Evaluation of Machine Learning Algorithms and Explainability Techniques to Detect Hearing Loss From a Speech-in-Noise Screening Test

Predictors of Speech-in-Noise Understanding in a Population of Occupationally Noise-Exposed Individuals

Understanding speech in noise is particularly difficult for individuals occupationally exposed to noise due to a mix of noise-induced auditory lesions and the energetic masking of speech signals. For years, the monitoring of conventional audiometric thresholds has been the usual method to check and preserve auditory function. Recently, suprathreshold deficits, notably, difficulties in understanding speech in noise, has pointed out the need for new monitoring tools. The present study aims to identify the most important variables that predict speech in noise understanding in order to suggest a new method of hearing status monitoring. Physiological (distortion products of otoacoustic emissions, electrocochleography) and behavioral (amplitude and frequency modulation detection thresholds, conventional and extended high-frequency audiometric thresholds) variables were collected in a population of individuals presenting a relatively homogeneous occupational noise exposure. Those variables were used as predictors in a statistical model (random forest) to predict the scores of three different speech-in-noise tests and a self-report of speech-in-noise ability. The extended high-frequency threshold appears to be the best predictor and therefore an interesting candidate for a new way of monitoring noise-exposed professionals.

Artificial intelligence approaches for tinnitus diagnosis: leveraging high-frequency audiometry data for enhanced clinical predictions

This research investigates the application of machine learning to improve the diagnosis of tinnitus using high-frequency audiometry data. A Logistic Regression (LR) model was developed alongside an Artificial Neural Network (ANN) and various baseline classifiers to identify the most effective approach for classifying tinnitus presence. The methodology encompassed data preprocessing, feature extraction focused on point detection, and rigorous model evaluation through performance metrics including accuracy, Area Under the ROC Curve (AUC), precision, recall, and F1 scores. The main findings reveal that the LR model, supported by the ANN, significantly outperformed other machine learning models, achieving an accuracy of 94.06%, an AUC of 97.06%, and high precision and recall scores. These results demonstrate the efficacy of the LR model and ANN in accurately diagnosing tinnitus, surpassing traditional diagnostic methods that rely on subjective assessments. The implications of this research are substantial for clinical audiology, suggesting that machine learning, particularly advanced models like ANNs, can provide a more objective and quantifiable tool for tinnitus diagnosis, especially when utilizing high-frequency audiometry data not typically assessed in standard hearing tests. The study underscores the potential for machine learning to facilitate earlier and more accurate tinnitus detection, which could lead to improved patient outcomes. Future work should aim to expand the dataset diversity, explore a broader range of algorithms, and conduct clinical trials to validate the models' practical utility. The research highlights the transformative potential of machine learning, including the LR model and ANN, in audiology, paving the way for advancements in the diagnosis and treatment of tinnitus.

Toward Generalizable Machine Learning Models in Speech, Language, and Hearing Sciences: Estimating Sample Size and Reducing Overfitting

PURPOSE

Many studies using machine learning (ML) in speech, language, and hearing sciences rely upon cross-validations with single data splitting. This study's first purpose is to provide quantitative evidence that would incentivize researchers to instead use the more robust data splitting method of nested k-fold cross-validation. The second purpose is to present methods and MATLAB code to perform power analysis for ML-based analysis during the design of a study.

METHOD

First, the significant impact of different cross-validations on ML outcomes was demonstrated using real-world clinical data. Then, Monte Carlo simulations were used to quantify the interactions among the employed cross-validation method, the discriminative power of features, the dimensionality of the feature space, the dimensionality of the model, and the sample size. Four different cross-validation methods (single holdout, 10-fold, train-validation-test, and nested 10-fold) were compared based on the statistical power and confidence of the resulting ML models. Distributions of the null and alternative hypotheses were used to determine the minimum required sample size for obtaining a statistically significant outcome (5% significance) with 80% power. Statistical confidence of the model was defined as the probability of correct features being selected for inclusion in the final model.

RESULTS

ML models generated based on the single holdout method had very low statistical power and confidence, leading to overestimation of classification accuracy. Conversely, the nested 10-fold cross-validation method resulted in the highest statistical confidence and power while also providing an unbiased estimate of accuracy. The required sample size using the single holdout method could be 50% higher than what would be needed if nested k-fold cross-validation were used. Statistical confidence in the model based on nested k-fold cross-validation was as much as four times higher than the confidence obtained with the single holdout-based model. A computational model, MATLAB code, and lookup tables are provided to assist researchers with estimating the minimum sample size needed during study design.

CONCLUSION

The adoption of nested k-fold cross-validation is critical for unbiased and robust ML studies in the speech, language, and hearing sciences.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.25237045.

Synergistic integration of Multi-View Brain Networks and advanced machine learning techniques for auditory disorders diagnostics

In the field of audiology, achieving accurate discrimination of auditory impairments remains a formidable challenge. Conditions such as deafness and tinnitus exert a substantial impact on patients' overall quality of life, emphasizing the urgent need for precise and efficient classification methods. This study introduces an innovative approach, utilizing Multi-View Brain Network data acquired from three distinct cohorts: 51 deaf patients, 54 with tinnitus, and 42 normal controls. Electroencephalogram (EEG) recording data were meticulously collected, focusing on 70 electrodes attached to an end-to-end key with 10 regions of interest (ROI). This data is synergistically integrated with machine learning algorithms. To tackle the inherently high-dimensional nature of brain connectivity data, principal component analysis (PCA) is employed for feature reduction, enhancing interpretability. The proposed approach undergoes evaluation using ensemble learning techniques, including Random Forest, Extra Trees, Gradient Boosting, and CatBoost. The performance of the proposed models is scrutinized across a comprehensive set of metrics, encompassing cross-validation accuracy (CVA), precision, recall, F1-score, Kappa, and Matthews correlation coefficient (MCC). The proposed models demonstrate statistical significance and effectively diagnose auditory disorders, contributing to early detection and personalized treatment, thereby enhancing patient outcomes and quality of life. Notably, they exhibit reliability and robustness, characterized by high Kappa and MCC values. This research represents a significant advancement in the intersection of audiology, neuroimaging, and machine learning, with transformative implications for clinical practice and care.

Explainable machine learning reveals the relationship between hearing thresholds and speech-in-noise recognition in listeners with normal audiograms

Some individuals complain of listening-in-noise difficulty despite having a normal audiogram. In this study, machine learning is applied to examine the extent to which hearing thresholds can predict speech-in-noise recognition among normal-hearing individuals. The specific goals were to (1) compare the performance of one standard (GAM, generalized additive model) and four machine learning models (ANN, artificial neural network; DNN, deep neural network; RF, random forest; XGBoost; eXtreme gradient boosting), and (2) examine the relative contribution of individual audiometric frequencies and demographic variables in predicting speech-in-noise recognition. Archival data included thresholds (0.25-16 kHz) and speech recognition thresholds (SRTs) from listeners with clinically normal audiograms (n = 764 participants or 1528 ears; age, 4-38 years old). Among the machine learning models, XGBoost performed significantly better than other methods (mean absolute error; MAE = 1.62 dB). ANN and RF yielded similar performances (MAE = 1.68 and 1.67 dB, respectively), whereas, surprisingly, DNN showed relatively poorer performance (MAE = 1.94 dB). The MAE for GAM was 1.61 dB. SHapley Additive exPlanations revealed that age, thresholds at 16 kHz, 12.5 kHz, etc., on the order of importance, contributed to SRT. These results suggest the importance of hearing in the extended high frequencies for predicting speech-in-noise recognition in listeners with normal audiograms.

Characterization of Synthetic Health Data Using Rule-Based Artificial Intelligence Models

The aim of this study is to apply and characterize eXplainable AI (XAI) to assess the quality of synthetic health data generated using a data augmentation algorithm. In this exploratory study, several synthetic datasets are generated using various configurations of a conditional Generative Adversarial Network (GAN) from a set of 156 observations related to adult hearing screening. A rule-based native XAI algorithm, the Logic Learning Machine, is used in combination with conventional utility metrics. The classification performance in different conditions is assessed: models trained and tested on synthetic data, models trained on synthetic data and tested on real data, and models trained on real data and tested on synthetic data. The rules extracted from real and synthetic data are then compared using a rule similarity metric. The results indicate that XAI may be used to assess the quality of synthetic data by (i) the analysis of classification performance and (ii) the analysis of the rules extracted on real and synthetic data (number, covering, structure, cut-off values, and similarity). These results suggest that XAI can be used in an original way to assess synthetic health data and extract knowledge about the mechanisms underlying the generated data.

Artificial Intelligence and Machine (Deep) Learning in Otorhinolaryngology: A Bibliometric Analysis Based on VOSviewer and CiteSpace

BACKGROUND

Otorhinolaryngology diseases are well suited for artificial intelligence (AI)-based interpretation. The use of AI, particularly AI based on deep learning (DL), in the treatment of human diseases is becoming more and more popular. However, there are few bibliometric analyses that have systematically studied this field.

OBJECTIVE

The objective of this study was to visualize the research hot spots and trends of AI and DL in ENT diseases through bibliometric analysis to help researchers understand the future development of basic and clinical research.

METHODS

In all, 232 articles and reviews were retrieved from The Web of Science Core Collection. Using CiteSpace and VOSviewer software, countries, institutions, authors, references, and keywords in the field were visualized and examined.

RESULTS

The majority of these papers came from 44 nations and 498 institutions, with China and the United States leading the way. Common diseases used by AI in ENT include otosclerosis, otitis media, nasal polyps, sinusitis, and so on. In the early years, research focused on the analysis of hearing and articulation disorders, and in recent years mainly on the diagnosis, localization, and grading of diseases.

CONCLUSIONS

The analysis shows the periodical hot spots and development direction of AI and DL application in ENT diseases from the time dimension. The diagnosis and prognosis of otolaryngology diseases and the analysis of otolaryngology endoscopic images have been the focus of current research and the development trend of future.

Characterization of Inclination Analysis for Predicting Onset of Heart Failure from Primary Care Electronic Medical Records

The aim of this study is to characterize the performance of an inclination analysis for predicting the onset of heart failure (HF) from routinely collected clinical biomarkers extracted from primary care electronic medical records. A balanced dataset of 698 patients (with/without HF), including a minimum of five longitudinal measures of nine biomarkers (body mass index, diastolic and systolic blood pressure, fasting glucose, glycated hemoglobin, low-density and high-density lipoproteins, total cholesterol, and triglycerides) is used. The proposed algorithm achieves an accuracy of 0.89 (sensitivity of 0.89, specificity of 0.90) to predict the inclination of biomarkers (i.e., their trend towards a 'survival' or 'collapse' as defined by an inclination analysis) on a labeled, balanced dataset of 40 patients. Decision trees trained on the predicted inclination of biomarkers have significantly higher recall (0.69 vs. 0.53) and significantly higher negative predictive value (0.60 vs. 0.55) than those trained on the average values computed from the measures of biomarkers available before the onset of the disease, suggesting that an inclination analysis can help identify the onset of HF in the primary care patient population from routinely available clinical data. This exploratory study provides the basis for further investigations of inclination analyses to identify at-risk patients and generate preventive measures (i.e., personalized recommendations to reverse the trend of biomarkers towards collapse).

Profiling hearing aid users through big data explainable artificial intelligence techniques

Debilitating hearing loss (HL) affects ~6% of the human population. Only 20% of the people in need of a hearing assistive device will eventually seek and acquire one. The number of people that are satisfied with their Hearing Aids (HAids) and continue using them in the long term is even lower. Understanding the personal, behavioral, environmental, or other factors that correlate with the optimal HAid fitting and with users' experience of HAids is a significant step in improving patient satisfaction and quality of life, while reducing societal and financial burden. In SMART BEAR we are addressing this need by making use of the capacity of modern HAids to provide dynamic logging of their operation and by combining this information with a big amount of information about the medical, environmental, and social context of each HAid user. We are studying hearing rehabilitation through a 12-month continuous monitoring of HL patients, collecting data, such as participants' demographics, audiometric and medical data, their cognitive and mental status, their habits, and preferences, through a set of medical devices and wearables, as well as through face-to-face and remote clinical assessments and fitting/fine-tuning sessions. Descriptive, AI-based analysis and assessment of the relationships between heterogeneous data and HL-related parameters will help clinical researchers to better understand the overall health profiles of HL patients, and to identify patterns or relations that may be proven essential for future clinical trials. In addition, the future state and behavioral (e.g., HAids Satisfiability and HAids usage) of the patients will be predicted with time-dependent machine learning models to assist the clinical researchers to decide on the nature of the interventions. Explainable Artificial Intelligence (XAI) techniques will be leveraged to better understand the factors that play a significant role in the success of a hearing rehabilitation program, constructing patient profiles. This paper is a conceptual one aiming to describe the upcoming data collection process and proposed framework for providing a comprehensive profile for patients with HL in the context of EU-funded SMART BEAR project. Such patient profiles can be invaluable in HL treatment as they can help to identify the characteristics making patients more prone to drop out and stop using their HAids, using their HAids sufficiently long during the day, and being more satisfied by their HAids experience. They can also help decrease the number of needed remote sessions with their Audiologist for counseling, and/or HAids fine tuning, or the number of manual changes of HAids program (as indication of poor sound quality and bad adaptation of HAids configuration to patients' real needs and daily challenges), leading to reduced healthcare cost.