Otoneurological expert system

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.

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.

Predictive Capability of an iPad-Based Medical Device (medx) for the Diagnosis of Vertigo and Dizziness

Background

Making the correct diagnosis of patients presenting with vertigo and dizziness in clinical practice is often challenging.

Objective

In this study we examined the performance of the iPad based program medx in the prediction of different clinical vertigo and dizziness diagnoses and as a diagnostic tool to distinguish between them.

Patients and methods

The data collection was done in the outpatient clinic of the German Center of Vertigo and Balance Disorders. The “gold standard diagnosis” was defined as the clinical diagnosis of the specialist during the visit of the patient based on standardized history and clinical examination. Another independent and blinded physician finalized each patient’s case in the constellatory diagnostic system of medx based on an algorithm using all available clinical information. These diagnoses were compared to the “gold standard” by retrospective review of the charts of the patients. The accuracy provided by medx was defined as the number of correctly classified diagnoses. In addition, the probability of being test positive when a disease was present (sensitivity), of being test negative when a disease was absent (specificity), of having the disease when the test is positive (positive predictive value) and of not having the disease when the test is negative (negative predictive value) for the most common diagnoses were reported. Sixteen possible different vertigo and dizziness diagnoses could be provided by medx.

Results

A total of 610 patients (mean age 58.1 ± 16.3 years, 51.2% female) were included. The accuracy for the most common diagnoses was between 82.1 and 96.6% with a sensitivity of 40 to 80.5% and a specificity of more than 80%. When analyzing the quality of medx in a multiclass problem for the six most common clinical diagnoses, the sensitivity, specificity, positive and negative predictive values were as follows: Bilateral vestibulopathy (81.6, 97.1, 71.1, and 97.5%), Menière’s disease (77.8, 97.6, 87.0, and 95.3%), benign paroxysmal positional vertigo (61.7, 98.3, 86.6, and 93.4%), downbeat nystagmus syndrome (69.6, 97.7, 71.1, and 97.5%), vestibular migraine (34.7, 97.8, 76.1, and 88.3%), and phobic postural vertigo (80.5, 82.5, 52.5, and 94.6%).

Conclusion

This study demonstrates that medx is a new and easy approach to screen for different diagnoses. With the high specificity and negative predictive value, the system helps to rule out differential diagnoses and can therefore also lead to a cost reduction in the health care system. However, the sensitivity was unexpectedly low, especially for vestibular migraine. All in all, this device can only be a complementary tool, in particular for non-experts in the field.

Disease Profiling for Computerized Peer Support of Ménière's Disease

Background

Peer support is an emerging form of person-driven active health care. Chronic conditions such as Ménière’s disease (a disorder of the inner ear) need continuing rehabilitation and support that is beyond the scope of routine clinical medical practice. Hence, peer-support programs can be helpful in supplementing some of the rehabilitation aspects.

Objective

The aim of this study was to design a computerized data collection system for the peer support of Menière’s disease that is capable in profiling the subject for diagnosis and in assisting with problem solving.

Methods

The expert program comprises several data entries focusing on symptoms, activity limitations, participation restrictions, quality of life, attitude and personality trait, and an evaluation of disease-specific impact. Data was collected from 740 members of the Finnish Ménière’s Federation and utilized in the construction and evaluation of the program.

Results

The program verifies the diagnosis of a person by using an expert system, and the inference engine selects 50 cases with matched symptom severity by using a nearest neighbor algorithm. These cases are then used as a reference group to compare with the person’s attitude, sense of coherence, and anxiety. The program provides feedback for the person and uses this information to guide the person through the problem-solving process.

Conclusions

This computer-based peer-support program is the first example of an advanced computer-oriented approach using artificial intelligence, both in the profiling of the disease and in profiling the person’s complaints for hearing loss, tinnitus, and vertigo.

Genetic Algorithm Based Approach in Attribute Weighting for a Medical Data Set

Genetic algorithms have been utilized in many complex optimization and simulation tasks because of their powerful search method. In this research we studied whether the classification performance of the attribute weighted methods based on the nearest neighbour search can be improved when using the genetic algorithm in the evolution of attribute weighting. The attribute weights in the starting population were based on the weights set by the application area experts and machine learning methods instead of random weight setting. The genetic algorithm improved the total classification accuracy and the median true positive rate of the attribute weighted k-nearest neighbour method using neighbour’s class-based attribute weighting. With other methods, the changes after genetic algorithm were moderate.

Postural stability and quality of life after guided and self-training among older adults residing in an institutional setting

Purpose

To evaluate whether rehabilitation of muscle force or balance improves postural stability and quality of life (QoL), and whether self-administered training is comparable with guided training among older adults residing in an institutional setting.

Patients and methods

A randomized, prospective intervention study was undertaken among 55 elderly patients. Three intervention groups were evaluated: a muscle force training group; a balance and muscle force training group; and a self-administered training group. Each group underwent 1-hour-long training sessions, twice a week, for 3 months. Postural stability was measured at onset, after 3 months, and after 6 months. Time-domain-dependent body sway variables were calculated. The fall rate was evaluated for 3 years. General health related quality of life (HRQoL) was measured with a 15D instrument. Postural stability was used as a primary outcome, with QoL and falls used as secondary outcomes.

Results

Muscle force trainees were able to undertake training, progressing towards more strenuous exercises. In posturography, the number of spiky oscillations was reduced after training, and stationary fields of torque moments of the ankle increased, providing better postural stability in all groups; in particular, the zero crossing rate of weight signal and the number of low variability episodes in the stabilogram were improved after training. While no difference was found between different training groups in posturography outcomes, a reduction of fall rate was significant in only the guided training groups. A significant part of the variability of the QoL could be explained by the posturography outcome (46%). However, the outcome of training was associated with a reduced QoL.

Conclusion

Even moderate or severely demented residents could do exercises in five-person groups under the supervision of a physiotherapist. An improvement in postural stability was observed in all training groups, indicating that even self-administered training could be beneficial. Posturography outcome indicated that training alters the postural strategy by reducing the oscillatory fluctuations of body sway signal. However, only guided training tended to reduce falls. Short training intervention programs may decrease QoL by changing the elderly’s daily routine and making it more active and exhausting.

Risk factors of falls in community dwelling active elderly

OBJECTIVE

To search for measures to describe and relate to accidental falls in community dwelling elderly.

METHOD

A EuroQol EQ-5D questionnaire based on a patient's otoneurological case history provided a general health related quality of life measure, a fall history for the last 3 months and force platform measures for 96 active elderly from a pensioner organization.

RESULTS

On average, the elderly experienced 0.3 falls over the preceding three months. A fall was seen to cause a significant deterioration in the quality of life and vertigo and caused fear of falling. The postural instability correlated with falls. Vertigo was present among 42% and was most commonly characterized as episodic and rotatory in factorial analysis items relating to vertigo correlated to falls and balance complaints. Four factors were identified and three of these correlated with falls. Vestibular failure correlated to a fall occurring when a person was rising up; Movement intolerance correlated with falls due to slips and trips, and Near-syncope factor correlated to falls for other reasons. In posturography, the variable measuring critical time describing the memory based "closed loop" control of postural stability carried a risk for accidental fall with an odds ratio of 6. The variable measuring zero crossing velocity showed a high rate of velocity change around the neutral position of stance.

CONCLUSION

Vertigo and poor postural stability were the major reasons for falls in the active elderly. In ageing, postural control is shifted towards open loop control (visual, proprioception, exteroception and vestibular) instead of closed loop control and is a factor that contributes to a fall.

Meniere's disease: a reappraisal supported by a variable latency of symptoms and the MRI visualisation of endolymphatic hydrops

OBJECTIVES

To evaluate the onset of vertigo, hearing loss and tinnitus in Ménière's disease and the associated endolymphatic hydrops (EH) of the inner ear.

DESIGN

Multicentre evaluation of three patient groups.

SETTINGS

Disease-specific symptoms were reviewed among referred patients in a tertiary referral hospital in Finland and in members of a Finnish Ménière Association in Finland. The MRI of a separate group of patients was undertaken in a tertiary referral centre in Japan.

PARTICIPANTS

340 patients were reviewed in the referral hospital along with 740 members of the Ménière Association. MRI was undertaken in 224 patients in Japan.

PRIMARY AND SECONDARY OUTCOME MEASURES

Latency and symptom development in Ménière's disease, and the appearance of EH of the inner ear in monosymptomatic patients and in Ménière's disease.

RESULTS

The mean age of the first symptom was 43.8 years, with 10% of the patients being older than 65 years. The time delay between hearing loss and vertigo was more than 5 years in 20% of the members and of the patients. Gadolinium-contrasted MRI demonstrated EH in 90% of the patients with Ménière's disease, in which 75% was bilateral among patients with unilateral symptoms. In monosymptomatic patients with vertigo, tinnitus or hearing loss; EH was demonstrated in 55-90% of the patients either in the cochlea and/or the vestibulum of the symptomatic ear.

CONCLUSIONS

Ménière's disease often shows bilateral EH and comprises a continuum from a monosymptomatic disease to the typical symptom complex of the disease. We suggest that a 3T MRI measurement should be carried out in patients with sensory-neural hearing loss, vertigo and tinnitus, 4 h after the intravenous injection of a gadolinium-contrast agent to verify the inner ear pathology. This may lead to a better management of the condition.

Characterization of presbyequilibrium among institutionalized elderly persons

OBJECTIVE

The aim was to characterize dizziness, vertigo, poor maintenance of posture, and sudden instabilities (called presbyequilibrium) among institutionalized elderly to model and identify possible treatable causes.

METHODS

A questionnaire based study focusing on symptoms among 72 elderly persons from a single residential facility and followed them for 3 years.

RESULTS

Dizziness, vertigo, poor maintenance of posture, and black-outs were reported by 68% of the 72 elderly and make them at risk for falls, and reduced quality of life. The most common complaint was postural instability, with a tendency to fall. "Spinning" vertigo and "floating" sensation had a strong inter-correlation and correlated with habitual falls. The various dizziness symptoms often occurred in combinations. Attacks of self-experienced syncope never occurred alone but always in combination with "spinning vertigo" or "tendency to fall". In factorial analysis, presbyequilibrium could be divided into six categories. Two of these categories correlated with falls.

CONCLUSIONS

Among elderly, presbyequilibrium is commonly characterized by a combination of phenomena involving perceptual, orientation, postural, and autonomic manifestations. It is often difficult to obtain an accurate history from the elderly and the presence of vestibular symptoms is frequently overlooked. Taking a careful history and utilizing the classification of symptoms that emerged from the factorial analysis may give a deeper understanding of the etiology of presbyequilibrium, thereby facilitating appropriate rehabilitation.

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.

Generating decision trees from otoneurological data with a variable grouping method

When medical data sets are modelled by machine learning methods, wealth of variables may be available. This paper deals with variable selection for decision tree induction in the context of two otoneurological data sets: vertigo data, and postoperative nausea and vomiting data. First, a variable grouping method based on measures of association and graph theoretic techniques was used to gain insight into data. Then, representations of learning data were defined using the information from discovered variable groups, and decision trees were generated. The use of variable grouping method was beneficial by revealing interesting associations between variables and enabling generation of accurate and reasonable decision trees that modelled the application areas from different viewpoints.

Usefulness of imputation for the analysis of incomplete otoneurologic data

The usefulness of imputation in the treatment of missing values of an otoneurologic database for the discriminant analysis was evaluated on the basis of the agreement of imputed values and the analysis results. The data consisted of six patient groups with vertigo (N=564). There were 38 variables and 11% of the data was missing. Missing values were filled in with the means, regression and Expectation-Maximisation (EM) imputation methods and a random imputation method provided the baseline results. Means, regression and EM methods agreed on 41-42% of the imputed missing values. The level of agreement between these and the random method was 20-22%. Despite the moderate agreement between the means, regression and EM methods, the discriminant functions were similar and accurate (prediction accuracy 83-99%). The discriminant functions obtained from the randomly imputed data were also accurate having prediction accuracy 88-97%. Imputation seems to be a useful method for treating the missing data in this database. However, a lot of data was missing in otoneurologic tests, which are likely to be of less importance in the diagnosis of vertiginous patients. Consequently, the disagreement of the methods did not affect clearly the discriminant analysis, and, therefore, future research requires more complete data and advanced imputation methods.

Production of diagnostic rules from a neurotologic database with decision trees

A decision tree is an artificial intelligence program that is adaptive and is closely related to a neural network, but can handle missing or nondecisive data in decision-making. Data on patients with Meniere's disease, vestibular schwannoma, traumatic vertigo, sudden deafness, benign paroxysmal positional vertigo, and vestibular neuritis were retrieved from the database of the otoneurologic expert system ONE for the development and testing of the accuracy of decision trees in the diagnostic workup. Decision trees were constructed separately for each disease. The accuracies of the best decision trees were 94%, 95%, 99%, 99%, 100%, and 100% for the respective diseases. The most important questions concerned the presence of vertigo, hearing loss, and tinnitus; duration of vertigo; frequency of vertigo attacks; severity of rotational vertigo; onset and type of hearing loss; and occurrence of head injury in relation to the timing of onset of vertigo. Meniere's disease was the most difficult to classify correctly. The validity and structure of the decision trees are easily comprehended and can be used outside the expert system.

Discovering diagnostic rules from a neurotologic database with genetic algorithms

Data on patients with Meniere's disease, vestibular schwannoma, traumatic vertigo, sudden deafness, benign paroxysmal positional vertigo, or vestibular neuritis were retrieved from the database of otoneurologic expert system ONE for the development and testing of a genetic algorithm (GA). The accuracy of the diagnostic rules in solving the test cases was 81%, 91%, 92%, 95%, 96%, and 98% for the respective diseases. The best rules retrieved from the GA were described by a set of questions with the most likely answers. The most important questions concerned the duration of hearing loss and the occurrence of head injury. The validity and structure of the rules created with a GA can be analyzed in detail. For rare diseases, some other reasoning process can be used, for example, case-based reasoning.

Otoneurological expert system for vertigo

We have developed an otoneurological expert system (ONE) to aid the diagnostics of vertigo, to assist teaching and to implement a database for research. The ONE database is set to harvest data on patient history, signs and test results necessary for diagnostic work with vertiginous patients. A method based on pattern recognition was used in the reasoning process. Questions about symptoms, signs and test results are weighted and scored for each disease and the most likely disease is recognized from defined disease profiles. Missing information and uncertainties are solved with a method resembling fuzzy logic. ONE was validated by comparing diagnoses assessed by physicians with those provided by the system. It proved to be a valid decision-maker by solving 65% of the cases correctly, while the physicians' mean was 69%. To improve ONE further, a follow-up should be implemented for the patients, since diagnosing sudden deafness and Meniere's disease during the first visit is often impossible. We aim to obtain new information on diseases involving vertigo by applying adaptive computer applications, such as genetic algorithms, to the reasoning process.