Introduction

Advanced chronic liver disease (ACLD) is characterised by complex haemostatic alterations. While thrombocytopenia due to portal hypertension is a well-known phenomenon in ACLD, changes in platelet function remain a topic of ongoing debate and studies are often limited by the use of platelet count-dependent assays.

Aims & Methods

We aimed to investigate whether alterations in platelet function assessed by flow cytometry predict liver disease progression and mortality. Specifically, we prospectively included ACLD patients undergoing hepatic venous pressure gradient (HVPG) measurement and same-day platelet function assessment. Platelet activation was evaluated using flow cytometry by measuring the expression of P-selectin on the platelet surface following stimulation with either (i) protease-activated receptor (PAR)-1 agonist SFLLRN, (ii) PAR-4 agonist AYPGKF or (iii) epinephrin.

Results

107 ACLD patients (age: 55.3 [46.4-62.9] years; 71% male; 59.8% decompensated) with a median HVPG of 18 (12-21) mmHg and a MELD (model for end-stage liver disease) of 11.0 (9.0-14.5) were included.
During a median follow-up of 25.3 (15.7-31.2) months, 29 patients experienced first or further hepatic decompensation, and 17 died. Overall, more pronounced platelet activation in response to SFLLRN (HR per 100 MFI [median fluorescence intensity]: 0.95 [95%CI:0.91-0.99]; p=0.011) and AYPGKF (HR per 100 MFI: 0.93 [95%CI:0.89-0.98]; p=0.005) was linked to a significantly lower risk of first/further decompensation. Importantly, after adjusting for systemic inflammation (i.e., interleukin 6 [IL-6]), portal hypertension (i.e., HVPG) and disease severity (i.e., MELD) in a multivariable Cox regression model (see Table), we observed a significant link between AYPGKF-inducible platelet activation and a reduced risk of decompensation (aHR per 100 MFI: 0.95 [95%CI:0.90-1.00]; p=0.036; model 2), as well as a clear trend for SFLLRN-inducible platelet activation (model 1). Furthermore, increased platelet activation in response to SFLLRN (HR per 100 MFI: 0.92 [95%CI:0.86-0.97]; p=0.006) and AYPGKF (HR per 100 MFI: 0.93 [95%CI:0.87-0.99]; p=0.034) was also linked to an improved transplant-free survival. The prognostic impact of SFLLRN-inducible platelet activation remained significant after adjusting for IL-6 and MELD (aHR: per 100 MFI: 0.93 [95%CI:0.87-1.00]; p=0.040).
During follow-up, portal vein thrombosis (PVT) occurred in 6 patients. Interestingly, increased platelet activation in response to epinephrine was significantly associated with a higher risk of PVT development (HR per 10 MFI: 1.08 [95%CI:1.02-1.14]; p=0.004).

Conclusion

The flow cytometry-based assessment of platelet activation may overcome the impact of a low platelet count, i.e., the primary limitation of platelet function studies in ACLD. Interestingly, higher PAR-1 and PAR-4 mediated platelet activation was independently associated with a reduced risk of hepatic decompensation and an improved transplant-free survival, thus arguing against the recently proposed hypothesis that hyperactive platelets drive disease progression. Finally, increased platelet activation in response to epinephrin was linked to a higher risk of de novo PVT occurrence.

Disclosure

Benedikt Simbrunner: Travel support from AbbVie and Gilead. David JM Bauer: Travel support from AbbVie and Gilead; Speaker fees from AbbVie and Siemens. Philipp Schwabl: Consulting fees from PharmaIN; Travel support from Falk and Phenex Pharmaceuticals. Mattias Mandorfer: Speaker and/or consultant and/or advisory board member for AbbVie, Collective Acumen, Gilead, and W. L. Gore & Associates; Travel support from AbbVie and Gilead. Thomas Reiberger: Grant support from Abbvie, Boehringer-Ingelheim, Gilead, Gore, Intercept, MSD, Myr Pharmaceuticals, Philips Healthcare, Pliant, and Siemens; Speaking honoraria from Abbvie, Gilead, Gore, Intercept, Roche, MSD; Consulting/advisory board fee from Abbvie, Bayer, Boehringer-Ingelheim, Gilead, Intercept, MSD, Siemens; Travel support from Abbvie, Boehringer-Ingelheim, Gilead and Roche. Thomas Gremmel: Speaker fees from Amgen, Bayer, Boehringer-Ingelheim, Bristol Myers Squibb, Daiichi- Sankyo, Novartis, and Pfizer; Grant support from Boehringer-Ingelheim, Bristol Myers Squibb, Medtronic and Abbott.

Introduction

Early detection of neoplasia in Barrett’s Esophagus (BE) remains challenging. Although computer-aided detection (CADe) systems are increasingly available to support endoscopists, successful CADe implementation largely depends on the quality of endoscopic images, which can vary significantly in clinical practice. This study introduces an innovative computer-aided quality (CAQ) system designed for BE endoscopy, capable of assessing various image quality parameters, providing real-time feedback to the endoscopist, and operating in conjunction with an established CADe system.

Aims & Methods

The CAQ system was trained on 4,926 images from 243 BE patients to assess both objective (e.g., blurriness, illumination, and specular reflections) and subjective (i.e., mucosal cleanliness and esophageal expansion) image quality factors. The system is able to provide real-time feedback on these quality parameters to the endoscopist. Additionally, it is configured to function as a preprocessing filter for a previously developed CADe system, automatically excluding lower-quality images. To validate the CAQ system’s performance as a standalone tool, we constructed an endoscopic image quality test set, which included 647 images from 51 non-dysplastic BE patients across eight hospitals. These images were annotated for objective (e.g. motion blur, lighting) and subjective (i.e. esophageal expansion, mucosal cleanliness) image quality parameters by two experts. Additionally, to evaluate the CAQ system’s role as a preprocessing step for an established CADe system, we created the Barrett CADe test set, containing 956 frames from 62 neoplastic BE patients and 557 frames from 35 non-dysplastic BE patients from 12 Barrett referral centers. Outcome measures included agreement scores with experts for standalone image quality assessment and sensitivity, specificity, and Area-under-the-Curve (AUC) for BE neoplasia detection.

Results

As a stand-alone system, the CAQ system achieved Cohen’s Kappa scores for agreement with expert annotators of 0.73, 0.91, and 0.89 for objective image quality parameters, mucosal cleanliness, and esophageal expansion, respectively—comparable to inter-annotator scores of 0.73, 0.93, and 0.83. When used as a preprocessing filter for the CADe system, the CAQ system improved the CADe's sensitivity from 82% to 90% and the AUC from 87% to 91%, while specificity remained stable at 75% (Table 1).

Table 1. Performance of the CADe system for Barrett’s neoplasia detection with and without the CAQ system.

Conclusion

This study introduces the first CAQ system specifically aimed at automated quality control in BE endoscopy. As a standalone tool, the system effectively distinguishes poorly from well-visualized mucosa. When combined with an established CADe system, it enhances detection rates for neoplasia, highlighting its potential to improve diagnostic accuracy in BE surveillance.