Objective: To generate an up-to-date bundle to manage acute biliary pancreatitis using an evidence-based, artificial intelligence (AI)-assisted GRADE method. Summary background data: A care bundle is a set of core elements of care that are distilled from the most solid evidence-based practice guidelines and recommendations. Methods: The research questions were addressed in this bundle following the PICO criteria. The working group summarized the effects of interventions with the strength of recommendation and quality of evidence applying the GRADE methodology. ChatGPT AI system was used to independently assess the quality of evidence of each element in the bundle, together with the strength of the recommendations. Results: The seven elements of the bundle discourage antibiotic prophylaxis in patients with acute biliary pancreatitis, support the use of a full-solid diet in patients with mild to moderately-severe acute biliary pancreatitis, and recommend early enteral nutrition in patients unable to feed by mouth. The bundle states that ERCP should be performed within the first 48-72 hours of hospital admission in patients with cholangitis. Early laparoscopic cholecystectomy should be performed in patients with mild acute biliary pancreatitis. When operative intervention is needed for necrotizing pancreatitis, this should start with the endoscopic step-up approach. Conclusions: We have developed a new care bundle with seven key elements for managing patients with acute biliary pancreatitis. This new bundle, whose scientific strength has been increased thanks to the alliance between human knowledge and AI from the new ChatGPT software, should be introduced to emergency departments, wards, and ICUs.

The 2023 MANCTRA Acute Biliary Pancreatitis Care Bundle: A Joint Effort Between Human Knowledge and Artificial Intelligence (ChatGPT) to Optimize the Care of Patients With Acute Biliary Pancreatitis in Western Countries

Podda, Mauro
Primo
Conceptualization
;
Pisanu, Adolfo
2024-01-01

Abstract

Objective: To generate an up-to-date bundle to manage acute biliary pancreatitis using an evidence-based, artificial intelligence (AI)-assisted GRADE method. Summary background data: A care bundle is a set of core elements of care that are distilled from the most solid evidence-based practice guidelines and recommendations. Methods: The research questions were addressed in this bundle following the PICO criteria. The working group summarized the effects of interventions with the strength of recommendation and quality of evidence applying the GRADE methodology. ChatGPT AI system was used to independently assess the quality of evidence of each element in the bundle, together with the strength of the recommendations. Results: The seven elements of the bundle discourage antibiotic prophylaxis in patients with acute biliary pancreatitis, support the use of a full-solid diet in patients with mild to moderately-severe acute biliary pancreatitis, and recommend early enteral nutrition in patients unable to feed by mouth. The bundle states that ERCP should be performed within the first 48-72 hours of hospital admission in patients with cholangitis. Early laparoscopic cholecystectomy should be performed in patients with mild acute biliary pancreatitis. When operative intervention is needed for necrotizing pancreatitis, this should start with the endoscopic step-up approach. Conclusions: We have developed a new care bundle with seven key elements for managing patients with acute biliary pancreatitis. This new bundle, whose scientific strength has been increased thanks to the alliance between human knowledge and AI from the new ChatGPT software, should be introduced to emergency departments, wards, and ICUs.
File in questo prodotto:
File Dimensione Formato  
The_2023_MANCTRA_Acute_Biliary_Pancreatitis_Care.562.pdf

embargo fino al 01/02/2025

Tipologia: versione post-print (AAM)
Dimensione 796.91 kB
Formato Adobe PDF
796.91 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/372603
Citazioni
  • ???jsp.display-item.citation.pmc??? 3
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact