Interpretable Clinical Decision Support System for Audiology Based on Predicted Common Audiological Functional Parameters (CAFPAs)

被引:6
作者
Buhl, Mareike [1 ,2 ]
机构
[1] Carl von Ossietzky Univ Oldenburg, Med Phys, D-26111 Oldenburg, Germany
[2] Cluster Excellence Hearing4all, D-26111 Oldenburg, Germany
关键词
CDSS; audiology; precision medicine; interpretability; machine learning; expert knowledge; BIG DATA;
D O I
10.3390/diagnostics12020463
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
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.
引用
收藏
页数:23
相关论文
共 42 条
[1]  
[Anonymous], 1999, Zeitschrift Fur Audiologie
[2]  
Beale T., 2002, PROC OOPSLA WORKSHOP, V105, P1
[3]   Principles and Practice of Explainable Machine Learning [J].
Belle, Vaishak ;
Papantonis, Ioannis .
FRONTIERS IN BIG DATA, 2021, 4
[4]   Preparing Laboratories for Interconnected Health Care [J].
Bietenbeck, Andreas ;
Streichert, Thomas .
DIAGNOSTICS, 2021, 11 (08)
[5]   Sensitivity and specificity of automatic audiological classification using expert-labelled audiological data and Common Audiological Functional Parameters [J].
Buhl, Mareike ;
Warzybok, Anna ;
Schaedler, Marc Rene ;
Kollmeier, Birger .
INTERNATIONAL JOURNAL OF AUDIOLOGY, 2021, 60 (01) :16-26
[6]   Common Audiological Functional Parameters (CAFPAs) for single patient cases: deriving statistical models from an expert-labelled data set [J].
Buhl, Mareike ;
Warzybok, Anna ;
Schaedler, Marc Rene ;
Majdani, Omid ;
Kollmeier, Birger .
INTERNATIONAL JOURNAL OF AUDIOLOGY, 2020, 59 (07) :534-547
[7]   Common Audiological Functional Parameters (CAFPAs): statistical and compact representation of rehabilitative audiological classification based on expert knowledge [J].
Buhl, Mareike ;
Warzybok, Anna ;
Schaedler, Marc Rene ;
Lenarz, Thomas ;
Majdani, Omid ;
Kollmeier, Birger .
INTERNATIONAL JOURNAL OF AUDIOLOGY, 2019, 58 (04) :231-245
[8]   Machine Learning Interpretability: A Survey on Methods and Metrics [J].
Carvalho, Diogo, V ;
Pereira, Eduardo M. ;
Cardoso, Jaime S. .
ELECTRONICS, 2019, 8 (08)
[9]  
Deutsche Gesellschaft fur Hals-Nasen-Ohren-Heilkunde Kopfund Hals-Chirurgie e. V. (DGHNO-KHC), 2020, 017071 AWMF
[10]   A Systematic Review of Interventions to Reduce the Effects of Cognitive Biases in the Decision-Making of Audiologists [J].
Galvin, Karyn L. ;
Featherston, Rebecca J. ;
Downie, Laura E. ;
Vogel, Adam P. ;
Hamilton, Bridget ;
Granger, Catherine ;
Shlonsky, Aron .
JOURNAL OF THE AMERICAN ACADEMY OF AUDIOLOGY, 2020, 31 (02) :158-165