Search

Background: In 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., Methods: To 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., Results: The 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., Conclusion: This 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.

Background: There is a growing interest in high income countries to control expenditure on medicines by improving the rationale for their selection. However, in middle income countries with differing priorities and needs, little attention has been paid to this issue. In this paper we explore the policies and processes for the selection and use of medicines in a group of hospitals in Chile, a middle income country which has recently joined the OECD. Methods: A combination of qualitative and quantitative methods was used. A national survey questionnaire was distributed to investigate the role and operation of PTCs (Pharmacy and Therapeutics Committees). Interviews were conducted with key actors in the selection of medicines in large urban public hospitals. Results: The national survey had an overall response rate of 42% (83 out of 196), whilst 7 out of 14 hospitals participated in the qualitative study. High complexity hospitals are large urban hospitals; all of which claim to have a working PTC. The pharmacy offices are mainly involved in dispensing medicines with little involvement in clinical duties. The interviews conducted suggest that the formulary of all the hospitals visited is no more than a stock list. PTCs are unable to influence the prescribing practices of doctors. Members do not feel prepared to challenge the opinions of specialists requesting a certain drug, and decisions are based primarily on costs. The inclusion of medicines in the clinical practice of hospitals is as a result of doctors bypassing the PTC and requesting the purchase of exceptional items, some of which are included in the formulary if they are widely used. Conclusions: There is an urgent need to develop medicine policies in hospitals in Chile. The procedures used to purchase medicines need to be revised. Central guidance for PTCs could help ensure a more rational use of medicines. PTCs need to be empowered to design formularies which cover all the clinical needs of doctors, training members in the analysis of scientific evidence beyond their own specialities. An influential PTC can take the appropriate measures and design workable policies to enforce a cost effective-use of resources. [ABSTRACT FROM AUTHOR]