A drug recommender system for the treatment of hypertension

Background: One third (20% to 30%) of patients suffering from hypertension show increased blood pressure resistant to treatment. This resistance often has multifactorial causes, like therapeutic inertia and inappropriate medication but also poor patient adherence. Evidence-based guidelines aim to support appropriate health care decisions. However, (i) research and appraisal of clinical guidelines is often not practicable in daily routine care and (ii) guidelines alone are often insufficient to make suitable and personalized treatment decisions. Shared decision-making (SDM) can significantly improve patient adherence, but is also difficult to implement in routine care due to time constraints.

Methods: Clinical Decision Support Systems (CDSSs), designed to support clinical decision-making by providing explainable and personalized treatment recommendations, are expected to remedy the aforementioned issues. In this work we describe a digital recommendation system for the pharmaceutical treatment of hypertension and compare its recommendations with clinical experts. The proposed therapy recommender algorithm combines external evidence (knowledge-based) - derived from clinical guidelines and drugs' professional information - with information stored in routine care data (data-based) - derived from 298 medical records and 900 doctor-patient contacts from 7 general practitioners practices. The developed Graphical User Interface (GUI) visualizes recommendations along with personalized treatment information and intents to support SDM. The CDSS was evaluated on 23 artificial test patients (case vignettes), by comparing its output with recommendations from five specialized physicians.

Results: The results show that the proposed algorithm provides personalized treatment recommendations with large agreement with clinical experts. This is true for agreement with all experts (agree_all), with any expert (agree_any), and with the majority vote of all experts (agree_majority). The performance of a solely data-based approach can be additionally improved by applying evidence-based rules (external evidence). When comparing the achieved results (agree_all) with the inter-rater agreement among experts, the CDSS's recommendations partly agree more often with the experts than the experts among each other.

Conclusion: Overall, the feasibility and performance of medication recommendation systems for the treatment of hypertension could be shown. The major challenges when developing such a CDSS arise from (i) the availability of sufficient and appropriate training and evaluation data and (ii) the absence of standardized medical knowledge such as computerized guidelines. If these challenges are solved, such treatment recommender systems can support physicians with exploiting knowledge stored in routine care data, help to comply with the best available clinical evidence and increase the adherence of the patient by reducing site-effects and individualizing therapies.