NaHyun Kim

.
​​Medidata

​​​​​​

Education

-2013-2016  PhD, Yonsei University Graduate School

-2010-2012  MPH, Yonsei University Graduate School
Career history

-2020.12 - Present  Medidata AI Solution Specialist, Medidata Korea

-2018.10 - 2020.12  Medical Writer, Department of Korea Innovation Solution, IQVIA

-2018.02 - 2018.10  Medical Writer, Division of Post-marketing Surveillance, ADM Korea

-2016.12 - 2018.02  Senior Researcher, Division of Tuberculosis and AIDS, Korea Center for Disease Control and Prevention
Summary of experience

Nahyun Kim, PhD, has more than 10 years of experience in clinical research and epidemiologic observational studies. In the recent 3 years, Dr.Kim has been working in Medidata Korea to help the pharmaceutical industry utilize clinical trial data and advanced statistical methods and machine learning technology to produce data-driven evidence and operate their trials in more efficient manner.

Enable Smart, Data-driven Decisions Through AI in Clinical Development Programs

COVID-19 played a big role in changing the paradigm of the clinical environment. In the post-pandemic era, big data and AI technology as new manners of clinical trials have been suggested to enable smart data-driven decisions in clinical programs.  

Medidata AI's approach to trial design involves utilizing the industry's largest dataset, comprising over 30,000 clinical trials and 10 million participants. This vast pool of data allows for the creation of more accurate and efficient trial designs. The AI algorithms analyze historical data to predict outcomes and identify potential challenges before they arise, ensuring more robust and reliable trial frameworks​. Data-driven evidence generated by AI techniques can discover novel factors or correlation to impact overall clinical process before trials’ initiation. For example, synthetic data generated by generative AI can be used in exploratory analysis to find new patterns or trends in some disease areas prior to building proof of concept of studies or study design. Besides, this scientific evidence can help find the right target population or predicting potential patients with high risks or severe safety issues before clinical operation. This helps reduce the possibility of protocol amendments which is one of factors to delay clinical operation and can boost patient engagement including patient retention during operation.

Big data analysis also can help site selections and monitoring sites before or during operation. Predictive models of machine learning algorithms can improve patient recruitment and retention, optimizes site selection, and streamlines study execution. This reduces the time and resources needed to initiate and conduct trials, leading to faster development of therapies​ As a result, big data and AI technology can be a gamechanger in accelerating the clinical development process, enhancing trial accuracy, and ultimately bringing safer and more effective treatments to market more efficiently​ .