{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["15(1)"],"submitter":["Chiu IM"],"pubmed_abstract":["Delays or misdiagnoses in detecting pneumoperitoneum can significantly increase mortality and morbidity. We developed and validated a deep learning model designed to identify pneumoperitoneum in computed tomography images. The model is trained on abdominal scans from Far Eastern Memorial Hospital (January 2012-December 2021) and evaluated using a simulated test set (14,039 scans) and a prospective test set (6351 scans) collected from the same center between December 2022 and May 2023. External validation included 480 scans from Cedars-Sinai Medical Center. Overall, the model achieves a sensitivity of 0.81-0.83 and a specificity of 0.97-0.99 across retrospective, prospective, and external validation; sensitivity improves to 0.92-0.98 when cases with a small amount of free air (total volume "],"journal":["Nature communications"],"pagination":["9660"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11544264"],"repository":["biostudies-literature"],"pubmed_title":["PACT-3D, a deep learning algorithm for pneumoperitoneum detection in abdominal CT scans."],"pmcid":["PMC11544264"],"pubmed_authors":["Ouyang D","Lin WC","Chiu IM","Kuo KH","Huang TY","Pan YJ","Lu CY"],"additional_accession":[]},"is_claimable":false,"name":"PACT-3D, a deep learning algorithm for pneumoperitoneum detection in abdominal CT scans.","description":"Delays or misdiagnoses in detecting pneumoperitoneum can significantly increase mortality and morbidity. We developed and validated a deep learning model designed to identify pneumoperitoneum in computed tomography images. The model is trained on abdominal scans from Far Eastern Memorial Hospital (January 2012-December 2021) and evaluated using a simulated test set (14,039 scans) and a prospective test set (6351 scans) collected from the same center between December 2022 and May 2023. External validation included 480 scans from Cedars-Sinai Medical Center. Overall, the model achieves a sensitivity of 0.81-0.83 and a specificity of 0.97-0.99 across retrospective, prospective, and external validation; sensitivity improves to 0.92-0.98 when cases with a small amount of free air (total volume ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Nov","modification":"2026-07-16T18:50:32.675Z","creation":"2025-04-04T18:56:21.074Z"},"accession":"S-EPMC11544264","cross_references":{"pubmed":["39511229"],"doi":["10.1038/s41467-024-54043-1"]}}