A case study was done to see if EMRs could be used to help determine patients in need of celiac disease testing

• Using Natural Language Processing (NLP) EMRs were searched for 16 free text and related terms in 216 celiac disease patients and 280 controls
• They also searched the EMRs for ICD9 (International Classification of Disease) codes that suggest an increased risk of celiac disease in 202 patients with celiac disease and 524 controls
• For each approach, the optimal number of hits was determined to be assigned as celiac disease
• Results: “Using two hits as the cut-off, the NLP algorithm identified 72.9% of all celiac patients (sensitivity), and ruled out CD in 89.9% of the controls”
• “In a representative US population of individuals without a prior celiac diagnosis (assuming that 0.6% had undiagnosed CD), this NLP algorithm could identify a group of individuals where 4.2% would have CD (positive predictive value). ICD9 code search using three hits as the cut-off had a sensitivity of 17.1% and a specificity of 88.5% (positive predictive value was 0.9%)” (Ludvigsson et al., 2013).

For more information read the full article here!