Explainable AI models for predicting drop coalescence in microfluidics device DOI Creative Commons
Jin-Wei Hu, Kewei Zhu, Sibo Cheng

et al.

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 481, P. 148465 - 148465

Published: Jan. 2, 2024

In the field of chemical engineering, understanding dynamics and probability drop coalescence is not just an academic pursuit, but a critical requirement for advancing process design by applying energy only where it needed to build necessary interfacial structures, increasing efficiency towards Net Zero manufacture. This research applies machine learning predictive models unravel sophisticated relationships embedded in experimental data on microfluidics device. Through deployment SHapley Additive exPlanations values, features relevant processes are consistently identified. Comprehensive feature ablation tests further delineate robustness susceptibility each model. Furthermore, incorporation Local Interpretable Model-agnostic Explanations local interpretability offers elucidative perspective, clarifying intricate decision-making mechanisms inherent model's predictions. As result, this provides relative importance outcome interactions. It also underscores pivotal role model reinforcing confidence predictions complex physical phenomena that central engineering applications.

Language: Английский

Fabrication and Applications of Microfluidic Devices: A Review DOI Open Access
Adelina-Gabriela Niculescu, Cristina Chircov, Alexandra Cătălina Bîrcă

et al.

International Journal of Molecular Sciences, Journal Year: 2021, Volume and Issue: 22(4), P. 2011 - 2011

Published: Feb. 18, 2021

Microfluidics is a relatively newly emerged field based on the combined principles of physics, chemistry, biology, fluid dynamics, microelectronics, and material science. Various materials can be processed into miniaturized chips containing channels chambers in microscale range. A diverse repertoire methods chosen to manufacture such platforms desired size, shape, geometry. Whether they are used alone or combination with other devices, microfluidic employed nanoparticle preparation, drug encapsulation, delivery, targeting, cell analysis, diagnosis, culture. This paper presents technology terms available platform fabrication techniques, also focusing biomedical applications these remarkable devices.

Language: Английский

Citations

456
Machine Learning‐Reinforced Noninvasive Biosensors for Healthcare DOI
Kaiyi Zhang, Jianwu Wang, Tianyi Liu

et al.

Advanced Healthcare Materials, Journal Year: 2021, Volume and Issue: 10(17)

Published: June 24, 2021

The emergence and development of noninvasive biosensors largely facilitate the collection physiological signals processing health-related data. utilization appropriate machine learning algorithms improves accuracy efficiency biosensors. Machine learning-reinforced are started to use in clinical practice, health monitoring, food safety, bringing a digital revolution healthcare. Herein, recent advances applied healthcare summarized. First, different types collected categorized Then adopted subsequent data introduced their practical applications reviewed. Finally, challenges faced by raised, including privacy adaptive capability, prospects real-time out-of-clinic diagnosis, onsite safety detection proposed.

Language: Английский

Citations

111
Emergence of microfluidics for next generation biomedical devices DOI Creative Commons
Subham Preetam, Bishal Kumar Nahak, Santanu Patra

et al.

Biosensors and Bioelectronics X, Journal Year: 2022, Volume and Issue: 10, P. 100106 - 100106

Published: Jan. 8, 2022

The attention in lab-on-a-chip devices with their potent application medical engineering has prolonged swiftly over the last ten years. Travelling through technology development, innovative microfluidics shown enormous potential to lift biomedical research traditions that are not imaginable using conventional techniques. advances arena of have prompted high-tech uprisings numerous disciplines, including diagnostics, single-cell analysis, micro- and nano device fabrication, organ-in-chip platforms, med-tech applications. speedy development is motivated by cumulative cooperation among central nanomaterials microfluidic aptitudes range Microfluidic gadgets presently undertake a significant part organic, synthetic, designing applications, multiple approaches create vital channel highlight measurements. In this review, critical assessments on frontiers platforms carried out towards advancements capabilities for new-edge It been exhibited offers scope benefits contrasted customary strategies, further developed controllability consistency specified nanomaterial attributes. Herein, authors discussed how innumerable empower manufacture systems advanced optical, mechanical, electrical chemical, bio-interfacial properties ranging from basics microfluidics, various factors, types, fabrication procedure A comprehensive investigation state-of-the-art usage field steered exemplarily understand advantages. Moreover, our assessment provides an interdisciplinary overview modern microfabrication strategies can be adopted academic industrial interests.

Language: Английский

Citations

111
Machine learning for microfluidic design and control DOI Creative Commons
David McIntyre, Ali Lashkaripour, Polly M. Fordyce

et al.

Lab on a Chip, Journal Year: 2022, Volume and Issue: 22(16), P. 2925 - 2937

Published: Jan. 1, 2022

Microfluidics has developed into a mature field with applications across science and engineering, having particular commercial success in molecular diagnostics, next-generation sequencing, bench-top analysis. Despite its ubiquity, the complexity of designing controlling custom microfluidic devices present major barriers to adoption, requiring intuitive knowledge gained from years experience. If these were overcome, microfluidics could miniaturize biological chemical research for non-experts through fully-automated platform development operation. The intuition experts can be captured machine learning, where complex statistical models are trained pattern recognition subsequently used event prediction. Integration learning significantly expand adoption impact. Here, we current state design control devices, possible applications, limitations.

Language: Английский

Citations

88
Janus smart materials with asymmetrical wettability for on-demand oil/water separation: a comprehensive review DOI

Jingling Gong,

Bin Xiang, Yuqing Sun

et al.

Journal of Materials Chemistry A, Journal Year: 2023, Volume and Issue: 11(46), P. 25093 - 25114

Published: Jan. 1, 2023

Janus materials with asymmetrical wettability for on-demand oil/water separation.

Language: Английский

Citations

74
Organ-on-a-chip meets artificial intelligence in drug evaluation DOI Creative Commons
Shiwen Deng, Caifeng Li, Junxian Cao

et al.

Theranostics, Journal Year: 2023, Volume and Issue: 13(13), P. 4526 - 4558

Published: Jan. 1, 2023

Drug evaluation has always been an important area of research in the pharmaceutical industry. However, animal welfare protection and other shortcomings traditional drug development models pose obstacles challenges to evaluation. Organ-on-a-chip (OoC) technology, which simulates human organs on a chip physiological environment functionality, with high fidelity reproduction organ-level physiology or pathophysiology, exhibits great promise for innovating pipeline. Meanwhile, advancement artificial intelligence (AI) provides more improvements design data processing OoCs. Here, we review current progress that made generate OoC platforms, how single multi-OoCs have used applications, including testing, disease modeling, personalized medicine. Moreover, discuss issues facing field, such as large reproducibility, point integration OoCs AI analysis automation, is benefit future Finally, look forward opportunities faced by coupling AI. In summary, advancements development, combinations AI, will eventually break state

Language: Английский

Citations

56
Artificial-intelligence-led revolution of construction materials: From molecules to Industry 4.0 DOI Creative Commons
Xing Quan Wang, Pengguang Chen, Cheuk Lun Chow

et al.

Matter, Journal Year: 2023, Volume and Issue: 6(6), P. 1831 - 1859

Published: June 1, 2023

Language: Английский

Citations

52
Recent developments and future perspectives of microfluidics and smart technologies in wearable devices DOI Open Access

Sasikala Apoorva,

Nam‐Trung Nguyen, Kamalalayam Rajan Sreejith

et al.

Lab on a Chip, Journal Year: 2024, Volume and Issue: 24(7), P. 1833 - 1866

Published: Jan. 1, 2024

Wearable devices are increasingly popular in health monitoring, diagnosis, and drug delivery. Advances allow real-time analysis of biofluids like sweat, tears, saliva, wound fluid, urine.

Language: Английский

Citations

27
High-throughput microfluidic systems accelerated by artificial intelligence for biomedical applications DOI Open Access
Jianhua Zhou, Jianpei Dong, Hongwei Hou

et al.

Lab on a Chip, Journal Year: 2024, Volume and Issue: 24(5), P. 1307 - 1326

Published: Jan. 1, 2024

This review outlines the current advances of high-throughput microfluidic systems accelerated by AI. Furthermore, challenges and opportunities in this field are critically discussed as well.

Language: Английский

Citations

20
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

et al.

Biosensors, Journal Year: 2025, Volume and Issue: 15(2), P. 94 - 94

Published: Feb. 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.

Language: Английский

Citations

2