Machine learning and natural language processing (NLP) approach to predict early progression to first-line treatment in real-world hormone receptor-positive (HR+)/HER2-negative advanced breast cancer patients. (February 2021)

• Record Type: Journal Article
• Authors: Ribelles, Nuria; Jerez, Jose M.; Rodriguez-Brazzarola, Pablo; Jimenez, Begoña; Diaz-Redondo, Tamara; Mesa, Hector; Marquez, Antonia; Sanchez-Muñoz, Alfonso; Pajares, Bella; Carabantes, Francisco; Bermejo, Maria J.; Villar, Ester; Dominguez-Recio, Maria E.; Saez, Enrique; Galvez, Laura; Godoy, Ana; Franco, Leo; Ruiz-Medina, Sofia; Lopez, Irene; Alba, Emilio
• Is Part Of: European journal of cancer. Volume 144(2021)
• Page Start: 224
• Page End: 231
• Publication Date: 2021-02
• Subjects: Breast cancer -- Hormone receptor positive -- CDK4/6-inhibitors -- machine learning -- Natural language processing -- Electronic health records; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Cancer; Tumors; Electronic journals; Periodicals; Electronic journals; 616.994
• DOI: 10.1016/j.ejca.2020.11.030
• Languages: English
• ISSNs: 0959-8049

Abstract

Abstract: Background: CDK4/6 inhibitors plus endocrine therapies are the current standard of care in the first-line treatment of HR+/HER2-negative metastatic breast cancer, but there are no well-established clinical or molecular predictive factors for patient response. In the era of personalised oncology, new approaches for developing predictive models of response are needed. Materials and methods: Data derived from the electronic health records (EHRs) of real-world patients with HR+/HER2-negative advanced breast cancer were used to develop predictive models for early and late progression to first-line treatment. Two machine learning approaches were used: a classic approach using a data set of manually extracted features from reviewed (EHR) patients, and a second approach using natural language processing (NLP) of free-text clinical notes recorded during medical visits. Results: Of the 610 patients included, there were 473 (77.5%) progressions to first-line treatment, of which 126 (20.6%) occurred within the first 6 months. There were 152 patients (24.9%) who showed no disease progression before 28 months from the onset of first-line treatment. The best predictive model for early progression using the manually extracted dataset achieved an area under the curve (AUC) of 0.734 (95% CI 0.687–0.782). Using the NLP free-text processing approach, the best model obtained an AUC of 0.758 (95% CI 0.714–0.800). The best model to predict long responders using manually extracted data obtained an AUC of 0.669 (95% CI 0.608–0.730). With NLP free-text processing, the best model attained an AUC of 0.752 (95% CI 0.705–0.799). Conclusions: Using machine learning methods, we developed predictive models for early and late progression to first-line treatment of HR+/HER2-negative metastatic breast cancer, also finding that NLP-based machine learning models are slightly better than predictive models based on manually obtained data. Highlights: There are no well-established predictive factors of response to CDK4/6 inhibitors. Data from real-world patients may be more relevant from a healthcare point of view. Machine learning algorithms and NLP analyses can be useful in this task. Free-text from medical notes would be more useful than structured data.