Dataset Information

Quantification of TFF3 expression from a non-endoscopic device predicts clinically relevant Barrett's oesophagus by machine learning.

ABSTRACT:

Background

Intestinal metaplasia (IM) is pre-neoplastic with variable cancer risk. Cytosponge-TFF3 test can detect IM. We aimed to 1) assess whether quantitative TFF3 scores can distinguish clinically relevant Barrett's oesophagus (BO) (C≥1 or M≥3) from focal IM pathologies (C<1, M<3 or IM of gastro-oesophageal junction); 2) whether TFF3 counts can be automated to inform clinical practice.

Methods

Patients from the Barett's oEsophagus Screening Trial 2 (BEST2) case-control and BEST3 randomised trials were used. For aim 1, TFF3-positive glands were scored manually and correlated with clinical diagnosis. For aim 2, machine learning approach was used to obtain TFF3 count and logistic regression with cross-validation was trained on the BEST2 dataset (n = 529) and tested in the BEST3 dataset (n = 158).

Findings

Patients with clinically relevant BO had higher mean TFF3 gland count compared to focal IM pathologies (mean difference 4.14; 95% confidence interval, CI 2.76-5.52, p < 0.001). The mean class-balanced validation accuracy was 0.84 (95% CI 0.77-0.90), and precision of 0.95 (95% CI 0.87-1.00) for detecting clinically relevant BO. Applying this model on BEST3 showed precision of 0.91 (95% CI 0.85-0.97) for focal IM pathologies with a class-balanced accuracy of 0.77 (95% CI 0.69-0.84). Using this model, 55% of patients (87/158) in BEST3 would fall below the threshold for clinically relevant BO and could avoid gastroscopy, while only missing 5.1% of patients (8/158).

Interpretation

Automated Cytosponge-TFF3 gland quantification may enable thresholds to be set to trigger confirmatory gastroscopy to minimize overdiagnosis of focal IM pathologies with very low cancer-associated risk.

Funding

Cancer Research UK (12088/16893 and C14478/A21047).

SUBMITTER: Berman AG

PROVIDER: S-EPMC9297109 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Barrett's oesophagus (BE) is the precursor lesion to adenocarcinoma of the oesophagus. Understanding of the molecular alterations in this multistage process may contribute to improved diagnosis and treatment. Secreted protein acidic and rich in cysteine (SPARC) is a matricellular protein that modulates cell adhesion and growth. Alterations in SPARC expression have been observed in a variety of solid tumours. The aim of this study was to assess the prevalence and timing of SPARC mRNA expression in Barrett's multistage disease and to investigate the impact of SPARC alterations on the development and progression of this disease. SPARC mRNA expression was measured using a quantitative real-time RT-PCR method in 108 specimens from 19 patients with BE without carcinoma, 20 patients with Barrett's-associated adenocarcinoma (EA), and a control group (CG) of 10 patients without evidence of gastro-oesophageal reflux disease. The median SPARC mRNA expression was significantly upregulated in BE tissues compared to paired normal oesophagus (NE) tissues for the BE group (P=0.004) and for the EA group (P<0.001). The SPARC mRNA expression was significantly higher in adenocarcinoma of the oesophagus compared to matching NE tissue and compared to Barrett's tissues in the EA group (P<0.001). Furthermore, SPARC expression values were significantly different between metaplastic and dysplastic Barrett's tissues (P=0.014). In histologically normal squamous oesophagus tissues obtained from carcinoma patients (EA group), the SPARC mRNA expression was significantly higher compared to NE mucosa from the BE group and the CG group (P=0.03). These findings suggest that the upregulation of SPARC mRNA expression is an early event in the development and progression of BE and EA, and that high SPARC expression may be a clinically useful biomarker for the detection of occult adenocarcinoma, and that a widespread 'field effect' is present in the NE of patients with oesophageal adenocarcinoma.