international journal of medical informatics 77 ( 2 0 0 8 ) 421–430 journal homepage: www.intl.elsevierhealth.com/journals/ijmi A quantitative approach of using genetic algorithm in designing a probability scoring system of an adverse drug reaction assessment system Yvonne Koh a , Chun Wei Yap a , Shu Chuen Li a,b,* a Department of Pharmacy, National University of Singapore, Republic of Singapore b Discipline of Pharmacy & Experimental Pharmacology, School of Biomedical Science, University of Newcastle, Australia article info Article history: Received 10 January 2007 Received in revised form 3 June 2007 Accepted 19 August 2007 Keywords: ADR causality Genetic algorithm ADR assessment Probability scoring system abstract Background: The detrimental effects of adverse drug reactions (ADRs) are well established. Hence, precise and accurate assessment of ADRs’ causality which can differentiate signal from noise is crucial in screening, management and minimisation of ADRs. Objective: The current study reported our attempt to improve the scoring system of a pre- viously published algorithm of ADR assessment by our group using a genetic algorithm approach so that the final score can measure the probability of ADR causality. Design: Using ADR cases obtained from the Centre for Drug Administration, the national cen- tre for pharmacovigilance in Singapore, with known causality probability values as reference points, rules were developed to define possible combinations of criteria for ‘Definite’ ADR cases and ‘Probable’ ADR cases. A new scoring system was developed using these param- eters with the help of genetic algorithm, and tested on 37 ‘Definite’ and 431 ‘Not Definite’ ADR cases. In addition, sensitivity and specificity analysis were performed to allow a com- parison of performance between our algorithm and that used by the Adverse Drug Reaction Advisory Committee in Australia (ADRAC). Results: The new scoring system is able to provide a probability of the causality of an ADR by a suspected drug. When applied to the ‘Definite’ and ‘Not Definite’ ADR reports, the new algorithm gave a sensitivity of 83.8% and specificity of 71.0%. Conclusions: Using a quantitative method of assessing causality in the new algorithm allows rare and new ADRs to be more readily identified since a quantitative score can give a more precise degree of ADR causality. This scoring system that provides a probability score would help to make this algorithm more informative and assistive for clinicians, regulatory agencies or pharmaceutical companies to generate ADR alerts. The higher sensitivity value displayed by our algorithm also shows that it would be a good ADR screening tool. © 2007 Elsevier Ireland Ltd. All rights reserved. 1. Introduction The detrimental effects of adverse drug reactions (ADRs) con- tributing to major problems like morbidity, mortality and high ∗ Corresponding author at: Discipline of Pharmacy & Experimental Pharmacology, School of Biomedical Science, University of Newcastle, Callaghan, NSW 2308, Australia. Tel.: +61 2 49215921; fax: +61 2 49212044. E-mail address: Shuchuen.li@newcastle.edu.au (S.C. Li). cost of patient care are well established [1–4]. In order to effec- tively manage and minimize ADRs, more precise and accurate assessment of the causality of the ADRs as well as predic- tors for likely occurrence of ADRs are needed. In the former 1386-5056/$ – see front matter © 2007 Elsevier Ireland Ltd. All rights reserved. doi:10.1016/j.ijmedinf.2007.08.010