Development of Machine-Learning Models for Tinnitus-Related Distress Classification Using Wavelet-Transformed Auditory Evoked Potential Signals and Clinical Data.

Tinnitus is a highly prevalent condition, affecting more than 1 in 7 adults in the EU and causing negative effects on sufferers' quality of life. In this study, we utilised data collected within the "UNITI" project, the largest EU tinnitus-related research programme. Initially, we extracted characteristics from both auditory brainstem response (ABR) and auditory middle latency response (AMLR) signals, which were derived from tinnitus patients. We then combined these features with the patients' clinical data, and integrated them to build machine learning models for the classification of individuals and their ears according to their level of tinnitus-related distress. Several models were developed and tested on different datasets to determine the most relevant features and achieve high performances. Specifically, seven widely used classifiers were utilised on all generated datasets: random forest (RF), linear, radial, and polynomial support vector machines (SVM), naive bayes (NB), neural networks (NN), and linear discriminant analysis (LDA). Results showed that features extracted from the wavelet-scattering transformed AMLR signals were the most informative data. In combination with the 15 LASSO-selected clinical features, the SVM classifier achieved optimal performance with an AUC value, sensitivity, and specificity of 92.53%, 84.84%, and 83.04%, respectively, indicating high discrimination performance between the two groups.

Development and Evaluation of Automated Tools for Auditory-Brainstem and Middle-Auditory Evoked Potentials Waves Detection and Annotation.

Auditory evoked potentials (AEPs) are brain-derived electrical signals, following an auditory stimulus, utilised to examine any obstructions along the brain neural-pathways and to diagnose hearing impairment. The clinical evaluation of AEPs is based on the measurements of the latencies and amplitudes of waves of interest; hence, their identification is a prerequisite for AEP analysis. This process has proven to be complex, as it requires relevant clinical experience, and the existing software for this purpose has little practical use. The aim of this study was the development of two automated annotation tools for ABR (auditory brainstem response)- and AMLR (auditory middle latency response)-tests. After the acquisition of 1046 raw waveforms, appropriate pre-processing and implementation of a four-stage development process were performed, to define the appropriate logical conditions and steps for each algorithm. The tools' detection and annotation results, regarding the waves of interest, were then compared to the clinicians' manual annotation, achieving match rates of at least 93.86%, 98.51%, and 91.51% respectively, for the three ABR-waves of interest, and 93.21%, 92.25%, 83.35%, and 79.27%, respectively, for the four AMLR-waves. The application of such tools in AEP analysis is expected to assist towards an easier interpretation of these signals.

Predicting the optimal therapeutic intervention for tinnitus patients using random forest regression: A preliminary study of UNITI's decision support system model.

Tinnitus is the conscious perception of a phantom sound in absence of an external or internal stimulus. More than 1 in 7 adults in the EU experience tinnitus and for a large proportion of them tinnitus is an intrusive, persistent, and disabling condition, which impairs their life quality. Therefore, tinnitus is posed as a major global burden, which requires a precision-medicine approach in terms of treatments that are tailored to individual patients, due to its high heterogeneity. UNITI is a research and innovation project which aims towards this goal, unifying treatments and interventions for tinnitus. In the context UNITI, a randomized controlled trial (RCT) is being conducted and all the participants' data will be utilized for the development of a clinical decision support system (CDSS). This CDSS will predict the optimal therapeutic intervention for a tinnitus patient based on their profile. In this paper, we present a preliminary study of the CDSS model development process. We describe the available input data, the pre-processing steps conducted, the algorithms tested to model the CDSS' prediction, the models' results, and the future work in the context of this project. The R2 score of the selected model is currently 0.65, indicating that its development process is in the right direction but further tuning and hyperparameter optimization is needed. Clinical Relevance- The proposed model will be integrated in a CDSS aiming at indicating the optimal treatment strategy for a tinnitus patient based their personal profile.

Electrophysiological differences in distinct hearing threshold level individuals with and without tinnitus distress.

Tinnitus is the perception of sound when no actual external noise is present. Tinnitus is highly prevalent, with more than 1 in 7 adults in the EU having tinnitus, and it causes negative effects on quality of life for many individuals. However, there is currently no cure for tinnitus and its pathophysiology and genesis are unknown. Auditory evoked potentials (AEPs) provide a non-invasive means by which the electrical signals evoked by the brain can be recorded, and constitute a useful indicator for the evaluation of auditory disorders such as tinnitus and hearing loss. The present study analyzed a total of 98 auditory middle evoked potential (AMLR) waveforms, a subtype of AEPs, from 49 participants with subjective tinnitus, attempting to identify differences in AMLR parameters between sufferers with and without tinnitus distress. The waveforms were divided into three categories according to the ear's hearing level, and comparisons were made between sufferers in the same hearing level category. The results of the analysis indicated some statistically significant differences in AMLR latencies and amplitudes between the compared groups. Clinical Relevance- Identification of the electro-physiological profile of subjective tinnitus sufferers based on the distress manifested by tinnitus using AMLRs.

An Integrated Bioinformatics Analysis towards the Identification of Diagnostic, Prognostic, and Predictive Key Biomarkers for Urinary Bladder Cancer.

Bladder cancer (BCa) is one of the most prevalent cancers worldwide and accounts for high morbidity and mortality. This study intended to elucidate potential key biomarkers related to the occurrence, development, and prognosis of BCa through an integrated bioinformatics analysis. In this context, a systematic meta-analysis, integrating 18 microarray gene expression datasets from the GEO repository into a merged meta-dataset, identified 815 robust differentially expressed genes (DEGs). The key hub genes resulted from DEG-based protein-protein interaction and weighted gene co-expression network analyses were screened for their differential expression in urine and blood plasma samples of BCa patients. Subsequently, they were tested for their prognostic value, and a three-gene signature model, including COL3A1, FOXM1, and PLK4, was built. In addition, they were tested for their predictive value regarding muscle-invasive BCa patients' response to neoadjuvant chemotherapy. A six-gene signature model, including ANXA5, CD44, NCAM1, SPP1, CDCA8, and KIF14, was developed. In conclusion, this study identified nine key biomarker genes, namely ANXA5, CDT1, COL3A1, SPP1, VEGFA, CDCA8, HJURP, TOP2A, and COL6A1, which were differentially expressed in urine or blood of BCa patients, held a prognostic or predictive value, and were immunohistochemically validated. These biomarkers may be of significance as prognostic and therapeutic targets for BCa.

Why a Clinical Decision Support System is needed for Tinnitus?

Tinnitus is the perception of a phantom sound and the individual's reaction to it. Although much progress has been made, tinnitus remains an unresolved scientific and clinical issue, affecting more than 10% of the general population and having a high prevalence and socioeconomic burden. Clinical decision support systems (CDSS) are used to assist clinicians in their complex decision-making processes, having been proved that they improve healthcare delivery. In this paper, we present a CDSS for tinnitus, attempting to address the question which treatment approach is optimal for a particular patient based on specific parameters. The CDSS will be developed in the context of the EU-funded "UNITI" project and, after the project completion, it will be able to determine the suitability and expected attachment of a particular patient to a list of available clinical interventions, utilizing predictive and classification machine learning models.Clinical Relevance - The proposed clinically utilizable CDSS will be able to suggest the optimal treatment strategy for the tinnitus patient based on a set of heterogeneous data.

Managing the Intervention Costs of Musculoskeletal Disorders in the Hospital Workplace.

OCCUPATIONAL APPLICATIONSThis study demonstrates the applicability of multicriteria tools to solve occupational health and safety (OSH) problems related to cost management in the healthcare sector. To the best of our knowledge, this is the first work in which linear programming and established methods for risk assessment of work-related musculoskeletal disorders (i.e., the Key Item Method) have been combined with the knowledge and experience of the corresponding safety engineer (or OSH auditor or consultant). The ease of implementation of the whole process facilitates its future utilization in working practice without adding an undue burden on existing OSH practices.

TECHNICAL ABSTRACTBackground: Managing the intervention costs of musculoskeletal disorders (MSDs) through the optimal use of the resources and the evaluation of interventions is a cornerstone in Occupational Safety and Health (OSH) management in the healthcare sector.Purpose: We aim to create a practically useful tool for the allocation of work-related MSDs intervention costs and the support of relevant OSH decisions in the hospital workplace.Methods: A legally established risk assessment method was combined with the widely applied Key Item Method and linear programming to develop a functional cost allocation tool for allocating the work-related MSDs intervention costs in the hospital workplace. The proposed tool indicates where investments should be made in an intervention or combination of interventions, to jointly achieve minimization of the risk and maximization of convenience with the minimum possible cost. The primary goal of our study was to evaluate interventions indicated by the tool, in terms of reducing the risk values related to MSDs. The sample studied consisted of 15 female nurses of "Metaxa" Cancer Hospital (Greece). The main selected interventions were related to ergonomic training, improving work conditions, tidiness, and equipment.Results: Implementing these interventions over a two-month period (September to November 2019) led to a significant reduction in employees' risk of strain.Conclusions: The proposed tool can be practically useful in allocating OSH intervention costs for a certain safety investment.

Serious games for Parkinson's Disease management as implemented in PROPHETIC platform.

In this paper, we describe the serious games, integrated into PROPHETIC which is an innovating personal healthcare service for a holistic remote management of Parkinson's disease (PD) patients. The main objective of the three developed serious games is to allow health professionals to remotely monitor and appraise the overall physical status of their patients. The significant benefits for the patients, making use of this platform, is the improvement of their engagement, empowerment and, consequently, the provision of education about their condition and its management. The design of the serious games was based on the clinical needs derived from the literature and their primary target is to assess and record specific physical capabilities of the patient. All the games scores and the recorded parameters are gathered and also presented to the clinicians, offering them a precise overview of the patient's motor status and the possibility to modify the therapeutic plan, if required.

Data Quality Challenges in a Learning Health System.

This paper discusses the topic of data quality, which concerns the global research and business community and constitutes a challenging task. The data quality prerequisite becomes even more critical when it pertains to critical and sensitive data, such as the healthcare domain data. To begin with, the paper outlines the basic definitions and concepts of data quality and its dimensions. The related research work on data quality assessment is presented and our approach for data quality assurance is introduced. This approach is implemented in our designed cloud platform, called MODELHealth, which is intended for supporting clinical work and administrative decision-making process.

The "Prisoner's Dilemma" in the Tumor Biology Context: The Warburg Effect, Proliferation Dynamics and Equilibria.

There are numerous theories concerning carcinogenesis. Starting from the Warburg effect, which was one of the first theories concerning the mitochondrial dysfunction in tumor cells. Further on, the "two-hit" theory, where tumors were considered to be the outcome of genetic aberrations or mutations and more specifically of a certain number of "hits" each one resulting in a mutation. One of the main physical problems of biological systems is proliferation. Proliferation brings forwards two main questions: First, under a given population of cells, at time t what will be the precise population at time t+24h (or any other time point)? Second, what are the metabolic strategies followed by tumor cells in order to facilitate for their growth? In the present work we have used experimental data obtained from proliferation experiments of leukemic cells, where cell population and glucose consumption were evaluated. These data were further used to examine whether cells progress through competitive behavior or synergistically. Our results have shown that cells probably progress through a cooperative strategy.

Bioinformatics Analysis Reveals Ki-67 Specific microRNA Functions in Pediatric Embryonal Tumors.

Pediatric Central Nervous System (CNS) neoplasms are the second most prevalent tumors of childhood. CNS malignancies are considered as the most notorious type of tumors, due to their anatomic position manifesting an imminent threat to the patients' life. miRNAs are molecules that play a significant role in CNS tumor biology. At the same time diagnostic markers such as Ki-67 have played an important role in CNS tumor diagnosis. In a previous study we have identified several miRNAs, common to different subtypes of pediatric embryonal CNS malignancies as well as, we have identified miRNAs that manifest significant dynamics with respect to their expression and the neoplasmatic subtype. Among the previously reported miRNAs, several have manifested significant differences with respect to Ki-67 expression. Those miRNAs, were further analyzed bioinformatically and related functions were revealed, where some of them confirmed Ki-67 role as a proliferation marker but also predicted novel miRNAs functions in pediatric embryonal tumors.