Common Audiological Functional Parameters (CAFPAs): statistical and compact representation of rehabilitative audiological classification based on expert knowledge

Buhl, Mareike; Warzybok, Anna; Schädler, Marc René; Lenarz, Thomas; Majdani, Omid; Kollmeier, Birger

doi:10.1080/14992027.2018.1554912

Cited by 8 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the threshold-related CAFPAs C A1 and C A2 are among the best-predicted ones. These are closely related to the audiogram (8). For predicting them, the models selected suitable audiogram frequencies, as well as the hearing threshold level L2.5 at 1.5 kHz from the adaptive categorical loudness scaling (ACALOS).…”

Section: Model Interpretability Via Feature Importance Assessmentmentioning

confidence: 99%

“…Most often occurring distortions were described as the availability bias, confirmation bias, and premature closure, amongst others ( 7 ). Lastly, different physicians may have access to different measurements (data) because different clinics may use different test batteries in their assessment kits which can vary with respect to their measurement precision and validity ( 8 ). Additionally, it is possible that in the longitudinal evaluation of a patient, required data from previous potential examinations is missing, or inconsistencies in the administered tests entail difficulties for a physician newly involved in the case ( 8 ).…”

Section: Introductionmentioning

confidence: 99%

“…Lastly, different physicians may have access to different measurements (data) because different clinics may use different test batteries in their assessment kits which can vary with respect to their measurement precision and validity ( 8 ). Additionally, it is possible that in the longitudinal evaluation of a patient, required data from previous potential examinations is missing, or inconsistencies in the administered tests entail difficulties for a physician newly involved in the case ( 8 ). In summary, the aforementioned factors arguably lead to variability in the clinical decision-making process across physicians and clinics, and facilitate distortions in diagnostic outcomes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Common Audiological Functional Parameters (CAFPAs) as Interpretable Intermediate Representation in a Clinical Decision-Support System for Audiology

Saak

Hildebrandt

Kollmeier

et al. 2020

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

The application of machine learning for the development of clinical decision-support systems in audiology provides the potential to improve the objectivity and precision of clinical experts' diagnostic decisions. However, for successful clinical application, such a tool needs to be accurate, as well as accepted and trusted by physicians. In the field of audiology, large amounts of patients' data are being measured, but these are distributed over local clinical databases and are heterogeneous with respect to the applied assessment tools. For the purpose of integrating across different databases, the Common Audiological Functional Parameters (CAFPAs) were recently established as abstract representations of the contained audiological information describing relevant functional aspects of the human auditory system. As an intermediate layer in a clinical decision-support system for audiology, the CAFPAs aim at maintaining interpretability to the potential users. Thus far, the CAFPAs were derived by experts from audiological measures. For designing a clinical decision-support system, in a next step the CAFPAs need to be automatically derived from available data of individual patients. Therefore, the present study aims at predicting the expert generated CAFPA labels using three different machine learning models, namely the lasso regression, elastic nets, and random forests. Furthermore, the importance of different audiological measures for the prediction of specific CAFPAs is examined and interpreted. The trained models are then used to predict CAFPAs for unlabeled data not seen by experts. Prediction of unlabeled cases is evaluated by means of model-based clustering methods. Results indicate an adequate prediction of the ten distinct CAFPAs. All models perform comparably and turn out to be suitable choices for the prediction of CAFPAs. They also generalize well to unlabeled data. Additionally, the extracted relevant features are plausible for the respective CAFPAs, facilitating interpretability of the predictions. Based on the trained models, a prototype of a clinical decision-support system in audiology can be implemented and extended towards clinical databases in the future.

show abstract

Section: Model Interpretability Via Feature Importance Assessmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Common Audiological Functional Parameters (CAFPAs) as Interpretable Intermediate Representation in a Clinical Decision-Support System for Audiology

Saak

Hildebrandt

Kollmeier

et al. 2020

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the purpose of showing the application of the Beta-MCA model to medical data, a data set containing Common Audiological Functional Parameters (CAFPAs) is used. CAFPAs were introduced by Buhl et al [ 9 , 23 ] as an abstract representation of the human auditory system which are independent of audiological tests performed for the respective patients. The data used here comprises CAFPA values determined by an expert survey, where leading clinical audiologists and physicians labelled the database from Hörzentrum Oldenburg, Germany, by indicating audiological findings, treatment recommendations, and CAFPAs for 287 single patients.…”

Section: Methodsmentioning

confidence: 99%

“…In this work, we aim at generalizations of standard noisy-OR models towards models with observable values that lie within an interval, as they occur, e.g., for medical data analysis. An example for medical data that we will use is provided in the form of Common Audiological Functional Parameters (CAFPAs) [ 9 , 23 ] describing certain audiological symptoms which can be used to infer different types of causes for hearing loss or hearing deficits. Another example that we will use is image data that are conventionally stored by assigning a pixel value in an interval (e.g.,

).…”

Section: Introductionmentioning

confidence: 99%

Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data

Mousavi

Buhl

Guiraud

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

Latent Variable Models (LVMs) are well established tools to accomplish a range of different data processing tasks. Applications exploit the ability of LVMs to identify latent data structure in order to improve data (e.g., through denoising) or to estimate the relation between latent causes and measurements in medical data. In the latter case, LVMs in the form of noisy-OR Bayes nets represent the standard approach to relate binary latents (which represent diseases) to binary observables (which represent symptoms). Bayes nets with binary representation for symptoms may be perceived as a coarse approximation, however. In practice, real disease symptoms can range from absent over mild and intermediate to very severe. Therefore, using diseases/symptoms relations as motivation, we here ask how standard noisy-OR Bayes nets can be generalized to incorporate continuous observables, e.g., variables that model symptom severity in an interval from healthy to pathological. This transition from binary to interval data poses a number of challenges including a transition from a Bernoulli to a Beta distribution to model symptom statistics. While noisy-OR-like approaches are constrained to model how causes determine the observables’ mean values, the use of Beta distributions additionally provides (and also requires) that the causes determine the observables’ variances. To meet the challenges emerging when generalizing from Bernoulli to Beta distributed observables, we investigate a novel LVM that uses a maximum non-linearity to model how the latents determine means and variances of the observables. Given the model and the goal of likelihood maximization, we then leverage recent theoretical results to derive an Expectation Maximization (EM) algorithm for the suggested LVM. We further show how variational EM can be used to efficiently scale the approach to large networks. Experimental results finally illustrate the efficacy of the proposed model using both synthetic and real data sets. Importantly, we show that the model produces reliable results in estimating causes using proofs of concepts and first tests based on real medical data and on images.

show abstract

Auditory model-based parameter estimation and selection of the most informative experimental conditions

Dietze,

Reinsch,

Encke

et al. 2024

Acta Acust.

View full text Add to dashboard Cite

Identifying the causes underlying a person’s hearing impairment is challenging. It requires linking the results of listening tests to possible pathologies of the highly non-linear auditory system. This process is further aggravated by restrictions in measurement time, especially in clinical settings. A central but difficult goal is thus, to maximize the diagnostic information that is collectable within a given time frame. This study demonstrates the practical applicability of the model-based experiment-steering procedure introduced in Herrmann and Dietz (2021, Acta Acustica, 5:51). The approach chooses the stimuli that are presented and estimates the model parameters best predicting the subject’s performance using a maximum-likelihood method. The same binaural tone-in-noise detection task was conducted using two measurement procedures: A standard adaptive staircase procedure and the model-based selection procedure based on an existing model. The model-steered procedure reached the same accuracy of model parameter estimation in on average only 42% of the time that was required with the standard adaptive procedure. Difficulties regarding the choice of a reliable model and reasonable discretization steps of its parameters are discussed. Although the physiological causes of an individual’s results cannot directly be inferred using this procedure, a characterization in terms of functional parameters is possible.

show abstract

Common Audiological Functional Parameters (CAFPAs): statistical and compact representation of rehabilitative audiological classification based on expert knowledge

Cited by 8 publications

References 25 publications

Predicting Common Audiological Functional Parameters (CAFPAs) as Interpretable Intermediate Representation in a Clinical Decision-Support System for Audiology

Predicting Common Audiological Functional Parameters (CAFPAs) as Interpretable Intermediate Representation in a Clinical Decision-Support System for Audiology

Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data

Auditory model-based parameter estimation and selection of the most informative experimental conditions

Contact Info

Product

Resources

About