University of Waterloo researchers have developed an artificial intelligence (AI) model to reduce bias and enhance trust and accuracy in machine learning-generated decision-making and knowledge organization..According to a news release from the university, traditional machine learning models often yield biased results, favouring groups with large populations. Any potential solution requires a nuanced examination of patterns and sub-patterns from different classes or primary sources. The medical field is an obvious area where proper AI analysis could be helpful and shallow analysis, harmful. .Hospital staff and medical professionals rely on datasets containing thousands of medical records and complex computer algorithms to make critical decisions about patient care..Machine learning sorts data, which saves time. However, patient groups with rare symptomatic patterns may go undetected, leading to misdiagnosis and worse healthcare outcomes for specific patient groups. .Dr. Andrew Wong, a distinguished professor emeritus of systems design engineering at Waterloo, pioneered a model to eliminate these barriers by untangling complex patterns from data to relate them to specific underlying causes unaffected by anomalies and mislabeled instances. It can enhance trust and reliability in eXplainable Artificial Intelligence (XAI)..“This research represents a significant contribution to the field of XAI,” Wong said..“While analyzing a vast amount of protein binding data from X-ray crystallography, my team revealed the statistics of the physicochemical amino acid interacting patterns which were masked and mixed at the data level due to the entanglement of multiple factors present in the binding environment."."That was the first time we showed entangled statistics can be disentangled to give a correct picture of the deep knowledge missed at the data level with scientific evidence.”.The result showed potential to enable more reliable diagnoses and solutions by health professionals for various diseases at different stages. As a result, Wong and his team developed a new XAI model called Pattern Discovery and Disentanglement (PDD)..“With PDD, we aim to bridge the gap between AI technology and human understanding to help enable trustworthy decision-making and unlock deeper knowledge from complex data sources,” said Dr. Peiyuan Zhou, the lead researcher on Wong’s team. .The researchers foresee PDD making an immense contribution to clinical decision-making..Some case studies have demonstrated PDD can predict patients’ medical results based on their clinical records. The PDD system can also discover new and rare patterns in datasets so researchers and practitioners can detect mislabels or anomalies in machine learning..PDD has been commercialized via Waterloo Commercialization Office. The approach gained an Idea-to-Innovation Grant of $125,000 from the federal Natural Sciences and Engineering Research Council of Canada. .The resarchers’ study Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system appears in the journal NPJ Digital Medicine.
University of Waterloo researchers have developed an artificial intelligence (AI) model to reduce bias and enhance trust and accuracy in machine learning-generated decision-making and knowledge organization..According to a news release from the university, traditional machine learning models often yield biased results, favouring groups with large populations. Any potential solution requires a nuanced examination of patterns and sub-patterns from different classes or primary sources. The medical field is an obvious area where proper AI analysis could be helpful and shallow analysis, harmful. .Hospital staff and medical professionals rely on datasets containing thousands of medical records and complex computer algorithms to make critical decisions about patient care..Machine learning sorts data, which saves time. However, patient groups with rare symptomatic patterns may go undetected, leading to misdiagnosis and worse healthcare outcomes for specific patient groups. .Dr. Andrew Wong, a distinguished professor emeritus of systems design engineering at Waterloo, pioneered a model to eliminate these barriers by untangling complex patterns from data to relate them to specific underlying causes unaffected by anomalies and mislabeled instances. It can enhance trust and reliability in eXplainable Artificial Intelligence (XAI)..“This research represents a significant contribution to the field of XAI,” Wong said..“While analyzing a vast amount of protein binding data from X-ray crystallography, my team revealed the statistics of the physicochemical amino acid interacting patterns which were masked and mixed at the data level due to the entanglement of multiple factors present in the binding environment."."That was the first time we showed entangled statistics can be disentangled to give a correct picture of the deep knowledge missed at the data level with scientific evidence.”.The result showed potential to enable more reliable diagnoses and solutions by health professionals for various diseases at different stages. As a result, Wong and his team developed a new XAI model called Pattern Discovery and Disentanglement (PDD)..“With PDD, we aim to bridge the gap between AI technology and human understanding to help enable trustworthy decision-making and unlock deeper knowledge from complex data sources,” said Dr. Peiyuan Zhou, the lead researcher on Wong’s team. .The researchers foresee PDD making an immense contribution to clinical decision-making..Some case studies have demonstrated PDD can predict patients’ medical results based on their clinical records. The PDD system can also discover new and rare patterns in datasets so researchers and practitioners can detect mislabels or anomalies in machine learning..PDD has been commercialized via Waterloo Commercialization Office. The approach gained an Idea-to-Innovation Grant of $125,000 from the federal Natural Sciences and Engineering Research Council of Canada. .The resarchers’ study Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system appears in the journal NPJ Digital Medicine.
