OBJECTIVES: METHODS: RESULTS: CONCLUSIONS:

Acute pancreatitis (AP) is a common clinical pancreatic disease. Patients with different severity levels have different clinical outcomes. With the advantages of algorithms, machine learning (ML) has gradually emerged in the field of disease prediction, assisting doctors in decision-making. A systematic review was conducted using the PubMed, Web of Science, Scopus, and Embase databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Publication time was limited from inception to 29 May 2021. Studies that have used ML to establish predictive tools for AP were eligible for inclusion. Quality assessment of the included studies was conducted in accordance with the IJMEDI checklist. In this systematic review, 24 of 2,913 articles, with a total of 8,327 patients and 47 models, were included. The studies could be divided into five categories: 10 studies (42%) reported severity prediction; 10 studies (42%), complication prediction; 3 studies (13%), mortality prediction; 2 studies (8%), recurrence prediction; and 2 studies (8%), surgery timing prediction. ML showed great accuracy in several prediction tasks. However, most of the included studies were retrospective in nature, conducted at a single centre, based on database data, and lacked external validation. According to the IJMEDI checklist and our scoring criteria, two studies were considered to be of high quality. Most studies had an obvious bias in the quality of data preparation, validation, and deployment dimensions. In the prediction tasks for AP, ML has shown great potential in assisting decision-making. However, the existing studies still have some deficiencies in the process of model construction. Future studies need to optimize the deficiencies and further evaluate the comparability of the ML systems and model performance, so as to consequently develop high-quality ML-based models that can be used in clinical practice.

Irisin is a newly discovered myokine which links exercise to inflammation and inflammation-related diseases through macrophage regulation. However, the effect of irisin on the activity of inflammation related immune cells (such as neutrophils) has not been clearly described. The objective of our study was to explore the effect of irisin on the neutrophil extracellular traps (NETs) formation. Phorbol-12-myristate-13-acetate (PMA) was used to construct a classic neutrophil inflammation model that was used to observe the formation of NETs in vitro. We studied the effect of irisin on NETs formation and its regulation mechanism. Subsequently, acute pancreatitis (AP) was used to verify the protective effect of irisin in vivo, which was an acute aseptic inflammatory response disease model closely related to NETs. Our study found that addition of irisin significantly reduced the formation of NETs via regulation of the P38/MAPK pathway through integrin αVβ5, which might be the one of key pathways in NETs formation, and which could theoretically offset the immunoregulatory effect of irisin. Systemic treatment with irisin reduced the severity of tissue damage common in the disease and inhibited the formation of NETs in pancreatic necrotic tissue of two classical AP mouse models. The findings confirmed for the first time that irisin could inhibit NETs formation and protect mice from pancreatic injury, which further elucidated the protective effect of exercise on acute inflammatory injury.

We aimed to investigate outcomes of pancreatic extracorporeal shock wave lithotripsy (P-ESWL) for the removal of large pancreatic stones coexisting with pancreatic pseudocysts (PPCs) in chronic pancreatitis (CP). This is a prospective study performed in CP patients with at least 1 stone (≥5 mm). Patients were divided into the PPC group (stones coexisting with PPCs) or the control group (stones alone). Patients were initially subjected to successive P-ESWL treatments, followed by ERCP. Primary outcomes were P-ESWL adverse events, and secondary outcomes were stone clearance, long-term pain relief, improved quality-of-life scores, and PPC regression. A total of 849 patients (59 in the PPC group and 790 in the control group) was subjected to P-ESWL between March 2011 and October 2013. Occurrences of P-ESWL adverse events were similar between the PPC group and the control group (11.86% vs 12.41%, P = .940). After the treatment of initial P-ESWL combined with ERCP, the complete, partial, and nonclearance of stones occurred in 67.24%, 20.69%, and 12.07%, respectively, of patients in PPC group, with no significant difference from the control group (complete, partial, and nonclearance: 83.17%, 10.40%, and 11.39%, respectively; P = .106). Fifty-five of 59 patients (93.22%) with PPCs were followed for a median period of 21.9 months (range, 12.0-45.1). PPCs disappeared in 56.36% (31/55) and 76.36% (42/55) of patients after 3 months and 1 year of follow-up visits, respectively. Moreover, complete and partial pain relief were achieved in 63.64% (35/55) and 25.45% (14/55) of patients, respectively. The scores for quality of life (P < .001), physical health (P < .001), and weight loss (P < .001) improved. In our multispecialty tertiary center, initial P-ESWL followed by ERCP was safe in patients with coexisting pancreatic stones and PPCs and effective for stone clearance, main pancreatic duct drainage, and pain relief.

Exogenous antioxidant materials mimicking endogenous antioxidant systems are commonly used for the treatment of oxidative stress-induced injuries. Thus, artificial enzymes have emerged as promising candidates for balancing and treating the dysregulation of redox homeostasis in vivo. Herein, a one-pot hydrothermal strategy for the facile preparation of MoSe₂-polyvinylpyrrolidone (PVP) nanoparticles (NPs) is reported. The synthesized NPs were biodegradable due to their exposure to oxygen and exhibited high stability. Moreover, they effectively mimicked various naturally occurring enzymes (including catalase, superoxide dismutase, peroxidase, and glutathione peroxidase) and scavenged free radicals, such as 3-ethylbenzothiazoline-6-sulfonic acid, ·OH, ·O²⁻, and 1,1-diphenyl-2-picrylhydrazyl radical. Further apoptosis detection studies revealed that MoSe₂-PVP NPs significantly increased the cell survival probability in H₂O₂ in a concentration-dependent manner. The cytoprotective effect of MoSe₂-PVP NPs was explored for an animal model of acute pancreatitis, which confirmed its remarkable therapeutic efficacy. Owing to the biodegradable and biocompatible nature of MoSe₂-PVP NPs, the findings of this work can stimulate the development of other artificial nanoenzymes for antioxidant therapies. Graphical Abstract