Dr. Shawn Hsiang-Yin Chen received a bachelor's degree in Pharmacy from Taipei Medical University (TMU) and completed her M.S. and Doctor of Pharmacy (Pharm.D.) training from the University of Iowa. Dr. Chen had served as the Pharmacy Director at TMU -Wanfang Medical Center for 12 years and the Associate Dean at TMU Office of Global Engagement for 4 years. She is now a Professor and the Associate Dean for Education at TMU College of Pharmacy. Dr. Chen is the founding President of the American College of Clinical Pharmacy (ACCP) Taiwan Chapter. The lab includes presently 5 Ph.D. students (2 international and 3 domestic students), 7 master's students, 1 statistical research assistant, and many undergraduate students. The lab welcomes international students to explore the possibilities of applying new technologies in clinical pharmacy to extend and excel in our practice. Description of the Research Projects: The program participants can join two research projects in different directions based on their research interests: (1) Medication use data analysis projects: Data analysis by machine learning methods has been applied to medical and pharmacy research and practice to accelerate the progress with breakthrough results. The adverse drug reactions and treatment success theoretically depend on the patient, diseases, and medications-related features and can be computed to predict the therapeutic outcomes. The traditional statistical model gives us the overall picture of the drug response. The multiple regression analysis employed in epidemiology generates fewer risk factors by reducing the confounding effects than the machine methods. However, machine learning algorithms usually contain abundant features to increase the model performance. The excellent computation capacity of machine learning and deep learning can predict the occurrence of efficacy and adverse drug reactions in patients to help clinical pharmacists provide alternative pharmacotherapy to avoid unwanted effects. A computerized medication management system with machine learning enhancement further helps clinical pharmacists optimize the medication management cycle to ensure better medication safety. The core abilities of the lab are statistical and machine learning analysis skills. The lab utilizes the principles of pharmacoepidemiology, pharmacogenomics, and pharmacovigilance for managing adverse drug reactions. Applying the epidemiologic risk factor analysis and feature importance analysis in machine learning algorithms helps undermine the complex factorial influences and interactions. A closer examination of the factors at an individual level will reveal a direct picture of why the patient encounters the adverse drug reaction, being able to target and resolve the origins. The team published numerous articles on pediatric medication error prevention, formulary management and cost containment, medication reconciliation, human resource development, pharmacy informatics, and clinical pharmacy service projects to document pharmacists' value. The lab’s recent focus is using large databases, including Taiwanese and other countries, to analyze and predict adverse drug reactions. Representative publications include statistical and machine learning methods with genetic and non-genetic risk factors to predict cisplatin- or carboplatin-induced nephrotoxicity in lung cancer patients and anti-tuberculosis agents-induced hepatitis. (2) Innovative education projects New technologies are important to deliver medication patient education to the target populations in this era. The team extracted the key concepts of Global Initiatives for Asthma (GINA) Guideline and determined the main elements of patient education by expert validation. The Norma Engaging Multimedia Design (NEMD) was applied to develop interactive narratives and serious games to enhance the self-care ability of asthmatic children. The team also published the framework to advise developing serious games for children with chronic diseases. Social media is also an efficient path to facilitate medication education and communication. The team published a clinical trial during COVID period using a commonly used social media in Taiwan, LINE, to educate diabetic patients. The results indicated that social media enhanced the patient’s blood sugar, knowledge, attitude, and health literacy. To advocate extending the frontier and enhancing the performance of clinical pharmacy service, applying new technologies to educate patients, or even pharmacy students are important for pharmacy educators. Training Time and Periods: The lab welcomes students to join and stay for 2-3 months. A longer period can be discussed if the students want to apply for the Ph.D. study in the lab. Program Candidates: (1) Master graduates or students in clinical pharmacy programs with statistical knowledge. Those who excel in R or Pythons are preferred. (2) Master graduates or students in bioinformatics programs with undergraduate training in any health care professional programs are welcomed. (3) Master graduates or students in statistical or public health programs are welcomed.