USING ARTIFICIAL INTELLIGENCE FOR BIOMARKER ANALYSIS IN CLINICAL DIAGNOSTICS DOI
П. В. Селиверстов, V. Kutsenko,

V. G. Gorelova

et al.

Molekulyarnaya Meditsina (Molecular medicine), Journal Year: 2024, Volume and Issue: unknown, P. 31 - 40

Published: Nov. 6, 2024

Introduction. Artificial intelligence (AI) technologies are becoming crucial in clinical diagnostics due to their ability process and interpret large volumes of data. The implementation AI for biomarker analysis opens new opportunities personalized medicine, offering more accurate individualized approaches disease diagnosis treatment. relevance this review stems from the need systematize recent advances application analysis, which is critical early prediction chronic non-communicable diseases (NCDs). Material methods. peer-reviewed scientific publications reports leading research centers over past five years was conducted. Studies on algorithms analyzing genomic, proteomic, metabolomic biomarkers were reviewed, including machine learning methods deep neural networks. Special attention paid integration multi-marker panels improving accuracy cardiovascular, digestive, respiratory, endocrine system diseases, as well oncological neurodegenerative pathologies. Results. has significantly increased sensitivity specificity diagnostics, especially complex cases requiring multiple parameters. effectiveness been demonstrated lung, breast, colorectal cancer, cardiovascular complications NCDs progression, diabetes mellitus Alzheimer’s disease. AI’s significant contribution discovery biomarkers, optimization treatment, improvement therapeutic strategies noted. Conclusion. use become a breakthrough medical particularly oncology, cardiology, diseases. technology allows data about various contributes creating models prediction. Further development associated with advancement overcoming ethical regulatory barriers, will expand capabilities practice.

Language: Английский

E-Nose: a new frontier for non-invasive cancer detection and monitoring DOI Open Access
Ata Jahangir Moshayedi, Amir Sohail Khan, Ming Chen

et al.

Journal of Cancer Metastasis and Treatment, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 10, 2025

Electronic Nose (E-Nose) technology has emerged as a transformative tool in medical diagnostics, leveraging sensor arrays that mimic the human olfactory system to detect odors and volatile organic compounds (VOCs) various biological samples. E-Nose systems utilize range of types, such metal oxide semiconductors conducting polymers, generate unique “smell fingerprints” through pattern recognition algorithms. These have shown promise diagnosing conditions, including respiratory diseases, infectious metabolic disorders, neurological conditions. Notably, holds significant cancer offering non-invasive, cost-effective, rapid approach early detection monitoring. It demonstrated impressive accuracy (85%-95%) detecting cancers monitoring complications. However, challenges remain, issues with standardization, sensitivity, data interpretation. Despite these hurdles, technology’s market growth is fueled by increasing prevalence chronic diseases. Recent developments Artificial Intelligence (AI), particularly machine learning techniques like deep learning, enhanced diagnostic robustness devices. This paper explores evolution, core principles, applications, challenges, future potential technology, particular emphasis on integrating recent advancements AI for Future research collaboration across sectors are essential overcome existing integrate into mainstream healthcare.

Language: Английский

Citations

2
Two-dimensional nanomaterials-based optical biosensors empowered by machine learning for intelligent diagnosis DOI

Rongshuang Tang,

Jianyu Yang,

Changzhuan Shao

et al.

TrAC Trends in Analytical Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 118162 - 118162

Published: Feb. 1, 2025

Language: Английский

Citations

1
Artificial intelligence-assisted point-of-care devices for lung cancer DOI
Xinyi Ng, Anis Salwa Mohd Khairuddin,

Hai Chuan Liu

et al.

Clinica Chimica Acta, Journal Year: 2025, Volume and Issue: unknown, P. 120191 - 120191

Published: Feb. 1, 2025

Language: Английский

Citations

1
Investigating lung cancer microenvironment from cell segmentation of pathological image and its application in prognostic stratification DOI Creative Commons
Xu Zhang,

Zi-Han Zhang,

Yongmin Liu

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 11, 2025

Lung cancer, particularly adenocarcinoma, ranks high in morbidity and mortality rates worldwide, with a relatively low five-year survival rate. To achieve precise prognostic assessment clinical intervention for patients, thereby enhancing their prospects, there is an urgent need more accurate stratification schemes. Currently, the TNM staging system predominantly used practice evaluation, but its accuracy constrained by reliance on physician experience. Although biomarker discovery based molecular pathology offers new perspective assessment, dependence expensive gene panel testing limits widespread application. Pathological images contain abundant diagnostic information, providing avenue evaluation. In this study, we employed advanced Hover-Net technology to accurately quantify abundance of epithelial cells, lymphocytes, macrophages, neutrophils from pathological images, delved into biological significance these cellular abundances. Our research findings reveal that, contrast patients classified as N0 stage, those belonging N1 stage demonstrated marked elevation infiltration neutrophils. Notably, patterns lymphocytes exhibited inverse relationship activation status numerous pivotal pathways, including HALLMARK_HEME_METABOLISM pathway. Furthermore, our analysis distinguished FABP7 biomarker, exhibiting pronounced differential expression between levels neutrophil infiltration, indicate that can provide cost-effective offering strategies management lung adenocarcinoma.

Language: Английский

Citations

0
Development of In-house Chest Phantom for Pediatric Cancer Cases DOI Open Access

Yola Sri Wahyuni,

Choirul Anam, Ilham Alkian

et al.

International Journal of Scientific Research in Science and Technology, Journal Year: 2025, Volume and Issue: 12(1), P. 268 - 275

Published: Jan. 30, 2025

This study aims to develop an in-house phantom that can more cheaply represent pediatric lung cancer cases. The materials used in this were polymethyl methacrylate (PMMA) as a substitute for soft tissue, polyurethane (PU) foam and calcium carbonate replacement rib bones. Cancer or nodules represented using beeswax. evaluation was conducted IndoQCT software, with parameters such CT number, noise, signal-to-noise ratio (SNR), contrast-to-noise (CNR). numbers of cancer/nodule, normal lung, bone the are -217 -117, -979, 80, 871 HU, respectively. As comparison, number real patients -141 -103, -906, 73, 743 These findings indicate SNR, CNR values closely resemble imaging cancer/nodules. Thus, effectively human tissue substitutes.

Language: Английский

Citations

0
Deep Hybrid Neural Network: Unveiling Lung Cancer With Deep Hybrid Intelligence from CT Scans DOI Creative Commons
Chinmayee Nayak, Alakananda Tripathy, Manoranjan Parhi

et al.

Cureus Journal of Computer Science., Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 10, 2025

Language: Английский

Citations

0
Integrating Machine Learning Algorithms: A Hybrid Model for Lung Cancer Outcome Improvement DOI Creative Commons

Pradnyawant M. Gote,

Praveen Kumar, Hemant Kumar

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(9), P. 4637 - 4637

Published: April 22, 2025

Lung cancer is a major global health threat, affecting millions annually and resulting in severe complications high mortality rates, particularly when diagnosed late. It remains one of the leading causes cancer-related deaths worldwide, often detected at advanced stages due to lack early symptoms. This study introduces novel hybrid machine learning model aimed enhancing detection accuracy improving patient outcomes. By integrating traditional classifiers with deep techniques, proposed framework optimizes feature selection, hyperparameter tuning, data-balancing strategies, such as Adaptive Synthetic Sampling (ADASYN). A comparative evaluation existing models demonstrated substantial improvements predictive accuracy, ranging from 0.44% 9.69%, Gradient Boosting Random Forest achieving highest classification performance. The highlights importance methodologies refining lung diagnostics, ensuring robust, scalable, clinically viable models.

Language: Английский

Citations

0
Optimizing Bi-LSTM networks for improved lung cancer detection accuracy DOI Creative Commons

Su Diao,

Yajie Wan,

Danyi Huang

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0316136 - e0316136

Published: Feb. 24, 2025

Lung cancer remains a leading cause of cancer-related deaths worldwide, with low survival rates often attributed to late-stage diagnosis. To address this critical health challenge, researchers have developed computer-aided diagnosis (CAD) systems that rely on feature extraction from medical images. However, accurately identifying the most informative image features for lung detection significant challenge. This study aimed compare effectiveness both hand-crafted and deep learning-based approaches We employed traditional features, such as Gray Level Co-occurrence Matrix (GLCM) in conjunction machine learning algorithms. explore potential learning, we also optimized implemented Bidirectional Long Short-Term Memory (Bi-LSTM) network detection. The results revealed highest performance using was achieved by extracting GLCM utilizing Support Vector Machine (SVM) different kernels, reaching an accuracy 99.78% AUC 0.999. Bi-LSTM surpassed methods, achieving 99.89% 1.0000. These findings suggest proposed methodology, combining holds promise enhancing early ultimately improving systems.

Language: Английский

Citations

0
Optimizing pulmonary nodule segmentation in CT imaging: A comparative study of anchor-based and anchor-free detectors using attention mechanism DOI

K. Vino Aishwarya,

A. Asuntha,

Jayanth Murugan

et al.

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: March 18, 2025

Language: Английский

Citations

0
Smart nanomedicines powered by artificial intelligence: a breakthrough in lung cancer diagnosis and treatment DOI

Moloudosadat Alavinejad,

Moein Shirzad,

Mohammad Javad Javid-Naderi

et al.

Medical Oncology, Journal Year: 2025, Volume and Issue: 42(5)

Published: March 25, 2025

Language: Английский

Citations

0