{"title":"血流感染:基于机器学习模型(BLISCO)的可靠多维预后评分的推导与验证。","authors":"Marta Camici PhD , Benedetta Gottardelli PhD , Tommaso Novellino , Carlotta Masciocchi PhD , Silvia Lamonica , Rita Murri MD","doi":"10.1016/j.ajic.2024.07.011","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>A bloodstream infection (BSI) prognostic score applicable at the time of blood culture collection is missing.</div></div><div><h3>Methods</h3><div>In total, 4,327 patients with BSIs were included, divided into a derivation (80%) and a validation dataset (20%). Forty-two variables among host-related, demographic, epidemiological, clinical, and laboratory extracted from the electronic health records were analyzed. Logistic regression was chosen for predictive scoring.</div></div><div><h3>Results</h3><div>The 14-day mortality model included age, body temperature, blood urea nitrogen, respiratory insufficiency, platelet count, high-sensitive C-reactive protein, and consciousness status: a score of ≥ 6 was correlated to a 14-day mortality rate of 15% with a sensitivity of 0.742, a specificity of 0.727, and an area under the curve of 0.783. The 30-day mortality model further included cardiovascular diseases: a score of ≥ 6 predicting 30-day mortality rate of 15% with a sensitivity of 0.691, a specificity of 0.699, and an area under the curve of 0.697.</div></div><div><h3>Conclusions</h3><div>A quick mortality score could represent a valid support for prognosis assessment and resources prioritizing for patients with BSIs not admitted in the intensive care unit.</div></div>","PeriodicalId":7621,"journal":{"name":"American journal of infection control","volume":"52 12","pages":"Pages 1377-1383"},"PeriodicalIF":3.8000,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Bloodstream infection: Derivation and validation of a reliable and multidimensional prognostic score based on a machine learning model (BLISCO)\",\"authors\":\"Marta Camici PhD , Benedetta Gottardelli PhD , Tommaso Novellino , Carlotta Masciocchi PhD , Silvia Lamonica , Rita Murri MD\",\"doi\":\"10.1016/j.ajic.2024.07.011\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>A bloodstream infection (BSI) prognostic score applicable at the time of blood culture collection is missing.</div></div><div><h3>Methods</h3><div>In total, 4,327 patients with BSIs were included, divided into a derivation (80%) and a validation dataset (20%). Forty-two variables among host-related, demographic, epidemiological, clinical, and laboratory extracted from the electronic health records were analyzed. Logistic regression was chosen for predictive scoring.</div></div><div><h3>Results</h3><div>The 14-day mortality model included age, body temperature, blood urea nitrogen, respiratory insufficiency, platelet count, high-sensitive C-reactive protein, and consciousness status: a score of ≥ 6 was correlated to a 14-day mortality rate of 15% with a sensitivity of 0.742, a specificity of 0.727, and an area under the curve of 0.783. The 30-day mortality model further included cardiovascular diseases: a score of ≥ 6 predicting 30-day mortality rate of 15% with a sensitivity of 0.691, a specificity of 0.699, and an area under the curve of 0.697.</div></div><div><h3>Conclusions</h3><div>A quick mortality score could represent a valid support for prognosis assessment and resources prioritizing for patients with BSIs not admitted in the intensive care unit.</div></div>\",\"PeriodicalId\":7621,\"journal\":{\"name\":\"American journal of infection control\",\"volume\":\"52 12\",\"pages\":\"Pages 1377-1383\"},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2024-07-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"American journal of infection control\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0196655324006126\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"INFECTIOUS DISEASES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of infection control","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0196655324006126","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INFECTIOUS DISEASES","Score":null,"Total":0}
Bloodstream infection: Derivation and validation of a reliable and multidimensional prognostic score based on a machine learning model (BLISCO)
Background
A bloodstream infection (BSI) prognostic score applicable at the time of blood culture collection is missing.
Methods
In total, 4,327 patients with BSIs were included, divided into a derivation (80%) and a validation dataset (20%). Forty-two variables among host-related, demographic, epidemiological, clinical, and laboratory extracted from the electronic health records were analyzed. Logistic regression was chosen for predictive scoring.
Results
The 14-day mortality model included age, body temperature, blood urea nitrogen, respiratory insufficiency, platelet count, high-sensitive C-reactive protein, and consciousness status: a score of ≥ 6 was correlated to a 14-day mortality rate of 15% with a sensitivity of 0.742, a specificity of 0.727, and an area under the curve of 0.783. The 30-day mortality model further included cardiovascular diseases: a score of ≥ 6 predicting 30-day mortality rate of 15% with a sensitivity of 0.691, a specificity of 0.699, and an area under the curve of 0.697.
Conclusions
A quick mortality score could represent a valid support for prognosis assessment and resources prioritizing for patients with BSIs not admitted in the intensive care unit.
期刊介绍:
AJIC covers key topics and issues in infection control and epidemiology. Infection control professionals, including physicians, nurses, and epidemiologists, rely on AJIC for peer-reviewed articles covering clinical topics as well as original research. As the official publication of the Association for Professionals in Infection Control and Epidemiology (APIC)