Disease Profiling for Computerized Peer Support of Ménière's Disease

Association of Head Injury, Neck Injury or Acoustic Trauma on Phenotype of Ménière's Disease

The aim of the present study was to investigate adverse effects of head injury, neck trauma, and chronic noise exposure on the complaint profile in people with Ménière's disease (MD). The study used a retrospective design. Register data of 912 patients with MD from the Finnish Ménière Federation database were studied. The data comprised case histories of traumatic brain injury (TBI), neck trauma and occupational noise exposure, MD specific complaints, impact related questions, and the E-Qol health-related quality of life instrument. TBI was classified based on mild, moderate, and severe categories of transient loss of consciousness (TLoC). The mean age of the participants was 60.2 years, the mean duration of the disease was 12.6 years, and 78.7% were females. Logistic regression analysis, linear correlation, and pairwise comparisons were used in evaluating the associations. 19.2% of the participants with MD had a history of TBI. The phenotype of participants with TBI was associated with frequent vestibular drop attacks (VDA), presyncope, headache-associated vertigo, and a reduction in the E-QoL. Logistic regression analysis explained the variability of mild TBI in 6.8%. A history of neck trauma was present in 10.8% of the participants. Neck trauma associated with vertigo (NTwV) was seen in 47 and not associated with vertigo in 52 participants. The phenotype of NTwV was associated with balance problems, VDA, physical strain-induced vertigo, and hyperacusia. Logistic regression analysis explained 8.7% of the variability of the complaint profile. Occupational noise exposure was recorded in 25.4% of the participants and correlated with the greater impact of tinnitus, hyperacusis, and hearing loss. Neither the frequency, duration, or severity of vertigo or nausea were significantly different between the baseline group and the TBI, NTwV, or noise-exposure groups. The results indicate that TBI and NTwV are common among MD patients and may cause a confounder effect.

Machine Learning Techniques for Differential Diagnosis of Vertigo and Dizziness: A Review

Vertigo is a sensation of movement that results from disorders of the inner ear balance organs and their central connections, with aetiologies that are often benign and sometimes serious. An individual who develops vertigo can be effectively treated only after a correct diagnosis of the underlying vestibular disorder is reached. Recent advances in artificial intelligence promise novel strategies for the diagnosis and treatment of patients with this common symptom. Human analysts may experience difficulties manually extracting patterns from large clinical datasets. Machine learning techniques can be used to visualize, understand, and classify clinical data to create a computerized, faster, and more accurate evaluation of vertiginous disorders. Practitioners can also use them as a teaching tool to gain knowledge and valuable insights from medical data. This paper provides a review of the literatures from 1999 to 2021 using various feature extraction and machine learning techniques to diagnose vertigo disorders. This paper aims to provide a better understanding of the work done thus far and to provide future directions for research into the use of machine learning in vertigo diagnosis.

Exploratory Data Mining Techniques (Decision Tree Models) for Examining the Impact of Internet-Based Cognitive Behavioral Therapy for Tinnitus: Machine Learning Approach

Background

There is huge variability in the way that individuals with tinnitus respond to interventions. These experiential variations, together with a range of associated etiologies, contribute to tinnitus being a highly heterogeneous condition. Despite this heterogeneity, a “one size fits all” approach is taken when making management recommendations. Although there are various management approaches, not all are equally effective. Psychological approaches such as cognitive behavioral therapy have the most evidence base. Managing tinnitus is challenging due to the significant variations in tinnitus experiences and treatment successes. Tailored interventions based on individual tinnitus profiles may improve outcomes. Predictive models of treatment success are, however, lacking.

Objective

This study aimed to use exploratory data mining techniques (ie, decision tree models) to identify the variables associated with the treatment success of internet-based cognitive behavioral therapy (ICBT) for tinnitus.

Methods

Individuals (N=228) who underwent ICBT in 3 separate clinical trials were included in this analysis. The primary outcome variable was a reduction of 13 points in tinnitus severity, which was measured by using the Tinnitus Functional Index following the intervention. The predictor variables included demographic characteristics, tinnitus and hearing-related variables, and clinical factors (ie, anxiety, depression, insomnia, hyperacusis, hearing disability, cognitive function, and life satisfaction). Analyses were undertaken by using various exploratory machine learning algorithms to identify the most influencing variables. In total, 6 decision tree models were implemented, namely the classification and regression tree (CART), C5.0, GB, XGBoost, AdaBoost algorithm and random forest models. The Shapley additive explanations framework was applied to the two optimal decision tree models to determine relative predictor importance.

Results

Among the six decision tree models, the CART (accuracy: mean 70.7%, SD 2.4%; sensitivity: mean 74%, SD 5.5%; specificity: mean 64%, SD 3.7%; area under the receiver operating characteristic curve [AUC]: mean 0.69, SD 0.001) and gradient boosting (accuracy: mean 71.8%, SD 1.5%; sensitivity: mean 78.3%, SD 2.8%; specificity: 58.7%, SD 4.2%; AUC: mean 0.68, SD 0.02) models were found to be the best predictive models. Although the other models had acceptable accuracy (range 56.3%-66.7%) and sensitivity (range 68.6%-77.9%), they all had relatively weak specificity (range 31.1%-50%) and AUCs (range 0.52-0.62). A higher education level was the most influencing factor for ICBT outcomes. The CART decision tree model identified 3 participant groups who had at least an 85% success probability following the undertaking of ICBT.

Conclusions

Decision tree models, especially the CART and gradient boosting models, appeared to be promising in predicting ICBT outcomes. Their predictive power may be improved by using larger sample sizes and including a wider range of predictive factors in future studies.

Vestibular drop attacks in Ménière's disease

The aim of the present study was to evaluate the severity of vestibular drop attack (VDA) in Ménière's disease (MD) and to examine the association between VDA severity and other MD-related complaints. The study used a cross-sectional survey design using an electronic questionnaire. The mean age of participants was 56.7 years, and the mean duration of MD was 12.4 years. Four categories of VDA were identified based on level of severity. VDA occurred in 305 (50.7%) of the 602 patients. Of these, 133 patients (22%) experienced mild VDA (i.e., associated with tripping); 80 (13%) experienced moderate VDA (i.e., associated with fall threat unless they had been able to grab support); and 92 (15%) experienced severe VDA (i.e., patients fell to the ground, as in a classical Tumarkin attack). In 70%of participants, VDA occurred less than once a week. VDA lasted for only a few seconds in 90%of participants. 87%reported single attacks, whereas 13%experienced VDA in clusters. VDA was associated with visual auras, reduced quality of life, poor postural control, and fatigue. Approximately half of MD patients experience VDA with varying degrees of severity. If VDA causes falls or near-falls, the attacks should be appropriately treated.

Recent Advances in the Application of Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery

This study presents an up-to-date survey of the use of artificial intelligence (AI) in the field of otorhinolaryngology, considering opportunities, research challenges, and research directions. We searched PubMed, the Cochrane Central Register of Controlled Trials, Embase, and the Web of Science. We initially retrieved 458 articles. The exclusion of non-English publications and duplicates yielded a total of 90 remaining studies. These 90 studies were divided into those analyzing medical images, voice, medical devices, and clinical diagnoses and treatments. Most studies (42.2%, 38/90) used AI for image-based analysis, followed by clinical diagnoses and treatments (24 studies). Each of the remaining two subcategories included 14 studies. Machine learning and deep learning have been extensively applied in the field of otorhinolaryngology. However, the performance of AI models varies and research challenges remain.

The Use of the Internet and Social Media by Individuals with Ménière's Disease: An Exploratory Survey of Finnish Ménière Federation Members

OBJECTIVES

The present study explored the use of the Internet and social media by individuals with Ménière's disease (MD).

MATERIALS AND METHODS

This study utilized a retrospective design and included the data of 465 individuals with MD from the Finnish Ménière Federation (FMF) database. Moreover, the participants included 346 females (i.e., approximately 75% of the sample), with roughly 95% of which middle-aged or older adults. An Internet-based survey was used to collect the demographic information and determine the use of the Internet and social media by individuals with MD in order to establish a computer-based peer support program.

RESULTS

Based on the findings, more than 90% of the respondents reported using the Internet, 70% used the Internet to gather information about MD, and 47% stated that they trusted the information on the Internet.

CONCLUSION

The Internet and social media are frequently used by individuals with MD to gather information about their health conditions. Therefore, it is essential to ensure that appropriate and accurate information is available via Internet websites and social media platforms.

Driving Habits and Risk of Traffic Accidents among People with Ménière's Disease in Finland

OBJECTIVES

The study evaluated the driving habits and risk of traffic accidents among people with Ménière's disease (MD) in Finland.

MATERIALS AND METHODS

The study used a cross-sectional survey design. Members of the Finnish Ménière Federation (FMF) were contacted and requested to participate in an online survey. In total, 558 FMF members (58.7% response rate) responded to the survey.

RESULTS

People with MD were responsible for significantly fewer traffic accidents (0.8%) annually than individuals in the general population (1.7%). In addition, the lifetime risk of car accidents was lower among subjects with MD (8.3%) than that among individuals in the general population (24 to 28%). Nearly half of the total participants had either reduced the frequency of driving or had given up driving because of their condition. Factors such as gender, balance problems, visual problems with visual aura, and syncope during vestibular drop attacks can help explain the reasons for giving up car driving. One third (35.9%) of the participants were able to anticipate the MD attack before they decided to drive a car. Participants with falls during a vestibular drop attack, attacks of rotary vertigo, syncope during vestibular drop attacks, and those who were of a younger age were at a higher risk of experiencing a vertigo attack while driving a car. The most common strategies to avoid car accidents were selective driving and not driving when symptoms appeared.

CONCLUSION

The results show that people with MD are at a lower risk of traffic accidents than individuals in the general population, which can be explained by selective driving.

Internet-Based Self-Help for Ménière's Disease: Details and Outcome of a Single-Group Open Trial

PURPOSE

In this article, we present the details and the pilot outcome of an Internet-based self-help program for Ménière's disease (MD).

METHOD

The Norton-Kaplan model is applied to construct a strategic, person-focused approach in the enablement process. The program assesses the disorder profile and diagnosis. In the therapeutic component of the program, the participant defines vision and time frame, inspects confounding factors, determines goals, establishes a strategy, and starts to work on the important problems caused by the disorder. The program works interactively, utilizes collaboration with significant others, and enhances positive thinking. Participants took part in an Internet-based self-help program. Data were collected interactively using open-ended and structured questionnaires on various disease-specific and general health aspects. The pilot outcome of 41 patients with MD was evaluated.

RESULTS

The analysis of the pilot data showed statistically significant improvement in their general health-related quality of life (p < .001). Also, the outcome of the Posttraumatic Growth Inventory (Cann et al., 2010) showed small to moderate change as a result of the intervention.

CONCLUSIONS

The Internet-based self-help program can be helpful in the rehabilitation of patients with MD to supplement medical therapy.

Patient-reported benefits from patient organization magazines and Internet-based peer support in Ménière's disease

OBJECTIVES

To facilitate self-help, the Finnish Ménière's Federation (FMF) provides various kinds of support to persons with Ménière's disease (MD), which includes patient magazines (PM) and Internet-based peer support (iPS). The current study aimed to evaluate the benefits reported by MD patients in terms of PM and iPS.

METHOD

The study used a cross-sectional survey design with a mixture of structured and open-ended questions administered online. A sample of 185 patients from the FMF membership database provided complete data.

RESULTS

Ninety-two percent of the respondents rated PM as useful, or very useful. The main benefits of PM included: information on the disease and complaints, information about elements of peer support program, patient's experience with useful positive case studies, relevant news on MD, and information of activity of the FMF. Of the 185 persons, 68 reported that they did not have a need for peer support as their disease was either in silent phase or did not cause any annoyance. The main reasons for nonuse were: mild disease, personal reasons, and problems in using. Regarding the benefits of iPS, 75% of recent and 64% of chronic MD patients said that they would benefit from such a program. The main benefits of iPS included: reliable information on the disease and its management, peer support useful for coping with the disease, information about managing MD symptoms, information about managing attitude, and information about therapy. Moreover, the study identified different groups of individuals, which included: nonusers of support from patient organizations, those who used the support but did not feel they benefited, and those who used and also benefited from such programs.

CONCLUSION

The current study results provide some information about the preferences of MD patients regarding different forms of support and could certainly prove helpful while developing wider support strategies.