Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug 22;24(1):281.
doi: 10.1186/s12876-024-03331-7.

Development and validation of a nomogram based on Lasso-Logistic regression for predicting splenomegaly secondary to acute pancreatitis

Bohan Huang #  1   2 , Feng Cao #  1   2 , Yixuan Ding  1   2 , Ang Li  1   2 , Tao Luo  1   2 , Xiaohui Wang  1   2 , Chongchong Gao  1   2 , Zhe Wang  1   2 , Chao Zhang  1   2 , Fei Li  3   4
Affiliations

Development and validation of a nomogram based on Lasso-Logistic regression for predicting splenomegaly secondary to acute pancreatitis

Bohan Huang et al. BMC Gastroenterol. .

Abstract

Purpose: Investigate the clinical characteristics of splenomegaly secondary to acute pancreatitis (SSAP) and construct a nomogram prediction model based on Lasso-Logistic regression.

Methods: A retrospective case-control study was conducted to analyze the laboratory parameters and computed tomography (CT) imaging of acute pancreatitis (AP) patients recruited at Xuanwu Hospital from December 2014 to December 2021. Lasso regression was used to identify risk factors, and a novel nomogram was developed. The performance of the nomogram in discrimination, calibration, and clinical usefulness was evaluated through internal validation.

Results: The prevalence of SSAP was 9.2% (88/950), with the first detection occurring 65(30, 125) days after AP onset. Compared with the control group, the SSAP group exhibited a higher frequency of persistent respiratory failure, persistent renal failure, infected pancreatic necrosis, and severe AP, along with an increased need for surgery and longer hospital stay (P < 0.05 for all). There were 185 and 79 patients in the training and internal validation cohorts, respectively. Variables screened by Lasso regression, including platelet count, white blood cell (WBC) count, local complications, and modified CT severity index (mCTSI), were incorporated into the Logistic model. Multivariate analysis showed that WBC count ≦9.71 × 109/L, platelet count ≦140 × 109/L, mCTSI ≧8, and the presence of local complications were independently associated with the occurrence of SSAP. The area under the receiver operating characteristic curve was 0.790. The Hosmer-Lemeshow test showed that the model had good fitness (P = 0.954). Additionally, the nomogram performed well in the internal validation cohorts.

Conclusions: SSAP is relatively common, and patients with this condition often have a worse clinical prognosis. Patients with low WBC and platelet counts, high mCTSI, and local complications in the early stages of the illness are at a higher risk for SSAP. A simple nomogram tool can be helpful for early prediction of SSAP.

Keywords: Acute pancreatitis; Lasso-Logistic regression; Nomogram; Risk factors; Splenomegaly.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Screening of variables based on Lasso regression. A The characteristics of variability in the coefficients of variables; B Determining the optimal value for parameter λ in the Lasso regression model using the cross-validation method
Fig. 2
Fig. 2
Nomogram for predicting splenomegaly secondary to acute pancreatitis. WBC, white blood cell; PLT, platelet; CTSI, modified computed tomography severity index
Fig. 3
Fig. 3
Receiver operating curves. A Training cohort. B Internal validation cohort. AUC, area under the ROC (receiver operating characteristic) curve
Fig. 4
Fig. 4
Calibration curves for predicting the probability of splenomegaly secondary to acute pancreatitis. A Training cohort. B Internal validation cohort
Fig. 5
Fig. 5
Decision curve analysis in the prediction of splenomegaly secondary to acute pancreatitis. A Training cohort. B Internal validation cohort
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Mederos MA, Reber HA, Girgis MD. Acute pancreatitis: a review. JAMA. 2021;325(4):382–90. 10.1001/jama.2020.20317 - DOI - PubMed
    1. Boxhoorn L, Voermans RP, Bouwense SA, et al. Acute pancreatitis. Am Gastroenterol Assoc Inst Guidel Initial Manage. 2020;396(10252):726–34. - PubMed
    1. Yu C, Ding L, Jiang M, et al. Dynamic changes and nomogram prediction for sinistral portal hypertension in moderate and severe acute pancreatitis. Front Med (Lausanne). 2022;9:875263. 10.3389/fmed.2022.875263 - DOI - PMC - PubMed
    1. Xiping Z, Ruiping Z, Binyan Y, et al. Protecting effects of a large dose of dexamethasone on spleen injury of rats with severe acute pancreatitis. J Gastroenterol Hepatol. 2010;25(2):302–8. 10.1111/j.1440-1746.2009.05999.x - DOI - PubMed
    1. Lankisch PG. The spleen in inflammatory pancreatic disease. Gastroenterology. 1990;98(2):509–16. 10.1016/0016-5085(90)90848-U - DOI - PubMed

Publication types