A combined nomogram based on radiomics and hematology to predict the pathological complete response of neoadjuvant immunochemotherapy in esophageal squamous cell carcinoma

Abstract

Background: To predict pathological complete response (pCR) in patients receiving neoadjuvant immunochemotherapy (nICT) for esophageal squamous cell carcinoma (ESCC), we explored the factors that influence pCR after nICT and established a combined nomogram model.

Methods: We retrospectively included 164 ESCC patients treated with nICT. The radiomics signature and hematology model were constructed utilizing least absolute shrinkage and selection operator (LASSO) regression, and the radiomics score (radScore) and hematology score (hemScore) were determined for each patient. Using the radScore, hemScore, and independent influencing factors obtained through univariate and multivariate analyses, a combined nomogram was established. The consistency and prediction ability of the nomogram were assessed utilizing calibration curve and the area under the receiver operating factor curve (AUC), and the clinical benefits were assessed utilizing decision curve analysis (DCA).

Results: We constructed three predictive models.The AUC values of the radiomics signature and hematology model reached 0.874 (95% CI: 0.819-0.928) and 0.772 (95% CI: 0.699-0.845), respectively. Tumor length, cN stage, the radScore, and the hemScore were found to be independent factors influencing pCR according to univariate and multivariate analyses (P < 0.05). A combined nomogram was constructed from these factors, and AUC reached 0.934 (95% CI: 0.896-0.972). DCA demonstrated that the clinical benefits brought by the nomogram for patients across an extensive range were greater than those of other individual models.

Conclusions: By combining CT radiomics, hematological factors, and clinicopathological characteristics before treatment, we developed a nomogram model that effectively predicted whether ESCC patients would achieve pCR after nICT, thus identifying patients who are sensitive to nICT and assisting in clinical treatment decision-making.

Keywords: Esophageal squamous cell carcinoma; Hematology; Neoadjuvant immunochemotherapy; Nomogram; Pathological complete response; Radiomics.

Fig. 1

The research workflow. After the patient was enrolled, radiomics and hematology analyses were conducted separately, using LASSO regression to reduce the dimensionality of features. Then, radScore and hemScore were calculated, and they were combined with independent factors influencing pCR to develop a nomogram. Evaluated the predictive ability of three models, including ROC curve, calibration curve, DCA, etc.

Fig. 2

Flowchart of patient enrollment

Fig. 3

Radiomics signature and hematology model predictive performance. A: Radiomics signature value bar plot for every ESCC patient. The optimal threshold value for distinguishing among cohorts with non-pCR versus pCR is -0.151. B: Comparison of radScore among non-pCR versus pCR cohorts (P < 0.001). C: Hematology model value bar plot for every ESCC patient. The optimal threshold value for distinguishing among cohorts with non-pCR versus pCR is -0.933. D: Comparison of hemScore among non-pCR versus pCR cohorts (P < 0.001). The green color in the figure represents non-pCR patients, while the blue color represents pCR patients

Fig. 4

Comparison of predictive performance of the combined nomogram, radiomics signature, and hematology model. A: Receiver operating characteristic curves of the combined nomogram, radiomics signature, and hematology model. B: Nomogram based on independent predictors (radScore, hemScore, cN stage, and tumor length). C: Calibration curves of the combined nomogram to estimate the consistency among the estimated pCR probability by the combined nomogram and the authentic pCR. The ideal situation is shown by the black dashed line, which acts as the reference line and shows when the predicted and actual values coincide; the actual situation of the nomogram is shown by the solid blue line, referred to as the apparent line; the bias-corrected line is shown by the solid green line, which shows the corrected nomogram's actual situation. D: The models' clinical benefits were assessed using decision curve analysis. The black horizontal line indicates that when all patients do not receive treatment, regardless of the probability threshold, there is no clinical net benefit. The gray diagonal represents the change in clinical net benefit as the probability threshold changes when all patients receive treatment