During National Kidney Month, the Office of the National Coordinator for Health Information Technology (ONC) joins communities across the country to raise awareness about kidney disease and to highlight our efforts to support patients through research. In particular, ONC is collaborating with the National Institutes of Health’s National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) to enhance data infrastructure for patient-centered outcomes research (PCOR) through a project advancing artificial intelligence (AI) and machine learning called Training Data for Machine Learning to Enhance PCOR Data Infrastructure (the PCOR Machine Learning Project).

The PCOR Machine Learning Project has established a working group to bring federal partners together on a quarterly basis. It is also leveraging expertise from leaders in biomedical, technology, and patient-advocacy organizations as well as academic researchers and practicing clinicians. Both groups met for the first time in January 2020 and discussed use cases to consider, data sources, techniques for addressing health disparities and bias, and other relevant topics.

The Burden of Chronic Kidney Disease

AI and machine learning hold promise for more accurately predicting, preventing, and treating a variety of health problems, including chronic kidney disease (CKD), which affects 37 million Americans. CKD involves the gradual loss of function in the kidneys over time. The disease can lead to high blood pressure, low blood count, weak bones, and it can increase the risk for heart disease.

Patients with early stages of CKD often have no symptoms, but the disease can progress to end-stage kidney failure, which is deadly without routine dialysis or a kidney transplant. Millions of Americans are at higher risk for CKD, including people who have diabetes, high blood pressure, and family history of kidney failure.

HHS Progress on AI and Machine Learning

PCOR aims to produce new scientific evidence to inform and support the healthcare decisions of patients, families, and their healthcare providers. To build more data capacity for PCOR, the Office of the Assistant Secretary for Planning and Evaluation coordinates a broad portfolio of projects throughout the Department of Health and Human Services.

Through the PCOR Machine Learning Project, ONC and NIDDK aim to advance the application of AI and machine learning algorithms in PCOR by defining the requirements for high-quality training data sets. These data sets are essential to train prediction models that use machine learning algorithms, to extract features most relevant to specified research goals, and to reveal meaningful associations in the data. The project is using kidney disease as a sample use case to identify which unanswered questions would benefit most from AI and machine learning applications using data from multiple sources.

Current and planned project activities include:

1. Capturing lessons learned from the process of developing high-quality training data sets focusing on data annotation, data curation, and establishing data quantity and quality requirements;
2. Developing machine learning models and identifying approaches to evaluate model performance; and
3. Disseminating project resources and materials to encourage future applications of these methods by PCOR researchers.

The Challenge Ahead

Engagement and expertise from a variety of stakeholders are critical to understanding which kidney disease use cases would benefit most from AI, where relevant data are stored and how to retrieve them, and what the best practices are for training data and model development.

Throughout the next two years, the PCOR Machine Learning Project will help identify factors that can contribute to the development of robust training data sets and build a foundation for AI and machine learning approaches in PCOR.

Find more information on project’s progress and other findings at ONC’s PCOR machine learning page.