Dataset Information

Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data.

ABSTRACT: For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates based on longitudinal data are challenging to create due to disease complexity, variation, and irregular visit intervals. Here, we utilize RadImageNet pretrained models to diagnose five types of ILD with multimodal data and a transformer model to determine a patient's 3-year survival rate. When clinical history and associated CT scans are available, the proposed deep learning system can help clinicians diagnose and classify ILD patients and, importantly, dynamically predict disease progression and prognosis.

SUBMITTER: Mei X

PROVIDER: S-EPMC10119160 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data.

Mei Xueyan X Liu Zelong Z Singh Ayushi A Lange Marcia M Boddu Priyanka P Gong Jingqi Q X JQX Lee Justine J DeMarco Cody C Cao Chendi C Platt Samantha S Sivakumar Ganesh G Gross Benjamin B Huang Mingqian M Masseaux Joy J Dua Sakshi S Bernheim Adam A Chung Michael M Deyer Timothy T Jacobi Adam A Padilla Maria M Fayad Zahi A ZA Yang Yang Y

Nature communications 20230420 1

For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates b ...[more]

PMID: 37080956

Similar Datasets

Project description:BackgroundPrognosis prediction is crucial for non-small cell lung cancer (NSCLC) treatment planning. While tumor hypoxia significantly impacts patient outcomes, identifying hypoxic genomic markers remains challenging. This study sought to identify hypoxic computed tomography (CT) radiomic features and create an artificial intelligence (AI) model for NSCLC through the integration of multi-modal data.MethodsIn total, 452 NSCLC patients were enrolled in this study, including patients from The Second Affiliated Hospital of Soochow University (SC, n=112), The Cancer Genome Atlas (TCGA)-NSCLC dataset (n=74), the radiogenomics dataset (n=130), and the Gene Expression Omnibus (GEO) datasets (GSE19188: n=82, and GSE87340: n=54). Hypoxia status was classified using optimized cut-off values of hypoxia enrichment scores, which were calculated through single-sample gene set enrichment analysis (ssGSEA) of hypoxic genes. Radiomic features were extracted using three-dimensional (3D)-Slicer software. The least absolute shrinkage and selection operator (LASSO) algorithm was used to identify hypoxic CT radiomic features. A model named ssuBERT (semantic structured unit embedded in Bidirectional Encoder Representations from Transformers) was developed to analyze electronic health records (EHRs). An AI model for overall survival prediction was constructed by integrating CT radiomic features, ssuBERT features, and clinical data, and evaluated using five-fold cross-validation.ResultsHigher hypoxia levels were correlated with worse survival outcomes. Twenty-eight radiomic features showed significant discriminatory power in detecting hypoxia status with an area under the curve (AUC) of 0.8295. The ssuBERT model achieved a weighted accuracy of 0.945 in recognizing semantic structured units in EHRs. The EHR model exhibited superior predictive performance among the single-modal models with an AUC of 0.7662. However, the multi-modal AI model had the highest average AUC of 0.8449 and an F1 score of 0.7557.ConclusionsThe AI model demonstrated potential in predicting NSCLC patient prognosis through multi-modal data integration, warranting further validation.

Project description:BackgroundThe prognostic and theragnostic role of histopathological subsets in systemic sclerosis interstitial lung disease (SSc-ILD) have been largely neglected due to the paucity of treatment options and the risks associated with surgical lung biopsy. The novel drugs for the treatment of ILDs and the availability of transbronchial cryobiopsy provide a new clinical scenario making lung biopsy more feasible and a pivotal guide for treatment. The aim of our study was to investigate the usefulness of lung biopsy in SSc ILD with a systematic literature review (SLR).MethodsPubMed, Embase and Cochrane databases were searched up to June 30, 2023. Search terms included both database-specific controlled vocabulary terms and free-text terms relating to lung biopsy and SSc-ILD diagnostic and prognosis. The SLR was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA). Studies were selected according to the PEO (population, exposure, and outcomes) framework and Quality assessment of diagnostic accuracy studies (QUADAS) were reported.ResultsWe selected 14 articles (comprising 364 SSc-ILD patients). The paucity and heterogeneity of the studies prevented a systematic analysis. Diffuse cutaneous SSc was present in 30-100% of cases. Female predominance was observed in all studies (ranging from 64 to 100%). Mean age ranged from 42 to 64 years. Mean FVC was 73.98 (+/-17.3), mean DLCO was 59.49 (+/-16.1). Anti-Scl70 antibodies positivity was detected in 33% of cases (range: 0-69.6). All patients underwent surgical lung biopsies, and multiple lobes were biopsied in a minority of studies (4/14). Poor HRCT-pathologic correlation was reported with HRCT-NSIP showing histopathologic UIP in up to 1/3 of cases. Limited data suggest that SSc-UIP patients may have a worse prognosis and response to immunosuppressive treatment compared to other histopathologic patterns.ConclusionsThe data from this SLR clearly show the paucity and heterogeneity of the studies reporting lung biopsy in SSc ILD. Moreover, they highlight the need for further research to address whether the lung biopsy can be helpful to refine prognostic prediction and guide therapeutic choices.

Dataset Information

Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data.

Publications

Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets