JMIR Publications

ABSTRACT

Background:

Using computers to help make clinical diagnoses has been a goal of artificial intelligence since its inception. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning based methods to predict the ICD-CM codes based on electronic health records. We report an alternative approach, which is to infer clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations.

Objective:

We report a natural language processing system for generating medical assessment based on patient information described in the electronic health record (EHR) notes.

Methods:

We processed EHR notes into the Subjective, Objective, Assessment and Plan (SOAP) sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to generate “expert-like” assessment of the patient automatically. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources.

Results:

We evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models with a large margin.

Conclusions:

N2MAG could generate a medical assessment from the subject and objective descriptions in EHR note. Future work will assess its potential for clinical decision support.