Panjwani, Gianeshwaree Alias Rachna

This study proposes a novel two-dimensional Empirical Mode Decomposition (2D EMD)-based deep learning framework to enhance model performance in multi-class image classification tasks and potential early detection of diseases in healthcare using medical imaging. To validate this approach, we apply it to gastrointestinal (GI) endoscopic image classification using the publicly available Kvasir dataset, which contains eight GI image classes with 1000 images each. The proposed 2D EMD-based design procedure decomposes images into a full set of intrinsic mode functions (IMFs) to enhance image features beneficial for AI model development. Integrating 2D EMD into a deep learning pipeline, we evaluate its impact on four popular models (ResNet152, VGG19bn, MobileNetV3L, and SwinTransformerV2S). The results demonstrate that subtracting IMFs from the original image consistently improves accuracy, F1-score, and AUC for all models. The study reveals a notable enhancement in model performance, with an approximately 9% increase in accuracy compared to counterparts without EMD integration for ResNet152. Similarly, there is an increase of around 18% for VGG19L, 3% for MobileNetV3L, and 8% for SwinTransformerV2. Additionally, explainable AI (XAI) techniques, such as Grad-CAM, illustrate that the model focuses on GI regions for predictions. This study highlights the efficacy of 2D EMD in enhancing deep learning model performance for GI image classification, with potential applications in other domains.

Phonoenterography (PEG) offers a non-invasive and radiation-free technique to assess gastrointestinal activity through acoustic signal analysis. In this feasibility study, 110 high-resolution PEG recordings (44.1 kHz, 16-bit) were acquired from eight healthy individuals, yielding 6314 prominent bowel sound (PBS) segments through automated segmentation. Each event was characterized using a 279-feature acoustic profile comprising Mel-frequency cepstral coefficients (MFCCs), their first-order derivatives (Δ-MFCCs), and six global spectral parameters. After normalization and dimensionality reduction with PCA and UMAP (cosine distance, 35 neighbors, minimum distance = 0.01), five clustering strategies were evaluated. K-Means (k = 5) achieved the most favorable balance between cluster quality (silhouette = 0.60; Calinski–Harabasz = 19,165; Davies–Bouldin = 0.68) and interpretability, consistently identifying five acoustic patterns: single-burst, multiple-burst, harmonic, random-continuous, and multi-modal. Temporal modeling of clustered events further revealed distinct sequential dynamics, with Single-Burst events showing the longest dwell times, random continuous the shortest, and strong diagonal elements in the transition matrix confirming measurable state persistence. Frequent transitions between random continuous and multi-modal states suggested dynamic exchanges between transient and overlapping motility patterns. Together, these findings demonstrate that unsupervised PEG-based analysis can capture both acoustic variability and temporal organization of bowel sounds. This annotation-free approach provides a scalable framework for real-time gastrointestinal monitoring and holds potential for clinical translation in conditions such as postoperative ileus, bowel obstruction, irritable bowel syndrome, and inflammatory bowel disease.

Background/Objectives: Menopause, marked by permanent cessation of menstruation, is a universal transition associated with vasomotor, genitourinary, psychological, and metabolic changes. These conditions significantly affect health-related quality of life (HRQoL) and increase the risk of chronic diseases. Despite their impact, timely diagnosis and individualized management are often limited by delayed care, fragmented health systems, and cultural barriers. Methods: This review summarizes current applications of artificial intelligence (AI) in postmenopausal health, focusing on risk prediction, early detection, and personalized treatment. Evidence was compiled from studies using biomarkers, imaging, wearable sensors, electronic health records, natural language processing, and digital health platforms. Results: AI enhances disease prediction and diagnosis, including improved accuracy in breast cancer and osteoporosis screening through imaging analysis, and cardiovascular risk stratification via machine learning models. Wearable devices and natural language processing enable real-time monitoring of underreported symptoms such as hot flushes and mood disorders. Digital technologies further support individualized interventions, including lifestyle modification and optimized medication regimens. By improving access to telemedicine and reducing bias, AI also has the potential to narrow healthcare disparities. Conclusions: AI can transform postmenopausal care from reactive to proactive, offering personalized strategies that improve outcomes and quality of life. However, challenges remain, including algorithmic bias, data privacy, and clinical implementation. Ethical frameworks and interdisciplinary collaboration among clinicians, data scientists, and policymakers are essential for safe and equitable adoption.

Heart failure, a significant global health burden, is divided into heart failure with reduced ejection fraction (HFrEF) and preserved ejection fraction (HFpEF), characterized by systolic dysfunction and diastolic stiffness, respectively. While HFrEF benefits from pharmacological and device-based therapies, HFpEF lacks effective treatments, with both conditions leading to high rehospitalization rates and reduced quality of life, especially in older adults with comorbidities. This review explores the role of artificial intelligence (AI) in advancing autonomic neuromodulation for heart failure management. AI enhances patient selection, optimizes stimulation strategies, and enables adaptive, closed-loop systems. In HFrEF, vagus nerve stimulation and baroreflex activation therapy improve functional status and biomarkers, while AI-driven models adjust stimulation dynamically based on physiological feedback. In HFpEF, AI aids in deep phenotyping to identify responsive subgroups for neuromodulatory interventions. Clinical tools support remote monitoring, risk assessment, and symptom detection. However, challenges like data integration, ethical oversight, and clinical adoption limit real-world application. Algorithm transparency, bias minimization, and equitable access are critical for success. Interdisciplinary collaboration and ethical innovation are essential to develop personalized, data-driven, patient-centered heart failure treatment strategies through AI-guided neuromodulation.

Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO® stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software®. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed.

Accurate analysis of medical videos remains a major challenge in deep learning (DL) due to the need for effective spatiotemporal feature mapping that captures both spatial detail and temporal dynamics. Despite advances in DL, most existing models in medical AI focus on static images, overlooking critical temporal cues present in video data. To bridge this gap, a novel DL-based framework is proposed for spatiotemporal feature extraction from medical video sequences. As a feasibility use case, this study focuses on gastrointestinal (GI) endoscopic video classification. A 3D convolutional neural network (CNN) is developed to classify upper and lower GI endoscopic videos using the hyperKvasir dataset, which contains 314 lower and 60 upper GI videos. To address data imbalance, 60 matched pairs of videos are randomly selected across 20 experimental runs. Videos are resized to 224 × 224, and the 3D CNN captures spatiotemporal information. A 3D version of the parallel spatial and channel squeeze-and-excitation (P-scSE) is implemented, and a new block called the residual with parallel attention (RPA) block is proposed by combining P-scSE3D with a residual block. To reduce computational complexity, a (2 + 1)D convolution is used in place of full 3D convolution. The model achieves an average accuracy of 0.933, precision of 0.932, recall of 0.944, F1-score of 0.935, and AUC of 0.933. It is also observed that the integration of P-scSE3D increased the F1-score by 7%. This preliminary work opens avenues for exploring various GI endoscopic video-based prospective studies.