, the United States, and Singapore to determine the gene responsible for two cases of monogenic diabetes. Their results were published in.

“Diabetes affects over 350 million people worldwide, and the discovery and study of genes responsible provide important insights for understanding disease mechanisms,” Dr. Zalloua explained. “With better understanding, we can improve quality of life and develop cost-effective care for diabetes patients.”

Diabetes mellitus is a group of metabolic diseases, all of which are characterized by high blood glucose levels. If left untreated, diabetes can lead to severe complications including blindness, kidney and heart disease, stroke, loss of limbs, and reduced life expectancy. It is a major public health problem, affecting hundreds of millions of people worldwide and representing a substantial economic burden on society.Ěý

There are two types of diabetes: Type 1 and Type 2 diabetes. Type 1 usually begins in childhood with individuals suffering from their body’s inability to produce enough insulin, while Type 2 is commonly associated with obesity and usually occurs during middle age. Both types tend to run in families and genetic factors contribute to the disease, with interactions between genetic and environmental factors being critical.Ěý

Dr. Zalloua said. “Remarkably, many of these genes encode key proteins for pancreas development.”

To determine which genes play a part in the development of diabetes, the research team examined two different patients with diabetes: one, a young French boy with neonatal diabetes, and a second Turkish child with diabetes diagnosed at 14 months. They showed that the patients inherited mutated alleles of one particular gene, ONECUT1. Two mutated alleles led to a severe form of neonatal diabetes where the child developed a small pancreas and a missing gall bladder, while one mutated allele saw an increased risk of diabetes in the second patient. The researchers were able to determine that ONECUT1 and its expression is a major player in diabetes.

Dr. Zalloua was the person who originally identified additional cases from the region linked to this gene, including a case from a patient in Lebanon. Analysis of these patients revealed various different ONECUT1 mutations, all linked to a risk of diabetes.

ONECUT1 affects a variety of processes including glucose metabolism, an important factor in the disease mechanism of diabetes. Its expression also influences the development of the pancreas and the gallbladder. Previous studies of ONECUT1 have focused on the gene’s role in retinal development, but it is now clear that ONECUT1 acts to determine what type of cell a stem cell becomes. Some human stem cells are pluripotent, meaning they can become any kind of cell in the body, and genes including ONECUT1 are the deciders. Mutations in this gene can therefore disrupt a very complex process at various stages.

The pancreas plays an essential role in converting food to fuel in the body: it helps in digestion and in regulating blood sugar. Two of the main pancreatic hormones are insulin, which acts to lower blood sugar, and glucagon, which acts to raise blood sugar. A functioning healthy pancreas automatically produces the right amount of insulin; in people with diabetes, the pancreas either produces little or no insulin, or the cells do not respond to the insulin that is produced.

To further validate their findings, the researchers examined a cohort of over 2000 German people with presumed type 2 diabetes, and identified 13 incidences of ONECUT1 mutations. In another, larger and multi-ethnic, cohort of almost 20,000 people with type 2 diabetes, the researchers also found that people with variants of the ONECUT1 gene were more likely to develop type 2 diabetes. However, they noted that the risk varied with the specific variant.

Identifying the cause means we can pinpoint the best treatment, offering an opportunity to shift focus from broad population-based standards of care to tailored treatments targeted to an individual molecular profile.

“We found that ONECUT1 controls mechanisms regulating endocrine development, which is involved in a wide spectrum of diabetes types,” Dr. Zalloua said. “We highlighted the broad contribution of ONECUT1 to diabetes pathogenesis, marking an important step towards precision medicine for diabetes.”

Jade Sterling
Science Writer
18 January 2022

The post Khalifa University Researcher Contributes to the Finding of a Novel Gene Involved in Human Diabetes appeared first on Khalifa University.

When data is sparse and medical knowledge of a disease is limited, combining modelling approaches can lead to more accurate predictions of clinical outcomes

Big data in healthcare is nothing new. Hospital records, medical records, results of medical examinations and biomedical research generate vast quantities of information that need to be handled carefully and accurately.

Sometimes, clinicians and researchers don’t understand how a disease progresses or the biochemical mechanisms behind a disease. Other times the data available is sparse because it depends on when the patient physically attends a clinic or appointment.

In the first case, the predictive accuracy of clinical outcomes for any mathematical model is limited as the underlying biological mechanisms are only partly understood. Machine learning techniques do not require knowledge of the underlying interactions in biomedical problems but infrequent data does impact their use, restraining any algorithm from accurately inferring the corresponding disease dynamics.ĚýĚý

Combining the two approaches could be the solution. Dr. Haralampos Hatzikirou, Associate Professor of Mathematics at Khalifa University, proposed a method to improve individualized predictions in cancer patients based on the Bayesian coupling of mathematical modelling and machine learning. This approach was tested on a simulated dataset for brain tumor patients and on two real cohorts of patients with leukemia and ovarian cancer. The results were closely aligned with the actual clinical data for individual patients, suggesting its potential use in enabling accurate personalized clinical predictions in healthcare.

Dr. Hatzikirou worked with Pietro Mascheroni, Michael Meyer-Hermann and Juan Carlos Lopez Alfonso from Braunschweig Integrated Center of Systems Biology and Helmholtz Centre for Infectious Research, Germany, and Dr. Symeon Savvopoulos, Mathematics Post-doctoral Fellow at Khalifa University.

The results were published in

In oncology, this clinical data is the cornerstone of providing personalized healthcare to the patient, but using the data is more challenging.

“Although mathematical models can be extremely powerful in proposing biological hypotheses, they require adequate knowledge of the underlying biological mechanisms of the analyzed system,” Dr. Hatzikirou explained. “Typically, this knowledge is not complete and we only know a limited amount of mechanistic interactions, such as molecular pathways, seen in cancer. Therefore, even though mathematical models provide a good description of an idealized version of what’s going on in cancer dynamics, they can’t always allow for accurate and quantitative predictions.

“On the other hand, machine learning techniques can handle the inherent complexity of biomedical problems. While mathematical models rely on causality, statistical learning methods identify correlations among data so they can systematically process large amounts of data and infer hidden data patterns. However, the data for each patient is limited to being collected whenever a patient is in the hospital or clinic. This doesn’t provide the algorithm with enough data to make meaningful individualized inferences.”

Dr. Hatzikirou and the research team proposed the first Bayesian method that combines the two techniques.

Bayes’ Theorem deals with probabilities based on prior experiences. These priors provide some information but once there is more data, the priors can be updated. It’s the law of probability governing the strength of evidence, saying how much to revise our probabilities when we observe new evidence. For example, if you know your patient has a positive cancer test result, and that’s all you know, you can look at how many people with a positive test result actually have cancer, and that is input to determining the probability that your patient has cancer.

The team first tested their approach on a simulated dataset of 500 virtual patients with brain cancer. Their model accounted for oxygen consumption by tumor cells, formation of new blood vessels due to the cancer spreading, and detecting the compression of other blood vessels by tumors growing and squashing them. For this demonstration, the team considered the tumor cell density to be the ‘modelable’ variable and the other variables as ‘unmodelable’ to represent the unknown mechanisms of disease progression. In the simulation, each patient attended appointments over a three-year period to serve as the sparse data collection opportunities.

First, a mathematical model for brain tumor growth was simulated, then a machine learning model, before finally the combined approach for comparison against the two individual models. The team found that their combined approach performs particularly well for prediction times larger than six months.

“Our method was able to correct the mathematical model predictions for most of the patients, particularly at later times,” Dr. Savvopoulos said. “We then tested our method on two cohorts of real life patients, using their data to more carefully test the effects of ‘unmodelable’ variables, or those unknowns. We used clinical datasets from patients with leukemia and patients with ovarian cancer.”

“Our proposed method aspires to solve a dire problem in personalized medicine that is related to the limited time-points of patient data collection and limited knowledge in cancer biology,” Dr. Hatzikirou said. “In all our tests, we found our model had excellent predictive capacity, but we did recognize some limitations that should be addressed when applying the methodology to real cases.”

Most importantly, this new combined approach is not restricted to Oncology. Most applications of clinical predictions concern data that is heterogeneous and sparse and there are always unknowns in our knowledge of disease mechanisms.

Jade Sterling
Science Writer
24 October 2021

The post Combining Mathematical Modeling and Machine Learning to Better Predict Tumor Growth appeared first on Khalifa University.

Health challenges remain one of the long-standing issues in the Arab region but biomedical computing research is one way to tackle these challenges.Ěý

By Dr. Ahsan H. Khandoker

Read Arabic storyĚý.

A combination of factors is driving the growth in demand for healthcare in the Middle East, including aging populations, longer life expectancies, and sedentary lifestyles that lead to an increase in obesity, cancer, and diabetes.

Thanks to recent advances in computing technology, biomedical computing has become one of the most influential research areas worldwide. There has been an explosion in the volume of biomedical data generated by the technologies involved in modern healthcare, but these volumes of data pose great analytical challenges in the quest to infer the knowledge buried within.

Researchers across the Arab region have successfully advanced a diverse spectrum of biomedical computing applications, as well as stimulating commercial interest. In an article published in, a journal for the Association of Computing Machinery, my colleagues and I shed light on these notable research efforts and demonstrate how this research addresses healthcare issues in the region. We focus on three main areas of biomedical computing: biomedical imaging, biomedical signal analysis, and bioinformatics.

Biomedical image analysis has been used extensively in the Arab world due to the region’s strong prevalence of diseases that rely on imaging techniques for accurate diagnosis. Across the region, numerous research groups have published work in this area, using various machine learning techniques. Research includes localization of cardiac structures using magnetic resonance imaging (MRI), computer-aided diagnosis for understanding tumor behavior, and diagnosis of Alzheimer’s disease using diffusion tensor images. With the onset of the Covid-19 pandemic, many researchers have also proposed methods for fast and accurate CT image segmentation, which is crucial to the diagnosis of Covid-19.

Biomedical signal analysis is another area that is key, given the advances in the technology of recording different physiological signals from the human body. These signals can be used in diagnosing various diseases as well as modulating the function of different organs. The Khalifa University Biomedical Signal Processing research group is developing non-invasive fetal phonocardiogram, as well as adult electrocardiogram (ECG) signal processing techniques to prevent stillbirths and sudden cardiac deaths.

Cardiovascular disease represents a leading cause of death in the Arab region, as well as worldwide, and the KU team is proud to contribute to the global research efforts to diagnose and predict cardiac arrhythmia complications. The team has developed a new device presenting a novel algorithm to predict a heart attack long before its onset, and successfully developed the first proof-of-concept, low-cost phonocardiogram sensor that can detect fetal heart sounds and give a reliable estimation of the fetal heart rate and its variability.

Brain signal analysis is another notable research direction pursued in biomedical computing applications. Researchers have identified and characterized the brain networks associated with cognitive deficits in patients, with neurological pathologies such as Alzheimer’s disease understood to be caused by alterations in these brain networks. This research could complement current Alzheimer’s Disease diagnostic metrics, especially at early stages of the disease.

Another study has proposed a technique to assess the mental capacity to preserve attention for long durations, with the technique able to monitor changes in the communication patterns among different brain regions with reduced attention. Biomedical signal analysis research in the region has resulted in influential and diverse contributions that aim to resolve multiple technical challenges in the field and address several population health issues.

Researchers in the field of bioinformatics have leveraged high-performance computational methods to tackle hereditary diseases prevalent in the region. There have been multiple efforts to develop national genome programs, with the projects focusing on unravelling the mutations responsible for inherited disorders in the population. The Emirati project, for example, has characterized 1,000 individual genomes with aspirations to eventually cover the entire population of the country. This bioinformatics research has the potential to dramatically enhance the quality of life of millions of people around the Arab region.

Built upon the success demonstrated in different biomedical computing tracks, the Arab region has witnessed a strong momentum for entrepreneurial activities in many sectors, for example, the work of the KU Biomedical Signal Processing research group that resulted in a UAE-based start-up company licensed to commercialize their phonogram technology for fetal wellbeing at home, called Medical Advanced Research Project (MARP ).

Research in biomedical computing is stimulating the budding culture of entrepreneurship and new ventures across the region, opening avenues of development that could magnify the outcomes of the biomedical computing research community in the region. Much of this work is being undertaken by Khalifa University’s Healthcare Engineering Innovation Group (HEIG) and Biotechnology Center (BTC).

Dr. Ahsan H. Khandoker is an Associate Professor of the Department of Biomedical Engineering at Khalifa University.Ěý

The post Biomedical Computing in the Arab World: Unlocking the Potential of a Growing Research Community appeared first on Khalifa University.