Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory have created a machine-learning system to extract data from patient vital signs and make predictions on treatments for ICU patients. The approach called "ICU Intervene" can also make predictions far into the future as well as providing reasoning for the model’s predictions, giving physicians more insight
This is very exciting, as the importance of proper ICU treatments hits pretty close to home for me. If this system proves itself to be accurate, in my opinion it can't be implemented fast enough.
"Deep neural-network-based predictive models in medicine are often criticized for their black-box nature," says Nigam Shah, an associate professor of medicine at Stanford University who was not involved in the paper. "However, these authors predict the start and end of medical interventions with high accuracy, and are able to demonstrate interpretability for the predictions they make."
This is very exciting, as the importance of proper ICU treatments hits pretty close to home for me. If this system proves itself to be accurate, in my opinion it can't be implemented fast enough.
"Deep neural-network-based predictive models in medicine are often criticized for their black-box nature," says Nigam Shah, an associate professor of medicine at Stanford University who was not involved in the paper. "However, these authors predict the start and end of medical interventions with high accuracy, and are able to demonstrate interpretability for the predictions they make."