Using a novel hybrid AI-based paper-to-digital pipeline for extracting patient-level clinical data from routine hospital records in Kenya: a retrospective multicentre study
Timothy Tuti, Franklin Okech, Niels Peek, Janette Karimi, Muthoni Ogolla, Cynthia Khazhenzi, Mike English · 2026
Read Using a novel hybrid AI-based paper-to-digital pipeline for extracting patient-level clinical data from routine hospital records in Kenya: a retrospective multicentre study by Timothy Tuti, Franklin Okech, Niels Peek, Janette Karimi, Muthoni Ogolla, Cynthia Khazhenzi, Mike English (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/pmc-13528387.txt.
Description
Timothy Tuti and colleagues built an AI pipeline that turns paper hospital forms into digital patient data in Kenya. Published in 2026, the retrospective multicenter study co-designed machine-readable newborn-unit forms with nurses, doctors, and records officers at eight Kenyan hospitals. Where electronic records are scarce, paper charts leave managers with thin aggregate summaries instead of patient-level data.
Pilots covered 7,118 newborn admissions, with designed forms present in over nine tenths of files. The pipeline read checkbox fields with near-perfect scores and free text with high exact accuracy and low error rates. Manual extraction time fell by half and forms needing correction fell by three fifths. The authors present a scalable bridge for settings where full electronic records remain out of reach. Readers get a field-tested digitization model with measured gains.
Catalog record
| CREATOR | Timothy Tuti, Franklin Okech, Niels Peek, Janette Karimi, Muthoni Ogolla, Cynthia Khazhenzi, Mike English |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |