A Nomogram That Includes Neutrophils and High-Density Lipoprotein Cholesterol Can Predict the Prognosis of Acute Ischaemic Stroke

Abstract

Lipids are implicated in inflammatory responses affecting acute ischaemic stroke prognosis. Therefore, we aimed to develop a predictive model that considers neutrophils and high-density lipoprotein cholesterol to predict its prognosis. This prospective study enrolled patients with acute ischaemic stroke within 24 h of onset between January 2015 and December 2017. The main outcome was a modified Rankin Scale score ≥3 at the 90th day of follow-up. Patients were divided into training and testing sets. The training set was divided into four states according to the median of neutrophils and high-density lipoprotein cholesterol levels in all patients. Through binary logistic regression analysis, the relationship between factors and prognosis was determined. A nomogram based on the results was developed; its predictive value was evaluated through internal and external validations. Altogether, 1,090 patients were enrolled with 872 (80%) and 218 (20%) in the training and testing sets, respectively. In the training set, the major outcomes occurred in 24 (10.4%), 24 (11.6%), 37 (17.2%), and 49 (22.3%) in states 1-4, respectively (P = 0.002). Validation of calibration and decision curve analyses showed that the nomogram showed better performance. The internal and external testing set receiver operating characteristics verified the predictive value [area under the curve = 0.794 (0.753-0.834), P < 0.001, and area under the curve = 0.973 (0.954-0.992), P < 0.001, respectively]. A nomogram that includes neutrophils and high-density lipoprotein cholesterol can predict the prognosis of acute ischaemic stroke, thus providing us with an effective visualization tool.

Keywords: high-density lipoprotein cholesterol; neutrophil; nomogram; prognosis; stroke.

Figure 1

Research process and design. N, Neutrophil; HDL-C, high-density lipoprotein cholesterol.

Figure 2

Nomogram for predicting short-term prognosis of acute ischemic stroke. In the neutrophils and high-density lipoprotein cholesterol states variable, state 1 scored 0 points, state 2 scored 14.3 points, state 3 scored 28.7 points, and state 4 scored 43.0 points. Age ≥60 years old, with a history of stroke, mRS >1 before the onset and NIHSS >5 at admission were recorded as 40.3 points, 31.5 points, 82.2 points and 100 points, respectively. Otherwise score 0 points (see Supplementary Materials). State 1: N <4.79 × 10⁹ /L and HDL-C ≥1.08 mmol/L; State 2: N <4.79 × 10⁹ /L and HDL-C <1.08 mmol/L; State 3: N ≥4.79 × 10⁹ /L and HDL-C ≥1.08 mmol/L; State 4: N ≥4.79 × 10⁹ /L and HDL-C <1.08 mmol/L; N, Neutrophil; HDL-C, high-density lipoprotein cholesterol.

Figure 3

Calibration curve and decision curve analysis of training set and testing set. Internal and external validation of predictive models. (A) The calibration curve of the prediction model in the training set; (B) The calibration curve of the prediction model in the testing set; (C) The decision curve analysis of the prediction model in the training set; (D) The decision curve analysis of the prediction model in the testing set.

Figure 4

Receiver operating curve of training set and testing set. Internal and external validation of predictive models. (A) The receiver operating curve of the prediction model in the training set; (B) The receiver operating curve of the prediction model in the testing set; (C) Part of the result data display of the receiver operating curve of the nomograph in the training set and the test set.