<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Development and validation of an artificial intelligence proof-of-concept tool for risk-based quality assessment of generic medicines: a South African case study

dc.contributor.authorLorraine Danks
dc.contributor.authorBoitumelo Semete-Makokotlela
dc.contributor.authorChristelna Reynecke
dc.contributor.authorSeima Dijeng
dc.contributor.authorBathusi Kgosietsile
dc.contributor.authorJapie van Tonder
dc.contributor.authorCornelia van Graan
dc.contributor.authorJason Hinch
dc.contributor.authorAdriaan Kruger
dc.contributor.authorStuart Walker
dc.contributor.authorSam Salek
dc.date.accessioned2026-11-18T07:11:38Z
dc.date.issued2026
dc.descriptionOfficial PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution. Rights classification: FULL_TEXT_OK. Licence verified from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13250854/ (checked 2026-11-18). Source: South African Health Products Regulatory Authority (SAHPRA), Pretoria, South Africa; Botswana Medicines Regulatory Authority (BoMRA), Gaborone, Botswana; Scigenix (Pty) Ltd., Pretoria, South Africa; nuvoteQ (Pty) Ltd., Pretoria, South Africa African relevance: Sector: Manufacturing. SAHPRA, BoMRA and South African firms develop and validate LEXI, a RAG/LLM tool for pharmaceutical manufacturing-quality dossier triage in African regulators. Official PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution.
dc.description.abstractIntroductionRegulatory authorities in African countries face persistent challenges in ensuring the timely authorization of quality generic medicines due to limited technical capacity and extensive review timelines. The South African medicines regulator (SAHPRA) piloted a risk-based assessment (RBA) framework to expedite the Chemistry, Manufacturing, and Controls (CMC) evaluation of generic medicines. Building on this initiative, an artificial intelligence (AI)-driven tool, termed LEXI, was developed and validated to automate SAHPRA’s RBA triage for generic medicines and was externally validated at two African NRAs.MethodsLEXI was designed based on SAHPRA’s established RBA quality matrix, using 210 of its product dossiers, and was validated under the Good Automated Manufacturing Practice (GAMP5) framework. The system employed Retrieval-Augmented Generation (RAG) architecture with Meta’s Llama 3.1 large language model, supported by regulatory data integrations from the European Directorate for the Quality of Medicines (EDQM) and the World Health Organization Prequalification Programme. Validation comprised three qualification phases—installation (IQ), operational (OQ), and performance (PQ)—and was conducted across two African national regulatory authorities (NRAs): SAHPRA and the Botswana Medicines Regulatory Authority (BoMRA).ResultsDuring external validation across 60 dossiers, LEXI demonstrated 91.7% overall predictive accuracy (55/60; 95% CI: 81.6-97.2%), with sensitivity of 96.9% (31/32; 95% CI: 83.8-99.9%) and specificity of 85.7% (24/28; 95% CI: 67.3-96.0%), with a median 91% time reduction; performance varied by criterion and dossier structure. Criterion-level accuracy exceeded 95% for most critical quality attributes (CQAs). Adaptations allowed for effective oper
dc.format.mimetypeapplication/pdf
dc.identifier.doi10.3389/fmed.2026.1811333
dc.identifier.urihttps://doi.org/10.3389/fmed.2026.1811333
dc.identifier.urihttps://library.dare.co.zw/handle/123456789/5108
dc.language.isoen
dc.publisherFrontiers Media SA
dc.rightsCC BY 4.0. Licence evidence: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13250854/
dc.rights.holderNamed authors
dc.rights.licenseCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceSouth African Health Products Regulatory Authority (SAHPRA), Pretoria, South Africa; Botswana Medicines Regulatory Authority (BoMRA), Gaborone, Botswana; Scigenix (Pty) Ltd., Pretoria, South Africa; nuvoteQ (Pty) Ltd., Pretoria, South Africa
dc.source.urihttps://doi.org/10.3389/fmed.2026.1811333
dc.subjectManufacturing
dc.subjectartificial intelligence
dc.subjectBoMRA
dc.subjectgeneric medicines
dc.subjectLlama 3.1
dc.subjectlow- and middle-income countries
dc.subjectrisk-based assessment
dc.subjectSAHPRA
dc.subjectuniversal health coverage
dc.subjectFrontiers in Medicine
dc.titleDevelopment and validation of an artificial intelligence proof-of-concept tool for risk-based quality assessment of generic medicines: a South African case study
dc.typejournal article

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
applied_manufacturing_10_3389_fmed_2026_1811333.pdf
Size:
7.76 MB
Format:
Adobe Portable Document Format