Predicting the efficiency of chidamide in patients with angioimmunoblastic T-cell lymphoma using machine learning algorithm

Abstract

Background: Chidamide is subtype-selective histone deacetylase (HDAC) inhibitor that showed promising result in clinical trials to improve prognosis of angioimmunoblastic T-cell lymphoma (AITL) patients. However, in real world settings, contradictory reports existed as to whether chidamide improve overall survival (OS). Therefore, we aimed to develop an interpretable machine learning (Machine learning)-based model to predict the 2-year overall survival of AITL patients based on chidamide usage and baseline features.

Methods: A total of 183 patients with AITL were randomly divided into training set and testing set. We used 5 ML algorithms to build predictive models. Recursive feature elimination (RFE) method was used to filter for the most important features. The ML models were interpreted and the relevance of the selected features was determined using the Shapley additive explanations (SHAP) method and the local interpretable model-agnostic explanationalgorithm.

Results: A total of 183 patients with newly diagnosed AITL from 2012 to 2022 from 3 centers in China were enrolled in our study. Seventy-one patients were dead within 2 years after diagnosis. Five ML algorithms were built based on chidamide usage and 16 baseline features to predict 2-year OS. Catboost model presented to be the best predictive model. After RFE screening, 12 variables demonstrated the best performance (AUC = 0.8651). Using chidamide ranked third among all the variables that correlated with 2-year OS.

Conclusion: This study demonstrated that the Catboost model with 12 variables could effectively predict the 2-year OS of AITL patients. Combining chidamide in the treatment therapy was positively correlated with longer OS of AITL patients.

Keywords: angioimmunoblastic T-cell lymphoma; biomarker; chidamide; machine learning; prognosis.

FIGURE 1

Flowchart. OS: overall survival; RFE: recursive feature elimination; SHAP: Shapley additive explanations; LIME, local interpretable model–agnostic explanation.

FIGURE 2

The ROC curves of five ML models. [(A) Training set. (B) Testing set].

FIGURE 3

Using RFE method to screen the optimal variables on Catboost model (A). The ROC curves of the optimized Catboost model (B).

FIGURE 4

Attribution of 12 features in the optimized Catboost model based on the SHAP algorithm. (A) Summary of SHAP analysis on the data set. One dot represents a case in the data set, and the color of a dot indicates the value of the feature. Blue indicates the lowest range and red the highest range. (B) Ranking of feature importance indicated by SHAP. SHAP values provide a clear depiction of how each feature influences the model’s prediction, indicating whether the impact is positive or negative. For example, from the SHAP plot, we can observe that B symptoms have the most significant contribution. A higher value of B symptoms corresponds to a positive SHAP value, suggesting a positive impact on the prediction, supporting a likelihood of death. Conversely, a lower value of B symptoms results in a negative SHAP value, indicating a negative impact on the prediction, supporting survival.

FIGURE 5

Results of LIME with Catboost applied to two randomly selected patients. Orange attributes support death, while blue attributes support survival. Taking the first patient as an example, the upper left corner of the LIME plot shows a survival prediction probability of 0.79 and a death prediction probability of 0.21, indicating a higher likelihood of survival for the patient within 2 years. The middle section lists the individual features along with their corresponding coefficients, which reflect their impact on the prediction. For instance, the coefficient for B symptoms is 0.14, shown in blue, suggesting that the absence of B symptoms increases the model’s predicted probability of survival by 0.14. Similarly, the absence of Edema/Serous effusion increases the survival probability by 0.11, while the absence of Chidamide use increases the probability of death by 0.08.