Abstract
Common Audiological Functional Parameters (CAFPAs) were previously introduced as abstract, measurement-independent representation of audiological knowledge, and expert-estimated CAFPAs were shown to be applicable as an interpretable intermediate layer in a clinical decision support system (CDSS). Prediction models for CAFPAs were built based on expert knowledge and one audiological database to allow for data-driven estimation of CAFPAs for new, individual patients for whom no expert-estimated CAFPAs are available. Based on the combination of these components, the current study explores the feasibility of constructing a CDSS which is as interpretable as expert knowledge-based classification and as data-driven as machine learning-based classification. To test this hypothesis, the current study investigated the equivalence in performance of predicted CAFPAs compared to expert-estimated CAFPAs in an audiological classification task, analyzed the importance of different CAFPAs for high and comparable performance, and derived explanations for differences in classified categories. Results show that the combination of predicted CAFPAs and statistical classification enables to build an interpretable but data-driven CDSS. The classification provides good accuracy, with most categories being correctly classified, while some confusions can be explained by the properties of the employed database. This could be improved by including additional databases in the CDSS, which is possible within the presented framework.
Highlights
Clinical decision support systems (CDSS) provide the potential to improve objectivity in clinical decision-making, e.g., by providing clinical experts with probabilities for medical findings or diagnoses which are based on large amounts of patient data [1,2]
Rows depict different prediction models compared to expert-estimated Common Audiological Functional Parameters (CAFPAs), and columns depict different comparison sets
The current study explored the feasibility of constructing a clinical decision support system (CDSS) for audiology based on Common Audiological Functional Parameters (CAFPAs) which is as interpretable as expert knowledge-based classification and as data-driven as machine learning-based classification
Summary
Clinical decision support systems (CDSS) provide the potential to improve objectivity in clinical decision-making, e.g., by providing clinical experts with probabilities for medical findings or diagnoses which are based on large amounts of patient data [1,2]. CDSS need to be developed in collaboration with experts [5,6,7]. A CDSS developed in collaboration with experts can combine the advantages of expert knowledge and automatic prediction or classification [7,9]. If an expert is highly experienced, her or his knowledge is highly developed from previous patients, and many connections between different patient cases may be implicitly available. It takes time, work experience and effort to obtain a high degree of experience, and subjective influences are possible. CDSS are not able to use subjective impressions about patients
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
