Poiesy

The Mission

Creating predictive model for the success rate of autologous stem cell transplants

The challenge

Creating a big-data-based, machine-learning model for prediction of success rate after transplantation after autologous bone marrow transplantation. We look at various predictive markers of the hematopoietic cells that would give information on various properties like adhesion, affinity and polarity.

The solution

The project aims to raise the success rate autologous bone marrow transplantation from cyropreserved samples by harnessing the power of big data and machine learning. The solution involves the development of an advanced predictive model that utilizes a diverse range of data points, or markers, associated with hematopoietic stem cells. These markers provide crucial insights into properties such as adhesion, affinity, and polarity, offering a comprehensive prediction of the transplantation results. By leveraging large datasets and employing machine learning algorithms, the model seeks to identify patterns and correlations within the data (we are using publicly available open databases and we process publications for further data). This enables the system to make accurate predictions regarding the success rate of autologous bone marrow transplantation outcomes. The multidimensional analysis of hematopoietic cell properties provides a more nuanced and personalized approach to transplantation, offering valuable information for medical professionals to optimize treatment strategies and enhance patient outcomes.