Predictive risk model of mild cognitive impairment in patients with malignant haematological diseases after haematopoietic stem cell transplantation.

Objective: This study is to develop and validate a robust risk prediction model for mild cognitive impairment (MCI) in patients with malignant haematological diseases after haematopoietic stem cell transplantation (HSCT).

Methods: In this study, we analysed the clinical data of the included patients. Logistic regression analysis was used to identify independent risk factors for cognitive impairment after HSCT in patients with malignant haematological diseases, and a risk prediction model was constructed. Multiple cohorts of patients with haematological malignancies after HSCT (282 cases) from the Affiliated Hospital of Xuzhou Medical University and the First People's Hospital of Yancheng City between April 2019 and February 2022, and patients from the Affiliated Huaian No.1 People's Hospital of Nanjing Medical University between March 2022 and July 2023 were used for external validation. Logistic regression analysis was performed to develop the predictive model. The predictive value and consistency of the model were evaluated using the area under the curve (AUC) and calibration method, respectively. Decision curve analysis (DCA) was performed to access the utility of the model.

Results: Approximately half (52.26%) of the patients in the study developed mild cognitive impairment (MCI). Older age, allogeneic HSCT, anxiety, graft-versus-host disease, and longer hospital stay were associated with a higher risk of developing MCI. ROC curve analysis confirmed the sound performance of the predictive model and external validation, with AUC of 0.897 and 0.789 respectively. The direction of the calibration curves of the training and validation sets is closer to the diagonal (ideal curve), indicating good model consistency; the DCA curves also show that the model has good predictive ability and stability.

Conclusions: We conclude that it is possible to predict mild cognitive impairment with readily available, mostly pretransplant predictors. The accuracy of the risk prediction models can be improved for use in clinical practice, possibly by adding pretransplant patient-reported functioning and comorbidities.