Abstract
BackgroundIn Chile, a patient needing a specialty consultation or surgery has to first be referred by a general practitioner, then placed on a waiting list. The Explicit Health Guarantees (GES in Spanish) ensures, by law, the maximum time to solve 85 health problems. Usually, a health professional manually verifies if each referral, written in natural language, corresponds or not to a GES-covered disease. An error in this classification is catastrophic for patients, as it puts them on a non-prioritized waiting list, characterized by prolonged waiting times.MethodsTo support the manual process, we developed and deployed a system that automatically classifies referrals as GES-covered or not using historical data. Our system is based on word embeddings specially trained for clinical text produced in Chile. We used a vector representation of the reason for referral and patient's age as features for training machine learning models using human-labeled historical data. We constructed a ground truth dataset combining classifications made by three healthcare experts, which was used to validate our results.ResultsThe best performing model over ground truth reached an AUC score of 0.94, with a weighted F1-score of 0.85 (0.87 in precision and 0.86 in recall). During seven months of continuous and voluntary use, the system has amended 87 patient misclassifications.ConclusionThis system is a result of a collaboration between technical and clinical experts, and the design of the classifier was custom-tailored for a hospital's clinical workflow, which encouraged the voluntary use of the platform. Our solution can be easily expanded across other hospitals since the registry is uniform in Chile.
Highlights
In Chile, a patient needing a specialty consultation or surgery has to first be referred by a general practitioner, placed on a waiting list
Since we were interested in choosing the best embedding for the Explicit Health Guarantees (GES)/non-GES classification task, we selected between three different embeddings using this classification as extrinsic evaluation
The general dataset, constructed with non-GES referrals, showed the best performance in the classification task. This result agrees with the work by Chen et al [33] where they found, for the English language, that word embeddings trained over a clinical corpus outperform an embedding calculated over a general domain larger corpus
Summary
In Chile, a patient needing a specialty consultation or surgery has to first be referred by a general practitioner, placed on a waiting list. A health professional manually verifies if each referral, written in natural language, corresponds or not to a GES-covered disease. An error in this classification is catastrophic for patients, as it puts them on a non-prioritized waiting list, characterized by prolonged waiting times. GES prioritizes 80 health conditions and their maximum amount of time, starting from the initial referral time, that patients may have to wait for treatment. It offers a higher economic coverage than non-GES pathologies for specific pathologies and care services [5]. A non-GES example is a glaucoma, which damages the optic nerve and can cause loss of vision
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
