Deep-learning technique predicts clinical treatment outcomes

 by Quasar

A new methodology simulates counterfactual, time-varying, and dynamic treatment strategies, allowing doctors to choose the best course of action.

 

When it comes to developing the best medical treatment, doctors must take decisions that will suit the patient’s needs. If doctors know the health report of said patient, they will predict the outcome of their health under various medical treatments and will be able to choose the best treatment as soon as possible.

There is a deep-learning technique, named G-Net, developed by the researchers at MIT and IBM, which provides a window into causal counterfactual prediction, providing physicians the opportunity to explore how a patient might fare under different treatment plans.      G-Net uses recurrent neural networks. (RNN - node connections that allow them to better model temporal sequences with complex and nonlinear dynamics)

G-Net is the first deep-learning approach which can predict both the population-level and individual-level treatment effects under dynamic and time varying treatment strategies.

To test and validate G-Net’s predictive abilities, the researchers considered the circulatory system in septic patients in the ICU. During the tests, CVSim (a mechanistic model of a human cardiovascular system) was used to generate observational patient data, which is used to compare against counterfactual prediction. Testing G-Net’s prediction capability, the team generated two counterfactual datasets. Each contained roughly 1,000 known patient health trajectories, which were created from CVSim using the same “patient” condition as the starting point under treatment A. Then at timestep 33, treatment changed to plan B or C, depending on the dataset. The team then performed 100 prediction trajectories for each of these 1,000 patients, whose treatment and medical history was known up until timestep 33 when a new treatment was administered. In these cases, the prediction agreed well with the “ground-truth” observations for individual patients and averaged population-level trajectories.

Since the g-computation framework is flexible, the researchers wanted to examine G-Net’s prediction using different nonlinear models — in this case, long short-term memory (LSTM) models, which are a type of RNN that can learn from previous data patterns or sequences — against the more classical linear models and a multilayer perception model (MLP), a type of neural network that can make predictions using a nonlinear approach.

While G-Net has done well with simulated data, more needs to be done before it can be applied to real patients. Since neural networks can be thought of as “black boxes” for prediction results, the researchers are beginning to investigate the uncertainty in the model to help ensure safety. In contrast to these approaches that recommend an “optimal” treatment plan without any clinician involvement, G-Net is an easy way to interpret information to conceive best fitted treatments for patients. Further, the team has moved on to using real data from ICU patients with sepsis, bringing it one step closer to implementation in hospitals.

 

Source: 

https://news.mit.edu/2022/deep-learning-technique-predicts-clinical-treatment-outcomes