Journal of Interdisciplinary Research Applied to Medicine

25 pages, 13661 KB

Open AccessArticle

Compact Propagation and Morphology-Based EEG Features for Real-Time Seizure Detection Using Machine Learning

by Dhanushka Wijesinghe and Ivan T. Lima, Jr.

J. Interdiscip. Res. Appl. Med. 2026, 6(2), 8; https://doi.org/10.3390/jdream6020008 (registering DOI) - 12 May 2026

Abstract

Accurate and efficient seizure detection remains a major challenge for portable EEG-based monitoring systems, where computational and power limitations restrict the use of deep learning approaches. We introduce a compact set of fourteen propagation-based EEG features that quantify spike directionality, propagation velocity, and spatial coherence across channels. These physiologically interpretable features were evaluated using a gradient-boosted XGBoost classifier on the TUH Seizure Corpus under a leave-one-subject-out cross-validation framework. The proposed model achieved 97.8% accuracy, 98.7% specificity, 93.6% sensitivity, and a weighted F1 score of 97.8% using 2 s epochs and eight electrodes. The framework remained robust across generalized, focal, and complex partial seizure types and maintained consistent short-window performance. The compact 14-feature representation enables efficient, accurate, and interpretable seizure detection with strong potential for real-time wearable EEG-based applications. The proposed gradient-boosting approach demonstrates that shallow, interpretable architectures can achieve performance comparable to deep learning methods while offering improved computational efficiency, making them promising for low-power embedded implementations. Full article

► Show Figures

Figure 1

6 pages, 1250 KB

Open AccessCase Report

Symptomatic Pedicle Ossification Following Fibular Free Flap Reconstruction: Case Report and Review of the Literature

by Mattie Rosi-Schumacher, Susan Karki, Ayham Al Afif and Ryan McSpadden

J. Interdiscip. Res. Appl. Med. 2026, 6(2), 7; https://doi.org/10.3390/jdream6020007 - 24 Apr 2026

Viewed by 157

Abstract

Ossification of the vascular pedicle following fibula free flap (FFF) reconstruction is an uncommon and typically asymptomatic complication. Symptomatic cases requiring intervention are rare. We report a 29-year-old man with anterior maxillary osteosarcoma who underwent tumor resection followed by reconstruction with an osteocutaneous FFF. Calcification within the surgical site region was noted on imaging at two months after fibular reconstruction. By five months, he developed progressive trismus and pain with mastication. Computed tomography demonstrated a calcified structure extending from the mandible to the reconstructed maxilla along the flap pedicle, raising concern for tumor recurrence. Surgical excision was performed, and histopathology revealed benign woven bone without evidence of malignancy. Postoperatively, trismus improved, and flap viability was preserved. Retained periosteum during FFF harvest maintains osteogenic potential and may result in pedicle ossification. In symptomatic patients, particularly when recurrence is suspected, surgical resection is both diagnostic and therapeutic. Full article

► Show Figures

Figure 1

15 pages, 1180 KB

Open AccessArticle

SNAP: A Multidimensional Tool for Psychotherapeutic Process Analysis—Development and Pilot Study of Perceived Clinical Utility

by Roberta Stanzione, Chiara Scognamiglio, Lucia Luciana Mosca, Simona Verniti, Valeria Cioffi, Enrica Tortora and Enrico Moretto

J. Interdiscip. Res. Appl. Med. 2026, 6(2), 6; https://doi.org/10.3390/jdream6020006 - 16 Apr 2026

Viewed by 280

Abstract

This paper introduces SNAP (Structure, Narrative, Activation, Process, Next), a multidimensional clinical reflection tool supporting psychotherapists in systematically attending to phenomenological, relational, and process-oriented dimensions. SNAP integrates Gestalt therapy, complex systems theory, and the Research Domain Criteria (RDoC) framework, comprising 73 items across five dimensions. A pilot acceptability and perceived utility study (N = 20 psychotherapists) used a retrospective pre-post design in which participants provided retrospective pre-exposure and post-exposure ratings for each item. Post-exposure ratings were higher overall than retrospective pre-exposure ratings (T2: M = 6.69, SD = 0.54 vs. T1: M = 6.02, SD = 0.70; mean difference +0.67; Hedges’ g = 0.28, Cohen’s d = 0.29; 15/73 items p < 0.05 uncorrected; 2/73 after Benjamini-Hochberg FDR correction). The largest descriptive contrasts were observed in phenomenological dimensions: Next (g = 0.61), Activation (g = 0.49), Narrative (g = 0.43), and Process-Therapist (g = 0.41). Structural bio-psycho-social dimensions showed minimal contrasts (d = −0.02 to 0.15). Absolute post-exposure ratings were high across items (89% rated 6/9 or above), supporting good acceptability and perceived usefulness within this sample. These preliminary findings support SNAP as a promising, positively perceived framework for clinical reflection. Larger-sample psychometric validation is warranted. Full article

► Show Figures

Figure 1

18 pages, 2746 KB

Open AccessFeature PaperArticle

Facial Beauty According to AI: Algorithmic Aesthetics and the Transformation of Contemporary Beauty

by Nitzan Kenig, Aina Muntaner Vives and Javier Montón Echeverría

J. Interdiscip. Res. Appl. Med. 2026, 6(2), 5; https://doi.org/10.3390/jdream6020005 - 15 Apr 2026

Viewed by 1883

Abstract

Background: Generative artificial intelligence (AI) can produce realistic human faces that are shared on social media, from where younger generations often derive body image norms. Aesthetic bias in these systems may promote unrealistic standards of beauty. This study examines whether generative AI produces facial images that are perceived by humans as more attractive than real human faces. Thus, we examine AI-generated facial imagery as a contemporary site of consumer culture, where beauty may become biased, unrealistic, and commodified: generating an algorithmically optimized product circulating through social media and digital platforms without proper regulation. Methods: Fifty AI-generated female faces were prospectively compared with 50 photographs of female models from a model agency. Facial attractiveness was rated by plastic surgeons, using a Likert scale and Mann–Whitney U for analysis. Results: AI-generated images received higher mean aesthetic scores than real photographs (7.79 vs. 6.88, p < 0.05), despite prompts requesting unattractive features. Conclusions: The AI model showed a small but consistent bias toward enhanced facial attractiveness. As AI-generated imagery increasingly shapes visual culture, this bias may contribute to unrealistic beauty standards, highlighting the need for AI literacy, responsible use of AI, and ethical oversight, especially when shared on social media. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

J. Interdiscip. Res. Appl. Med., Volume 6, Issue 2 (June 2026) – 4 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI