Data Analytics and Modeling for Appointment No-show in Community Health Centers

Iman Mohammadi, Huanmei Wu, Ayten Turkcan, Tammy Toscos, Bradley N. Doebbeling

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Objectives: Using predictive modeling techniques, we developed and compared appointment no-show prediction models to better understand appointment adherence in underserved populations. Methods and Materials: We collected electronic health record (EHR) data and appointment data including patient, provider and clinical visit characteristics over a 3-year period. All patient data came from an urban system of community health centers (CHCs) with 10 facilities. We sought to identify critical variables through logistic regression, artificial neural network, and naïve Bayes classifier models to predict missed appointments. We used 10-fold cross-validation to assess the models’ ability to identify patients missing their appointments. Results: Following data preprocessing and cleaning, the final dataset included 73811 unique appointments with 12,392 missed appointments. Predictors of missed appointments versus attended appointments included lead time (time between scheduling and the appointment), patient prior missed appointments, cell phone ownership, tobacco use and the number of days since last appointment. Models had a relatively high area under the curve for all 3 models (e.g., 0.86 for naïve Bayes classifier). Discussion: Patient appointment adherence varies across clinics within a healthcare system. Data analytics results demonstrate the value of existing clinical and operational data to address important operational and management issues. Conclusion: EHR data including patient and scheduling information predicted the missed appointments of underserved populations in urban CHCs. Our application of predictive modeling techniques helped prioritize the design and implementation of interventions that may improve efficiency in community health centers for more timely access to care. CHCs would benefit from investing in the technical resources needed to make these data readily available as a means to inform important operational and policy questions.

Original languageEnglish (US)
JournalJournal of Primary Care and Community Health
Volume9
DOIs
StatePublished - Nov 1 2018
Externally publishedYes

Fingerprint

Community Health Centers
Appointments and Schedules
Electronic Health Records
Vulnerable Populations
Urban Health
Cell Phones
Aptitude
Ownership
Tobacco Use
Patient Compliance

Keywords

  • access to care
  • appointment non-adherence
  • community health centers
  • electronic health records
  • predictive modeling

ASJC Scopus subject areas

  • Community and Home Care
  • Public Health, Environmental and Occupational Health

Cite this

Data Analytics and Modeling for Appointment No-show in Community Health Centers. / Mohammadi, Iman; Wu, Huanmei; Turkcan, Ayten; Toscos, Tammy; Doebbeling, Bradley N.

In: Journal of Primary Care and Community Health, Vol. 9, 01.11.2018.

Research output: Contribution to journalArticle

Mohammadi, Iman ; Wu, Huanmei ; Turkcan, Ayten ; Toscos, Tammy ; Doebbeling, Bradley N. / Data Analytics and Modeling for Appointment No-show in Community Health Centers. In: Journal of Primary Care and Community Health. 2018 ; Vol. 9.
@article{0212a071f5b847b4a4da4d311be83557,
title = "Data Analytics and Modeling for Appointment No-show in Community Health Centers",
abstract = "Objectives: Using predictive modeling techniques, we developed and compared appointment no-show prediction models to better understand appointment adherence in underserved populations. Methods and Materials: We collected electronic health record (EHR) data and appointment data including patient, provider and clinical visit characteristics over a 3-year period. All patient data came from an urban system of community health centers (CHCs) with 10 facilities. We sought to identify critical variables through logistic regression, artificial neural network, and na{\"i}ve Bayes classifier models to predict missed appointments. We used 10-fold cross-validation to assess the models’ ability to identify patients missing their appointments. Results: Following data preprocessing and cleaning, the final dataset included 73811 unique appointments with 12,392 missed appointments. Predictors of missed appointments versus attended appointments included lead time (time between scheduling and the appointment), patient prior missed appointments, cell phone ownership, tobacco use and the number of days since last appointment. Models had a relatively high area under the curve for all 3 models (e.g., 0.86 for na{\"i}ve Bayes classifier). Discussion: Patient appointment adherence varies across clinics within a healthcare system. Data analytics results demonstrate the value of existing clinical and operational data to address important operational and management issues. Conclusion: EHR data including patient and scheduling information predicted the missed appointments of underserved populations in urban CHCs. Our application of predictive modeling techniques helped prioritize the design and implementation of interventions that may improve efficiency in community health centers for more timely access to care. CHCs would benefit from investing in the technical resources needed to make these data readily available as a means to inform important operational and policy questions.",
keywords = "access to care, appointment non-adherence, community health centers, electronic health records, predictive modeling",
author = "Iman Mohammadi and Huanmei Wu and Ayten Turkcan and Tammy Toscos and Doebbeling, {Bradley N.}",
year = "2018",
month = "11",
day = "1",
doi = "10.1177/2150132718811692",
language = "English (US)",
volume = "9",
journal = "Journal of primary care & community health",
issn = "2150-1319",
publisher = "Sage Periodicals Press",

}

TY - JOUR

T1 - Data Analytics and Modeling for Appointment No-show in Community Health Centers

AU - Mohammadi, Iman

AU - Wu, Huanmei

AU - Turkcan, Ayten

AU - Toscos, Tammy

AU - Doebbeling, Bradley N.

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Objectives: Using predictive modeling techniques, we developed and compared appointment no-show prediction models to better understand appointment adherence in underserved populations. Methods and Materials: We collected electronic health record (EHR) data and appointment data including patient, provider and clinical visit characteristics over a 3-year period. All patient data came from an urban system of community health centers (CHCs) with 10 facilities. We sought to identify critical variables through logistic regression, artificial neural network, and naïve Bayes classifier models to predict missed appointments. We used 10-fold cross-validation to assess the models’ ability to identify patients missing their appointments. Results: Following data preprocessing and cleaning, the final dataset included 73811 unique appointments with 12,392 missed appointments. Predictors of missed appointments versus attended appointments included lead time (time between scheduling and the appointment), patient prior missed appointments, cell phone ownership, tobacco use and the number of days since last appointment. Models had a relatively high area under the curve for all 3 models (e.g., 0.86 for naïve Bayes classifier). Discussion: Patient appointment adherence varies across clinics within a healthcare system. Data analytics results demonstrate the value of existing clinical and operational data to address important operational and management issues. Conclusion: EHR data including patient and scheduling information predicted the missed appointments of underserved populations in urban CHCs. Our application of predictive modeling techniques helped prioritize the design and implementation of interventions that may improve efficiency in community health centers for more timely access to care. CHCs would benefit from investing in the technical resources needed to make these data readily available as a means to inform important operational and policy questions.

AB - Objectives: Using predictive modeling techniques, we developed and compared appointment no-show prediction models to better understand appointment adherence in underserved populations. Methods and Materials: We collected electronic health record (EHR) data and appointment data including patient, provider and clinical visit characteristics over a 3-year period. All patient data came from an urban system of community health centers (CHCs) with 10 facilities. We sought to identify critical variables through logistic regression, artificial neural network, and naïve Bayes classifier models to predict missed appointments. We used 10-fold cross-validation to assess the models’ ability to identify patients missing their appointments. Results: Following data preprocessing and cleaning, the final dataset included 73811 unique appointments with 12,392 missed appointments. Predictors of missed appointments versus attended appointments included lead time (time between scheduling and the appointment), patient prior missed appointments, cell phone ownership, tobacco use and the number of days since last appointment. Models had a relatively high area under the curve for all 3 models (e.g., 0.86 for naïve Bayes classifier). Discussion: Patient appointment adherence varies across clinics within a healthcare system. Data analytics results demonstrate the value of existing clinical and operational data to address important operational and management issues. Conclusion: EHR data including patient and scheduling information predicted the missed appointments of underserved populations in urban CHCs. Our application of predictive modeling techniques helped prioritize the design and implementation of interventions that may improve efficiency in community health centers for more timely access to care. CHCs would benefit from investing in the technical resources needed to make these data readily available as a means to inform important operational and policy questions.

KW - access to care

KW - appointment non-adherence

KW - community health centers

KW - electronic health records

KW - predictive modeling

UR - http://www.scopus.com/inward/record.url?scp=85056742795&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056742795&partnerID=8YFLogxK

U2 - 10.1177/2150132718811692

DO - 10.1177/2150132718811692

M3 - Article

C2 - 30451063

AN - SCOPUS:85056742795

VL - 9

JO - Journal of primary care & community health

JF - Journal of primary care & community health

SN - 2150-1319

ER -