Artificial intelligence identifies inflammation and confirms fibroblast foci as prognostic tissue biomarkers in idiopathic pulmonary fibrosis

Mäkelä, Kati; Mäyränpää, Mikko I.; Sihvo, Hanna-Kaisa; Bergman, Paula; Sutinen, Eva; Ollila, Hely; Kaarteenaho, Riitta; Myllärniemi, Marjukka

doi:10.1016/j.humpath.2020.10.008

Cited by 32 publications

(25 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, AI has already proven to be an excellent tool in the diagnosis and stratification of patients with pulmonary fibrosis [59] , [60] .Christe et al investigated the performance of AI-based models for the automatic classification of idiopathic interstitial pneumonia into radiological CT patterns, based on chest CT scans and clinical markers in comparison with two expert readers [59] . This model achieved similar accuracy in comparison with human readers: 0,81, 0,70, and 0,81, respectively [59] .…”

Section: Role Of the Aimentioning

confidence: 99%

Long-COVID diagnosis: From diagnostic to advanced AI-driven models

Cau

Faa

Nardi

et al. 2022

European Journal of Radiology

View full text Add to dashboard Cite

SARS-COV 2 is recognized to be responsible for a multi-organ syndrome. In most patients, symptoms are mild. However, in certain subjects, COVID-19 tends to progress more severely. Most of the patients infected with SARS-COV2 fully recovered within some weeks. In a considerable number of patients, like many other viral infections, various long-lasting symptoms have been described, now defined as “long COVID-19 syndrome”. Given the high number of contagious over the world, it is necessary to understand and comprehend this emerging pathology to enable early diagnosis and improve patents outcomes. In this scenario, AI-based models can be applied in long-COVID-19 patients to assist clinicians and at the same time, to reduce the considerable impact on the care and rehabilitation unit. The purpose of this manuscript is to review different aspects of long-COVID-19 syndrome from clinical presentation to diagnosis, highlighting the considerable impact that AI can have.

show abstract

Section: Role Of the Aimentioning

confidence: 99%

Long-COVID diagnosis: From diagnostic to advanced AI-driven models

Cau

Faa

Nardi

et al. 2022

European Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…FF, comprising aggregates of fibroblasts and myofibroblasts surrounded by metaplastic EC, represents the cardinal pathological lesion of active fibrogenesis [ 3 ]. Several studies have found a strong correlation between the presence/number of FF and both disease progression and mortality [ 4 , 5 , 6 , 7 , 8 , 9 ]. The sandwich of EC covering FF is the area of aberrant epithelial–mesenchymal crosstalk wherein an imbalance between profibrotic and antifibrotic mediators is thought to occur.…”

Section: Introductionmentioning

confidence: 99%

RNA Sequencing of Epithelial Cell/Fibroblastic Foci Sandwich in Idiopathic Pulmonary Fibrosis: New Insights on the Signaling Pathway

Calabrese

Lunardi

Tauro

et al. 2022

IJMS

View full text Add to dashboard Cite

Idiopathic pulmonary fibrosis (IPF) is a progressive and fatal lung disease characterized by irreversible scarring of the distal lung. IPF is best described by its histopathological pattern of usual interstitial pneumonia (UIP), characterized by spatial heterogeneity with alternating interstitial fibrosis and areas of normal lung, and temporal heterogeneity of fibrosis characterized by scattered fibroblastic foci (FF), dense acellular collagen and honeycomb changes. FF, comprising aggregated fibroblasts/myofibroblasts surrounded by metaplastic epithelial cells (EC), are the cardinal pathological lesion and their presence strongly correlates with disease progression and mortality. We hypothesized that the EC/FF sandwich from patients with UIP/IPF has a distinct molecular signature which could offer new insights into the crosstalk of these two crucial actors in the disease. Laser capture microdissection with RNAseq was used to investigate the transcriptome of the EC/FF sandwich from IPF patients versus controls (primary spontaneous pneumothorax). Differentially expressed gene analysis identified 23 up-regulated genes mainly related to epithelial dysfunction. Gene ontology analysis highlighted the activation of different pathways, mainly related to EC, immune response and programmed cell death. This study provides novel insights into the IPF pathogenetic pathways and suggests that targeting some of these up-regulated pathways (particularly those related to secreto-protein/mucin dysfunction) may be beneficial in IPF. Further studies in a larger number of lung samples, ideally from patients with early and advanced disease, are needed to validate these findings.

show abstract

“…While shifting paradigms over the years have suggested dissociation of early inflammation from advanced fibrosis in IPF, our current findings suggest that inflammatory mechanisms remain active in advanced disease. Recently, artificial intelligence based approaches have also identified mononuclear inflammation, alveolar macrophages and fibroblast foci as potential prognostic biomarkers of IPF [ 33 ]. In addition to the increased expression of chemokines, we also show positive correlation between multiple chemokines in several pathways within the IPF cohort, further emphasizing the potential role of these pathways in disease progression.…”

Section: Discussionmentioning

confidence: 99%

Integrated plasma proteomics and lung transcriptomics reveal novel biomarkers in idiopathic pulmonary fibrosis

et al. 2021

View full text Add to dashboard Cite

Background Idiopathic pulmonary fibrosis (IPF) is a fatal lung disease with a significant unmet medical need. Development of transformational therapies for IPF is challenging in part to due to lack of robust predictive biomarkers of prognosis and treatment response. Importantly, circulating biomarkers of IPF are limited and none are in clinical use. Methods We previously reported dysregulated pathways and new disease biomarkers in advanced IPF through RNA sequencing of lung tissues from a cohort of transplant-stage IPF patients (n = 36) in comparison to normal healthy donors (n = 19) and patients with acute lung injury (n = 11). Here we performed proteomic profiling of matching plasma samples from these cohorts through the Somascan-1300 SomaLogics platform. Results Comparative analyses of lung transcriptomic and plasma proteomic signatures identified a set of 34 differentially expressed analytes (fold change (FC) ≥ ± 1.5, false discovery ratio (FDR) ≤ 0.1) in IPF samples compared to healthy controls. IPF samples showed strong enrichment of chemotaxis, tumor infiltration and mast cell migration pathways and downregulated extracellular matrix (ECM) degradation. Mucosal (CCL25 and CCL28) and Th2 (CCL17 and CCL22) chemokines were markedly upregulated in IPF and highly correlated within the subjects. The mast cell maturation chemokine, CXCL12, was also upregulated in IPF plasma (fold change 1.92, FDR 0.006) and significantly correlated (Pearson r = − 0.38, p = 0.022) to lung function (%predicted FVC), with a concomitant increase in the mast cell Tryptase, TPSB2. Markers of collagen III and VI degradation (C3M and C6M) were significantly downregulated (C3M p < 0.001 and C6M p < 0.0001 IPF vs control) and correlated, Pearson r = 0.77) in advanced IPF consistent with altered ECM homeostasis. Conclusions Our study identifies a panel of tissue and circulating biomarkers with clinical utility in IPF that can be validated in future studies across larger cohorts.

show abstract

Artificial intelligence identifies inflammation and confirms fibroblast foci as prognostic tissue biomarkers in idiopathic pulmonary fibrosis

Cited by 32 publications

References 48 publications

Long-COVID diagnosis: From diagnostic to advanced AI-driven models

Long-COVID diagnosis: From diagnostic to advanced AI-driven models

RNA Sequencing of Epithelial Cell/Fibroblastic Foci Sandwich in Idiopathic Pulmonary Fibrosis: New Insights on the Signaling Pathway

Integrated plasma proteomics and lung transcriptomics reveal novel biomarkers in idiopathic pulmonary fibrosis

Contact Info

Product

Resources

About