Related Experiment Video
Updated: Mar 27, 2026
A Preclinical Model of Exertional Heat Stroke in Mice
Published on: July 1, 2021
Heat and hearts: An exposure-anchored computational phenotyping framework for assessing cardiovascular vulnerability
Peter M Graffy1, Benjamin W Barrett1, Daniel E Horton2
1Department of Preventive Medicine, Northwestern University, Chicago, IL, USA; Institute for Artificial Intelligence in Medicine, Northwestern University, Chicago, IL, USA.
Insights
Extreme heat increases cardiovascular risk. A new computational phenotype (HECV) identifies heat-vulnerable patients using EHR data and temperature, enabling proactive health responses.
Area of Science:
- Cardiology
- Environmental Health
- Health Informatics
Background:
- Extreme heat poses significant risks to cardiovascular health.
- Identifying individuals vulnerable to heat-related cardiovascular events is crucial for public health.
- Electronic Health Records (EHR) offer a rich data source for developing predictive health tools.
Purpose of the Study:
- To develop and validate a computational phenotype for heat exposure-anchored cardiovascular vulnerability (HECV).
- To utilize longitudinal EHR data linked with high-resolution temperature data for phenotype development.
- To create a scalable risk tool for identifying heat-vulnerable patients.
Main Methods:
- Assembled a cohort from a large health system (2017-2024) and linked EHR data to daily temperature (Daymet).
- Identified HECV cases and matched controls, using EHR data for phenome-wide association studies (PheWAS) and logistic regression.
- Evaluated the model's risk discrimination using time-to-event outcomes and time-dependent area-under-the-curve (AUC) in a held-out test set.
Main Results:
- The study included 104,439 patients; key predictors of HECV included low free thyroxine, reduced kidney function, and cardiovascular medications.
- PheWAS revealed associations between HECV and chronic kidney disease, mitral valve disorders, and venous thromboembolism.
- The HECV risk model demonstrated strong discrimination with AUCs of 0.85 (2-year), 0.82 (3-year), and 0.81 (5-year), with significant risk stratification.
Conclusions:
- Routinely collected EHR data combined with external heat metrics can effectively identify patients with elevated HECV.
- The developed computational phenotyping tool is discriminative, scalable, and supports proactive clinical and public-health interventions.
- This tool enables early identification of heat-vulnerable patients, facilitating timely interventions before adverse events occur.
Objective:
Extreme heat is associated with increased cardiovascular vulnerability. We developed and validated a heat exposure-anchored cardiovascular vulnerability (HECV) computational phenotype for outpatient visits using longitudinal EHR data linked to high-resolution temperature.
Materials And Methods:
We assembled a loyalty cohort of adult patients from a large Chicago-based health system (2017-2023) and linked all encounters to Daymet daily temperature data for acute heat exposure at a 1 km2 resolution. HECV cases were identified and matched to non-HECV controls. Structured EHR data from the 12 months prior to diagnosis informed a phenome-wide association study (PheWAS) and penalized conditional logistic regression. The model was evaluated in a held-out test set using a January 1, 2018 landmark, with calculated time-to-event outcomes and time-dependent area-under-the-curve.
Results:
Among 104,439 loyalty cohort patients (62.7% female; mean age 43.6 years), key predictors included low free thyroxine, reduced kidney function, cardiovascular medications, and prior echocardiography. PheWAS showed associations with chronic kidney disease, mitral valve disorders, and venous thromboembolism (all p < 0.001). Our model for HECV risk discrimination had an AUC = 0.85 at 2 years, 0.82 at 3 years, and 0.81 at 5 years. Risk stratification showed clear separation: 2-year HECV incidence ranged from 20.4% (lowest tertile) to 50.0% (highest); 5-year risk from 87.0% to 98.1%.
Conclusion:
Routinely collected EHR features, combined with external heat metrics, can identify patients with elevated HECV and support proactive clinical or public-health responses. Computational phenotyping of HECV produced a discriminative, scalable risk tool with strong time-dependent AUCs, enabling identification of heat-vulnerable patients prior to event onset.
More Related Videos
08:22In vitro Assessment of Myocardial Protection following Hypothermia-Preconditioning in a Human Cardiac Myocytes Model
Published on: October 27, 2020
10:21Evaluation of Hydration Status by Bioelectrical Impedance Vector Analysis in Patients with Ischemic Heart Disease Undergoing Exercise Stress Test
Published on: September 22, 2023
Related Concept Videos
01:20Exercise and Cardiovascular Response
Light to moderate physical activity initiates a series of interconnected responses in the body. The heart rate modestly increases in anticipation of the workout, followed by widespread vasodilation as oxygen consumption by skeletal muscles increases. This results in decreased peripheral resistance, increased capillary blood flow, and accelerated...
02:45Responses to Heat and Cold Stress
01:19Homeostatic Imbalances in Body Temperature
01:27Psychoneuroimmunology: Cardiovascular Disease
A key area of focus in PNI is the relationship between stress and coronary...
01:26Requirements for Human Life
Oxygen
Atmospheric air is only about 20 percent oxygen, but that oxygen is a key component of the chemical reactions that keep the body alive, including the reactions that produce ATP. Brain cells are susceptible to a lack of oxygen because they require a...
01:30Factors Influencing Heart Rate
Let us explore the significant factors affecting heart rate, including age, body temperature, posture, acute pain, chemical influences,...