UJ research team develops AI application set to diagnose life-threatening diseases
From left: Mr Adeola Ogunleye, Prof Qing-Guo Wang, Prof Tshilidzi Marwala
A TEAM OF SCIENTISTS FROM THE UNIVERSITY OF JOHANNESBURG, COLLABORATING ACROSS THEORETICAL AND EXPERIMENTAL PHYSICS AND COMPUTER SCIENCE, DEVELOPED AND TRAINED A NEW MACHINE LEARNING (ML) TECHNIQUE TO FINALLY PREDICT AND DIAGNOSE DISEASES SUCH AS LUNG CANCER, TUBERCULOSIS, CARDIOVASCULAR DISEASES AND MALARIA. THEIR FAR-REACHING RESULTS WERE RECENTLY PUBLISHED IN IEEE XPLORE.
machine learning has discovered a new forest building method. According to the lead author, Prof Qing-Guo Wang of UJ’s Institute of Intelligent Systems, the case study on the diagnosis of autistic spectrum disorder shows that the proposed method achieves the prediction accuracy of the ensemble at above 96% with reduced variance, which is much better than those reported in the literature. “In this new collaboration with Prof Tshilidzi Marwala, UJ’s Vice- Chancellor and Principal (a leading AI expert) and Mr Adeola Ogunleye, Machine Learning Engineer, we combined ‘Decision Trees’ and regression methods which are usually found in two difference branches of machine learning to take advantage of each.” A number of intelligent systems integrate two or more AI techniques (ANN, SVM, KNN) with a
The accurate diagnosis of diseases is critical to the survival of humans. At times, due to the overlapping nature and similarities of the symptoms, it can be challenging for an inexperienced clinician to properly diagnose diseases. Misdiagnosis of diseases has often led to increased costs, time and even death. However, to save costs and improve the quality of human diagnosis, artificial intelligence (AI) techniques have been applied. According to the white paper released by healthcare advisory PinnacleCare, 64% of medical practitioners surveyed testified that 10% of misdiagnoses lead to serious injury. UJ scientists have now made a significant breakthrough in both technique and understanding. Based on a suite of artificial neural networks (ANN) that they had designed and trained to acquire knowledge about the task at hand,
ALUMNI IMPUMELELO
18
Made with FlippingBook - Online catalogs