Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU
Objective To investigate and screen the risk factors and construct a risk prediction model for aspiration in enteral nutrition patients in ICU.Methods ICU patients who underwent enteral nutrition in the ICU of Qingdao Municipal Hospital were included from January 2022 to June 2023. Independent risk...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of New Medicine
2025-01-01
|
| Series: | Yixue xinzhi zazhi |
| Subjects: | |
| Online Access: | https://yxxz.whuznhmedj.com/futureApi/storage/attach/2501/bCIkXvexzfQOtmSWcgo0qjdpeP6tgEb7XtO59BVt.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586478669004800 |
|---|---|
| author | CHEN Yue ZHANG Hui GUAN Chun HU Fasheng |
| author_facet | CHEN Yue ZHANG Hui GUAN Chun HU Fasheng |
| author_sort | CHEN Yue |
| collection | DOAJ |
| description | Objective To investigate and screen the risk factors and construct a risk prediction model for aspiration in enteral nutrition patients in ICU.Methods ICU patients who underwent enteral nutrition in the ICU of Qingdao Municipal Hospital were included from January 2022 to June 2023. Independent risk factors for aspiration in enteral nutrition patients in the ICU were analyzed and predictive models were constructed using univariate analysis, Lasso regression, and multifactorial Logistic regression. The Random forest model ranked the importance of the independent factors, and the predictive models were visualized using Nomogram.Results A total of 500 patients were included and aspiration occurred in 285 patients, with the incidence of aspiration of 57% in enteral nutrition patients in the ICU. The independent risk factors were ranked in order of importance from highest to lowest as number of days of placement [OR=1.038, 95%CI(1.024, 1.052)], body position [OR=3.879, 95%CI(2.104, 7.152)], duration of daily enteral nutrition [OR=1.035, 95%CI(1.004, 1.067)], APACHE II score [OR=1.063, 95%CI(1.032, 1.095)], use of sedative and analgesic medication [OR=4.054, 95%CI(1.804, 9.108)], partial pressure of oxygen [OR=0.985, 95%CI(0.974, 0.997)]. The model in the training set had a prediction accuracy of 74.00%, a specificity of 69.48%, a sensitivity of 77.55%, and an area under curve (AUC) of ROC of 0.82[95%CI(0.78, 0.86)]. The model in the validation set had a prediction accuracy of 70.00%, a specificity of 68.85%, a sensitivity of 70.79%, and an AUC of 0.79[95% CI(0.72, 0.86)]. The calibration curve and decision curve showed that the model had good calibration and benefit.Conclusion The risk prediction model constructed in this study demonstrates strong predictive efficacy, offering a scientific and objective reference basis for clinical staff to assess the risk of aspiration, and facilitate the implementation of targeted preventive measures. |
| format | Article |
| id | doaj-art-628800d980704d8ab90bc696b5a8c369 |
| institution | Kabale University |
| issn | 1004-5511 |
| language | zho |
| publishDate | 2025-01-01 |
| publisher | Editorial Office of New Medicine |
| record_format | Article |
| series | Yixue xinzhi zazhi |
| spelling | doaj-art-628800d980704d8ab90bc696b5a8c3692025-01-25T11:47:10ZzhoEditorial Office of New MedicineYixue xinzhi zazhi1004-55112025-01-01351223210.12173/j.issn.1004-5511.2024090576583Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICUCHEN YueZHANG HuiGUAN ChunHU FashengObjective To investigate and screen the risk factors and construct a risk prediction model for aspiration in enteral nutrition patients in ICU.Methods ICU patients who underwent enteral nutrition in the ICU of Qingdao Municipal Hospital were included from January 2022 to June 2023. Independent risk factors for aspiration in enteral nutrition patients in the ICU were analyzed and predictive models were constructed using univariate analysis, Lasso regression, and multifactorial Logistic regression. The Random forest model ranked the importance of the independent factors, and the predictive models were visualized using Nomogram.Results A total of 500 patients were included and aspiration occurred in 285 patients, with the incidence of aspiration of 57% in enteral nutrition patients in the ICU. The independent risk factors were ranked in order of importance from highest to lowest as number of days of placement [OR=1.038, 95%CI(1.024, 1.052)], body position [OR=3.879, 95%CI(2.104, 7.152)], duration of daily enteral nutrition [OR=1.035, 95%CI(1.004, 1.067)], APACHE II score [OR=1.063, 95%CI(1.032, 1.095)], use of sedative and analgesic medication [OR=4.054, 95%CI(1.804, 9.108)], partial pressure of oxygen [OR=0.985, 95%CI(0.974, 0.997)]. The model in the training set had a prediction accuracy of 74.00%, a specificity of 69.48%, a sensitivity of 77.55%, and an area under curve (AUC) of ROC of 0.82[95%CI(0.78, 0.86)]. The model in the validation set had a prediction accuracy of 70.00%, a specificity of 68.85%, a sensitivity of 70.79%, and an AUC of 0.79[95% CI(0.72, 0.86)]. The calibration curve and decision curve showed that the model had good calibration and benefit.Conclusion The risk prediction model constructed in this study demonstrates strong predictive efficacy, offering a scientific and objective reference basis for clinical staff to assess the risk of aspiration, and facilitate the implementation of targeted preventive measures.https://yxxz.whuznhmedj.com/futureApi/storage/attach/2501/bCIkXvexzfQOtmSWcgo0qjdpeP6tgEb7XtO59BVt.pdfenteral nutritionaspirationiculasso regressionrandom forestpredictive modelnomogram |
| spellingShingle | CHEN Yue ZHANG Hui GUAN Chun HU Fasheng Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU Yixue xinzhi zazhi enteral nutrition aspiration icu lasso regression random forest predictive model nomogram |
| title | Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU |
| title_full | Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU |
| title_fullStr | Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU |
| title_full_unstemmed | Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU |
| title_short | Construction of a predictive model for the risk of aspiration in enteral nutrition patients in ICU |
| title_sort | construction of a predictive model for the risk of aspiration in enteral nutrition patients in icu |
| topic | enteral nutrition aspiration icu lasso regression random forest predictive model nomogram |
| url | https://yxxz.whuznhmedj.com/futureApi/storage/attach/2501/bCIkXvexzfQOtmSWcgo0qjdpeP6tgEb7XtO59BVt.pdf |
| work_keys_str_mv | AT chenyue constructionofapredictivemodelfortheriskofaspirationinenteralnutritionpatientsinicu AT zhanghui constructionofapredictivemodelfortheriskofaspirationinenteralnutritionpatientsinicu AT guanchun constructionofapredictivemodelfortheriskofaspirationinenteralnutritionpatientsinicu AT hufasheng constructionofapredictivemodelfortheriskofaspirationinenteralnutritionpatientsinicu |