Partnership Aims to Improve Early Cognitive Decline Detection with NLP

Brigham and Women's Hospital has partnered with artificial intelligence (AI) software company Melax Tech to build and validate a clinical decision support system (CDS) for early cognitive decline detection with a two-year, $2.5 million grant from the National Institutes of Health.

According to the press release, the project will leverage deep learning (DL) and natural language processing (NLP) to identify signs of cognitive decline from EHR data in an effort to improve early diagnosis of Alzheimer’s disease and related dementias (AD/ADRD) in primary care settings.

"This study is a critical step in our mission to improve the lives of those affected by Alzheimer's disease and related dementia," said Li Zhou, MD, PhD, a professor of medicine at Harvard Medical School and lead investigator at the Brigham and Women’s Hospital, who serves as a lead researcher on the project, in the press release. "Using deep learning algorithms and electronic health records can revolutionize how we approach early detection and intervention for AD/ADRD."

The project will focus on developing novel computational algorithms, such as ontology, deep learning, and NLP models, to flag patients with early cognitive decline using EHRs and supporting data, in addition to working with clinicians to design, develop, and assess a CDS to identify and manage these patients and make personalized care recommendations.

The tool will utilize NLP to extract cognitive concerns, symptoms, assessments, diagnoses, and social determinants of health (SDOH) factors from free-text sources and clinical notes within EHRs to identify at-risk patients.

The project’s investigators state in the press release that early interventions for Alzheimer's disease are crucial, especially following new research published last month in The Lancet: Public Health that predicts the number of people living with Alzheimer’s globally will triple to 153 million by 2050. This, combined with rising care costs, spurred the researchers to pursue improved early detection and primary care diagnoses for improved patient outcomes.

Other efforts to apply AI to aging and AD/ADRD research are underway at other institutions.

Last week, the Johns Hopkins Artificial Intelligence and Technology Collaboratory for Aging Research (JH AITC) shared that 14 pilot projects were awarded funding through a $20 million grant from the National Institute on Aging.

The funding seeks to bolster the development of AI devices to improve the health of older adults and help them live independently for longer. The grant will help support a newly-launched AI and technology collaborative among the Johns Hopkins University Schools of Medicine and Nursing, the Whiting School of Engineering, Johns Hopkins Technology Ventures, and the Carey Business School, and outside stakeholders such as patients and caregivers.

The 14 projects include efforts to develop a virtual reality platform to reduce social isolation, an AI-powered handlebar device to help seniors improve their balance, and advanced algorithms to screen for cataracts and other age-related ailments.