{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T19:00:24Z","timestamp":1790103624903,"version":"4.0.1"},"reference-count":23,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"38","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Innovation and Development of the Provincial Natural Science Foundation","award":["ZR2023LSW022"],"award-info":[{"award-number":["ZR2023LSW022"]}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9,18]]},"abstract":"<jats:sec>\n                    <jats:title\/>\n                    <jats:p>This study aimed to construct an intelligent prescription review system for inpatient narcotic and psychotropic drugs based on deep learning-based optical character recognition (OCR) and a local large language model (LLM) and evaluate its review performance and closed-loop management value. This study adopted a combined system development and retrospective validation design. Prescription images were first processed using OCR for text recognition and layout reconstruction. A local LLM was then applied to convert unstructured prescription text into standardized JavaScript Object Notation-formatted data. Subsequently, a locally developed rule base for narcotic and psychotropic drugs was used to evaluate prescription completeness, diagnosis-based dosage limits, medication instructions, physician signatures, and residual drug handling for injectable formulations. Using pharmacists\u2019 manual review results as the reference standard, 500 inpatient prescriptions for narcotic and psychotropic drugs were retrospectively included. System performance was evaluated in terms of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and Cohen\u2019s kappa coefficient. The system successfully implemented prescription image recognition, text structuring, rule-based validation, signature verification, residual drug calculation, and triggers for manual pharmacist review. In the retrospective validation, compared with pharmacists\u2019 manual review, the system identified 144 true positives, 16 false positives, 334 true negatives, and 6 false negatives. The overall accuracy was 95.6%, sensitivity was 96.0%, specificity was 95.4%, positive predictive value was 90.0%, negative predictive value was 98.2%, F1 score was 0.929, and Cohen\u2019s kappa coefficient was 0.897. The proposed OCR-LLM-based intelligent prescription review system for inpatient narcotic and psychotropic drugs demonstrates high accuracy and strong consistency. It can serve as a front-end screening and decision-support tool for pharmacists and provides technical support for standardized, traceable, and closed-loop management of specially controlled medications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/md.0000000000050741","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T17:01:26Z","timestamp":1789750886000},"page":"e50741","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["An intelligent OCR-LLM prescription review system for inpatient narcotic and psychotropic drugs"],"prefix":"10.1097","volume":"105","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6415-739X","authenticated-orcid":false,"given":"Rong","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Pharmacy, Affiliated Qingdao Third People\u2019s Hospital, Qingdao University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Information, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Information, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingrong","family":"Ma","sequence":"additional","affiliation":[{"name":"Purchasing Center, Jinan Maternity and Child Care Hospital, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Qingdao Central Hospital of Rehabilitation University, Qingdao, Shandong, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1334-6209","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260922","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1111\/jcpt.12389","article-title":"A systematic review of the prevalence and incidence of prescribing errors with high-risk medicines in hospitals.","volume":"41","author":"Alanazi","year":"2016","journal-title":"J Clin Pharm Ther"},{"key":"R2-20260922","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1111\/jan.14322","article-title":"Medication errors in prescription and administration in critically ill patients.","volume":"76","author":"Suclupe","year":"2020","journal-title":"J Adv Nurs"},{"key":"R3-20260922","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.jpain.2008.08.004","article-title":"Assessing controlled substance prescribing errors in a pediatric teaching hospital: an analysis of the safety of analgesic prescription practice in the transition from the hospital to home.","volume":"10","author":"Lee","year":"2009","journal-title":"J Pain"},{"key":"R4-20260922","doi-asserted-by":"crossref","first-page":"104703","DOI":"10.1016\/j.ijmedinf.2022.104703","article-title":"Comprehensive evaluation of using computerised provider order-entry system for hospital discharge orders.","volume":"160","author":"Colombini","year":"2022","journal-title":"Int J Med Inform"},{"key":"R5-20260922","doi-asserted-by":"crossref","first-page":"379","DOI":"10.2165\/00002018-200932050-00002","article-title":"Prevalence, incidence and nature of prescribing errors in hospital inpatients: a systematic review.","volume":"32","author":"Lewis","year":"2009","journal-title":"Drug Saf"},{"key":"R6-20260922","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1186\/s12913-023-09346-2","article-title":"Effect of improvement measures in reducing interruptions in a Japanese hospital pharmacy using a synthetic approach based on resilience engineering and systems thinking.","volume":"23","author":"Kojima","year":"2023","journal-title":"BMC Health Serv Res"},{"key":"R7-20260922","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1016\/j.sapharm.2025.05.001","article-title":"How do interruptions and distractions affect pharmacy practice? A scoping review of their impact and interventions in dispensing.","volume":"21","author":"Ayanaw","year":"2025","journal-title":"Res Social Adm Pharm"},{"key":"R8-20260922","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1007\/s10032-025-00543-9","article-title":"Tabular context-aware optical character recognition and tabular data reconstruction for historical records.","volume":"28","author":"Singh","year":"2025","journal-title":"Int J Doc Anal Recognit"},{"key":"R9-20260922","doi-asserted-by":"crossref","first-page":"3039","DOI":"10.3390\/diagnostics15233039","article-title":"Enhancing medical diagnosis document analysis with layout-aware multitask models.","volume":"15","author":"Tu","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"R10-20260922","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1136\/bmjqs-2014-003555","article-title":"Computerised physician order entry-related medication errors: analysis of reported errors and vulnerability testing of current systems.","volume":"24","author":"Schiff","year":"2015","journal-title":"BMJ Qual Saf"},{"key":"R11-20260922","doi-asserted-by":"crossref","first-page":"e0167683","DOI":"10.1371\/journal.pone.0167683","article-title":"The effects of clinical decision support systems on medication safety: an overview.","volume":"11","author":"Jia","year":"2016","journal-title":"PLoS One"},{"key":"R12-20260922","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/2046-4053-3-56","article-title":"The effectiveness of computerized order entry at reducing preventable adverse drug events and medication errors in hospital settings: a systematic review and meta-analysis.","volume":"3","author":"Nuckols","year":"2014","journal-title":"Syst Rev"},{"key":"R13-20260922","doi-asserted-by":"crossref","first-page":"14604582241263242","DOI":"10.1177\/14604582241263242","article-title":"Override rate of drug-drug interaction alerts in clinical decision support systems: a brief systematic review and meta-analysis.","volume":"30","author":"Felisberto","year":"2024","journal-title":"Health Informatics J"},{"key":"R14-20260922","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1093\/jamia\/ocaf139","article-title":"Effect of electronic drug-drug interaction alerts on patient and clinician outcomes: a systematic review.","volume":"32","author":"Holbrook","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"R15-20260922","doi-asserted-by":"crossref","first-page":"ooac045","DOI":"10.1093\/jamiaopen\/ooac045","article-title":"Deep learning-based NLP data pipeline for EHR-scanned document information extraction.","volume":"5","author":"Hsu","year":"2022","journal-title":"JAMIA Open"},{"key":"R16-20260922","doi-asserted-by":"crossref","first-page":"102323","DOI":"10.1016\/j.xcrm.2025.102323","article-title":"Large language model as clinical decision support system augments medication safety in 16 clinical specialties.","volume":"6","author":"Ong","year":"2025","journal-title":"Cell Rep Med"},{"key":"R17-20260922","doi-asserted-by":"crossref","first-page":"bbad493","DOI":"10.1093\/bib\/bbad493","article-title":"Opportunities and challenges for ChatGPT and large language models in biomedicine and health.","volume":"25","author":"Tian","year":"2023","journal-title":"Brief Bioinform"},{"key":"R18-20260922","doi-asserted-by":"crossref","first-page":"900543","DOI":"10.3389\/fmed.2022.900543","article-title":"Rethinking clinical decision-making to improve clinical reasoning.","volume":"9","author":"Corrao","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"R19-20260922","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1093\/jamia\/ocae074","article-title":"Large language models for biomedicine: foundations, opportunities, challenges, and best practices.","volume":"31","author":"Sahoo","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"R20-20260922","doi-asserted-by":"crossref","first-page":"5910","DOI":"10.1038\/s41598-026-36904-5","article-title":"Bridging the performance gap: systematic optimization of local LLMs for Japanese medical PHI extraction.","volume":"16","author":"Wada","year":"2026","journal-title":"Sci Rep"},{"key":"R22-20260922","doi-asserted-by":"crossref","first-page":"14604582211007536","DOI":"10.1177\/14604582211007536","article-title":"The appropriateness of clinical decision support systems alerts in supporting clinical workflows: a systematic review.","volume":"27","author":"Olakotan","year":"2021","journal-title":"Health Informatics J"},{"key":"R23-20260922","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1093\/jamia\/ocaf008","article-title":"Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines.","volume":"32","author":"Liu","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"R24-20260922","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI.","volume":"28","author":"Vasey","year":"2022","journal-title":"Nat Med"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000050741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T18:02:51Z","timestamp":1790100171000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000050741"}},"subtitle":["Development and retrospective validation"],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":23,"journal-issue":{"issue":"38","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000050741","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"assertion":[{"value":"2026-05-29","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-01","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}