Machine Learning Model Predicts Kinesiophobia in Postoperative Lung Cancer Patients

Strategic Insights -

A recent study conducted at Jinzhou Medical University in Jinzhou, People's Republic of China, has developed a machine learning model to predict the occurrence of kinesiophobia in postoperative lung cancer patients. Researchers found that the incidence of kinesiophobia among postoperative lung cancer patients was 43.74%, with significant predictors including positive coping style, social support, pain severity, personal income, surgical history, and gender. The model, which utilizes a random forest algorithm, demonstrated a high level of accuracy in predicting kinesiophobia, with an area under the receiver operating characteristic curve (AUROC) of 0.893, accuracy of 0.803, precision of 0.732, recall of 0.870, and F1 score of 0.795.

Key Takeaways:

  • The incidence of kinesiophobia among postoperative lung cancer patients was 43.74%.
  • Positive coping style, social support, pain severity, personal income, surgical history, and gender were identified as significant predictors of kinesiophobia.
  • The random forest model demonstrated a high level of accuracy in predicting kinesiophobia, with an AUROC of 0.893 and F1 score of 0.795.
  • The model effectively identified high-risk patients and provided a valuable foundation for early clinical screening and intervention.
  • Future research should incorporate heterogeneous datasets from multiple regions and healthcare institutions to improve the model's generalizability and clinical utility.

Statistics:

  • Incidence of kinesiophobia among postoperative lung cancer patients: 43.74% (519 patients).
  • AUROC of the random forest model: 0.893.
  • Accuracy of the random forest model: 0.803.
  • Precision of the random forest model: 0.732.
  • Recall of the random forest model: 0.870.
  • F1 score of the random forest model: 0.795.

Sources:

  • Development and validation of a risk prediction model for kinesiophobia in postoperative lung cancer patients: an interpretable machine learning algorithm study. Scientific Reports, 2025;15(1):19412.
  • Jinzhou Medical University, School of Nursing, Jinzhou, 121001, People's Republic of China.
  • Nature Portfolio, Heidelberger Platz 3, Berlin, 14197, Germany.