Sign in Subscribe
Cancer research

Artificial Intelligence and Machine Learning Techniques Hold Promise for Neuropathic Pain Prediction in Cancer Care

Strategic Insights

— 1 min read

Researchers at the School of Nursing in Amman, Jordan, have conducted a systematic review to evaluate the application of artificial intelligence and machine learning techniques in predicting neuropathic pain in patients with cancer. The study, published in the Digital Health journal, highlights the potential of AI and ML in enhancing NP prediction in cancer care. However, the researchers also note that methodological limitations, including poor calibration and limited external validation, hinder clinical adoption.

Key Takeaways:

  • The study aimed to evaluate the application of AI and ML techniques in predicting neuropathic pain and related outcomes among oncology patients.
  • A comprehensive search was conducted across multiple databases, including PubMed, EMBASE, Web of Science, and Google Scholar, for English-language studies published between January 2020 and February 2025.
  • Fourteen eligible studies were included based on predefined PICOS criteria, and the risk of bias was assessed using QUADAS-2 and PROBAST tools.
  • Most studies focused on breast cancer in high-income countries, and supervised models such as random forest, support vector machine, and deep learning architectures were dominant.
  • Key predictive features included acute postoperative pain, anxiety, type of surgery, and biomarkers like sphinganine-1-phosphate.
  • Only 14% of studies used external validation, and 5% assessed calibration.
  • Multimodal frameworks integrating clinical, emotional, imaging, and molecular data outperformed single-modality models.
  • The researchers concluded that AI and ML hold significant promise for enhancing NP prediction in cancer care, but standardization, explainable AI, and diverse datasets are essential for future progress.

Statistics:

  • 14 studies were included in the systematic review.
  • 14% of studies used external validation.
  • 5% of studies assessed calibration.
  • The area under the receiver operating characteristic curve (AUC) for random forest model was up to 0.94.
  • The AUC for support vector machine model was between 0.808-0.87.

Sources:

  • Artificial intelligence and machine learning techniques for predicting neuropathic pain in patients with cancer: A systematic review (Digital Health, 2025, 11)
  • Haneen A Taha et al. (School of Nursing, Clinical Nursing Department, Amman, Jordan)
  • Ruqayya S Zeilani et al. (Research team, School of Nursing, Amman, Jordan)
  • Digital Health - http://dhj.sagepub.com/ (SAGE Publishing)

Read more