Format

Send to

Choose Destination
See comment in PubMed Commons below
Int J Med Inform. 2017 Dec;108:169-174. doi: 10.1016/j.ijmedinf.2017.08.003. Epub 2017 Aug 26.

The value of EHR-based assessment of physician competency: An investigative effort with internal medicine physicians.

Author information

1
Design Interactive, 3504 Lake Lynda Drive Suite 400, Orlando, FL, 32817, United States.
2
Design Interactive, 3504 Lake Lynda Drive Suite 400, Orlando, FL, 32817, United States. Electronic address: erin.baker@designinteractive.net.

Abstract

OBJECTIVE:

The purpose of this study was to investigate the potential of developing an EHR-based model of physician competency, named the Skill Deficiency Evaluation Toolkit for Eliminating Competency-loss Trends (Skill-DETECT), which presents the opportunity to use EHR-based models to inform selection of Continued Medical Education (CME) opportunities specifically targeted at maintaining proficiency.

METHODS:

The IBM Explorys platform provided outpatient Electronic Health Records (EHRs) representing 76 physicians with over 5000 patients combined. These data were used to develop the Skill-DETECT model, a predictive hybrid model composed of a rule-based model, logistic regression model, and a thresholding model, which predicts cognitive clinical skill deficiencies in internal medicine physicians. A three-phase approach was then used to statistically validate the model performance.

RESULTS:

Subject Matter Expert (SME) panel reviews resulted in a 100% overall approval rate of the rule based model. Area under the receiver-operating characteristic curves calculated for each logistic regression curve resulted in values between 0.76 and 0.92, which indicated exceptional performance. Normality, skewness, and kurtosis were determined and confirmed that the distribution of values output from the thresholding model were unimodal and peaked, which confirmed effectiveness and generalizability.

CONCLUSIONS:

The validation has confirmed that the Skill-DETECT model has a strong ability to evaluate EHR data and support the identification of internal medicine cognitive clinical skills that are deficient or are of higher likelihood of becoming deficient and thus require remediation, which will allow both physician and medical organizations to fine tune training efforts.

KEYWORDS:

Electronic health records; Physician competency; Predictive modeling; Quality of patient care; Standards of care

PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center