Hybrid Text Feature Modeling for Disease Group Prediction using Unstructured Physician Notes

11/26/2019
by   Gokul S Krishnan, et al.
0

Existing Clinical Decision Support Systems (CDSSs) largely depend on the availability of structured patient data and Electronic Health Records (EHRs) to aid caregivers. However, in case of hospitals in developing countries, structured patient data formats are not widely adopted, where medical professionals still rely on clinical notes in the form of unstructured text. Such unstructured clinical notes recorded by medical personnel can also be a potential source of rich patient-specific information which can be leveraged to build CDSSs, even for hospitals in developing countries. If such unstructured clinical text can be used, the manual and time-consuming process of EHR generation will no longer be required, with huge person-hours and cost savings. In this paper, we propose a generic ICD9 disease group prediction CDSS built on unstructured physician notes modeled using hybrid word embeddings. These word embeddings are used to train a deep neural network for effectively predicting ICD9 disease groups. Experimental evaluation showed that the proposed approach outperformed the state-of-the-art disease group prediction model built on structured EHRs by 15 proving our hypothesis and eliminating dependency on availability of structured patient data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/19/2019

Towards unstructured mortality prediction with free-text clinical notes

Healthcare data continues to flourish yet a relatively small portion, mo...
research
03/19/2020

Predicting Unplanned Readmissions with Highly Unstructured Data

Deep learning techniques have been successfully applied to predict unpla...
research
05/20/2022

Semi-self-supervised Automated ICD Coding

Clinical Text Notes (CTNs) contain physicians' reasoning process, writte...
research
02/08/2023

Clinical BioBERT Hyperparameter Optimization using Genetic Algorithm

Clinical factors account only for a small portion, about 10-30 controlla...
research
05/31/2019

Multimodal Ensemble Approach to Incorporate Various Types of Clinical Notes for Predicting Readmission

Electronic Health Records (EHRs) have been heavily used to predict vario...
research
06/09/2023

Leveraging text data for causal inference using electronic health records

Text is a ubiquitous component of medical data, containing valuable info...
research
01/19/2021

Inferring COVID-19 Biological Pathways from Clinical Phenotypes via Topological Analysis

COVID-19 has caused thousands of deaths around the world and also result...

Please sign up or login with your details

Forgot password? Click here to reset