Doctor recommendation on healthcare consultation platforms: an integrated framework of knowledge graph and deep learning

Abstract

PurposeRecommending suitable doctors to patients on healthcare consultation platforms is important to both the patients and the platforms. Although doctor recommendation methods have been proposed, they failed to explain recommendations and address the data sparsity problem, i.e. most patients on the platforms are new and provide little information except disease descriptions. This research aims to develop an interpretable doctor recommendation method based on knowledge graph and interpretable deep learning techniques to fill the research gaps.Design/methodology/approachThis research proposes an advanced doctor recommendation method that leverages a health knowledge graph to overcome the data sparsity problem and uses deep learning techniques to generate accurate and interpretable recommendations. The proposed method extracts interactive features from the knowledge graph to indicate implicit interactions between patients and doctors and identifies individual features that signal the doctors' service quality. Then, the authors feed the features into a deep neural network with layer-wise relevance propagation to generate readily usable and interpretable recommendation results.FindingsThe proposed method produces more accurate recommendations than diverse baseline methods and can provide interpretations for the recommendations.Originality/valueThis study proposes a novel doctor recommendation method. Experimental results demonstrate the effectiveness and robustness of the method in generating accurate and interpretable recommendations. The research provides a practical solution and some managerial implications to online platforms that confront information overload and transparency issues.

An empirical evaluation of the predictors and consequences of social media health-misinformation seeking behavior during the COVID-19 pandemic

“…Their findings revealed that overload of COVID-19 information significantly and directly affects COVID-19 fatalism and COVID-19 exhaustion. When too much information is available, it becomes a burden rather than a benefit; it is said to be experiencing information overload (Yuan and Deng, 2022). Information overload occurs when a user's ability to process information is surpassed by the volume of available information (Zhang et al, 2016).…”

Investigating the Impacts of Information Overload on Psychological Well-being of Healthcare Professionals: Role of COVID-19 Stressor

“… 4 , 19 Information overload is described as a condition in which there is so much pertinent and potentially effective information available that it becomes a burden rather than a benefit. 33 When a user’s information processing capacity is exceeded by the amount of information available, this is referred to as “information overload.” 34 Over the last few months, the growing levels of relevant health information, particularly through online sources, have exacerbated the problem of health information overload. Thus CIO can be defined as the volume of the information about COVID-19 which is prevalent on SM and is beyond the capacity of the user to process it.…”

Guest editorial: Interpretable AI-enabled online behavior analytics

“…The third article by Hui Yuan and Weiwei Deng presents an interpretable doctor recommendation method by combining a health knowledge graph and deep learning techniques. It provides a practical solution and managerial implications for online platforms that confront information overload and transparency issues (Yuan and Deng, 2022).…”