Data Science Track

Data Science in Clinical Research Track

 

Data science in clinical research is an emerging discipline in response to the explosion of available and complex data in biomedicine and related streams. Data Science in Clinical Research is an emerging discipline — for which there is not a standard definition — in response to the explosion of available and complex data in biomedicine and related streams. Examples of complex data include those from the laboratory (e.g., genomics and other “-omics”), biomedical imaging, electronic medical records, and other “found” data (e.g., social media). The TICR Program believes data science in the context of clinical research is best understood as an interdisciplinary hybrid of the fields of informatics, computer science, biostatistics, and epidemiology. As such, a data scientist has a broad background and expertise in accessing data, manipulating data, and forming inferences (i.e., summarizing raw data into meaningful messages) from data. A data scientist may typically not have as deep an expertise as a dedicated computer scientist, bio/clinical informatician, biostatistician, or epidemiologist in their respective fields, but instead she/he brings unique value because of his/her broad skill set accessing complex data, manipulating complex data, visualizing complex data, and being able to perform a broad array of analytic techniques.

 

The Data Science in Clinical Research Track of the Master’s Degree Program is tailored for researchers who seek to work in complex data environments (sometimes referred to as “Big Data”) and who desire to become facile in the manipulation of large (and perhaps unstructured and unwieldly) data structures and the summarization of data into meaningful messages. Coursework in the data science track extends upon MAS program’s foundation of epidemiology and biostatistics to include required and elective courses in advanced data manipulation, prediction, clustering/pattern recognition and data reduction. The Data Science in Clinical Research Track distinguishes itself from other data science training programs by being embedded into the context of human subjects-based health-related research and a solid base of epidemiology and clinical research. Many of the contextual examples used in the courses and student projects are from the life sciences and clinical care. Graduates of the Data Science in Clinical Research Track are poised to work in either leadership or supportive roles in academia, industry, or municipal health systems.


Scholars completing this track may list "Master of Advanced Studies, Clinical Research with Specialization in Data Science" on their curriculum vitae.


Please contact [email protected] for more information.

 

Apply to this program by June 15, 2024.

 

Sample Course Schedule

Year 1
Summer  Fall Winter Spring

EPI 201:  Responsible Conduct of Research (.5)

EPI 202: Designing Clinical Research (2)

EPI 218: Data Collection and Management (2)

BIOSTAT 212: Introduction to Statistical Computing in Clinical Research* (1) 

BIOSTAT 213: Introduction to Computing in the R Software Environment (2)*

Elective:

BIOSTAT 202: Introduction to the Science of "Big Data" (3)

EPI 203: Epidemiologic Methods (4)

EPI 204: Clinical Epidemiology (3)

BIOSTAT 200: Biostatistical Methods for Clinical Research I (3)

BIOSTAT 214**: Programming for Health Data Science in R II (2)

EPI 220/230: TICR Program Seminar for First-Year and Master's and Certificate Program Scholars (1)

EPI 222 - Social Determinants of Health and Health Disparities (1 or 2 units)

BIOSTAT 208: Biostatistical Methods for Clinical Research II (3)

BIOSTAT 216**: Machine Learning in R for the Biological Sciences (3)

EPI 220/230: TICR Program Seminar for First-Year and Master's and Certificate Program Scholars (1)

Elective:

DATASCI223: Applied Data Science with Python (2)

 

EPI 212: Publishing and Presenting Clinical Research (1)

BIOSTAT 209: Biostatistical Methods for Clinical Research III (3)

EPI 220/230: TICR Program Seminar for First-Year and Master's and Certificate Program Scholars (1)

 

Elective:

DATASCI224: Understanding Machine Learning: From Theory to Applications

DATASCI 225: Machine Learning in R
for the Biomedical Sciences II: Methods for Prediction, Pattern Recognition, and Data Reduction
(3)

Year 2
Fall Winter Spring

EPI 221 — Master's Seminar II (1)

 

EPI 221 — Master's Seminar II (1)

EPI 221 — Master's Seminar II (1)

*Data Science track students may request to place out of these courses with the permission of John Kornak, Program Director
** Students may opt to take these courses in MAS year 2