Abstract
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Pattern mining utilizes multiple algorithms to explore objective and sometimes unexpected patterns in real world data. This technique could be applied to electronic medical records (EMRs) data mining; however, it first requires a careful clinical assessment and validation. Objective: Examine the use of pattern mining techniques on a large clinical dataset to detect treatment and medication use patterns for childhood pneumonia. Methods: We applied three pattern mining algorithms to 680,138 medication administration records from 30,512 pediatric inpatients with diagnosis of pneumonia during a six-year period at a children’s hospital in China. Patients’ ages ranged from 0-17 years; 37.5% were 0-3 months old, 86.5% were under 5 years old 60.3% were male, and 60.1% had a hospital stay of 9-15 days. We used the FP-Growth, PrefixSpan, and USpan pattern mining algorithms. The first two are more traditional methods of pattern mining and mine a complete set of frequent medication use patterns. PrefixSpan also incorporates an administration sequence. The newer USpan method considers medication utility, defined by the dose, frequency, and timing of use of the 652 individual medications in the dataset. Together, these three methods identified the top ten patterns from six age groups, forming a total of 180 distinct medication combinations. These medications encompassed the top 40 (72.0%) most frequently used medications. These patterns were then evaluated by subject matter experts to summarize five medication use and two treatment patterns. Results: We identified five medication use patterns: 1) anti-asthmatics AND expectorants AND corticosteroids; 2) antibiotics AND (anti-asthmatics OR expectorants OR corticosteroids); 3) third-generation cephalosporin antibiotics with (or followed by) traditional antibiotics; 4) antibiotics AND (medications for enteritis OR skin diseases); and 5) (anti-asthmatics OR expectorants OR corticosteroids) AND (medications for enteritis OR skin diseases). We also identified two frequent treatment patterns: 1) 42.1% of specific medication administration records were of intravenous therapy with antibiotics, diluents, and nutritional supplements; and 2) 13.1% were of various combinations of inhalation of anti-asthmatics, expectorants, and/or corticosteroids. Fleiss’ Kappa for the subject experts’ evaluation was 0.693, indicating moderate agreement. Conclusions: Utilizing a pattern mining approach, we summarized five medication use patterns and two treatment patterns. These warrant further investigation.

This publication has 32 references indexed in Scilit: