Predicting Depression Risk in Patients with Cancer Using Multimodal Data

Studies in health technology and informatics, vol. 302, pp. 817–818

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.

Authors 8

1. Anne de Hond Aachen

   Leiden University Medical Center · Stanford University

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands

   Stanford University, Stanford, CA, USA

2. Marieke Meija van Buchem Aachen

   Leiden University Medical Center · Stanford University

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands

   Stanford University, Stanford, CA, USA

3. Claudio Fanconi

   ETH Zurich · Stanford University

   Affiliation as printed

   ETH Zürich, Zürich, Switzerland

   Stanford University, Stanford, CA, USA

4. Mohana Roy

   Stanford University

   Affiliation as printed

   Stanford University, Stanford, CA, USA

5. Douglas W. Blayney

   Stanford University

   Affiliation as printed

   Stanford University, Stanford, CA, USA

6. Ilse M.J. Kant

   University Medical Center Utrecht

   Affiliation as printed

   University Medical Center Utrecht, Utrecht, The Netherlands

7. Ewout Willem Steyerberg Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands

8. Tina Hernandez‐Boussard

   Stanford University

   Affiliation as printed

   Stanford University, Stanford, CA, USA