Machine Learning Project Targets Advances to Improve Patient Care

In a move to speed the progress of medical research and help translate those advances into areas like cancer diagnostics, medical imaging, precision medicine and voice-enabled technologies, the Pittsburgh Health Data Alliance is teaming with Amazon Web Services on a machine learning partnership.

The PHDA, formed four years ago by the University of Pittsburgh, UPMC and Carnegie Mellon University, uses big data to transform the way diseases are treated and prevented, and to better engage patients in their care. The consortium says new machine learning technologies and advances in computing power, like those offered by Amazon SageMaker and Amazon EC2, make it possible to rapidly translate insights discovered in the lab into treatments and services that could dramatically improve human health.

Scientists from Pitt and Carnegie Mellon expect to accelerate research and product commercialization efforts across eight projects, enabling physicians to better predict the course of a person’s disease and response to treatment. Areas being explored include:

• Using a patient’s verbal and visual cues to diagnose mental health symptoms.
• Reducing diagnostic errors by mining secure, anonymous data from a patient’s medical record.
• Developing algorithms and software tools to better understand the origin and evolution of tumor cells. The project will use machine learning to gain insights into how tumors develop and to predict how they are likely to change and grow in the future.

David Vorp, associate dean for research at Pitt’s Swanson School of Engineering, and his team will use AWS resources to improve the diagnosis and treatment of abdominal aortic aneurysms, the 13th leading cause of death in Western countries.