Metraipolis › archive › dc_e69ebfea1f15
An Offline Smartphone Check for Drug Interactions and Past Reactions in Handwritten Prescriptions: A Technical Feasibility Study in Rural Bangladeshi Outpatient Care — arXiv:2608.27239
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27239
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:07:53.948Z
- SHA-256 of the archived text
e77fa603668d89cd4f51e3b0a390030e88842c44bf0f69c144954f46a6ae099f- Stable URL of this page
https://metraipolis.com/documento/dc_e69ebfea1f15
How to cite
An Offline Smartphone Check for Drug Interactions and Past Reactions in Handwritten Prescriptions: A Technical Feasibility Study in Rural Bangladeshi Outpatient Care — arXiv:2608.27239 — arXiv (en), https://arxiv.org/abs/2608.27239 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e69ebfea1f15 (Metraipolis archive dc_e69ebfea1f15, sha256 e77fa603668d89cd4f51e3b0a390030e88842c44bf0f69c144954f46a6ae099f)
BibTeX
@misc{dce69ebfea1f15,
title = {An Offline Smartphone Check for Drug Interactions and Past Reactions in Handwritten Prescriptions: A Technical Feasibility Study in Rural Bangladeshi Outpatient Care — arXiv:2608.27239},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27239},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e69ebfea1f15; sha256 e77fa603668d89cd4f51e3b0a390030e88842c44bf0f69c144954f46a6ae099f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27239. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Rural Bangladeshi outpatient clinics keep no patient records, prescriptions are handwritten, and physicians have under a minute per patient, so they easily miss a known adverse drug reaction (ADR) or drug-drug interaction (DDI). We built and evaluated an offline Android application that photographs a handwritten prescription, detects and reads each medicine line, resolves brand names to active ingredients, and retrieves, but never predicts, documented interactions and the patient's recorded reactions. This quantitative technical-feasibility study, with qualitative error analysis, involved no patients or clinicians. Reference data combine two Bangladeshi drug registries (27,880 brands) with 190,421 DDI pairs. A YOLOv8n line detector reached [email protected] = 0.687 on held-out prescriptions but recalled only 60.6% of lines at the deployed cutoff. On-device ML Kit read 11.8% of 780 benchmark handwritten words exactly. We trained a CRNN-CTC reader on public handwriting data, decoded it against the brand lexicon, and fine-tuned it on 660 author-labelled prescription crops. On benchmark words, the reader accepted the correct ingredient for 41.5% and a wrong one for 4.2%, versus 21.0% and 5.3% for ML Kit at its preset cutoff (McNemar p<10^-20). On scorable lines from held-out real prescriptions, the reader accepted the correct ingredient for 36.0% [26.8, 46.3] and a wrong one for 2.2% [0.6, 7.8]. In 62 simulated runs on a mid-range phone, median time per patient was 26-31 s and 59 of 62 runs finished within 60 s, but 62% of medicine lines still needed a manual check. A cross-visit medication history added after the evaluation passed seven automated tests and one two-visit functional test but was not evaluated. The pipeline is feasible within the clinic workflow; reading handwriting, not retrieval, is the bottleneck. Nothing here demonstrates a clinical benefit. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.27239 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T15:31:59.887Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).