Nomogram to predict 6-month mortality in acute ischemic stroke patients treated with endovascular treatment

Abstract

Background: Acute Ischemic Stroke (AIS) presents significant challenges in evaluating the effectiveness of Endovascular Treatment (EVT). This study develops a novel prognostic model to predict 6-month mortality post-EVT, aiding in identifying patients likely to benefit less from this intervention, thus enhancing therapeutic decision-making.

Methods: We employed a cohort of AIS patients from Shenyang First People's Hospital, serving as the Validation set, to develop our model. LASSO regression was used for feature selection, followed by logistic regression to create a prognostic nomogram for predicting 6-month mortality post-EVT. The model's performance was validated using a dataset from PLA Northern Theater Command General Hospital, assessing discriminative ability (C-index), calibration (calibration plot), and clinical utility (decision curve analysis). Statistical significance was set at p < 0.05.

Results: The development cohort consisted of 219 patients. Six key predictors of 6-month mortality were identified: "Lack of Exercise" (OR, 4.792; 95% CI, 1.731-13.269), "Initial TICI Score 1" (OR, 1.334; 95% CI, 0.628-2.836), "MRS Score 5" (OR, 1.688; 95% CI, 0.754-3.78), "Neutrophil Percentage" (OR, 1.08; 95% CI, 1.042-1.121), "Onset Blood Sugar" (OR, 1.119; 95% CI, 1.007-1.245), and "Onset NIHSS Score" (OR, 1.074; 95% CI, 1.029-1.121). The nomogram demonstrated a high predictive capability with a C-index of 0.872 (95% CI, 0.830-0.911) in the development set and 0.830 (95% CI, 0.726-0.920) in the validation set.

Conclusion: Our nomogram, incorporating factors such as Lack of Exercise, Initial TICI Score 1, MRS Score 5, Neutrophil Percentage, Onset Blood Sugar, and Onset NIHSS Score, provides a valuable tool for predicting 6-month mortality in AIS patients post-EVT. It offers potential to refine early clinical decision-making and optimize patient outcomes, reflecting a shift toward more individualized patient care.

Keywords: endovascular treatment; ischemic stroke; mortality; nomogram; prediction.

Figure 1

Flow chart outlining the patient inclusion process. AIS, acute ischemic stroke; EVT, endovascular therapy.

Figure 2

Texture feature selection using the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. (A) Tuning parameter (λ) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The Binomial Deviance was plotted vs. log (λ). Dotted vertical lines were drawn at the optimal values by using the minimum criteria and the 1 standard error of the minimum criteria (the 1-SE criteria). A λ value of 0.048, with log (λ), −3.034 was chosen (the minimum criteria) according to 10-fold cross-validation. (B) LASSO coefficient profiles of the 57 features. A coefficient profile plot was produced against the log (λ) sequence. Vertical line was drawn at the value selected using 10-fold cross-validation, where optimal λ resulted in 6 nonzero coefficients.

Figure 3

Nomogram for predicting the probability of 6-month mortality in Chinese acute ischemic stroke patients undergoing endovascular treatment based on Lack of Exercise, Initial TICI Score 1, MRS Score 5, Neutrophil Percentage, Onset Blood Sugar, and Onset NIHSS Score.

Figure 4

Receiver operating characteristic curves for risk of 6-month mortality in acute ischemic stroke patients treated with endovascular treatment. (A) shows the ROC Curve for the Training set. (B) depicts the ROC Curve for the Validation set. Sensitivity and specificity of several risk thresholds of the prediction model are plotted.

Figure 5

The calibration curves of the nomogram for predicting 6-month mortality of stroke patients treated with EVT. (A) presents the Calibration Plot for the Training Set. (B) shows the Calibration Plot for the Validation Set. The x-axis represents the predicted probability of unfavorable outcome calculated using the nomogram. The y-axis represents the actual rate of unfavorable outcome. The dashed line is the reference line where an ideal nomogram would lie, the dotted line represents the nomogram’s performance, and the solid line adjusts for any deviation from the nomogram.

Figure 6

Decision curve analysis of the nomogram, encompassing both the training and validation set. (A) Decision Curve for the Training Data set, demonstrating the net benefit across various threshold probabilities. (B) Decision Curve for the Validation Data set, depicting corresponding net benefits. The x-axis illustrates the threshold probability while the y-axis measures the net benefit. The black, red, and green lines respectively represent the net benefit of universally treating all patients, treating no patients, and the nomogram’s application. This decision curve analysis method is employed to evaluate the prognostic value of nomogram strategies, with the developed nomogram specifically designed to assess the probability of post-EVT mortality among AIS patients. Notably, the quintessential goal of this nomogram is not merely to gauge post-EVT mortality probability but pivotally to distinguish patients who may derive marginal benefit from EVT. Consequently, it enables clinicians to identify and subsequently tailor therapeutic interventions for those at a high risk of post-EVT death—potentially involving additional procedures such as hematoma evacuation or decompressive craniectomy—while avoiding potentially non-beneficial interventions for those at lower risk. In the context of this study, the reference risk was calculated presuming a universal need for further treatment to prevent death, with a zero net benefit defining a scenario where no patients require additional intervention. The threshold probability is determined at the point where the anticipated benefit of further therapy aligns with the expected benefit of foregoing additional intervention. Consequently, the most favored model is the nomogram that yields the highest net benefit at any given threshold probability.