作者
Scott Silvey,Nilang Patel,Jinze Liu,Asiya Tafader,Mahum Nadeem,Galvin Dhaliwal,Jacqueline G. O’Leary,Heather Patton,Timothy R. Morgan,Shari S. Rogal,Jasmohan S. Bajaj
摘要
Background and Aims Despite the poor prognosis associated with missed or delayed spontaneous bacterial peritonitis (SBP) diagnosis, <15% get timely paracentesis, which persists despite guidelines/education in the US. Measures to exclude SBP non-invasively where timely paracentesis cannot be performed could streamline this burden. Methods Using Veterans Health Administration Corporate Data Warehouse (VHA-CDW) we included cirrhosis patients between 2009-2019 who underwent timely paracentesis and collected relevant clinical information (demographics, cirrhosis severity, medications, vitals, and comorbidities). XGBoost-models were trained on 75% of the primary cohort, with 25% reserved for testing. The final model was further validated in two cohorts: Validation cohort #1: In VHA-CDW, those without prior SBP who received 2nd early paracentesis, and Validation cohort #2: Prospective data from 276 non-electively admitted University hospital patients. Results Negative predictive values (NPV) at 5,10 & 15% probability cutoffs were examined. Primary cohort: n=9,643 (mean age 63.1±8.7 years, 97.2% men, SBP:15.0%) received first early paracentesis. Testing-set NPVs for SBP were 96.5%, 93.0% and 91.6% at the 5%, 10% and 15% probability thresholds respectively. In Validation cohort #1: n=2844 (mean age 63.14±8.37 years, 97.1% male, SBP: 9.7%) with NPVs were 98.8%, 95.3% and 94.5%. In Validation cohort #2: n=276 (mean age 56.08±9.09, 59.6% male, SBP: 7.6%) with NPVs were 100%, 98.9% and 98.0% The final ML model showed the greatest net benefit on decision-curve analyses. Conclusions A machine learning model generated using routinely collected variables excluded SBP with high negative predictive value. Applying this model could ease the need to provide paracentesis in resource-limited settings by excluding those unlikely to have SBP. Despite the poor prognosis associated with missed or delayed spontaneous bacterial peritonitis (SBP) diagnosis, <15% get timely paracentesis, which persists despite guidelines/education in the US. Measures to exclude SBP non-invasively where timely paracentesis cannot be performed could streamline this burden. Using Veterans Health Administration Corporate Data Warehouse (VHA-CDW) we included cirrhosis patients between 2009-2019 who underwent timely paracentesis and collected relevant clinical information (demographics, cirrhosis severity, medications, vitals, and comorbidities). XGBoost-models were trained on 75% of the primary cohort, with 25% reserved for testing. The final model was further validated in two cohorts: Validation cohort #1: In VHA-CDW, those without prior SBP who received 2nd early paracentesis, and Validation cohort #2: Prospective data from 276 non-electively admitted University hospital patients. Negative predictive values (NPV) at 5,10 & 15% probability cutoffs were examined. Primary cohort: n=9,643 (mean age 63.1±8.7 years, 97.2% men, SBP:15.0%) received first early paracentesis. Testing-set NPVs for SBP were 96.5%, 93.0% and 91.6% at the 5%, 10% and 15% probability thresholds respectively. In Validation cohort #1: n=2844 (mean age 63.14±8.37 years, 97.1% male, SBP: 9.7%) with NPVs were 98.8%, 95.3% and 94.5%. In Validation cohort #2: n=276 (mean age 56.08±9.09, 59.6% male, SBP: 7.6%) with NPVs were 100%, 98.9% and 98.0% The final ML model showed the greatest net benefit on decision-curve analyses. A machine learning model generated using routinely collected variables excluded SBP with high negative predictive value. Applying this model could ease the need to provide paracentesis in resource-limited settings by excluding those unlikely to have SBP.