Role of Machine Learning Assisted Biosensors in Point-of-Care-Testing For Clinical Decisions

ACS Sensors, Год журнала: 2024, Номер 9(9), С. 4495 - 4519

Опубликована: Авг. 15, 2024

Point-of-Care-Testing (PoCT) has emerged as an essential component of modern healthcare, providing rapid, low-cost, and simple diagnostic options. The integration Machine Learning (ML) into biosensors ushered in a new era innovation the field PoCT. This article investigates numerous uses transformational possibilities ML improving for algorithms, which are capable processing interpreting complicated biological data, have transformed accuracy, sensitivity, speed procedures variety healthcare contexts. review explores multifaceted applications models, including classification regression, displaying how they contribute to capabilities biosensors. roles ML-assisted electrochemical sensors, lab-on-a-chip electrochemiluminescence/chemiluminescence colorimetric wearable sensors diagnosis explained detail. Given increasingly important role PoCT, this study serves valuable reference researchers, clinicians, policymakers interested understanding emerging landscape point-of-care diagnostics.

Язык: Английский

---

AI-Driven Sensing Technology: Review

Sensors, Год журнала: 2024, Номер 24(10), С. 2958 - 2958

Опубликована: Май 7, 2024

Machine learning and deep technologies are rapidly advancing the capabilities of sensing technologies, bringing about significant improvements in accuracy, sensitivity, adaptability. These advancements making a notable impact across broad spectrum fields, including industrial automation, robotics, biomedical engineering, civil infrastructure monitoring. The core this transformative shift lies integration artificial intelligence (AI) with sensor technology, focusing on development efficient algorithms that drive both device performance enhancements novel applications various engineering fields. This review delves into fusion ML/DL shedding light their profound design, calibration compensation, object recognition, behavior prediction. Through series exemplary applications, showcases potential AI to significantly upgrade functionalities widen application range. Moreover, it addresses challenges encountered exploiting these for offers insights future trends advancements.

Язык: Английский

---

Cross-site validation of lung cancer diagnosis by electronic nose with deep learning: a multicenter prospective study

Respiratory Research, Год журнала: 2024, Номер 25(1)

Опубликована: Май 10, 2024

Abstract Background Although electronic nose (eNose) has been intensively investigated for diagnosing lung cancer, cross-site validation remains a major obstacle to be overcome and no studies have yet performed. Methods Patients with as well healthy control diseased groups, were prospectively recruited from two referral centers between 2019 2022. Deep learning models detecting cancer eNose breathprint developed using training cohort one site then tested on the other site. Semi-Supervised Domain-Generalized (Semi-DG) Augmentation (SDA) Noise-Shift (NSA) methods or without fine-tuning was applied improve performance. Results In this study, 231 participants enrolled, comprising training/validation of 168 individuals (90 16 controls, 62 controls) test 63 (28 10 25 controls). The model satisfactory results in same hospital while directly applying trained yielded suboptimal (AUC, 0.61, 95% CI: 0.47─0.76). performance improved after data augmentation (SDA, AUC: 0.89 [0.81─0.97]; NSA, AUC:0.90 [0.89─1.00]). Additionally, methods, further (SDA plus fine-tuning, AUC:0.95 [0.89─1.00]; NSA [0.90─1.00]). Conclusion Our study revealed that deep can achieve fine-tuning. Accordingly, breathprints emerge convenient, non-invasive, potentially generalizable solution detection. Clinical trial registration This is not clinical therefore registered.

Язык: Английский

---

Chemical Nose-Based Non-Invasive Detection of Breast Cancer Using Exhaled Breath

Sensors, Год журнала: 2025, Номер 25(7), С. 2210 - 2210

Опубликована: Март 31, 2025

Breast cancer (BC) is the most commonly occurring in women and one of leading causes death worldwide. BC mortality related to early tumor detection, highlighting importance detection methods. This work aims develop a robust, accurate highly reliable, non-invasive, low-cost screening method for routine using exhaled breath (EB) analysis. For this, samples were collected from 267 women: 131 breast patients 136 healthy women. After collection, measured commercially available electronic nose. The signals obtained each sample first processed then went through feature extraction step. An SVM model was optimized with respect accuracy matrix validation set by applying Monte Carlo cross-validation 100 iterations, iteration containing 20% data. results 80, 94, 88, 95% recall, precision, accuracy, specificity, correspondingly. Once optimization had concluded, 22 unknown analyzed model, an specificity 91% achieved.

Язык: Английский

---

Artificial intelligence-driven transformative applications in disease diagnosis technology

Medical Review, Год журнала: 2025, Номер unknown

Опубликована: Апрель 11, 2025

Abstract The integration of artificial intelligence (AI) in medical diagnostics represents a transformative advancement healthcare, with projected market growth reaching $188 billion by 2030. This comprehensive review examines the latest developments AI-driven diagnostic technologies across multiple disease domains, particularly focusing on cancer, Alzheimer’s (AD), and diabetes. Through systematic bibliometric analysis using GraphRAG methodology, we analyzed research publications from 2022 to 2024, revealing distribution impact AI applications various fields. In cancer diagnostics, systems have achieved breakthrough performances analyzing imaging molecular data, notable advances early detection capabilities 19 different types. For AD diagnosis, AI-powered tools demonstrated up 90 % accuracy risk through non-invasive methods, including speech pattern blood-based biomarkers. diabetes care, AI-integrated incorporating deep neural networks electronic nose technology shown remarkable predicting onset before clinical manifestation. These collectively indicate paradigm shift toward more precise, efficient, accessible approaches. However, challenges remain standardization, data quality, implementation. synthesizes current progress while highlighting potential for revolutionize enhanced accuracy, detection, personalized patient care.

Язык: Английский

---

Observation of odd–even effect in 1-alcohols through pentapeptide-coated quartz crystal microbalance sensors with molecular docking study

Applied Physics Letters, Год журнала: 2025, Номер 126(16)

Опубликована: Апрель 21, 2025

The discrimination between odd and even carbon chain molecules is crucial in detecting metabolites resulting from impaired biosynthetic processes. However, the of these metabolomes via gas sensors presents significant challenges due to lack connection material–gas interaction odd–even molecules. In this study, a homologous series 1-alcohols systematically investigated, quantitatively comparing measured signals obtained using pentapeptide-coated pentapeptide–gas interactions calculated molecular docking simulations. sensor exhibits clear effect both absorption desorption processes, demonstrating better odd- even-numbered compounds. results indicate that during process closely associated with hydrophobic pentapeptide molecule, while affecting phase may vary depending on properties. insights into involved will facilitate development materials for metabolites, which can enhance accuracy gas-sensing technologies toward health monitoring applications.

Язык: Английский

---

Breath Analysis Using Quartz Tuning Forks for Predicting Blood Glucose Levels Using Artificial Neural Networks

ACS Sensors, Год журнала: 2024, Номер 9(10), С. 5468 - 5478

Опубликована: Окт. 16, 2024

Diabetes Mellitus (DM), a widespread metabolic disorder, poses lifelong health implications, demanding timely diagnosis and cautious monitoring for effective disease management. Traditional blood glucose tests are invasive require medical expertise intermittent checking, motivating the investigation of alternative, noninvasive methods. This study introduces an approach employing breath analysis through set 12 quartz tuning fork-based sensors enhanced using nanomaterials dedicated artificial neural network (ANN) algorithms data interpretation. The methodology involves capturing unique signatures frequency-based sensor array. accompanying classification algorithm, customized data, enables precise from 245 individuals as diabetic, prediabetic, or healthy. A regression algorithm predicted values was compared with actual obtained measurement. clinical relevance has been examined error grids. array coupled ANN can identify control samples 97% test accuracy. Blood correlation coefficient 0.89 mean square 0.13.

Язык: Английский

---

Enhance Ethanol Sensing Performance of Fe-Doped Tetragonal SnO2 Films on Glass Substrate with a Proposed Mathematical Model for Diffusion in Porous Media

Sensors, Год журнала: 2024, Номер 24(14), С. 4560 - 4560

Опубликована: Июль 14, 2024

This research enhances ethanol sensing with Fe-doped tetragonal SnO2 films on glass, improving gas sensor reliability and sensitivity. The primary objective was to improve the sensitivity operational efficiency of sensors through Fe doping. were synthesized using a flexible adaptable method that allows for precise doping control, energy-dispersive X-ray spectroscopy (EDX) confirming homogeneous distribution within matrix. A morphological analysis showed surface structure ideal sensing. results demonstrated significant improvement in response (1 20 ppm) lower temperatures compared undoped sensors. exhibited higher sensitivity, enabling detection low concentrations showing rapid recovery times. These findings suggest interaction between molecules surface, performance. mathematical model based diffusion porous media employed further analyze optimize considers matrix, considering factors such as morphology concentration. Additionally, choice electrode material plays crucial role extending sensor’s lifespan, highlighting importance selection design.

Язык: Английский

---

Enhanced Diabetes Detection and Blood Glucose Prediction Using TinyML-Integrated E-Nose and Breath Analysis: A Novel Approach Combining Synthetic and Real-World Data

Bioengineering, Год журнала: 2024, Номер 11(11), С. 1065 - 1065

Опубликована: Окт. 25, 2024

Diabetes mellitus, a chronic condition affecting millions worldwide, necessitates continuous monitoring of blood glucose level (BGL). The increasing prevalence diabetes has driven the development non-invasive methods, such as electronic noses (e-noses), for analyzing exhaled breath and detecting biomarkers in volatile organic compounds (VOCs). Effective machine learning models require extensive patient data to ensure accurate BGL predictions, but previous studies have been limited by small sample sizes. This study addresses this limitation employing conditional generative adversarial networks (CTGAN) generate synthetic from real-world tests involving 29 healthy diabetic participants, resulting over 14,000 new samples. These were used validate detection prediction, integrated into Tiny Machine Learning (TinyML) e-nose system real-time analysis. proposed achieved an 86% accuracy identification using LightGBM (Light Gradient Boosting Machine) 94.14% Random Forest. results demonstrate efficacy enhancing with both real data, particularly systems integrating e-noses TinyML. signifies major advancement monitoring, underscoring transformative potential TinyML-powered healthcare applications.

Язык: Английский

---

Theoretical Study of Gas Sensing toward Acetone by a Single-Atom Transition Metal (Sc, Ti, V, and Cr)-Doped InP₃ Monolayer

ACS Omega, Год журнала: 2024, Номер 9(45), С. 45059 - 45067

Опубликована: Окт. 30, 2024

Acetone (C3H6O) gas in the exhaled breath of diabetic patients can be used as an important biomarker for painless and noninvasive diagnosis diabetes mellitus. In this paper, based on density functional theory (DFT), adsorption behaviors pristine single-atom transition metal (X = Sc, Ti, V, Cr)-doped InP3 surfaces (denoted X-InP3) toward C3H6O molecule were examined to explore potential these two-dimensional (2D) materials a sensitive sensor acetone gas. The calculation results indicate unfavorable detection property 2D-InP3 surface upon with unsatisfied response (12.4%). introduction (Sc, Cr) into layer has significantly improved capacity molecule. Owing high values (−98.0%, 393.3%, 393.3%), Ti-InP3, V-InP3, Cr-InP3 layers show their superiority at room temperature, which Ti-InP3 achieves recycle use through heating 698 K. Sc-InP3 is unsuitable sensing poor (8.1%). Our work first gives theoretical predication about performance acetone, may provide emerging kind material mellitus indicated by

Язык: Английский

---