'Carrusel': an expert system for vestibular diagnosis

Development and Validation of a Machine Learning Model for Detection and Classification of Vertigo

PURPOSE

This study aims to investigate whether artificial intelligence can improve the diagnostic accuracy of vertigo related diseases.

EXPERIMENTAL DESIGN

Based on the clinical guidelines, clinical symptoms and laboratory test results were extracted from electronic medical records as variables. These variables were then input into a machine learning diagnostic model for classification and diagnosis. This study encompasses two primary objectives: Task 1 to distinguish between patients with Benign Paroxysmal Positional Vertigo (BPPV) and non-BPPV. In Task 2, further classifying non-BPPV patients into Ménière's Disease (MD), Vestibular Migraine (VM), and Sudden Sensorineural Hearing Loss accompanied by Vertigo (SSNHLV). The sensitivity, precision, and area under the curve (AUC) metric is primarily used to assess the performance of the machine learning model development phase in a prospective validation cohort.

RESULTS

In our study, 1789 patients were recruited as the training cohort and 1148 patients as the prospective validation cohort. The comprehensive diagnostic performance of the XGBoost model surpasses that of traditional models. The sensitivity, accuracy, and AUC in task 1 were 98.32%, 87.03%, and 0.947, respectively. In task 2, the sensitivity values for MD, SSNHLV, and VM were 89.00%, 100.0%, and 79.40%, respectively. The precision values were 88.80%, 100.0%, and 80.00%, respectively. The AUC values were 0.933, 1.000, and 0.931, respectively. The model can significantly improve the accuracy of diagnosing vertigo diseases.

CONCLUSIONS

This system may enhance the accuracy of classification and diagnosis of vertigo diseases. It offers initial therapy or referrals to clinical doctors, particularly in resource-limited settings.

LEVEL OF EVIDENCE

N/A Laryngoscope, 2024.

Development of an Automated Triage System for Longstanding Dizzy Patients Using Artificial Intelligence

Objective

To report the first steps of a project to automate and optimize scheduling of multidisciplinary consultations for patients with longstanding dizziness utilizing artificial intelligence.

Study Design

Retrospective case review.

Setting

Quaternary referral center.

Methods

A previsit self-report questionnaire was developed to query patients about their complaints of longstanding dizziness. We convened an expert panel of clinicians to review diagnostic outcomes for 98 patients and used a consensus approach to retrospectively determine what would have been the ideal appointments based on the patient's final diagnoses. These results were then compared retrospectively to the actual patient schedules. From these data, a machine learning algorithm was trained and validated to automate the triage process.

Results

Compared with the ideal itineraries determined retrospectively with our expert panel, visits scheduled by the triage clinicians showed a mean concordance of 70%, and our machine learning algorithm triage showed a mean concordance of 79%.

Conclusion

Manual triage by clinicians for dizzy patients is a time-consuming and costly process. The formulated first-generation automated triage algorithm achieved similar results to clinicians when triaging dizzy patients using data obtained directly from an online previsit questionnaire.

Application of machine learning in the diagnosis of vestibular disease

Machine learning is considered a potential aid to support human decision making in disease prediction. In this study, we determined the utility of various machine learning algorithms in classifying peripheral vestibular (PV) and non-PV diseases based on the results of equilibrium function tests. A total of 1009 patients who had undergone our standardized neuro-otological examinations were recruited. We applied five supervised machine learning algorithms (random forest, adaboost, gradient boosting, support vector machine, and logistic regression). After preprocessing the data, optimizing the hyperparameters using GridSearchCV, and performing a final evaluation on the test set using scikit-learn, we evaluated the predictive capability using various performance metrics, namely, accuracy, F1-score, area under the receiver operating characteristic curve, precision, recall, and Matthews correlation coefficient (MCC). All five machine learning algorithms yielded satisfactory results; the accuracy of the algorithms ranged from 76 to 79%, with the support vector machine classifier having the highest accuracy. In cases where the predictions of the five models were consistent, the accuracy of the PV diagnostic results was improved to 83%, whereas it increased to 85% for the non-PV diagnostic results. Future research should increase the number of patients and optimize the classification methods to obtain the highest diagnostic accuracy.

A Questionnaire-Based Ensemble Learning Model to Predict the Diagnosis of Vertigo: Model Development and Validation Study

Background

Questionnaires have been used in the past 2 decades to predict the diagnosis of vertigo and assist clinical decision-making. A questionnaire-based machine learning model is expected to improve the efficiency of diagnosis of vestibular disorders.

Objective

This study aims to develop and validate a questionnaire-based machine learning model that predicts the diagnosis of vertigo.

Methods

In this multicenter prospective study, patients presenting with vertigo entered a consecutive cohort at their first visit to the ENT and vertigo clinics of 7 tertiary referral centers from August 2019 to March 2021, with a follow-up period of 2 months. All participants completed a diagnostic questionnaire after eligibility screening. Patients who received only 1 final diagnosis by their treating specialists for their primary complaint were included in model development and validation. The data of patients enrolled before February 1, 2021 were used for modeling and cross-validation, while patients enrolled afterward entered external validation.

Results

A total of 1693 patients were enrolled, with a response rate of 96.2% (1693/1760). The median age was 51 (IQR 38-61) years, with 991 (58.5%) females; 1041 (61.5%) patients received the final diagnosis during the study period. Among them, 928 (54.8%) patients were included in model development and validation, and 113 (6.7%) patients who enrolled later were used as a test set for external validation. They were classified into 5 diagnostic categories. We compared 9 candidate machine learning methods, and the recalibrated model of light gradient boosting machine achieved the best performance, with an area under the curve of 0.937 (95% CI 0.917-0.962) in cross-validation and 0.954 (95% CI 0.944-0.967) in external validation.

Conclusions

The questionnaire-based light gradient boosting machine was able to predict common vestibular disorders and assist decision-making in ENT and vertigo clinics. Further studies with a larger sample size and the participation of neurologists will help assess the generalization and robustness of this machine learning method.

A Systematic Review of Clinical Vestibular Symptom Triage, Tools, and Algorithms

OBJECTIVE

The evaluation of peripheral vestibular disorders in clinical practice is an especially difficult endeavor, particularly for the inexperienced clinician. The goal of this systematic review is thus to evaluate the design, approaches, and outcomes for clinical vestibular symptom triage and decision support tools reported in contemporary published literature.

DATA SOURCES

A comprehensive search of existing literature in August 2020 was conducted using MEDLINE, CINAHL, and EMBASE using terms of desired diagnostic tools such as algorithm, protocol, and questionnaire as well as an exhaustive set of terms to encompass vestibular disorders.

REVIEW METHODS

Study characteristics, tool metrics, and performance were extracted using a standardized form. Quality assessment was conducted using a modified version of the Quality of Diagnostic Accuracy Studies 2 (QUADAS-2) assessment tool.

RESULTS

A total of 18 articles each reporting a novel tool for the evaluation of vestibular disorders were identified. Tools were organized into 3 discrete categories, including self-administered questionnaires, health care professional administered tools, and decision support systems. Most tools could differentiate between specific vestibular pathologies, with outcome measures including sensitivity, specificity, and accuracy.

CONCLUSION

A multitude of tools have been published to aid with the evaluation of vertiginous patients. Our systematic review identified several low-evidence reports of triage and decision support tools for the evaluation of vestibular disorders.

Artificial Intelligence Applications in Otology: A State of the Art Review

Objective

Recent advances in artificial intelligence (AI) are driving innovative new health care solutions. We aim to review the state of the art of AI in otology and provide a discussion of work underway, current limitations, and future directions.

Data Sources

Two comprehensive databases, MEDLINE and EMBASE, were mined using a directed search strategy to identify all articles that applied AI to otology.

Review Methods

An initial abstract and title screening was completed. Exclusion criteria included nonavailable abstract and full text, language, and nonrelevance. References of included studies and relevant review articles were cross-checked to identify additional studies.

Conclusion

The database search identified 1374 articles. Abstract and title screening resulted in full-text retrieval of 96 articles. A total of N = 38 articles were retained. Applications of AI technologies involved the optimization of hearing aid technology (n = 5; 13% of all articles), speech enhancement technologies (n = 4; 11%), diagnosis and management of vestibular disorders (n = 11; 29%), prediction of sensorineural hearing loss outcomes (n = 9; 24%), interpretation of automatic brainstem responses (n = 5; 13%), and imaging modalities and image-processing techniques (n = 4; 10%). Publication counts of the included articles from each decade demonstrated a marked increase in interest in AI in recent years.

Implications for Practice

This review highlights several applications of AI that otologists and otolaryngologists alike should be aware of given the possibility of implementation in mainstream clinical practice. Although there remain significant ethical and regulatory challenges, AI powered systems offer great potential to shape how healthcare systems of the future operate and clinicians are key stakeholders in this process.

Differential Diagnostic Reasoning Method for Benign Paroxysmal Positional Vertigo Based on Dynamic Uncertain Causality Graph

The accurate differentiation of the subtypes of benign paroxysmal positional vertigo (BPPV) can significantly improve the efficacy of repositioning maneuver in its treatment and thus reduce unnecessary clinical tests and inappropriate medications. In this study, attempts have been made towards developing approaches of causality modeling and diagnostic reasoning about the uncertainties that can arise from medical information. A dynamic uncertain causality graph-based differential diagnosis model for BPPV including 354 variables and 885 causality arcs is constructed. New algorithms are also proposed for differential diagnosis through logical and probabilistic inference, with an emphasis on solving the problems of intricate and confounding disease factors, incomplete clinical observations, and insufficient sample data. This study further uses vertigo cases to test the performance of the proposed method in clinical practice. The results point to high accuracy, a satisfactory discriminatory ability for BPPV, and favorable robustness regarding incomplete medical information. The underlying pathological mechanisms and causality semantics are verified using compact graphical representation and reasoning process, which enhance the interpretability of the diagnosis conclusions.

The methodology of Dynamic Uncertain Causality Graph for intelligent diagnosis of vertigo

Vertigo is a common complaint with many potential causes involving otology, neurology and general medicine, and it is fairly difficult to distinguish the vertiginous disorders from each other accurately even for experienced physicians. Based on comprehensive investigations to relevant characteristics of vertigo, we propose a diagnostic modeling and reasoning methodology using Dynamic Uncertain Causality Graph. The symptoms, signs, findings of examinations, medical histories, etiology and pathogenesis, and so on, are incorporated in the diagnostic model. A modularized modeling scheme is presented to reduce the difficulty in model construction, providing multiple perspectives and arbitrary granularity for disease causality representations. We resort to the "chaining" inference algorithm and weighted logic operation mechanism, which guarantee the exactness and efficiency of diagnostic reasoning under situations of incomplete and uncertain information. Moreover, the causal insights into underlying interactions among diseases and symptoms intuitively demonstrate the reasoning process in a graphical manner. These solutions make the conclusions and advices more explicable and convincing, further increasing the objectivity of clinical decision-making. Verification experiments and empirical evaluations are performed with clinical vertigo cases. The results reveal that, even with incomplete observations, this methodology achieves encouraging diagnostic accuracy and effectiveness. This study provides a promising assistance tool for physicians in diagnosis of vertigo.

Clinical decision support systems and computer-aided diagnosis in otology

OBJECTIVES

We reviewed the progress of the implementation of expert diagnostic systems in the field of otology.

STUDY DESIGN AND SETTING

We conducted a review of the literature at a research institute.

RESULTS

The utilization of expert diagnostic systems in otology is very limited. Previous applications focused primarily upon the diagnosis of vertiginous disorders with the use of deterministic algorithms and, more recently, with adaptive algorithms such as neural networks.

CONCLUSION

Expert systems provide greater diagnostic accuracy to physicians across a wide range of medical specialties. The success of such a system depends upon the strength of its reasoning algorithm, the validity of its knowledge base, and its ease of use.

SIGNIFICANCE

There have been no attempts to develop an adaptive expert system for the full range of otological conditions. Such a tool may be of great use to physicians as a diagnostic aid and educational resource, particularly for those located in isolated sites.

A practical assessment algorithm for diagnosis of dizziness

OBJECTIVE

We sought to test a 3-parameter model for diagnosis of dizziness based on the type and temporal characteristics of the dizziness and on hearing status.

STUDY DESIGN AND SETTING

We conducted a prospective blinded study at a tertiary referral neurotology practice. Before examination, patients completed a questionnaire reporting type and timing of dizziness symptoms and hearing status. Clinical diagnoses were compared with questionnaire results.

RESULTS

Fifty-seven patients completed the questionnaire. We were able to correctly classify 21 (60%) of the 35 subjects who had a common otogenic cause of vertigo by the diagnostic algorithm.

CONCLUSION

A simple classification of dizziness by type, timing, and hearing status can be self-reported by patients using a brief questionnaire. This classification scheme is as good as others of much greater complexity.

SIGNIFICANCE

The simple classification scheme reported here is based on history alone and facilitates triage of dizzy patients into diagnostic groups for work-up and management.

[Intelligent system to perform a diagnostic protocol for lymphatic invasion in laryngeal cancer]

Laryngeal carcinoma is the most frequent malignant tumour in head and neck. Node invasion is known to be one of the most important prognostic factors. The aim of this study has been to design an intelligent system to perform a diagnostic algorithm of metastasic neck nodes. 122 clinical reports of patients diagnosed of laryngeal carcinoma in our department have been reviewed. The compiled data have been: tumor site, T stage, N stage (clinical, after CT scan and post-surgery). The method used to design the intelligent system has been the ID3, which is able to generate a minimal decision tree. Palpation has been the variable that has given more information about node invasion. CT has proved to be more efficient in supraglottic tumours. ID3 method has shown to be useful in performing diagnostic algorithms, specially when the number of cases and diagnostic tests are high.

Comparison between diagnoses of human experts and a neurotologic expert system

The decision-making ability of a recently developed neurotologic expert system was compared with the diagnoses of six physicians. Five of the physicians were residents and one was a specialist in the field of otolaryngology. The test patients were randomly selected from vertiginous patients referred to an otolaryngology clinic. The expert system and the physicians first had identical information on patient history, symptoms, and tests. During the second phase of the study the physicians were allowed to use the full medical records. The correct diagnoses were certified by an experienced specialist in neurotology. The expert system did better in decision-making when both the expert system and the physicians had identical information on patients. However, when the physicians were allowed to use patient's complete medical records, they surpassed the expert system. The expert system diagnosed 65% of the cases, while the physicians first diagnosed 54% of the cases, and then with complete information, 69% of the cases. From the patients' medical records, the physicians obtained information on the time perspective of the symptoms and the progression of the disease. These aspects will be used to further improve the expert system.

Otoneurological expert system

An otoneurological expert system was developed to help collect data and diagnose both central and peripheral diseases causing vertigo. Patient history and otoneurological and other examination results are used in the reasoning process. The case history data can be either mandatory or supportive. Mandatory questions are used to confirm a diagnosis, and conflicting answers are used to reject an unlikely disease. Supportive questions support or suppress a diagnosis, but their presence is not obligatory. The reasoning procedure of the otoneurological expert system scores every question independently for different diagnoses, depending on how well they agree with the symptom entity of a disease. Diagnostic criteria are set for each disease. Graphic displays illustrate the linear and nonlinear correlation between the symptoms and diseases. Emphasis is placed on diminishing the possibility of a wrong decision rather than maximizing the likelihood of reaching only one right decision, so that even rare diseases can be taken into consideration.

Comparison of inference results of two otoneurological expert systems

In this paper, two different otoneurological expert systems, Vertigo and One, the latter developed by us, are considered. The expert systems are evaluated as regards their correctness in reasoning diagnoses. In the light of our data collected from randomly selected test patients, One, being a newer technique, is more effective, since it could infer more cases than vertigo did. All the data was also evaluated and diagnosed by otoneurological specialists, independently of the expert systems, to guarantee objectivity in evaluation of the results of the expert systems.

Reasoning in expert system ONE for vertigo work-up

An otoneurological expert system (ONE) was developed to help collect data and diagnose the work-up of vertigo of both central and peripheral diseases causing vertigo. Patient history and otoneurological and other examination results are used in the reasoning process. The history is interactively collected and is complemented with clinical examination results. The case history data can be either mandatory or supportive. Mandatory questions are used to confirm a diagnosis, and conflicting answers are used to reject an unlikely disease. Supportive questions support or suppress a diagnosis, but their presence is not obligatory. The reasoning procedure of ONE scores every question independently for different diagnoses, depending on how well they agree with the symptom entity of a disease. Diagnostic criteria are set for each disease, in Meniere's disease, for example, the full triad is required. Graphic displays illustrate the linear and nonlinear correlation between the symptoms and diseases. For instance, both second-long Tumarkin-type attacks and attacks lasting hours give a high score while intermediately long attacks score much lower in Meniere's disease. To be able to take even rare diseases into consideration we try to diminish the possibility of a wrong decision rather than maximize the likelihood of reaching only one right decision.

An expert system for the computer-aided diagnosis of dizziness and vertigo

We have developed an expert system to assist in the diagnostic work-up of otoneurological cases. Our otoneurological expert system ONE takes advantage of both patient history and clinical measurement data in order to supply all possible information about the patient's symptoms and other findings. This paper presents ONE after its initial stage of development, which included tests with numerous patients.

Artificial intelligence in medicine and male infertility

MAIN PROBLEM

fertility data is inadequately assessed by traditional statistical methods for a variety of reasons. First, the principal test of male fertility potential, the Semen Analysis (SA) is a composite of several dissimilar parameters, and the SA and other laboratory tests of fertility potential reflect physiological mechanisms that interact in complex ways. Second, patient data is often fragmented, obtained from multiple sources. Importantly, 2 patients are required for the final result.

METHODS

Novel and powerful computational method, the neural network, was explored to analyze fertility data. An integrated series of programs was written in the C computer language to implement a back propagation algorithm. A model data analysis system was chosen, predicting the penetration of zona-free hamster ova by sperm (Sperm Penetration Assay (SPA)) and the distance travelled by the farthest swimming sperm (Penetrak Assay) from the SA, for these 2 assays are generally believed by the reproductive medical community to be independent of the SA. The classification accuracy of the neural network was compared to 2 standard statistical methods, linear discriminant function analysis (LDFA) and quadratic discriminant function analysis (QDFA).

RESULTS

A neural network could be trained to correctly predict the Penetrak result in over 80% of assays it had not previously encountered, and another network could predict the SPA outcome in nearly 70%. The neural network was superior to LDFA and QDFA in predicting both assay outcomes (for Penetrak: LDFA = 64%, QDFA = 69%; for SPA: LDFA = 65%, QDFA = 45%).(ABSTRACT TRUNCATED AT 250 WORDS)