Rationalizing Medical Relation Prediction from Corpus-level Statistics

05/02/2020
by   Zhen Wang, et al.
0

Nowadays, the interpretability of machine learning models is becoming increasingly important, especially in the medical domain. Aiming to shed some light on how to rationalize medical relation prediction, we present a new interpretable framework inspired by existing theories on how human memory works, e.g., theories of recall and recognition. Given the corpus-level statistics, i.e., a global co-occurrence graph of a clinical text corpus, to predict the relations between two entities, we first recall rich contexts associated with the target entities, and then recognize relational interactions between these contexts to form model rationales, which will contribute to the final prediction. We conduct experiments on a real-world public clinical dataset and show that our framework can not only achieve competitive predictive performance against a comprehensive list of neural baseline models, but also present rationales to justify its prediction. We further collaborate with medical experts deeply to verify the usefulness of our model rationales for clinical decision making.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/17/2018

Classifying medical relations in clinical text via convolutional neural networks

Deep learning research on relation classification has achieved solid per...
research
05/01/2015

Grounded Discovery of Coordinate Term Relationships between Software Entities

We present an approach for the detection of coordinate-term relationship...
research
03/29/2020

Named Entities in Medical Case Reports: Corpus and Experiments

We present a new corpus comprising annotations of medical entities in ca...
research
12/11/2015

Distilling Knowledge from Deep Networks with Applications to Healthcare Domain

Exponential growth in Electronic Healthcare Records (EHR) has resulted i...
research
03/29/2021

IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction

Interpretability in Graph Convolutional Networks (GCNs) has been explore...
research
10/14/2021

Relation-aware Heterogeneous Graph for User Profiling

User profiling has long been an important problem that investigates user...
research
11/14/2022

Learning predictive checklists from continuous medical data

Checklists, while being only recently introduced in the medical domain, ...

Please sign up or login with your details

Forgot password? Click here to reset