Exploring data-driven algorithms to identify Lyme disease cases in electronic health records
Alexandra M Linz, Erica Scotty, Jennifer K Meece, Courtney C Nawrocki, Kiersten J Kugeler, Sarah A Hook, Alison F Hinckley, Anna M Schotthoefer · 2026
Read Exploring data-driven algorithms to identify Lyme disease cases in electronic health records by Alexandra M Linz, Erica Scotty, Jennifer K Meece, Courtney C Nawrocki, Kiersten J Kugeler, Sarah A Hook, Alison F Hinckley, Anna M Schotthoefer (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0349121.txt.
Description
Alexandra Linz and co-authors built data-driven rules to find Lyme disease cases inside electronic health records. In regions where Lyme is common, fast and accurate case finding would serve clinics and researchers alike. Their 2026 study used records from one health system and tested algorithms built only from structured, easily pulled fields.
Diagnosis codes, laboratory orders and results, demographics, and antibiotic orders all carried signal. A hand-built decision tree performed best. It required a Lyme code, a positive antibody test, and a doxycycline order close in time, in combination. That rule reached solid accuracy with high sensitivity. Linz and colleagues say such simple logic could anchor automated surveillance after wider testing.
Catalog record
| CREATOR | Alexandra M Linz, Erica Scotty, Jennifer K Meece, Courtney C Nawrocki, Kiersten J Kugeler, Sarah A Hook, Alison F Hinckley, Anna M Schotthoefer |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43594 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |