Construction of geriatric hypoalbuminemia predicting model for hypoalbuminemia patients with and without pneumonia and explainability analysis DOI Creative Commons
Ziqi Liu, Kang Qi, Zhilong Mi

и другие.

Frontiers in Medicine, Год журнала: 2024, Номер 11

Опубликована: Дек. 31, 2024

Background and objectives Pneumonia portrays a critical health concern in geriatrics. Geriatric pneumonia can lead to changes on other complications, which hypoalbuminemia is common complication. However, few studies have looked at the impact of course predicting. This study aims predicting geriatric non-pneumonia patients exploring clinical difference between two groups. Materials methods retrospective enrolled 42 group 76 group. The indicators different groups were analyzed, then mutual information-grey relational coefficient gradual fusion model was constructed predict future by vital signs, N-Terminal Pro-Brain Natriuretic Peptide, blood routine examination urine admission. Through sensitivity analysis model, we analysed important four examines with without pneumonia. Results predicted accuracy our 0.954, improve prediction nearly 17.6% compared classical machine learning method. AUC 0.96 0.9 showed examine most pneumonia, while patients. Conclusion combined more significant than that alone, characterized abnormal excretion due low protein. We suggested doctors should pay attention results when preventing

Язык: Английский

Biosensor-based methods for exosome detection with applications to disease diagnosis DOI

Weikang Ge,

Zheying Mu,

Shiao Yang

и другие.

Biosensors and Bioelectronics, Год журнала: 2025, Номер unknown, С. 117362 - 117362

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0

Exosomes and their roles in major depressive disorder: an overview of the research progress and perspectives DOI
Mei Tian, Sangyoon Yi, Li Zhao

и другие.

Deleted Journal, Год журнала: 2025, Номер unknown, С. 100035 - 100035

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0

A Comparative Analysis of Three Data Fusion Methods and Construction of the Fusion Method Selection Paradigm DOI Creative Commons
Ziqi Liu, Ziqiao Yin, Zhilong Mi

и другие.

Mathematics, Год журнала: 2025, Номер 13(8), С. 1218 - 1218

Опубликована: Апрель 8, 2025

Multisource and multimodal data fusion plays a pivotal role in large-scale artificial intelligence applications involving big data. However, the choice of strategies for different scenarios is often based on experimental comparisons, which leads to increased computational costs during model training suboptimal performance testing. In this paper, we present theoretical analysis early fusion, late gradual methods. We derive equivalence conditions between fusions within framework generalized linear models. Moreover, analyze failure presence nonlinear feature-label relationships. Furthermore, propose an approximate equation evaluating accuracy methods as function sample size, feature quantity, modality number. also critical size threshold at dominance models undergoes reversal. Finally, introduce method selection paradigm selecting most appropriate prior task execution demonstrate its effectiveness through extensive numerical experiments. Our expected solve problems resource construction, improving scalability efficiency

Язык: Английский

Процитировано

0

Exosomal Biomarkers: A Comprehensive Overview of Diagnostic and Prognostic Applications in Malignant and Non-Malignant Disorders DOI Creative Commons

Mahda Delshad,

Mohammad‐Javad Sanaei, Mohammad Hossein Mohammadi

и другие.

Biomolecules, Год журнала: 2025, Номер 15(4), С. 587 - 587

Опубликована: Апрель 15, 2025

Exosomes are small extracellular vesicles, ranging from 30 to 150 nm, that essential in cell biology, mediating intercellular communication and serving as biomarkers due their origin cells. for diagnosing various illnesses have gained significant investigation the high cost invasive nature of current diagnostic procedures. a clear advantage diagnosis diseases because they include certain signals indicative genetic proteomic profile ailment. This feature gives them potential be useful liquid biopsies real-time, noninvasive monitoring, enabling early cancer identification creation individualized treatment plans. According our analysis, trend toward utilizing exosomes prognostic tools has raised since 2012. In this regard, proportion malignant indications is higher compared with non-malignant ones. To precise, been used most gastrointestinal, thoracic, urogenital cancers, along cardiovascular, diabetic, breathing, infectious, brain disorders. best knowledge, first research examine all registered clinical trials look at biomarker.

Язык: Английский

Процитировано

0

Construction of geriatric hypoalbuminemia predicting model for hypoalbuminemia patients with and without pneumonia and explainability analysis DOI Creative Commons
Ziqi Liu, Kang Qi, Zhilong Mi

и другие.

Frontiers in Medicine, Год журнала: 2024, Номер 11

Опубликована: Дек. 31, 2024

Background and objectives Pneumonia portrays a critical health concern in geriatrics. Geriatric pneumonia can lead to changes on other complications, which hypoalbuminemia is common complication. However, few studies have looked at the impact of course predicting. This study aims predicting geriatric non-pneumonia patients exploring clinical difference between two groups. Materials methods retrospective enrolled 42 group 76 group. The indicators different groups were analyzed, then mutual information-grey relational coefficient gradual fusion model was constructed predict future by vital signs, N-Terminal Pro-Brain Natriuretic Peptide, blood routine examination urine admission. Through sensitivity analysis model, we analysed important four examines with without pneumonia. Results predicted accuracy our 0.954, improve prediction nearly 17.6% compared classical machine learning method. AUC 0.96 0.9 showed examine most pneumonia, while patients. Conclusion combined more significant than that alone, characterized abnormal excretion due low protein. We suggested doctors should pay attention results when preventing

Язык: Английский

Процитировано

1