Neural Machine Translation between Herbal Prescriptions and Diseases

TL;DR

This study employs deep learning models to translate herbal prescriptions to diseases and vice versa using a large-scale Taiwanese health insurance dataset, revealing associations with patient demographics and environmental factors.

Contribution

It introduces a dual neural network approach for herbal medicine and disease translation, leveraging extensive real-world data to uncover contextual factors influencing prescriptions.

Findings

Herbal prescriptions are linked to patient anatomy, sex, age, season, and year.

Temperature and GDP are associated with herbal prescription patterns.

Recurrent neural networks learn both syntax and semantics of herbal and disease data.

Abstract

The current study applies deep learning to herbalism. Toward the goal, we acquired the de-identified health insurance reimbursements that were claimed in a 10-year period from 2004 to 2013 in the National Health Insurance Database of Taiwan, the total number of reimbursement records equaling 340 millions. Two artificial intelligence techniques were applied to the dataset: residual convolutional neural network multitask classifier and attention-based recurrent neural network. The former works to translate from herbal prescriptions to diseases; and the latter from diseases to herbal prescriptions. Analysis of the classification results indicates that herbal prescriptions are specific to: anatomy, pathophysiology, sex and age of the patient, and season and year of the prescription. Further analysis identifies temperature and gross domestic product as the meteorological and socioeconomic factors that are associated with herbal prescriptions. Analysis of the neural machine transitional result indicates that the recurrent neural network learnt not only syntax but also semantics of diseases and herbal prescriptions.