Dr. Carmen Lilí Rodríguez, international academic coordinator of the Fundación Universitaria Iberoamericana (Iberoamerican University Foundation, FUNIBER), is participating in a study to develop an intelligent system for the early diagnosis of epileptic seizures, with the aim of providing timely treatments and better results for patients.
Epilepsy, a neurological condition characterized by abnormal electrical discharges in the brain, affects millions of people worldwide, exposing them to significant risks such as physical injury, loss of consciousness and seizures. Its causes include genetic factors, brain injuries, infections and tumors. Epilepsy can reduce quality of life and increase the risk of premature death due to accidents during seizures (such as falls or drowning) and associated problems such as depression, anxiety and cognitive impairment. Therefore, early detection of this condition is essential to improve the quality of life of patients and reduce complications.
To improve the diagnosis and treatment of epilepsy, advanced artificial intelligence (AI) techniques are being used. These tools, such as deep learning and hybrid models, have shown good results in the detection of neurological diseases, including epilepsy. An example of the application of AI in medical care is the detection of epileptic seizures through electroencephalography (EEG) signals, which record the electrical activity of the brain, showing positive results in the identification of the onset of seizures and in their classification.
Several studies have developed models based on machine and deep learning to classify brain activity, achieving levels of accuracy of over 90%. Likewise, other approaches based on wearable sensors and health data have been developed to predict epileptic seizures, also achieving high levels of accuracy. However, most of these models have limitations that reduce the guarantee of obtaining more reliable diagnoses.
In this context, the study developed an innovative approach using artificial intelligence to address this challenge. The methodology, called FIR (Fast Independent Component Analysis Random Forest), combines independent component analysis with prediction probability to create a more robust and accurate feature set. This model analyzes EEG data and optimizes the detection of epileptic seizures through the use of advanced algorithms such as support vector machines (SVM).
The results obtained are promising. The FIR+SVM model achieved 98.4% accuracy in the detection of epileptic seizures, significantly outperforming traditional methods. This advance not only represents a milestone in the use of artificial intelligence in medicine, but also has the potential to transform the way epilepsy is diagnosed and treated. By enabling earlier and more accurate detection, this system could reduce the risks associated with seizures, such as fatal accidents, and improve the planning of personalized treatments.
Furthermore, this approach has broader implications for the medical industry. The integration of machine learning models such as FIR into medical devices could facilitate continuous patient monitoring, providing real-time alerts and improving emergency response. In conclusion, the development of the FIR model represents a significant advance in the fight against epilepsy, as it has the potential to save lives and improve the quality of life for millions of people.
If you want to know more about this study, click here.
To read more research, consult the repository of UNEATLANTICO.
The Iberoamerican University Foundation (FUNIBER) offers a variety of study programs, such as the Master’s Degree in Strategic Management in Information Technologies. A program that provides professionals with the skills and abilities necessary to manage executive positions and direct organizational change projects using ICTs or to advise companies that wish to join the competitiveness of new businesses. Join the business development by studying our master’s program and get ready to take your career to the next level!