Jump to content

Choose locationChoose Location
  • Sign in or Enroll
    • Open I want to choose my medical group or hospital
    • Clear my location
Change Location
Sutter Health
  • Video Visits
  • Find Doctors
  • Find Locations
  • Treatments & Services
  • Locations
  • Sign in or Enroll
    • Video Visits
    • Find Doctors
    • Find Locations
    • Treatments & Services
    • COVID-19 Resources
    • Monkeypox Resources
    • Pay a Bill
    • Symptom Checker
    • Get Care Today
    • Health & Wellness
    • Classes & Events
    • Research & Clinical Trials
    • For Patients
    • About Sutter Health
    • Giving
    • Volunteering
    • Careers
    • News
    • For Medical Professionals
    • Other Business Services
Close Search
  • Home
  • Research
  • Biostatistics
Content

Predicting need for advanced illness or palliative care in a primary care population using electronic health record data.

Description

Jung K, Sudat SEK, Kwon N, Stewart WF, Shan NH., J Biomed Inform. 92:103115., 2019 Apr 01

Investigators

Sylvia Sudat, PhD

Abstract

Timely outreach to individuals in an advanced stage of illness offers opportunities to exercise decision control over health care. Predictive models built using Electronic health record (EHR) data are being explored as a way to anticipate such need with enough lead time for patient engagement. Prior studies have focused on hospitalized patients, who typically have more data available for predicting care needs. It is unclear if prediction driven outreach is feasible in the primary care setting.

In this study, we apply predictive modeling to the primary care population of a large, regional health system and systematically examine the impact of technical choices, such as requiring a minimum number of health care encounters (data density requirements) and aggregating diagnosis codes using Clinical Classifications Software (CCS) groupings to reduce dimensionality, on model performance in terms of discrimination and positive predictive value. We assembled a cohort of 349,667 primary care patients between 65 and 90 years of age who sought care from Sutter Health between July 1, 2011 and June 30, 2014, of whom 2.1% died during the study period. EHR data comprising demographics, encounters, orders, and diagnoses for each patient from a 12 month observation window prior to the point when a prediction is made were extracted. L1 regularized logistic regression and gradient boosted tree models were fit to training data and tuned by cross validation. Model performance in predicting one year mortality was assessed using held-out test patients.

Our experiments systematically varied three factors: model type, diagnosis coding, and data density requirements. We found substantial, consistent benefit from using gradient boosting vs logistic regression (mean AUROC over all other technical choices of 84.8% vs 80.7% respectively). There was no benefit from aggregation of ICD codes into CCS code groups (mean AUROC over all other technical choices of 82.9% vs 82.6% respectively). Likewise increasing data density requirements did not affect discrimination (mean AUROC over other technical choices ranged from 82.5% to 83%). We also examine model performance as a function of lead time, which is the interval between death and when a prediction was made. In subgroup analysis by lead time, mean AUROC over all other choices ranged from 87.9% for patients who died within 0 to 3 months to 83.6% for those who died 9 to 12 months after prediction time.

Pubmed Abstract

Pubmed AbstractOpens New Window

Associated Topics

  • Aging and Longevity
  • Biostatistics
  • Health Services
  • Medical Informatics

Related Publications

A multiple-imputation "forward bridging" approach to address changes in the classification of Asian race/ethnicity on the US death certificate.

Thompson CA, Boothroyd DB, Hastings KG, Cullen MR, Palaniappan LP, Rehkopf DH.
Am J Epidemiol. 187(2):347-357. doi: 10.1093/aje/kwx215.
2018 Feb 01

Validation of clinic weights from electronic health records against standardized weight measurements in weight loss trials.

Xiao L, Lv N, Rosas LG, Au D, Ma J.
Obesity (Silver Spring). doi: 10.1002/oby.21737. [Epub ahead of print]
2017 Jan 06

Using variable importance measures from causal inference to rank risk factors of schistosomiasis infection in a rural setting in China.

Sudat SE, Carlton EJ, Seto EY, Spear RC, Hubbard AE.
Epidemiol Perspect Innov. 7:3. doi: 10.1186/1742-5573-7-3.
2010 Jul 14

Predicting all-cause risk of 30-day hospital readmission using artificial neural networks.

Jamei M, Nisnevich A, Wetchler E, Sudat S, Liu E.
PLoS One. 12(7):e0181173. doi: 10.1371/journal.pone.0181173. eCollection 2017.
2017 Jul 14

Causal inference and prediction in health studies: environmental exposures and schistosomiasis, HIV-1 genotypic susceptibility scores and virologic suppression, and risk of hospital readmission for heart failure patients.

Sudat, S.
UC Berkeley. ProQuest ID: Sudat_berkeley_0028E_12729. Merritt ID: ark:/13030/m5xw4pw5. Retrieved from https://escholarship.org/uc/item/9z03362s
2012 Jun 01
The Sutter Health Network of Care
Expertise to fit your needs
Primary Care

Check-ups, screenings and sick visits for adults and children.

Specialty Care

Expertise and advanced technologies in all areas of medicine.

Emergency Care

For serious accidents, injuries and conditions that require immediate medical care.

Urgent Care

After-hours, weekend and holiday services.

Walk-In Care

Convenient walk-in care clinics for your non-urgent health needs.

About Sutter

  • About Our Network
  • Annual Report
  • Awards
  • Community Benefit
  • Contact Us
  • News
  • Giving
  • Find Care

  • Birth Centers
  • Care Centers
  • Emergency Rooms
  • Hospitals
  • Imaging
  • Labs
  • Surgery Centers
  • Urgent Care
  • Walk-In Care
  • View All >
  • Featured Services

  • Behavioral Health
  • Cancer Services
  • Family Medicine
  • Home Health and Hospice
  • Orthopedics
  • Pediatrics
  • Pregnancy
  • Primary Care
  • Women's Health
  • View All >
  • Patient Resources

  • Accepted Health Plans
  • Classes and Events
  • Estimate Costs
  • Health and Wellness
  • Medical Records
  • Medicare Advantage
  • My Health Online
  • Pay a Bill
  • Symptom Checker
  • Our Team

  • For Employees
  • Physician Careers
  • Recruiting Events
  • Residencies and Fellowships
  • Sutter Careers
  • Vendors
  • Volunteers
    • ADA Accessibility
    • Contact
    • Privacy
    • Do Not Sell My Personal Information

    • LinkedIn Opens new window
    • YouTube Opens new window
    • Facebook Opens new window
    • Twitter Opens new window
    • Glassdoor Opens new window
    • Instagram Opens new window

    Copyright © 2022 Sutter Health. All rights reserved. Sutter Health is a registered trademark of Sutter Health ®, Reg. U.S. Patent & Trademark office.

    Cookie Policy

    We use cookies to give you the best possible user experience. By continuing to use the site, you agree to the use of cookies. Privacy Policy Cookie Preferences

    Privacy Policy Cookie Preferences