65 Pharmaceutical Sciences and Research (PSR), 8(2), 2021, 65 -72 ARTICLE HISTORY Received : January 2021 Revised : August 2021 Accepted : August 2021 Mini Review Article *corresponding author Email : dhadhang.kurniawan@unsoed.ac.id Artifcial Intelligence toward Personalized Medicine Muhammad Wildan Gifari 1 , Pugud Samodro 2 , Dhadhang Wahyu Kurniawan 3* 1 Department of Biomedical Engineering, Institut Teknologi Sumatera, Lampung, Indonesia 2 Faculty of Medicine, Universitas Jenderal Soedirman, Purwokerto, Central Java, Indonesia 3 Department of Pharmacy, Faculty of Health Sciences, Universitas Jenderal Soedirman, Purwokerto, Central Java, Indonesia ABSTRACT In current medical practice when a patient feels symptoms he/she would consult the doctor. The doctor then gives medication in a one-fts-all fashion. However, recent genetics studies had shown that diferent genetic makeup can results in diferent efects on medication, so the medication should be customed for every individual. The main idea of “personalized medicine” is to provide the right intervention including medication to the right patient at the right time and dose. With this approach, the medication paradigm would shift from curative to preventive. The rise of personalized medicine had been possible because the information from ever-increasing biomolecular (proteomics, genomics, and other omics) and health-related data are successfully “mined” by Artifcial Intelligence (AI) tools. In this paper, we proposed that AI systems toward personalized medicine must have acceptable performance, be readily interpretable by the clinical community, and be validated in a large cohort. We examined a few landmark papers with the keyword “AI for personalized medicine application”; 1) automatic image-based patient classifcation, 2) automatic gene-based cancer classifcation, and 3) automatic health-record heart failure with preserved ejection fraction patient phenotyping. All the examples are evaluated by their performance, interpretability, and clinical validity. From the analysis, we concluded that AI for personalized medicine could beneft by fve factors: (1) standardization and pooling of genetics and health data, nationally and internationally, (2) the use of multi-modalities data, (3) disease specialist to guide the development of AI model, (4) investigation of AI-fnding by clinical community, and (5) follow-up of AI-fnding by the large clinical trial. Keywords: artifcial intelligence; personalized medicine INTRODUCTION In current medical practice, the doctor diagnoses a pathology for patients according to symptomps and clinical test, then prescribes medication in one-fts-all fashion, without considering genetics, metabolomics, or proteomics of the patient. If the patient has side efect with the medication he is taking, then the doctor will adjust the prescription. Although efective for mass manufacturing of drugs, this medication paradigm does not consider the biomolecular “omics” of the patient. Genetic efect of drug response had been demonstrated on racially diverse children with asthma (Mak et al., 2018). Another paper reviewed the genetics efect on diabetes mellitus type 2 prognosis (Ingelsson & McCarthy, 2018). In addition to genomics, metabolomics efects had been shown to afect response of paracetamol in rats (Clayton et al., 2006). Combination of “omics” data could identify genetics diference of patients that respond to Selective Serotonin Reuptake Inhibitors (SSRIs) (Nguyen et al., 2021). These fndings that correlate genetic plus “omics” with drug response raised the question whether the medicine could be personalized. Personalized medicine is a new paradigm in which disease prognosis and medication are monitored based on genomics profle or other health-related markers in personalized way. This is diferent from evidence-based medicine in which the best medication is based on average treatment efect (Blackstone, 2019). The vision of personalized medicine is to provide right intervention to the right patient, at the right time and dose (Fröhlich et al., 2018). Because disease prognosis and progression can be linked to individual gene and biomarker, medication would shift from reactive, in which drugs and treatments are performed when the patient already showed some symptomps, toward active, in which the doctor administers drugs and treatments at the very onset of the disease, even before the expected disease shows any symptoms. A promising example is the personalized medicine for cancer prevention (Kensler et al., 2016) and bioinformatics for cancer treatment (Singer et al., 2017). There are some factors that might impact personalized medicidine in past decade. One important factor is the gene sequencing advancement. Next generation gene sequencing technology (Shendure & Ji, 2008) and the Copyright @ 2021 Authors. This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original author, and source are properly cited.