About Team Research Publications Join Us

Division of Health AI

Northwell Health

Clinical AI built with the data and clinicians of one of the largest health systems in the United States.

Explore

About
Team
Research
Publications
Join us

Affiliations

Feinstein Institutes (opens in new tab)
Northwell Health (opens in new tab)
Zucker School of MedicineHofstra Northwell

Located at

Institute of Health System Science
Institute of Bioelectronic Medicine
Manhasset, New York

Admin

The Division

Division of Health AI lab, current team group photo with inset headshots — The current lab · Manhasset, NY

About.

Led by

Theodoros Zanos, PhD→

The Division of Health AI at Northwell Health and the Feinstein Institutes for Medical Research develops artificial intelligence and machine learning models to improve patient care and outcomes. The lab works at the intersection of artificial intelligence, computational neuroscience, and clinical medicine.

01 / Mission

Translational machine learning for one of the largest health systems in the United States. The lab develops clinical decision support, bioelectronic medicine algorithms, and operational tools alongside clinicians who would actually use them.

02 / The Lab Over Time

Group photos, year by year

Lab team in 2017, five members in the office

Lab team in 2018, outdoor group photo with team interns

Lab team in 2021, rooftop with the Manhattan skyline

Lab team in 2023, rooftop at dusk with the NYC skyline

Lab team in 2024, rooftop at sunset with the NYC skyline

Lab team in 2017, five members in the office.

Meet the current team→

03 / Selected Work

What the lab has built

Programs supported by NIH grants, deployed inside Northwell, and reported in peer-reviewed venues.

Clinical AI

Read the project→

Pandemic Response

Read the project→

Bioelectronic Medicine

Read the project

Explore the research Get in touch→

→

Operational AI

Workforce forecasting

DeepAR forecasting models for nursing demand at 12-month horizons across 10 Northwell units, used by hospital operations to plan staffing.

Read the project→

See all research→

Patient deterioration prediction

Deep learning models trained on more than 1.5 million Northwell hospitalizations predict in-hospital deterioration up to 17 hours in advance. Published in Nature Communications and supported by a $3.2M NIH grant.

COVID-19 clinical decision support

Machine learning tools developed during the pandemic to support clinical decisions for COVID-19 patients, drawing on data from more than 35,000 cases. Published in JAMA and Nature Communications.

Vagus nerve digital twin

High-resolution 3D reconstructions of human vagus nerves segmented from 200TB of imaging data using nn-U-Net. Supported by a $6.7M NIH grant.