Efficient Reuse of Natural Language Processing Models for Phenotype-Mention Identification in Free-text Electronic Medical Records: A Phenotype Embedding Approach

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 minimize the effort involved in reusing NLP models on free-text medical records. Methods: We formally define and analyse the model adaptation problem in phenotype-mention identification tasks. We identify "duplicate waste" and "imbalance waste", which collectively impede efficient model reuse. We propose a phenotype embedding based approach to minimize 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-mention identification tasks. The proposed approach can choose the best model for a new task, identifying up to 76% (duplicate waste), i.e. 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% (imbalance waste), i.e. 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 phenotypemention embedding approach is an effective way to model language patterns for phenotype-mention identification tasks and that its use can guide efficient NLP model reuse.

Exploring Suicidal Ideation Using an Innovative Mobile App-Strength Within Me: The Usability and Acceptability of Setting up a Trial Involving Mobile Technology and Mental Health Service Users

“…The data were analyzed to train the ML algorithms to produce a risk score that deduced the likelihood of suicide, which was analyzed using natural language processing (NLP). This involved extracting language patterns to make inferences about people’s thoughts and feelings [ 41 , 42 ]. A study demonstrated that NLP analysis using language from social media posts could identify people at risk of suicide [ 43 ].…”

Ontology-Based and Weakly Supervised Rare Disease Phenotyping from Clinical Notes

“…whether experienced by the patient or someone else), and temporality (i.e. whether historical) [14], [25]. These contextual features have been reasonably well detected with rule-based approaches, e.g.…”

Developing automated methods for disease subtyping in UK Biobank: an exemplar study on stroke

“…It may also be relevant to disease subtyping for other conditions, where information from images is important in the diagnosis of disease subtypes. Furthermore, the SemEHR tool used in this project can be easily adapted for research into other phenotypes by adopting transfer learning technologies [ 15 ].…”

“…ontology-driven inferences) [ 10 , 28 ] and identification of contextual mentions (e.g. negation, temporality and the person to whom the information refers to) [ 15 , 18 ]. Very few studies [ 17 ] have investigated methods to help derive disease sub-phenotypes from free text, where the information to derive these exists but additional clinical knowledge is needed to derive it.…”