Optimizing diabetic retinopathy detection with electric fish algorithm and bilinear convolutional networks DOI Creative Commons

Udayaraju Pamula,

Venkateswararao Pulipati,

Gamini Suresh

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 23, 2025

Diabetic Retinopathy (DR) is a leading cause of vision impairment globally, necessitating regular screenings to prevent its progression severe stages. Manual diagnosis labor-intensive and prone inaccuracies, highlighting the need for automated, accurate detection methods. This study proposes novel approach early DR by integrating advanced machine learning techniques. The proposed system employs three-phase methodology: initial image preprocessing, blood vessel segmentation using Hopfield Neural Network (HNN), feature extraction through an Attention Mechanism-based Capsule (AM-CapsuleNet). features are optimized Taylor-based African Vulture Optimization Algorithm (AVOA) classified Bilinear Convolutional (BCAN). To enhance classification accuracy, introduces hybrid Electric Fish Arithmetic (EFAOA), which refines exploration phase, ensuring rapid convergence. model was evaluated on balanced dataset from APTOS 2019 Blindness Detection challenge, demonstrating superior performance in terms accuracy efficiency. offers robust solution DR, potentially improving patient outcomes timely precise diagnosis.

Язык: Английский

The interplay of senescence and MMPs in myocardial infarction: implications for cardiac aging and therapeutics DOI

Ashok Kumar Balaraman,

Abdulmalik Saleh Alfawaz Altamimi, M. Arockia Babu

и другие.

Biogerontology, Год журнала: 2025, Номер 26(1)

Опубликована: Янв. 20, 2025

Язык: Английский

Процитировано

1
Strategies with spectroscopic and optical insights for optoelectronic applications of novel synthesized Schiff base: impact of nitro group DOI
Anjali Jha,

B. Rajesh Kumar,

Ch. Ravi Shankar Kumar

и другие.

Structural Chemistry, Год журнала: 2025, Номер unknown

Опубликована: Янв. 24, 2025

Язык: Английский

Процитировано

0
Reconfigurable Ultra-Miniaturized MIMO Antenna for Tissue-Independent Communication in Injectable Medical Implants DOI Creative Commons

L. Harlan,

M. Susila,

Sachin Kumar

и другие.

IEEE Access, Год журнала: 2025, Номер 13, С. 22663 - 22677

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
AI-Optimized Lattice Structures for Biomechanics Scaffold Design DOI Creative Commons
Francis T. Omigbodun, Bankole I. Oladapo

Biomimetics, Год журнала: 2025, Номер 10(2), С. 88 - 88

Опубликована: Фев. 1, 2025

This research paper explores the development of AI-optimized lattice structures for biomechanics scaffold design, aiming to enhance bone implant functionality by utilizing advanced human–AI systems. The primary objective is create that mimic mechanical properties natural and improve bioactivity biocompatibility, adapting patient-specific needs. We employed polylactic acid (PLA), calcium hydroxyapatite (cHAP), reduced graphene oxide (rGO) as base materials, leveraging their synergistic properties. scaffolds were intricately designed using nTopology software (nTop 5.12) fabricated via 3D printing techniques, optimizing biomechanical load-bearing cellular integration. study’s findings highlight a notable enhancement in scaffolds, with Gyroid design demonstrating 20% higher energy-absorption capacity than traditional designs. Thermal chemical analysis revealed 15% increase thermal stability composites, enhancing resilience under physiological conditions. However, identified minor inconsistencies filament diameter during printing, which could affect uniformity. These underscore potential integrating AI-driven material composites revolutionizing orthopedic technologies.

Язык: Английский

Процитировано

0
Advances in Wearable Nanomaterial-Based Sensors for Environmental and Health Monitoring: A Comprehensive Review DOI

Sikandar Aftab,

Ganesh Koyyada, Najaf Rubab

и другие.

Journal of environmental chemical engineering, Год журнала: 2025, Номер unknown, С. 115788 - 115788

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Optimized machine learning framework for cardiovascular disease diagnosis: a novel ethical perspective DOI Creative Commons
Ghadah Alwakid,

Farman Ul Haq,

Noshina Tariq

и другие.

BMC Cardiovascular Disorders, Год журнала: 2025, Номер 25(1)

Опубликована: Фев. 20, 2025

Alignment of advanced cutting-edge technologies such as Artificial Intelligence (AI) has emerged a significant driving force to achieve greater precision and timeliness in identifying cardiovascular diseases (CVDs). However, it is difficult high accuracy reliability CVD diagnostics due complex clinical data the selection modeling process useful features. Therefore, this paper studies AI-based feature techniques application AI classification. It uses methodologies Chi-square, Info Gain, Forward Selection, Backward Elimination an essence health indicators into refined eight-feature subset. This study emphasizes ethical considerations, including transparency, interpretability, bias mitigation. achieved by employing unbiased datasets, fair techniques, rigorous validation metrics ensure fairness trustworthiness diagnostic process. In addition, integration various Machine Learning (ML) models, encompassing Random Forest (RF), XGBoost, Decision Trees (DT), Logistic Regression (LR), facilitates comprehensive exploration predictive performance. Among diverse range XGBoost stands out top performer, achieving exceptional scores with 99% rate, 100% recall, F1-measure, precision. Furthermore, we venture dimensionality reduction, applying Principal Component Analysis (PCA) subset, effectively refining compact six-attribute Once again, shines model choice, yielding outstanding results. achieves accuracy, 98%, 100%, 97%, respectively, when applied subset derived from combination Chi-square Selection methods.

Язык: Английский

Процитировано

0
Recent Advances in Vehicle Driver Health Monitoring Systems DOI Creative Commons
Lauris Melders, Ruslans Šmigins, Aivars Birkavs

и другие.

Sensors, Год журнала: 2025, Номер 25(6), С. 1812 - 1812

Опубликована: Март 14, 2025

The need for creative solutions in the real-time monitoring of health is rapidly increasing, especially light incidents relation to drivers motor vehicles. A sensor-based system provides an integrated mechanism diagnosing and managing real time, enabling detection, prediction, recommendation treatment prevention disease onset. driver’s represents a significant advancement assurance driver safety well-being. From fitness trackers advanced biosensors, these devices have not only made healthcare more accessible but also transformed how people interact with their data. purpose this scoping review systematically collect evaluate information from publications on systems provide comprehensive overview current state research wearable or remote sensor technologies monitoring. It aims identify knowledge gaps that be addressed suggest future directions will help fill gaps. This approach involves topic vehicle contribute field. By focusing parameters automotive context, highlights potential different types bridge gap between safety.

Язык: Английский

Процитировано

0
Emerging Rapid Detection Methods for the Monitoring of Cardiovascular Diseases: Current Trends and Future Perspectives DOI Creative Commons
Rafi u Shan Ahmad, Wasim Khan,

Muhammad Shehzad Khan

и другие.

Materials Today Bio, Год журнала: 2025, Номер 32, С. 101663 - 101663

Опубликована: Март 14, 2025

Язык: Английский

Процитировано

0
Wearable-derived short sleep duration is associated with higher C-reactive protein in a placebo-controlled vaccine trial among young adults DOI Creative Commons
Chunxue Wang, Sara Mariani, Robert J. Damiano

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 26, 2025

Inadequate sleep has been associated with an increased risk of mortality and various health issues. We previously conducted a placebo-controlled vaccination trial healthy adults who were monitored by blood samples, questionnaires, wearable devices. C-reactive protein (CRP), systemic marker inflammation, linked to numerous outcomes, was found significantly increase post-vaccination in the trial. In this retrospective study, we investigated that if inflammation response triggered perturbations from vaccine placebo injections. Plasma hs-CRP levels measured on same day as intervention, prior vaccine/placebo administration two days after intervention. Associations duration CRP 188 participants regression models adjusting for age, sex, body mass index (BMI), comorbidities, status (vaccination or placebo), averaged daily steps. shorter wearable-derived Total Sleep Time (TST) Bed (TIB), well subjectively assessed Pittsburgh Quality Index (PSQI), independently higher incidence elevation administration. Our study suggests deprivation could be predictor inflammatory highlights potential application metrics public health.

Язык: Английский

Процитировано

0
Optimization of PETG 3D printing parameters for the design and development of biocompatible bone implants DOI Creative Commons
Muhammad Sultan,

Tauseef Aized,

Muhammad Farooq

и другие.

Frontiers in Bioengineering and Biotechnology, Год журнала: 2025, Номер 13

Опубликована: Март 27, 2025

The search for suitable manufacturing methods and the selection of biocompatible material with good mechanical properties is still a major challenge in implant development. polyethylene terephthalate glycol (PETG) thermoplastic extensively utilized biomedical applications, like tissue engineering, dental, scaffolds surgery, because its biocompatibility. Fused deposition modeling (FDM) gaining importance wide range applications developing custom shaped medical implants. This study aimed to fabricate cranial using optimized parameters 3D printed PETG properties. research investigates optimization key printing layer height, line width print speed by utilizing Box Behnken Design (BBD). Analysis suggests that influential FDM are height width, which significantly influence tensile compressive strength. analysis variance (ANOVA) showed 0.12 mm, 0.77 mm 25.75 mm/s indicated increased value strength, i.e., 51.18 MPa 52.33 MPa, respectively. effectiveness RSM model was confirmed validation experiment, errors less than 2%. Additionally, this presents process framework development customized implants computed tomography (CT) scan data patient. tested under uniaxial load shows an average peak 1088 N. goal assist surgeons overcoming clinical challenges faced while selecting materials in-house production patient-specific A further evaluation presented technology recommended potential use trials.

Язык: Английский

Процитировано

0