Comparing Population-based Risk-stratification Model Performance Using Demographic, Diagnosis and Medication Data Extracted From Outpatient Electronic Health Records Versus Administrative Claims

Abstract

The results show a promising performance of models predicting cost and hospitalization using outpatient EHR's diagnosis and medication data. More research is needed to evaluate the benefits of other EHR data types (eg, lab values and vital signs) for risk stratification.

Development and validation of algorithms to classify type 1 and 2 diabetes according to age at diagnosis using electronic health records

“…Although socioeconomic status variables were not captured in our databases, other baseline characteristics were highly similar between the HKDR and HKDSD, supporting the generalizability of our algorithms. Research platforms such as the HA's Data Collaboration Lab should allow more comprehensive use of EHR data to improve diabetes classification using more complex methodologies and to enhance population research [32][33][34].…”

Comparing clinician descriptions of frailty and geriatric syndromes using electronic health records: a retrospective cohort study

“…Although initial work focused on frailty as a physical syndrome related to muscle breakdown and weakness, more recently concepts like cognitive impairment and social factors have been incorporated into frailty definitions [ 22 ]. Our NLP algorithm was particularly valuable in this context as social factors are poorly coded in the structured fields [ 17 , 23 ].…”

“…Clinical notes included documentation from the following settings: outpatient visits, home-care/nursing visits, emergency room visits, discharge summaries, and patient e-mails and phone calls. Inpatient hospitalization records were represented incompletely in the outpatient EHR data, thus were removed to reduce potential data quality biases [ 16 , 17 ].…”

Uptake of 13-Valent Pneumococcal Conjugate Vaccine among US Adults Aged 19 to 64 Years with Immunocompromising Conditions

“…We also observed higher attrition in the claims cohort with requirement of four years of continuous enrollment (or until the end of the year the individual turned age 64), which raised the possibility that we may have selected a healthier or more stable cohort amongst the highrisk patients; however, sensitivity analysis not requiring the full four years of enrollment or follow up also suggested higher PCV13 uptake in the EHR cohort. In addition, while the potential gaps and challenges with reliability of coding in EHR vs. claims have been explored in the context of risk stratification, 14 the prevalence of most high-risk conditions largely defined by presence of International Classification of Diseases, 9 th and 10 th revision (ICD-9 and ICD-10, respectively) diagnosis codes in our study was similar or higher in the EHR database, the proportion of high-risk patients who were considered to have iatrogenic immunosuppression was higher in claims data. Unlike the other risk factors, iatrogenic immunosuppression risk was primarily determined by a combination of select immunosuppressive medications, with physician specialties that would prescribe or administer those medications (in order to differentiate the use of agents used for cancer as well as other indications).…”