Acute Myeloid Leukemia Survival Model using machine learning

Dataset

⁠

Loading www.nature.com⁠

⁠

Project outline

I. Background:

Acute Myeloid Leukemia (AML) is a type of blood cancer that develops in the bone marrow and progresses rapidly, affecting the production of normal blood cells. The prognosis for AML patients varies based on several factors, including age, cytogenetics, and response to treatment. Accurate prediction of survival for AML patients can help inform treatment decisions and improve patient outcomes. However, traditional prognostic models are limited in their accuracy and may not capture the full complexity of AML.

II. Method:

The goal of this project is to develop a machine learning model that can predict survival outcomes for AML patients based on clinical and genetic features. To achieve this, we will follow the following steps:

Data collection and preprocessing: We use the data provided in the above paper to build the training and validation cohort. Once the model is built, we will validate in a separate publicly available dataset.

Model development: We will explore different machine learning algorithms, with and without survival function in them, to develop a model that can accurately predict survival outcomes for AML patients. We will use cross-validation techniques to evaluate model performance and optimize hyperparameters.

Model interpretation: We will use feature importance analysis and SHAP values to identify the most relevant clinical and genetic features associated with survival outcomes. This can help inform future research into the underlying biological mechanisms of AML.

Validation and testing: We will validate the model on an independent test set and compare its performance to traditional prognostic models. We will also test the model's generalizability to different patient populations and explore potential biases or confounding factors.

III. Expected Outcome:

The successful completion of this project will lead to the development of a machine learning model that can accurately predict survival outcomes for AML patients. This model can help inform treatment decisions and improve patient outcomes by identifying high-risk patients who may require more aggressive therapies. Additionally, the model's interpretation can provide insights into the underlying biological mechanisms of AML and guide future research in this area. Overall, this project has the potential to advance our understanding of AML and improve patient care.

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.