The increasing dimensionality of healthcare datasets presents major challenges for clinical data analysis and interpretation. This study introduces a scalable ensemble feature selection (FS) strategy optimized for multi-biometric healthcare datasets aiming to: address the need for dimensionality reduction, identify the most significant features, improve machine learning models' performance, and enhance interpretability in a clinical context. The novel waterfall selection, that integrates sequentially (a) tree-based feature ranking and (b) greedy backward feature elimination, produces as output several sets of features. These subsets are then combined using a specific merging strategy to produce a single set of clinically relevant features. The overall method is applied to two healthcare datasets: the biosignal-based BioVRSea dataset, containing electromyography, electroencephalography, and center-of-pressure data for postural control and motion sickness assessment, and the image-based SinPain dataset, which includes MRI and CT-scan data to study knee osteoarthritis. Our ensemble FS approach demonstrated effective dimensionality reduction, achieving over a 50% decrease in certain feature subsets. The new reduced feature set maintained or improved the model classification metrics when tested with Support Vector Machine and Random Forest models. The proposed ensemble FS method retains selected features essential for distinguishing clinical outcomes, leading to models that are both computationally efficient and clinically interpretable. Furthermore, the adaptability of this method across two heterogeneous healthcare datasets and the scalability of the algorithm indicates its potential as a generalizable tool in healthcare studies. This approach can advance clinical decision support systems, making high-dimensional healthcare datasets more accessible and clinically interpretable.

Objective: This study introduces a novel method for the automated detection and quantification of meibomian gland morphology using gray value distribution profiles. The approach addresses limitations in traditional manual and deep learning-based meibography analysis, which are often time-consuming and prone to variability. Methods: This study enrolled 100 volunteers (mean age 40 ± 16 years, range 18–85) who suffered from dry eye and responded to the Ocular Surface Disease Index questionnaire for scoring ocular discomfort symptoms and infrared meibography for capturing imaging of meibomian glands. By leveraging pixel brightness variations, the algorithm provides real-time detection and classification of long, medium, and short meibomian glands, offering a quantitative assessment of gland atrophy. Results: A novel parameter, namely “atrophy index”, a quantitative measure of gland degeneration, is introduced. Atrophy index is the first instrumental measurement to assess single- and multiple-gland morphology. Conclusions: This tool provides a robust, scalable metric for integrating quantitative meibography into clinical practice, making it suitable for real-time screening and advancing the management of dry eyes owing to meibomian gland dysfunction.

The increasing dimensionality of healthcare datasets presents major challenges for clinical data analysis and interpretation. This study introduces an ensemble feature selection (FS) strategy designed to enhance clinical interpretability and computational efficiency when working with multi-biometric healthcare datasets. The presented approach consists of a sequential ensemble architecture that combines tree-based feature ranking with greedy backward selection, retaining only the most clinically informative features. The method is applied to two datasets: the BioVRSea dataset, containing biosignals such as electromyography, electroencephalography, and center-of-pressure data for postural control and motion sickness assessment, and the SinPain dataset, which includes MRI and CT imaging features to identify knee osteoarthritis. The ensemble FS approach demonstrated effective dimensionality reduction, achieving over a 50% decrease in certain feature subsets. The new reduced feature set maintained or improved the model classification metrics when tested with Support Vector Machine and Random Forest models. The proposed ensemble FS method retains selected features essential for distinguishing clinical outcomes, leading to models that are both computationally efficient and clinically interpretable. Furthermore, the adaptability of this method across two heterogeneous healthcare datasets and the scalability of the algorithm indicate its potential as a generalizable tool in healthcare studies, enabling more clinically meaningful AI-driven analysis. This approach can advance clinical decision support systems, making high-dimensional healthcare data more accessible and clinically interpretable.

Disrupted postural control (PC), a hallmark of neurological conditions such as Parkinson’s disease (PD) and mild traumatic brain injury (mTBI), has been associated with altered neural oscillatory dynamics measured via electroencephalography (EEG) [1]–[3]. However, few studies have employed ecologically valid paradigms to assess these dynamics [4]. In this study, we utilized BioVRSea, a multimodal virtual reality (VR) platform combining realistic postural perturbations with real-time EEG to examine cortical responses to multisensory stimulation [5]. We tested whether EEG time–frequency representations could differentiate pathological PC responses in PD and mTBI from normative function in matched healthy controls (HC). Motion sickness susceptibility and symptom changes were evaluated using the Motion Sickness Susceptibility Questionnaire (MSSQ) [6] and the Motion Sickness Symptoms Scale. In HC, only the older subgroup exhibited a significant increase in low-frequency (delta–theta, ≈1–7 Hz) power at 50% perturbation intensity and during the post-perturbation phase (cluster-level p < 0.05). Compared with matched controls, PD participants showed increased spectral power in both the delta–theta (≈1–7 Hz) and alpha–beta (≈10–30 Hz) ranges (cluster-level p < 0.05), particularly at higher perturbation intensities, suggesting impaired sensorimotor integration [7], [8]. In contrast, no significant EEG differences were observed between the mTBI group and matched controls (p > 0.05). These findings demonstrate the feasibility of synchronized VR–EEG paradigms for capturing challenge-dependent neural signatures of postural control dysfunction. Further validation is warranted to determine their potential clinical utility in neurological assessment.