KARACHI: Researchers at Aga Khan University and the University of Virginia are working on a project that will leverage the power of artificial intelligence (AI) to understand a particularly complex bowel disease known as "environmental enteric dysfunction". (EED). "
EED, often referred to as a neglected poverty disease, is common among children in low-income countries such as Pakistan, where the population is exposed to contaminated water and poor sanitation.
EED hinders the gut's ability to absorb essential nutrients It impairs the growth potential of children and makes them susceptible to a variety of diseases.
Data scientists have already shown how "intelligent" computers can help experienced radiologists and pathologists detect X-rays and biopsies
Dr. Sana Syed, Assistant Professor of Paediatrics at the University of Virginia (UVA) and Dr. Asad Ali, associate dean of research at Aga Khan University (AKU) are now using "deep learning," a type of AI to train a computer program. to analyze microscopic images of tissue deep inside the small intestine.
La AKU, The initiative, funded by a medical technology scholarship from the UVA, is being carried out in collaboration with the UVA Data Science Institute. As part of the project, computers will break down the size, shape, and structure of intestinal cell images into a matrix of numbers. Each number corresponds to a pixel, the smallest unit of an image. As the program scans more of these images, it becomes aware of abnormal patterns. Finally, the computer will learn to compare images of healthy intestines with those affected by EED and to identify the cellular-level differences that trigger the disorder.
Images of the EED-affected gut come from work in SEEM, which is a $ 1
Dr. In addition to SEEM's images, Syed will also analyze images from the pathological archives of the UVA, images provided by staff from the School of Medicine at the University of Zambia.
"The application of state-of-the-art data science methods in these images will help us to decode this complex, high-dimensional biomedical data and gain insights that will improve our diagnosis of the disease," Dr. Sana Syed from the UVA.
"Advances in computer technology provide a neutral, systematic way to process huge amounts of data, and this allows us a multi-omnichannel approach to investigate information on proteins, chemical compounds, and even microorganisms, to study all biological changes through EED Knowledge could then be used to test nutritional or pharmacological interventions that can reduce the harmful effects of EED. " Syed.
Dr. Syed and dr. Ali believes that these findings could pave the way in the long term Doctors diagnose EED. At present, the only way to conclusively identify the disease is through a "biopsy", an invasive procedure in which tissue samples are extracted from a person's intestine.
The researchers want to use their findings to create comprehensive screening biomarkers – chemical warning signals that would help future doctors diagnose EED through a simple blood or urine test.
"EED is one of the triggers of chronic public health problems in developing countries, including malnutrition, stunted growth and poor response to vaccines, said Dr. Asad Ali." The EED address will help us unsettle the vicious circle of poverty, leading to poor health and poor health and leading to poverty. "
SEEM is a multi-institutional partnership focused on EED, with project partners including AKU, the University of Virginia, the Cincinnati Children & # 39; s Hospital, the Massachusetts General Hospital and Washington University.
Published in Daily Times, May 30 th 2018.