Predicting Depression Risk in Patients with Cancer Using Multimodal Data

Stud Health Technol Inform. 2023 May 18:302:817-818. doi: 10.3233/SHTI230274.

Abstract

When patients with cancer develop depression, it is often left untreated. We developed a prediction model for depression risk within the first month after starting cancer treatment using machine learning and Natural Language Processing (NLP) models. The LASSO logistic regression model based on structured data performed well, whereas the NLP model based on only clinician notes did poorly. After further validation, prediction models for depression risk could lead to earlier identification and treatment of vulnerable patients, ultimately improving cancer care and treatment adherence.

Keywords: Natural Language Processing; depression; machine learning; oncology.

MeSH terms

  • Depression* / diagnosis
  • Electronic Health Records
  • Humans
  • Machine Learning
  • Natural Language Processing
  • Neoplasms* / complications
  • Patients
  • Risk Assessment