2026-10-14T17:31:59Z
https://api.figshare.com/v2/oai
oai:figshare.com:article/33865103
2026-09-16T17:21:28Z
category_21
category_734
category_931
category_106
portal_5
item_type_3
month_year_09_2026
<p>Application of AI models in PRISm.</p>
Qian Wu (209382)
Hui Guo (110581)
Ruihan Li (6611660)
Jinhuan Han (24998471)
Zhen Zhang (86004)
Ayajiang Jingesi (24998474)
Biotechnology
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Science Policy
searching across pubmed
respiratory disease diagnosis
precise risk stratification
past two years
enabling early detection
dynamic early warning
robust technical support
including exhaled metabolomics
environmental exposure assessment
environmental exposure
early identification
technical feasibility
including imaging
xlink ">
thereby providing
systematic review
study analyzes
static identification
source data
results demonstrating
remain nascent
published within
preliminarily validated
precision care
ovid medline
nine studies
multiple perspectives
multicenter data
modeling strategies
modality approaches
integrate multi
high performance
eleven studies
developmental potential
continuous evolution
compliant conditions
cochrane library
classification tasks
artificial intelligence
<div>
<p>Background</p><p>Artificial intelligence (AI) has expanded into respiratory disease diagnosis, subtyping, and prognosis, enabling early detection and precision care. However, AI applications in Preserved Ratio Impaired Spirometry (PRISm) remain nascent. This study analyzes this gap to guide future research.</p>
<p>Methods</p><p>A systematic review was conducted to analyze the application of AI in PRISm, searching across PubMed, Cochrane Library, Web of Science, Ovid Medline, Scopus and Embase.</p>
<p>Results</p><p>A total of eleven studies were included, all of which focused on diagnostic and classification tasks. Among these, three utilized radiomics models, four employed machine learning algorithms, two integrated machine learning with radiomics, and two applied deep learning approaches. Nine studies were published within the past two years, with results demonstrating the high performance and developmental potential of AI technologies in this domain. AI research on PRISm spans multiple disciplines, including exhaled metabolomics, environmental exposure assessment, radiomics, and deep learning.</p>
<p>Conclusion</p><p>Existing studies have preliminarily validated the technical feasibility of artificial intelligence for the early identification of PRISm from multiple perspectives, including imaging, metabolism, and environmental exposure. Modeling strategies that integrate multi-source data have demonstrated superior discriminatory performance compared to single-modality approaches. In the future, with the integration and sharing of multicenter data under privacy-compliant conditions, coupled with the continuous evolution of algorithm architectures toward enhanced generalizability, AI applications for PRISm are expected to transition from static identification to dynamic early warning, thereby providing more robust technical support for precise risk stratification of this condition.</p></div>
2026-09-16T17:21:21Z
Dataset
Dataset
10.1371/journal.pone.0353021.t001
https://figshare.com/articles/dataset/_p_Application_of_AI_models_in_PRISm_p_/33865103
CC BY 4.0