The machine learning and the artificial intelligence have been relieved in recent years as the perfect complement to make faster and more accurate not only the diagnosis of existing diseases, but also the future risk of suffering from cancer or dementia.
The implementation of this technology has acquired a presence in different areas of the scientific scene, such as medicine. Currently, advances in AI allow the early detection of diseases such as Alzheimer, a neurodegenerative pathology that modifies the brain and causes alterations that affect memory, understanding, judgment, behavior and functional activity.
The disease of Alzheimer It represents one of the greatest health challenges facing countries. Both because of the impact suffered by families with members affected by this disease and because of the high resources it requires from public health systems.
Researchers from Kaunas University of Technology (Lithuania) have developed an algorithm capable of predicting the onset of Alzheimer’s disease from brain images taken with functional magnetic resonance imaging.
An algorithm is capable of predicting the disease with 99% reliability
This new AI can identify early Alzheimer’s disease markers with more than 99% accuracy. By evaluating brain scans of older adults, the algorithm can detect subtle changes that often take place before diagnosis, allowing doctors to offer early treatment to high-risk people.
This algorithm, according to the researchers, could become a software that analyzes the data of vulnerable groups, such as people over 65 with a history of brain injury or high blood pressure.
Thus, AI successfully recognizes signs of mild cognitive impairment that generally do not produce noticeable symptoms, and is associated with changes in certain regions of the brain that can be detected on functional magnetic resonance imaging scans.
The researchers repurposed an existing neural network called ResNet18 and created an AI model capable of identifying these details with greater reliability. The AI was trained with 51,443 brain scans of 138 people. Then another 27,310 images were used to validate the algorithm, which was able to identify early cognitive decline with 99.99% accuracy and late MCI with 99.95% accuracy.
These images were divided into several different categories, ranging from healthy brains to various degrees of cognitive decline and Alzheimer’s. An additional 27,000 images were then used to test the algorithm, which was able to identify the appearance of premature signals with 99 percent accuracy.
Rytis Maskeliūnas, a researcher in the Department of Multimedia Engineering at KTU, and supervisor of the study, explains that they would not dare to say that a professional doctor should trust an algorithm 100%, but yes, specialists could examine the cases more closely. New advances will make medicine more accessible and cheaper. Although they will never truly replace the medical professional, technologies can encourage seeking help and timely diagnosis.
Thanks to recent progress in the development and application of AI, it is possible to detect Alzheimer’s cases up to 15 years in advance, through genetic testing and patient monitoring. In addition, it is expected that, in the future, this tool will also serve to predict other mental illnesses such as depression or even alert professionals to possible suicidal tendencies.
*The author is an expert in Innovation.
Innovation Expert
Guest column
Strategic entrepreneur, innovator and agent of change committed to his country and reinvention through his projects. He has a long history in the business world in the financial, telecommunications and technology sectors as well as in the field of social promotion, which has allowed him to develop methodologies for the identification, analysis and effective solution of current challenges.
Reference-www.eleconomista.com.mx