multi-source ehr trajectory contextual representation
A Masked language model for multi-source EHR trajectories contextual representation learning
Amirahmadi, Ali, Ohlsson, Mattias, Etminani, Kobra, Melander, Olle, Björk, Jonas
Using electronic health records data and machine learning to guide future decisions needs to address challenges, including 1) long/short-term dependencies and 2) interactions between diseases and interventions. Bidirectional transformers have effectively addressed the first challenge. Here we tackled the latter challenge by masking one source (e.g., ICD10 codes) and training the transformer to predict it using other sources (e.g., ATC codes).
masked language model, multi-source ehr trajectory contextual representation, representation, (12 more...)
2402.06675
Country:
- Europe > Sweden > Skåne County > Malmö (0.05)
- Europe > Sweden > Halland County > Halmstad (0.05)
Technology: