Deep semi-supervised learning via dynamic anchor graph embedding in latent space

Tu, Enmei; Wang, Zihao; Yang, Jie; Kasabov, Nikola

doi:10.1016/j.neunet.2021.11.026

Cited by 15 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Importantly, in our data set limited to EHR data, we did not have access to other clinical characteristics of patients with AF, such as symptomatology or type of AF (ie, paroxysmal versus persistent), which plays a major role in practical decisions regarding rhythm management. There are methods to map newly collected information (for example, if we were to obtain quality‐of‐life survey results in a subset of our population) to an existing latent space representation, termed semisupervised learning, 43 although such approaches were beyond the scope of this investigation.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of Quantitative Decision‐Making for Rhythm Management of Atrial Fibrillation Using Tabular Q‐Learning

Barrett

Suzuki

Hussein

et al. 2023

JAHA

View full text Add to dashboard Cite

Background Rhythm management is a complex decision for patients with atrial fibrillation (AF). Although clinical trials have identified subsets of patients who might benefit from a given rhythm‐management strategy, for individual patients it is not always clear which strategy is expected to have the greatest mortality benefit or durability. Methods and Results In this investigation 52 547 patients with a new atrial fibrillation diagnosis between 2010 and 2020 were retrospectively identified. We applied a type of artificial intelligence called tabular Q‐learning to identify the optimal initial rhythm‐management strategy, based on a composite outcome of mortality, change in treatment, and sustainability of the given treatment, termed the reward function. We first applied an unsupervised learning algorithm using a variational autoencoder with K‐means clustering to cluster atrial fibrillation patients into 8 distinct phenotypes. We then fit a Q‐learning algorithm to predict the best outcome for each cluster. Although rate‐control strategy was most frequently selected by treating providers, the outcome was superior for rhythm‐control strategies across all clusters. Subjects in whom provider‐selected treatment matched the Q‐table recommendation had fewer total deaths (4 [8.5%] versus 473 [22.4%], odds ratio=0.32, P =0.02) and a greater reward ( P =4.8×10 −6 ). We then demonstrated application of dynamic learning by updating the Q‐table prospectively using batch gradient descent, in which the optimal strategy in some clusters changed from cardioversion to ablation. Conclusions Tabular Q‐learning provides a dynamic and interpretable approach to apply artificial intelligence to clinical decision‐making for atrial fibrillation. Further work is needed to examine application of Q‐learning prospectively in clinical patients.

show abstract

Section: Discussionmentioning

confidence: 99%