Ultradense Electrochemical Chip and Machine Learning for High-Throughput, Accurate Anticancer Drug Screening DOI

Daniel S. Doretto,

Paula C. R. Corsato,

C. Silva

и другие.

ACS Sensors, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 29, 2024

Despite the potentialities of electrochemical sensors, these devices still encounter challenges in devising high-throughput and accurate drug susceptibility testing. The lack platforms for providing analyses over preclinical trials candidates remains a significant barrier to developing medicines. In this way, ultradense chips are combined with machine learning (ML) enable high-throughput, user-friendly, determination viability 2D tumor cells (breast colorectal) aiming at assays. effect doxorubicin (anticancer model) was assessed through cell detachment assays by interrogating Ru(NH3)63+ square wave voltammetry (SWV). This positive probe is presumed imply sensitive monitoring on-sensor cellular death because its electrostatic preconcentration so-called nanogap zone between electrode surface adherent cells. High-throughput were obtained merging fast individual SWV measurements (9 s) ability yield series. approach's applicability demonstrated across two analysis formats, drop-casting microfluidic One should also mention that fitting multivariate descriptor from selected input data via ML proved be essential determinations (98 104%) half-maximal lethal concentration drug. achieved results underscore potential method steering sensors toward enabling screening practical applications.

Язык: Английский

Deep Learning-Enhanced Portable Chemiluminescence Biosensor: 3D-Printed, Smartphone-Integrated Platform for Glucose Detection DOI Creative Commons

Chirag M. Singhal,

V. Kaushik,

Amit K. Awasthi

и другие.

Bioengineering, Год журнала: 2025, Номер 12(2), С. 119 - 119

Опубликована: Янв. 27, 2025

A novel, portable chemiluminescence (CL) sensing platform powered by deep learning and smartphone integration has been developed for cost-effective selective glucose detection. This features low-cost, wax-printed micro-pads (WPµ-pads) on paper-based substrates used to construct a miniaturized CL sensor. 3D-printed black box serves as compact WPµ-pad chamber, replacing traditional bulky equipment, such charge coupled device (CCD) cameras optical sensors. Smartphone enables seamless user-friendly diagnostic experience, making this highly suitable point-of-care (PoC) applications. Deep models significantly enhance the platform’s performance, offering superior accuracy efficiency in image analysis. dataset of 600 experimental images was utilized, out which 80% were model training, with 20% reserved testing. Comparative analysis conducted using multiple models, including Random Forest, Support Vector Machine (SVM), InceptionV3, VGG16, ResNet-50, identify optimal architecture accurate The sensor demonstrates linear detection range 10–1000 µM, low limit 8.68 µM. Extensive evaluations confirmed its stability, repeatability, reliability under real-world conditions. learning-powered not only improves analyte detection, but also democratizes access advanced diagnostics through technology. work paves way next-generation biosensing, transformative potential healthcare other domains requiring rapid reliable

Язык: Английский

Процитировано

1
Deep Learning-Assisted Smartphone-Based Electrochemiluminescence Visual Monitoring Biosensor: A Fully Integrated Portable Platform DOI Creative Commons
Manish Bhaiyya, Prakash Rewatkar, Amit Pimpalkar

и другие.

Micromachines, Год журнала: 2024, Номер 15(8), С. 1059 - 1059

Опубликована: Авг. 22, 2024

A novel, portable deep learning-assisted smartphone-based electrochemiluminescence (ECL) cost-effective (~10$) sensing platform was developed and used for selective detection of lactate. Low-cost, fast prototyping screen printing wax methods with paper-based substrate were to fabricate miniaturized single-pair electrode ECL platforms. The lab-made 3D-printed black box served as a reaction chamber. This integrated smartphone buck-boost converter, eliminating the need expensive CCD cameras, photomultiplier tubes, bulky power supplies. advancement makes this ideal point-of-care testing applications. Foremost, integration learning approach enhance not just accuracy sensors, but also expedite diagnostic procedure. models trained (3600 images) tested (900 using images obtained from experimentation. Herein, user convenience, an Android application graphical interface developed. app performs several tasks, which include capturing real-time images, cropping them, predicting concentration required bioanalytes through learning. device’s capability work in real environment by performing lactate sensing. fabricated device shows good liner range (from 50 µM 2000 µM) acceptable limit value 5.14 µM. Finally, various rigorous analyses, including stability, reproducibility, unknown sample analysis, conducted check durability stability. Therefore, becomes versatile applicable across domains harnessing cutting-edge technology integrating it smartphone.

Язык: Английский

Процитировано

5
AI-Reinforced Wearable Sensors and Intelligent Point-of-Care Tests DOI Open Access

Ghita Yammouri,

Abdellatif Ait Lahcen

Journal of Personalized Medicine, Год журнала: 2024, Номер 14(11), С. 1088 - 1088

Опубликована: Ноя. 1, 2024

Artificial intelligence (AI) techniques offer great potential to advance point-of-care testing (POCT) and wearable sensors for personalized medicine applications. This review explores the recent advances transformative of use AI in improving wearables POCT. The integration significantly contributes empowering these tools enables continuous monitoring, real-time analysis, rapid diagnostics, thus enhancing patient outcomes healthcare efficiency. Wearable powered by models tremendous opportunities precise non-invasive tracking physiological conditions that are essential early disease detection treatments. AI-empowered POCT facilitates rapid, accurate making medical kits accessible available even resource-limited settings. discusses key applications data processing, sensor fusion, multivariate analytics, highlighting case examples exhibit their impact different scenarios. In addition, challenges associated with privacy, regulatory approvals, technology integrations into existing system have been overviewed. outlook emphasizes urgent need continued innovation AI-driven health technologies overcome fully achieve revolutionize medicine.

Язык: Английский

Процитировано

5
Machine Learning-Driven Innovations in Microfluidics DOI Creative Commons

JinSeok Park,

Y. Kim, Hee‐Jae Jeon

и другие.

Biosensors, Год журнала: 2024, Номер 14(12), С. 613 - 613

Опубликована: Дек. 13, 2024

Microfluidic devices have revolutionized biosensing by enabling precise manipulation of minute fluid volumes across diverse applications. This review investigates the incorporation machine learning (ML) into design, fabrication, and application microfluidic biosensors, emphasizing how ML algorithms enhance performance improving design accuracy, operational efficiency, management complex diagnostic datasets. Integrating microfluidics with has fostered intelligent systems capable automating experimental workflows, real-time data analysis, supporting informed decision-making. Recent advances in health diagnostics, environmental monitoring, synthetic biology driven are critically examined. highlights transformative potential ML-enhanced systems, offering insights future trajectory this rapidly evolving field.

Язык: Английский

Процитировано

4
Decentralized electrochemical biosensors for biomedical applications: From lab to home DOI Creative Commons
Pramod K. Kalambate, Vipin Kumar,

Dhanjai Dhanjai

и другие.

Next Nanotechnology, Год журнала: 2025, Номер 7, С. 100128 - 100128

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Hydride-reduction-induced oxygen vacancies in CoV2O6 for machine learning-assisted enhanced electrochemical detection of homovanillic acid DOI Creative Commons

Sana Jawaid,

Razium Ali Soomro, Selcan Karakuş

и другие.

Journal of Materials Science Materials in Electronics, Год журнала: 2025, Номер 36(3)

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Innovative Diagnostic Approaches and Challenges in the Management of HIV: Bridging Basic Science and Clinical Practice DOI Creative Commons

Mohd Afzal,

Shagun Agarwal, Rabab Hassan Elshaikh

и другие.

Life, Год журнала: 2025, Номер 15(2), С. 209 - 209

Опубликована: Янв. 30, 2025

Human Immunodeficiency Virus (HIV) remains a major public health challenge globally. Recent innovations in diagnostic technology have opened new pathways for early detection, ongoing monitoring, and more individualized patient care, yet significant barriers persist translating these advancements into clinical settings. This review highlights the cutting-edge methods emerging from basic science research, including molecular assays, biosensors, next-generation sequencing, discusses practical logistical challenges involved their implementation. By analyzing current trends techniques management strategies, we identify critical gaps propose integrative approaches to bridge divide between laboratory innovation effective application. work emphasizes need comprehensive education, supportive infrastructure, multi-disciplinary collaborations enhance utility of improving outcomes patients with HIV.

Язык: Английский

Процитировано

0
Intelligent Microfluidics for Plasma Separation: Integrating Computational Fluid Dynamics and Machine Learning for Optimized Microchannel Design DOI Creative Commons
Kavita Manekar, Manish Bhaiyya,

Meghana A. Hasamnis

и другие.

Biosensors, Год журнала: 2025, Номер 15(2), С. 94 - 94

Опубликована: Фев. 6, 2025

Efficient separation of blood plasma and Packed Cell Volume (PCV) is vital for rapid sensing early disease detection, especially in point-of-care resource-limited environments. Conventional centrifugation methods are resource-intensive, time-consuming, off-chip, necessitating innovative alternatives. This study introduces "Intelligent Microfluidics", an ML-integrated microfluidic platform designed to optimize through computational fluid dynamics (CFD) simulations. The trifurcation microchannel, modeled using COMSOL Multiphysics, achieved yields 90-95% across varying inflow velocities (0.0001-0.05 m/s). input parameters mimic the viscosity density used with appropriate boundary conditions microchannels. Eight supervised ML algorithms, including Artificial Neural Networks (ANN) k-Nearest Neighbors (KNN), were employed predict key performance parameters, ANN achieving highest predictive accuracy (R2 = 0.97). Unlike traditional methods, this demonstrates scalability, portability, diagnostic potential, revolutionizing clinical workflows by enabling efficient real-time, diagnostics. By incorporating a detailed comparative analysis previous studies, efficiency, our work underscores superior ML-enhanced systems. platform's robust adaptable design particularly promising healthcare applications remote or resource-constrained settings where reliable tools urgently needed. novel approach establishes foundation developing next-generation, portable technologies tailored demands.

Язык: Английский

Процитировано

0
Machine-learning-assisted waveguide scattering microscopy for the immunological detection of bovine brucellosis: a proof concept DOI
Jéssica E. S. Fonsaca, Wanderson Sirley Reis Teixeira, Bianca Tieppo

и другие.

Sensors and Actuators B Chemical, Год журнала: 2025, Номер unknown, С. 137458 - 137458

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
FEN1-Aided RPA (FARPA) Coupled with Autosampling Microfluidic Chip Enables Highly Multiplexed On-Site Pathogen Screening DOI
Yi Ma,

Yuanmeng Wang,

Chen Chen

и другие.

Analytical Chemistry, Год журнала: 2025, Номер unknown

Опубликована: Март 6, 2025

A simple, rapid, low-cost, and multiplex detection platform is crucial for the diagnosis of infectious diseases, especially on-site pathogen screening. However, current methods are difficult to satisfy requirements minimal instrument multiplexed point-of-care testing (POCT). Herein, we propose a versatile easy-to-use (FARPA-chip) by combining FARPA with an autosampling microfluidic chip. pair universal recombinase polymerase amplification (RPA) primers introduced during double-stranded cDNA (ds-cDNA) preparation employed amplify multiple targets, followed amplicon-decoding chip, indicating no bias in amplifying different targets due RPA primers. FARPA-chip exhibits that as low 10 copies each target RNA starting sample can be sensitively detected 12-plex vector-borne viruses within 45 min cross-talk observed between targets. The feasibility this confirmed designing 9-plex detect 6 kinds clinically common respiratory from 16 clinical samples nasopharyngeal swabs, results completely consistent RT-qPCR. Furthermore, integrating quick extraction reagent, turnaround time significantly decreased <50 min, highlighting our enables cost-effective screening relatively high level multiplexing. Depending on number chambers design theoretically capable detecting up 24 pathogens, which should fulfill most purposes. We believe proposed could provide effective way series healthcare-related applications resource-limited settings.

Язык: Английский

Процитировано

0