In rare diseases, the computer-aided image analysis of patient portraits can facilitate and significantly improve diagnosis. This is demonstrated by an international team of scientists under the leadership of the University Hospital Bonn and the Charité – Universitätsmedizin Berlin on the basis of so-called GPI anchor deficiencies. Using data on genetic material, cell surface texture and typical facial features, researchers utilized artificial intelligence methods to simulate disease models. The results may also be ground-breaking for other diseases.
Mabry syndrome is a rare disease that causes mental retardation. It is triggered by a change in a single gene. “This disease belongs to a group that we describe as GPI anchor deficiencies and which includes more than 30 genes”, explains physician and physicist Prof. Dr. Peter Krawitz from the Institute for Genome Statistics and Bioinformatics of the University Hospital Bonn. GPI is the abbreviation for glycosylphosphatidylinositol. GPI anchors attach specific proteins to the cell membrane. If this does not work properly due to a gene mutation, signal transmission and further steps in the cell-cell communication are impaired.
The spectrum of the external appearance of GPI anchor deficiencies is very broad: The clinical impact of a mutation in a particular gene can range from mild to profound. This also applies to distinctive facial features. In Mabry syndrome for example, a narrow, sometimes tent-shaped upper lip, broad bridge of the nose and wide-set eyes with long palpebral fissures are among the classic features, but these may be more or less pronounced. This often complicates the diagnosis of this rare disease. The elevated alkaline phosphatase (AP) levels in the blood which are also considered characteristic for the syndrome cannot be detected in every patient. “The result is that many patients and their relatives often suffer many years of uncertainty until the correct diagnosis is made”, says Krawitz.
An international research team led by Dr. Alexej Knaus and Prof. Krawitz from the Institute for Genome Statistics and Bioinformatics of the University Hospital Bonn and Prof. Dr. Denise Horn from the Institute of Medical Genetics and Human Genetics of the Charité investigated how the diagnosis of GPI anchor deficiencies can be improved with the help of modern, particularly fast DNA sequencing methods, cell surface analysis and computer-aided image recognition (next-generation phenotyping).
The researchers applied artificial intelligence in image analysis
In the large-scale overview study, the scientists used photographs of the faces of a total of 91 patients. Cell surface changes characteristic for GPI anchor deficiencies were detected in some of the participants. Genetic analysis also revealed gene mutations that are typical for this rare group of diseases. “The artificial modelling of gene-typical faces that we achieved with these datasets clearly shows that the computer-aided evaluation of patients’ portraits can facilitate and improve the diagnosis of GPI anchor deficiencies, which is significant progress”, says lead author Dr. Knaus.
With the assistance of combined data from the laboratory and the computer, the authors hope to gain better understanding of the molecular processes involved in such diseases. For example, it was shown that increased blood alkaline phosphatase levels and conspicuous image analysis results provide a reliable indication of a new mutation in a GPI anchor deficiency. Because of the shared molecular causes shown during the research and the similarity of the patients that has now been quantified, Krawitz also advocates using the term “GPI anchor deficiency” for this group of diseases.
Bonn Universityhttps://tinyurl.com/ycq27csx

Continuous glucose monitors (CGM) can protect individuals who have had type 1 diabetes for years and are at risk of experiencing dangerously low blood sugar by increasing their awareness of the symptoms, according to a study.
Episodes of low blood sugar, known as hypoglycemia, are a major barrier to achieving glycemic control for people with diabetes.
The study’s publication comes as the Endocrine Society is developing a multi-year, multi-stakeholder initiative to improve understanding of hypoglycemia and reduce associated costs by implementing strategies to improve prevention and surveillance.
Severe hypoglycemia can cause seizures, loss of consciousness and death. Hypoglycemia linked to the use of insulin was responsible for an estimated $600 million (£510 million) in emergency room visits between 2007 and 2011.
“In individuals who have repeatedly experienced hypoglycemia, the body blunts awareness of symptoms warning of impending episodes,” said the study’s first author, Michael R. Rickels, M.D., M.S., of the Perelman School of Medicine at the University of Pennsylvania in Philadelphia, Pa. “Wearing a continuous glucose monitor that flags falling glucose levels and has built-in alarms raises recognition of the threat.”
Eleven individuals who had been diagnosed with type 1 diabetes for at least 10 years and had impaired awareness of hypoglycemia received CGMs to monitor their blood sugar levels during an 18-month period. The researchers found the participants became more aware of hypoglycemia events and were less likely to experience severe hypoglycemic episodes after they started using CGMs. However, the body’s defence mechanisms against developing low blood sugar remained impaired. The participants’ hemoglobin A1c levels, which track average blood glucose over time, did not change.
“While the body’s own defences against hypoglycemia did not improve, CGMs filled a valuable need in alerting individuals to oncoming episodes,” Rickels said. “In the absence of physiologic defences against the development of low blood glucose, near-constant use of continuous glucose monitoring may be required to minimize the burden of problematic hypoglycemia in patients with long-standing type 1 diabetes.”
The Endocrine Society and its 18 partners in the Hypoglycemia Quality Collaborative identified reducing and preventing the condition as a high priority.
The Society’s new hypoglycemia quality initiative aims to improve outcomes in individuals with type 2 diabetes. The project’s goals include decreasing the frequency and severity of hypoglycemia episodes, identifying patients who are at high risk in a timely manner, and supporting appropriate clinical interventions that can be administered in doctors’ offices and clinics, avoiding the need for hospitalization. The effort brings together stakeholders from industry, nonprofit organizations and patient groups.

Endocrine Societyhttps://tinyurl.com/yar6t4wb

By no means are only elderly people at risk from heart diseases. Physically active individuals can also be affected, for example if a seemingly harmless flu bug spreads to the heart muscle. Should this remain undetected and if, for example, a builder continues with his strenuous job or an athlete carries on training, this can lead to chronic inflammation and in the worst case even to sudden death.
Professor Eike Nagel and his 12 co-workers at the Institute for Experimental and Translational Cardio Vascular Imaging of Goethe University Frankfurt are developing better ways to predict and diagnose heart diseases. In recent years, the researchers have taken the lead in the development of a procedure that is still very new in heart scans. Nagel explains the advantages: “With the help of magnetic resonance imaging, we can look right inside the heart muscle.” Blood flow to the heart muscle is visualized and shows whether there are any constrictions of the arteries supplying the heart. Experts can also spot whether the heart muscle is scarred, inflamed or displays any other anomalies.
The comparatively fast method makes it possible to examine patients at an early stage and may prevent cardiac insufficiency or even a heart attack. “Diseases such as HIV, kidney damage, rheumatic diseases or tumours often affect the heart either directly or as a side effect of therapy,” says Nagel, describing groups potentially at risk. The cardiologist is convinced: “Nowadays we can treat or even cure so many diseases, but the heart suffers too and this should be carefully monitored as it mostly remains undetected.”
MRI is a non-invasive and gentle examination technique, which is less risky but just as efficient as an examination using a conventional heart catheter, where a thin tube is pushed in the direction of the heart through an artery. Nagel’s research group was recently able to demonstrate this in a large international multi-centre study that was met with international acclaim.
The Institute for Experimental and Translational Cardio Vascular Imaging also has state-of-the-art computer tomography equipment at its disposal that can produce three-dimensional images of the heart. These especially reveal calcium deposits and plaques in the artery walls which could rupture and trigger a sudden heart attack. “This allows us to determine the risk of a heart attack and the need for therapy fast and at an early stage, which can then be non-invasive,” says Nagel. Which technique is best for which patient is one of the research topics Nagel’s group is evaluating. In some patients, both may be needed and the Institute is optimally equipped to answer most aspects of heart disease thanks to its deep insight into the heart.
Nagel finds these rapid advances in imaging over the last decades fascinating: “Nowadays we can spot the slightest changes and literally get a clear picture of the heart’s condition.”
Goethe Universitäthttps://tinyurl.com/ycvjvutf

Cuff devices for blood pressure measurement are inconvenient, and mobile device apps for blood pressure measurement that are now being introduced may lack accuracy.
To solve this problem, a team of Michigan State University scientists have created a new app and hardware for smartphones to measure blood pressure with accuracy that may rival arm-cuff devices. The technology also includes a discovery of a more convenient measurement point.
“We targeted a different artery, the transverse palmer arch artery at the fingertip, to give us better control of the measurement,” said Anand Chandrasekhar, MSU electrical and computer engineering doctoral student and the lead author. “We were excited when we validated this location. Being able to use your fingertip makes our approach much easier and more accessible.”
The approach uses two sensors: an optical sensor on top of a force sensor. The sensor unit and other circuitry are housed in a 1 centimetre-thick case attached to the back of the phone. Users turn on the app and press their fingertip against the sensor unit. With their finger on the unit, they hold their phone at heart level and watch their smartphone screen to ensure they’re applying the correct amount of finger pressure.
“A key point was to see if users could properly apply the finger pressure over time, which lasts as long as an arm-cuff measurement,” Ramakrishna Mukkamala, MSU electrical and computer engineering professor and senior author said. “We were pleased to see that 90 percent of the people trying it were able to do it easily after just one or two practice tries.”
Internationally, this device could be a game-changer. While high blood pressure is treatable with lifestyle changes and medication, only around 20 percent of people with hypertension have their condition under control. This invention gives patients a convenient option, and keeping a log of daily measurements would produce an accurate average, discounting an occasional measurement anomaly, Mukkamala added.
The research team will continue to improve accuracy and hopes to pursue more comprehensive testing based on the standard protocol of the Association for the Advancement of Medical Instrumentation. The scientists are already making inroads to build improved hardware. Future iterations could be as thin as 1 millimetre and be part of a standard protective phone case.
Michigan State Universitymsutoday.msu.edu/news/2018/new-blood-pressure-app-and-hardware-rivals-arm-cuff-accuracy/

New research has estimated that each year five babies in every 1,000 born in England suffer a condition or sign linked to brain injury.
The study, conducted by researchers at the Neonatal Data Analysis Unit at Imperial College London and Chelsea and Westminster Hospital NHS Foundation Trust, analysed data on babies born between 2010 and 2015 to assess the number that may have sustained brain injury at or soon after birth.
The researchers used routinely recorded NHS data and so were able to measure the incidence rate of brain injury in newborns without any additional workload for doctors or nurses. Ultimately, this research could lead to a better understanding of how to prevent brain injury in preterm and full term babies.
Dr Chris Gale, lead author and Clinical Senior Lecturer in Neonatal Medicine at Imperial College London and Consultant Neonatologist at Chelsea and Westminster Hospital NHS Foundation Trust, said: “Brain injury at or soon after birth is a serious problem, as it can lead to long-term conditions later in life such as cerebral palsy, blindness, deafness and learning deficits. A proportion of these cases could be avoided.”
Neena Modi, Professor of Neonatal Medicine at Imperial College London and Head of the Neonatal Data Analysis Unit, said: “Before now UK health services did not have a standard definition of brain injury in babies and there has been no systematic collection of data for this purpose.
Professor Modi added: “With colleagues, and in collaboration with the Department of Health, we have devised a practical way to measure the incidence rate of brain injury in babies.”
Published in the journal Archives of Disease in Childhood, the research estimated that 3,418 babies suffered conditions linked to brain injury at or soon after birth in 2015, which equates to an overall incidence rate of 5.14 per 1,000 live births. For preterm births (babies born at or less than 37 weeks) the rate was 25.88 per 1,000 live births in 2015, more than seven times greater than the rate for full term births, which was 3.47 per 1,000 live births.
It is often not known whether a baby has suffered brain injury until later in life. Therefore, the new standardized definition of brain injuries in newborn babies, developed by a group of experts convened by the Department of Health, consists of a range of conditions and signs that are known to be related to brain injury. These include seizures or fits, bleeding within the brain, stroke just before or at birth, infections like meningitis, and damage caused by oxygen deprivation.
The research, commissioned by the Department of Health, is the first to present estimates for the number of babies with brain injuries based on a definition that includes multiple conditions in one measure.
It is also the first time this estimate has been made using data gathered routinely during day-to-day clinical care on neonatal units. The use of routine data required no additional work for clinical staff and provides a valuable way to measure the effectiveness of interventions to reduce brain injury.
As part of a drive to make England a safer place to give birth, the Department of Health has set a target of reducing the number of babies that incur brain injury during or soon after birth by 20% by 2020 and to halve them by 2030. Using these new estimates this equates to lowering the incidence of babies with brain injury to four per 1,000 live births by 2020 and to 2.5 babies per 1,000 live births by 2030.
Overall, the research found that the most common type of condition that contributed to brain injuries was damage caused by lack of oxygen to the brain, called hypoxic ischemic encephalopathy; this is seen mainly in full term babies. For preterm babies, the largest contributor to brain injuries is from bleeding into and around the ventricles of the brain, a condition called periventricular hemorrhage.
Dr Gale added: “Being able to measure how common brain injuries are allows health professionals and researchers to focus on reducing these devastating conditions. This includes the consistent use of treatments that reduce the risk of brain injuries in preterm infants, such as steroids and magnesium sulphate given to the mother before birth.
“This measure will also help us to evaluate other interventions, for example, making sure that as many preterm babies as possible are born at hospitals with advanced neonatal services on site, which we know reduces the risk of brain injury.
“The next step is to use routine data to understand the long-term effects of these conditions on the children and their families.”

Imperial College Londonhttps://tinyurl.com/ycnbqzlo