Your browser doesn't support javascript.
loading
Supporting the decision to perform molecular profiling for cancer patients based on routinely collected data through the use of machine learning.
Kasprzak, Julia; Westphalen, C Benedikt; Frey, Simon; Schmitt, Yvonne; Heinemann, Volker; Fey, Theres; Nasseh, Daniel.
Afiliación
  • Kasprzak J; Comprehensive Cancer Center (CCC Munich LMU), LMU University Hospital Munich, Pettenkoferstraße 8a, Munich, Germany. Julia.Kasprzak@med.uni-muenchen.de.
  • Westphalen CB; Comprehensive Cancer Center (CCC Munich LMU), LMU University Hospital Munich, Pettenkoferstraße 8a, Munich, Germany.
  • Frey S; Roche Pharma AG, Grenzach-Wyhlen, Germany.
  • Schmitt Y; Roche Pharma AG, Grenzach-Wyhlen, Germany.
  • Heinemann V; Comprehensive Cancer Center (CCC Munich LMU), LMU University Hospital Munich, Pettenkoferstraße 8a, Munich, Germany.
  • Fey T; German Cancer Research Center (DKFZ), German Cancer Consortium (DKTK, Partner Site Munich), Heidelberg, Germany.
  • Nasseh D; Comprehensive Cancer Center (CCC Munich LMU), LMU University Hospital Munich, Pettenkoferstraße 8a, Munich, Germany.
Clin Exp Med ; 24(1): 73, 2024 Apr 10.
Article en En | MEDLINE | ID: mdl-38598013
ABSTRACT

BACKGROUND:

Personalized medicine offers targeted therapy options for cancer treatment. However, the decision whether to include a patient into next-generation sequencing (NGS) testing is not standardized. This may result in some patients receiving unnecessary testing while others who could benefit from it are not tested. Typically, patients who have exhausted conventional treatment options are of interest for consideration in molecularly targeted therapy. To assist clinicians in decision-making, we developed a decision support tool using routine data from a precision oncology program.

METHODS:

We trained a machine learning model on clinical data to determine whether molecular profiling should be performed for a patient. To validate the model, the model's predictions were compared with decisions made by a molecular tumor board (MTB) using multiple patient case vignettes with their characteristics.

RESULTS:

The prediction model included 440 patients with molecular profiling and 13,587 patients without testing. High area under the curve (AUC) scores indicated the importance of engineered features in deciding on molecular profiling. Patient age, physical condition, tumor type, metastases, and previous therapies were the most important features. During the validation MTB experts made the same decision of recommending a patient for molecular profiling only in 10 out of 15 of their previous cases but there was agreement between the experts and the model in 9 out of 15 cases.

CONCLUSION:

Based on a historical cohort, our predictive model has the potential to assist clinicians in deciding whether to perform molecular profiling.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias Límite: Humans Idioma: En Revista: Clin Exp Med Asunto de la revista: MEDICINA Año: 2024 Tipo del documento: Article País de afiliación: Alemania Pais de publicación: Italia
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias Límite: Humans Idioma: En Revista: Clin Exp Med Asunto de la revista: MEDICINA Año: 2024 Tipo del documento: Article País de afiliación: Alemania Pais de publicación: Italia