DEVELOPING AI CHATBOT FOR ANSWERING QUESTIONS ON CROSS-REACTIVITY OF BETA-LACTAM ANTIBIOTICS
DOI:
https://doi.org/10.69598/tbps.22.1.61-79Keywords:
chatbot, cross-reactivity, beta-lactam antibioticsAbstract
Cross-reactivity among beta-lactam antibiotics is an important concern affecting patient safety and appropriate antibiotic selection. This study aimed to develop and evaluate an artificial intelligence (AI) chatbot for answering questions regarding cross-reactivity among beta-lactam antibiotics. The study consisted of two phases: 1) system development based on the System Development Life Cycle (SDLC), including the development of a knowledge base through a literature review and the development of the chatbot using Google Sheets, Dialogflow, and the LINE application; and 2) system evaluation, including assessment of the chatbot’s response accuracy using simulated scenarios and evaluation of its quality and user satisfaction by seven expert pharmacists. The chatbot achieved an overall response accuracy of 98.57%. The overall quality and satisfaction score was rated at a high level (4.22±0.39). Response speed received the highest score (4.86±0.38), followed by the provision of information supported by scientific evidence (4.71±0.49). The ability to begin using the chatbot without instructions received the lowest score (3.57±0.79), although it remained at a high level. The experts indicated that the chatbot could reduce information-searching time, increase confidence in medication selection, and reduce the risk of inappropriate medication use. The inclusion of chemical structure information, clinical evidence, and illustrations also facilitated understanding and supported clinical decision-making. In conclusion, the developed AI chatbot demonstrated high response accuracy and a high level of usability quality. It has the potential to serve as an information retrieval tool for beta-lactam antibiotic cross-reactivity and to support healthcare professionals in clinical decision-making.
References
Ningsanond T, Yothapitak C. Focus on adverse drug reaction. Bangkok: Thai Association of Hospital Pharmacists; 2009. (in Thai)
Warrington R, Silviu-Dan F. Drug allergy. Allergy Asthma Clin Immunol. 2011;7(1):S10.
Khan DA, Solensky R. Drug allergy. J Allergy Clin Immunol. 2010;125(2 Suppl 2):S126-37.
Hunziker T, Künzi UP, Braunschweig S, Zehnder D, Hoigné R. Comprehensive hospital drug monitoring (CHDM): Adverse skin reactions, a 20-year survey. Allergy. 1997;52(4):388-93.
Health Product Vigilance Center. Statistics of AE 1984-2022 [Internet]. Strategy and Planning Division, Food and Drug Administration; 2023 [cited 2024 Jul 6]. Available from: https://catalog.fda.moph.go.th/dataset/f455cba1-ead0-40a3-b78b-f20c378c6c53/resource/e85eae3a-f84a-4085-af73-56280f7ac584/download/-ae-1984-2022-1.pdf
Caruso C, Valluzzi RL, Colantuono S, Gaeta F, Romano A. β-lactam allergy and cross-reactivity: A clinician's guide to selecting an alternative antibiotic. J Asthma Allergy. 2021;14:31-46.
Romano A, Atanaskovic-Markovic M, Barbaud A, Bircher AJ, Brockow K, Caubet J-C, et al. Towards a more precise diagnosis of hypersensitivity to beta-lactams — An EAACI position paper. Allergy. 2020;75(6):1300-15.
Collins CD, Scheidel C, Anam K, Polega S, Malani AN, Hayward A, et al. Impact of an antibiotic side-chain-based cross-reactivity chart combined with enhanced allergy assessment processes for surgical prophylaxis antimicrobials in patients with β-lactam allergies. Clin Infect Dis. 2020;72(8):1404-12.
Suriyaamporn P, Sila-on W, Kansom T, Opanasopit P. The application of artificial intelligence in pharmaceutical technology and advancements in the pharmaceutical industry 4.0. Thai Bull Pharm Sci. 2025;20(1):17-36. (in Thai)
Suntharapot S, Sribundit N. Effectiveness of text messaging via application LINE on adherence to antiretroviral drug among HIV and AIDS patients in Khaoyoi hospital Phetchaburi. Thai Bull Pharm Sci. 2022;17(2):83-99. (in Thai)
Hadsoong W, Pamonsinlapatham P. LINE chatbot for cosmetic advertising information using Dialogflow and Google Sheets. Thai Bull Pharm Sci. 2025;20(2):145-59. (in Thai)
Pamonsinlapatham K. "Miss Clinic" AI chatbot assistant for answering questions and inquiries of medical facility operators in Nakhon Pathom province. Thai Bull Pharm Sci. 2026;21(1):111-24. (in Thai)
Sareekhajohnjaru K, Lochidamnuay S. Knowledge, opinions, legal enforcement, and factors related to legal enforcement of Medical Facilities Act among regulatory officers in provincial health offices. Thai Bull Pharm Sci. 2025;21(1):19-45. (in Thai)
Boonchuaichoo J, Klunsakul K, Teeraworakul P, Udomvatjanasak S. Information on beta-lactam antibiotic cross-reactivity for drug information services [special project report]. Nakhon Pathom: Silpakorn University; 2024.
Maroengsit W, Piyakulpinyo T, Phonyiam K, Pongnumkul S, Chaovalit P, Theeramunkong T. A survey on evaluation methods for chatbots. In: Proceedings of the 2019 11th International Conference on Machine Learning and Computing; 2019 Feb 22-24; Zhuhai, China. New York: Association for Computing Machinery; 2019. p. 111-9.
Al-Latayfeh M, Aleshawi A, El-Mulki OS, Baker M, Qaddoumi Z, Attar D, et al. Accuracy and reproducibility of different artificial intelligence chatbots' responses to patient-based vitreoretinal questions: A comparative study. Clin Ophthalmol. 2026;20:580133.
Topattanakul A, Phornprapa N, Sratthaphut L. AI chatbot development for answering high-alert drug injection compatibility questions in drug information services. In: Proceedings of the 15th NPRU National Academic Conference; 2023; Nakhon Pathom, Thailand: Nakhon Pathom Rajabhat University; 2023. p. 1879-90
Samanmit P. The development of AI chatbot as inquiry tool for interactions between herbs and cytochrome P450 [Dissertation]. Nakhon Pathom: Silpakorn University; 2024.
Phonphotthanamat W. A comparative study of verifying the content validity of a research instrument with the IOC CVR and CVI. RSU Libr J. 2022;28(1):169-92. (in Thai)
Jabjone S, Lowanichai S, Puttasimma T, Jongmuanwai B. Developing media of chatbot online learning for elderly. J Technol Manag Rajabhat Maha Sarakham Univ. 2020;7(2):47-58. (in Thai)
Ren R, Castro JW, Acuña ST, de Lara J. Evaluation techniques for chatbot usability: A systematic mapping study. Int J Softw Eng Knowl Eng. 2019;29(11n12):1673-702.
Rattanaphanit N, Sratthaphut L, Phornprapa N. Development of AI chatbot for answering medical cannabis questions. Thai J Hosp Pharm. 2025;35(2):147-59. (in Thai)
Comendador BE, Francisco B, Medenilla J, Nacion S, Serac T. Pharmabot: A pediatric generic medicine consultant chatbot. J Autom Control Eng. 2015;3:137-40.
Fang KY, Bjering H. Development of an interactive messenger chatbot for medication and health supplement reminders. In: Proceedings of the 36th National Conference: Health Information Management — Celebrating 70 Years of Strength in Diversity; 2019; Melbourne, Australia. Melbourne: Health information management association of Australia; 2019.
Laymouna MA. Informing the development of a chatbot for pharmacist needs in HIV care [dissertation]. Montreal: McGill University; 2023.
Downloads
Published
How to Cite
Issue
Section
License
All articles published and information contained in this journal such as text, graphics, logos and images is copyrighted by and proprietary to the Thai Bulletin of Pharmaceutical Sciences, and may not be reproduced in whole or in part by persons, organizations, or corporations other than the Thai Bulletin of Pharmaceutical Sciences and the authors without prior written permission.
