Incorporating Domain Knowledge into Health Recommender Systems Using Hyperbolic Embeddings

Abstract

In contrast to many other domains, recommender systems in health services may benefit particularly from the incorporation of health domain knowledge, as it helps to provide meaningful and personalised recommendations catering to the individual's health needs. With recent advances in representation learning enabling the hierarchical embedding of health knowledge into the hyperbolic Poincaré space, this work proposes a content-based recommender system for patient-doctor matchmaking in primary care based on patients' health profiles, enriched by pre-trained Poincaré embeddings of the ICD-9 codes through transfer learning. The proposed model outperforms its conventional counterpart in terms of recommendation accuracy and has several important business implications for improving the patient-doctor relationship.

Machine Learning in General Practice: Scoping Review of Administrative Task Support and Automation

“…Table 2 shows the six basic publication attributes of the complete set of 12 studies included following the completion of the identi cation and screening processes described above (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26). The years of publication in the included studies range from 1996 to 2022 with 10 studies published between 2017 and 2022 (15,16,(18)(19)(20)(21)(22)(23)(24)26). Collectively, the studies cross eight countries (USA, Spain, Canada, Great Britain, Poland, Portugal, Australia, and New Zealand) with seven studies originating primarily from the USA (15,16,(19)(20)(21)(22)26).…”

“…Collectively, the studies cross eight countries (USA, Spain, Canada, Great Britain, Poland, Portugal, Australia, and New Zealand) with seven studies originating primarily from the USA (15,16,(19)(20)(21)(22)26). Eight of the studies are journal articles (15-18, 21, 22, 24, 26) and four studies are conference papers (19,20,23,25). The aims of study target various settings of general practice through a variety of problems, such as scheduling, classifying electronic health record text, care management, and facilitating interactions with electronic health records.…”

“…The variety of current general practice problems identi ed concern appointment scheduling (15-17, 20, 21), teleconsultation (18), care management (19,24), communication (22), healthcare recommender systems (23), user interaction with electronic medical records (25), and resource management through scheduling (26), with the most frequently occurring problem being appointment scheduling. Similarly, the data reportedly used in all studies differs both across all identi ed problems and within the same problem from different researchers, with sources largely consisting of proprietary data taken from a variety of domains, including actual general practice clinics (15,17,(20)(21)(22)(23)(24), published clinical guidelines (19), electronic healthcare databases (16), and teleconsultation recordings (18), that differ considerably in their features. In looking at the level of involvement of GPs across all studies, it is not always clearly stated to what extent they participate in the actual research and only two studies clearly state involvement of GPs (18, 26).…”

“…Machine learning. In looking at the type of machine learning used, ten of the studies (15-19, 21, 22, 24-26) modelled their respective administrative tasks as supervised machine learning problems while one study (20) modelled its task as an unsupervised machine learning problem, and a nal study (23) investigated the use of representation learning and transfer learning. The speci c machine learning methods used to solve these problems varied widely from study to study with the single most frequently used technique being regression (15,16,21,24,26).…”

Recommending Best Course of Treatment Based on Similarities of Prognostic Markers

“…It prevents the situation where a doctor is under-appointed or over-appointed and the patients are not being treated even if doctors are available. Peito [35] proposed a HRS for patient-doctor matchmaking based on patients' individual health profiles and consultation history. Another utility HRS was proposed by Kim et al [1] that personalized diet recommended service through considering the real-time vital sign, family history, food preference, and intake of users to solve the limitations in the existing diet recommendation services.…”