Letrozole in the Treatment of 1st and 2nd Line Hormone Receptor Positive Breast Cancer: Pre-therapeutic Risk Assessment
|The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been evaluated by the U.S. Federal Government. Read our disclaimer for details.|
|ClinicalTrials.gov Identifier: NCT00241046|
Recruitment Status : Terminated
First Posted : October 18, 2005
Last Update Posted : April 19, 2012
The course of the disease in female patients with metastatic mammary carcinoma can vary greatly. In this connection, the individual prognosis depends on a complex interaction of tumor- and patient-related factors. To take account of such differences, it is necessary to employ individual methods of treatment which are suited to the course of each patient's disease. Prof. Possinger and Dr. Schmid (Charite Berlin) and Prof. Wischnewsky (University of Bremen) have developed an approach that can help to achieve this goal with the aid of computerized machine learning techniques (MLT).
The use of machine learning methods can be beneficial in oncology in two respects. On the one hand, an attempt can be made to individually estimate clinically relevant parameters like, for example, the recurrence probability or expected survival time as precisely as possible based on the established prognostic factors. And on the other hand, it may be possible with the aid of MLT to understand structural relationships between the clinical result and measured or established tumor-/patient-related variables.
To analyze the possible benefits of machine learning techniques for patients with metastatic breast cancer, the aim of study FEM-D-2 is to investigate whether it is possible to characterize those patients who either do or do not respond to a specific treatment with a precision of 90%, prospectively estimate the time until worsening of the disease under a given treatment, and classify patients in groups with favorable and poor chances of medium-term survival.
The use of inductive learning algorithms with machine learning also makes it possible to very accurately estimate the time until progression of the tumor growth. In patients who respond to letrozole therapy, the time until tumor progression depends on factors like pain, age, body mass index, disease-free interval, main localization of metastatic spread, and response to previous estrogen therapy. Only very minimal differences are found when comparing the actual time until progression of the disease and that calculated by the system (at least for survival times < 1 year). Furthermore, using machine learning techniques it has become possible to use initial data assessed before a letrozole treatment to estimate the survival time and distinguish patients with a high risk of dying soon from other patients with a more favorable prognosis.
|Condition or disease||Intervention/treatment||Phase|
|Metastatic Breast Cancer||Drug: Letrozole||Phase 4|
|Study Type :||Interventional (Clinical Trial)|
|Actual Enrollment :||13 participants|
|Intervention Model:||Single Group Assignment|
|Masking:||None (Open Label)|
|Official Title:||Letrozole in the Treatment of 1st and 2nd Line Hormone Receptor Positive Breast Cancer: Pre-therapeutic Risk Assessment|
|Study Start Date :||April 2002|
|Actual Primary Completion Date :||March 2005|
- Comparison of the the individual pretherapeutic predictions from the computer or doctor with the patient data obtained in a first- or second-line treatment of metastatic breast cancer after progression of the disease
- Determination of the individual response at 3 monthly assessments
To learn more about this study, you or your doctor may contact the study research staff using the contact information provided by the sponsor.
Please refer to this study by its ClinicalTrials.gov identifier (NCT number): NCT00241046