Development a Model for Drug Interaction Prediction Based on Patient State

Full Text (PDF, 722KB), PP.28-37

Views: 0 Downloads: 0


Nashwan Ahmed Al-Majmar 1,* Ayedh abdulaziz Mohsen 2 Mohammed Sharaf Al-Thulathi 3

1. Department of CS and IT, Faculty of Science, Ibb University, Department of Computers, AlJazeera University, Yemen

2. Department of CS and IT, Faculty of Science, Ibb University, Department of IT, Alqalam University,Yemen

3. Department of CS and IT, Faculty of Science,Ibb University, Yemen

* Corresponding author.


Received: 20 Apr. 2022 / Revised: 26 Jul. 2022 / Accepted: 24 Aug. 2022 / Published: 8 Dec. 2022

Index Terms

Prediction, Classification, Drug Interactions, Drug Family, Active Dose, Patient State


Drug interactions prediction is one of the health critical issues in drug producing and use. Proposing computational model for classifying and predicting interactions of drugs with high precision is a difficult problem. Medicines are classified into two classes: overlapping, non-overlapping. It was suggested an expert system for classifying and predicting interactions of drugs using various information about drugs, interference reasons and common factors between patients and active substance that causes interference, such as: effective dose of the drug, maximum dose, times of use per day and age of patients considering that only adult category selected. The proposed model can classify and predict interactions of drugs through patient's state taking into consideration that when changing one of mentioned factors, the effect of drugs will be changed and it may lead to appear new symptoms on the patients. There is a desktop application related with the mentioned model, which helps users to know drugs and drugs families and its interactions. Proposed model will be implemented in Python using following classifiers: Logistic Regression (LR), Support Vector Machine (SVM) and Neural Network (NN), which divided data according to their similarity related to the factors of occurrence of drug interference. As these techniques showed good results, NN technology is considered one of the best techniques in giving results where MLPClassifier achieved superior performance with 97.12%.

Cite This Paper

Nashwan Ahmed Al-Majmar, Ayedh Abdulaziz Mohsen, Mohammed Sharaf Al-Thulathi, "Development a Model for Drug Interaction Prediction Based on Patient State", International Journal of Intelligent Systems and Applications(IJISA), Vol.14, No.6, pp.28-37, 2022. DOI:10.5815/ijisa.2022.06.03


[1]I.H. Ahmed-Jushuf, K.W. Ah-See, S.P.Allison, M.N. Badminton, et al; British National Formulary BNF; 2010; edition 59; London; Published by BMJ Group Tavistock Square, London C1H 9JP, UKand RPS Publishing.
[2]Institute of Medicine to Make Human Mistakes: Building a Safer Health System, Report of the American Healthcare Commission, 1999 (Washington, DC) National Academy Press Oren E, Shaffer E, Golielmobt. 60 (1447-58)
[3]Bates DW, Lieb L, Collind, et al. The effect of computerized physician order insertion and team intervention on the prevention of serious drug errors, JAMA, 1998, Vol. 280 (1311-6)
[4]Tisch J, Merchia PSchmizJ, et al. Effects of the introduction of a computerized physician order on prescribing practices, Arch Trainee Med 2000, Vol. 160 (2741-7)
[5]Bates DW, Tisch JM, Lee J, et al. The Effect of Computerized Order Entry on the Prevention of Medication Errors J Am Med Inform Assoc, 1999, Vol. (pp. 313-21)
[6]Magnusd, Rodgers S, Avery AJ Physicians' Views on Computerized Drug Interaction Alerts: Questionnaire Questionnaire, J Clin Pharm Ther, 2002, Vol. 27 (. 377-82).
[8]Rashad Mohammed Murad, Drugs Interactions book, Department of Medicine and Toxics, College of Pharmacy and Dentistry, Damascus University, 2017.
[9]Maria Ashqar, M. Nidal Hussan, Drug_Foof Interactions, 2015-2016.
[10]Ayedh abdulaziz Mohsen, Muneer Alsurori, Buthiena Aldobai, Gamil Abdulaziz Mohsen, " New Approach to Medical Diagnosis Using Artificial Neural Network and Decision Tree Algorithm: Application to Dental Diseases", International Journal of Information Engineering and Electronic Business(IJIEEB), Vol.11, No.4, pp. 52-60, 2019. DOI: 10.5815/ijieeb.2019.04.06
[11]Mohsen, A. A., Alrashahy, T., Naoufel, K., & Noaman, S. (2019). Use of comparative classification techniques to build a system for diagnosing heart diseases. 2019 1st International Conference of Intelligent Computing and Engineering: Toward Intelligent Solutions for Developing and Empowering Our Societies, ICOICE 2019.
[12]Lo-Ciganic WH, Huang JL, Zhang HH, Weiss JC, Wu Y, Kwoh CK, Donohue JM, Cochran G, Gordon AJ, Malone DC, Kuza CC, Gellad WF. JAMA Netw Open. Evaluation of Machine-Learning Algorithms for Predicting Opioid Overdose Risk Among Medicare Beneficiaries with Opioid Prescriptions 2019 Mar one; 2(3): e190968. doi:10.1001/jamanetworkopen.2019.0968.
[13]Nguyen BP, Reese T, Decker S, Malone D, Boyce RD, Beyan O.Stud Health Technol Inform. Implementation of Clinical Decision Support Services to Detect Potential Drug-Drug Interaction Using Clinical Quality Language. 2019 Aug 21;264:724-728. doi: 10.3233/SHTI190318.
[14]Grizzle AJ, Horn J, Collins C, Schneider J, Malone DC, Stottlemyer B, Boyce RD "Identifying Common Methods Used by Drug Interaction Experts for Finding Evidence About Potential Drug-Drug Interactions: Web-Based Survey" J Med Internet Res 2019;21(1): e11182. DOI: 10.2196/11182; PMID: 30609981; PMCID: 6682289.
[15]A meta-learning framework using representation learning to predict drug-drug interaction, Journal of Biomedical Informatics,Department of Computer Science, Anna University, Chennai, Tamil Nadu, India, Received 14 January 2018, Revised 22 June 2018, Accepted 25 June 2018, Available online 26 June 2018.
[16]BMC Bioinformatics for Positive-Unlabeled Learning for Inferring Drug Interactions Based on Heterogeneous Attributes 2017, 18:140, DOI 10.1186/s12859-017-1546-7.
[17] Medical Expert System for Drugs Interactions for Safe and Effective Use of Drugs, Damascus University Journal Vol. (29) - No. (2) 2013.
[18]T Bertsche, J Pfaff, P Schiller, JKaltschmidt, MG Pruszydlo, W Stremmel, I Walter-Sack, WE Haefeli, J Encke. Prevention of adverse drug reactions in intensive care patients by personal intervention based on an electronic clinical decision support system. Intensive Care Medicine 2010, (Computer System Helps Reduce Adverse Drug Side Effects and Interactions in ICU Patients).
[19]ArcMesa Educators; Clinically Significant Drug Interaction with the Cytochrome P450 Enzyme System, Indiana University; 2009.
[20]I.M. Puspitasari, S. Soegijoko, et al; Development of an Integrated E-Prescription System with Adverse Drug Events Alert For Community Health Center in Indonesia, 2006.
[21]BenjamasJanchawee ibul Wongpoowarak; Development and trial of the drug interaction database system Songklanakarin J; Sci. Technol., 2003,25(4):525-534.