JMIR Publications

ABSTRACT

Background:

Many efforts have been put into the use of automated approaches, such as natural language processing (NLP), to mine or extract data from free-text medical records to construct comprehensive patient profiles for delivering better health-care. Reusing NLP models in new settings, however, remains cumbersome - requiring validation and/or retraining on new data iteratively to achieve convergent results.

Objective:

The aim of this work is to minimise the effort involved in reusing NLP models on free-text medical records.

Methods:

We formally define and analyse the model adaptation problem in phenotype identification tasks. We identify “duplicate waste” and “imbalance waste”, which collectively impede efficient model reuse. We propose a concept embedding based approach to minimise these sources of waste without the need for labelled data from new settings.

Results:

We conduct experiments on data from a large mental health registry to reuse NLP models in four phenotype identification tasks. The proposed approach can choose the best model for a new task, identifying up to 76% of phenotype mentions without the need for validation and model retraining, and with very good performance (93-97% accuracy). It can also provide guidance for validating and retraining the selected model for novel language patterns in new tasks, saving around 80% of the effort required in “blind” model-adaptation approaches.

Conclusions:

Adapting pre-trained NLP models for new tasks can be more efficient and effective if the language pattern landscapes of old settings and new settings can be made explicit and comparable. Our experiments show that the phenotype embedding approach is an effective way to model language patterns for phenotype identification tasks and that its use can guide efficient NLP model reuse.