Shall we repeat? Predicting the necessity to repeat blood testing in pediatric emergency departments of laboratory tests previously performed in the community using a machine learning model
Adi Shuchami, Teddy Lazebnik, Shai Ashkenazi, Avner Herman Cohen, Yael Reichenberg, Vered Shkalim Zemer · 2026
Read Shall we repeat? Predicting the necessity to repeat blood testing in pediatric emergency departments of laboratory tests previously performed in the community using a machine learning model by Adi Shuchami, Teddy Lazebnik, Shai Ashkenazi, Avner Herman Cohen, Yael Reichenberg, Vered Shkalim Zemer (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-0352682.txt.
Description
Adi Shuchami leads a team of six asking whether emergency departments repeat blood tests that community doctors just ran, in PLOS ONE in 2026. Children often arrive at the pediatric emergency department hours after a clinic blood draw, and the tests are frequently ordered again. Using records from a nationwide Israeli health organization, the team judged each repeat against preset criteria for whether it could change care, covering blood counts, electrolytes, and an inflammation marker.
Useful repeats were rare: roughly thirteen, sixteen, and nineteen percent for the three test families respectively. The rest consumed money, time, and children's comfort without guiding decisions. A standard gradient boosting model then learned to predict, from the community results and the child's background, whether a repeat was actually necessary. The authors propose decision support at the ordering screen, sparing most children a second needle while flagging the minority whose numbers genuinely need rechecking.
Catalog record
| CREATOR | Adi Shuchami, Teddy Lazebnik, Shai Ashkenazi, Avner Herman Cohen, Yael Reichenberg, Vered Shkalim Zemer |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34319 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |