The AI in Healthcare Virtual Summit focused on AI methods and tools that are set to transform healthcare, medicine, and diagnostics along with the latest applications within the industry.
Here are some key sessions during the summit that discussed machine learning for antibiotic discovery, creating personalized neuro medicine using AI and brain modelling, and deep learning for biomedical imaging.
Machine Learning for Antibiotic Discovery
Jonathan Stokes, Banting Fellow of the Broad Institute of MIT and Harvard, discussed the antibiotic-resistance crisis, and the training of a deep neural network to predict new antibiotics.
During the session, Jonathan went over the performance of their predictions on multiple chemical libraries that has led to the discovery of a molecule from the Drug Repurposing Hub – halicin – that is structurally divergent from conventional antibiotics and displays activity against a wide spectrum of pathogens.
“Halicin also effectively treated Clostridioides difficile and Acinetobacter baumannii infections in mice.” Jonathan expressed that deep learning approaches have utility in expanding our antibiotic arsenal.
Creating Personalized Neuromedicine Using Artificial Intelligence and Brain Modelling
During this session, Dalton Sakthivadivel, Biomedical Engineer of Stony Brook University, dove into how the utility of data in medicine is rapidly increasing due to increased precision and availability. Dalton explained that in order to maximize the impact this increase has, clinicians and researchers have been applying unique analysis methods to this data and translating the results into patient care.
One example of this is through personalizing medicine, which entails learning about and responding to a patient’s unique condition. As explained in Dalton’s presentation, within clinical neurosciences, modelling insights can be applied to patient care, on an individual level, by using artificial intelligence and machine learning.
“Through the intelligent analysis of diagnostic data, we can learn about a patient’s brain, and then simulate a patient by building a personal brain model. This enables clear and correct diagnosis, investigation of treatments, and prediction of outcomes.” Dalton also discussed a couple of key case studies to explore recent advances in the field of personalized medicine using computational neurodiagnostics, and how they have been performed.
Deep Learning for Biomedical Imaging
Scientist at Novartis, Xian Zhang, presented how biomedical imaging, such as cellular imaging, tissue imaging, medical imaging and organism imaging are a gold mine for AI and computer vision.
During this session, Xian discussed deep learning methods, including convolution neural networks, generative adversarial networks, autoencoders, and how these all have shown early success in segmentation, classification, regression applications, as well as potential in tasks such as registration, in silico labelling and gaining biological insights.