MS in Biomedical Data Science Curriculum | Icahn School of Medicine

The MDSAI program at the Icahn School of Medicine at Mount Sinai is a 30-credit program, designed to be completed in 18-24 months, that hones your technical skills through rigorous training and independent research. By applying informatics to biomedical problems, you can uncover the missing pieces to today’s most pressing health challenges. Our curriculum is designed to energize your computational, mathematical, and statistical thinking to maximize the impact on human health and well-being.

Course Descriptions Apply for Admissions Register for An Info Session

Program Requirements

During the first two semesters, students take courses immersed in concepts such as cellular and molecular biology, experimental design, statistical analysis, responsible conduct in research, and critical analysis and presentation of primary biomedical literature. Students also learn fundamental principles of data science applied to biomedical problems, including programming logic, computer architecture, algorithms, ML, and various AI tools. The third and fourth semesters focus on advanced electives and mentored laboratory research in the student’s area of interest, culminating in a Master’s capstone project.

Fundamentals of Biomedical Sciences (6 credits)
The course offers a practical and comprehensive overview of the most fundamental topics necessary for modern Biomedical Scientists. We focus on key concepts, their supporting experimental evidence, and their application in contemporary research and clinical science. Students choose three of the four 2-credit courses (six credits total):

BSR1030 Fundamentals of BMS I – Biochemistry & Molecular Biology
Concepts: Genetics, DNA and RNA regulation, Protein processing
BSR1031 Fundamentals of BMS II – Pharmacology & Drug Discovery
Concepts: Receptor theory, Structure-based drug design, Pharmacokinetics
BSR1032 Fundamentals of BMS III – Cell & Developmental Biology
Concepts: Cellular signaling, Cytoskeleton, Developmental Biology
BSR1033 Fundamentals of BMS IV – Neuroscience
Concepts: Neurophysiology, Neuroanatomy, Plasticity

Computer Systems (3 credits).
This course provides an introduction to computer systems and scientific computing environments to enable effective use of computational and data resources. The course is divided into 3 units, each worth 1 credit:

BDS1005 UNIX & Linux fundamentals
BDS1006 Architectures & Applications in Scientific Computing
BDS1007 Introduction to Scientific Programming in Python

Introduction to Algorithms (BDS2005, 3 credits)
This computer-science intensive course provides a survey of algorithms - that is, computational methods used to solve appropriately defined problems, and their implementation on modern scientific computing hardware.

Machine Learning for Biomedical Data Science (BDS3002, 3 credits)
This course is designed to train students in commonly used methods to organize, mine and learn from data sets, especially those that are complex and large (big data). These methods include classification, clustering, network inference and analysis, and outlier/anomaly detection.

Students must take the following two additional mandatory training requisites:

Responsible Conduct of Research (Eight hours of training, half credit)
Rigor and Reproducibility (Eight hours of training, half credit)

Students must take two-and-a-half to five elective credits in order to do complementary coursework in areas of greatest interest to them. Elective options include:

Introduction to Biostatistics | three credits
Biostatistics for Biomedical Research | three credits
Analysis of Categorical Data | three credits
Theory of Linear and Generalized Linear Models | three credits
Applied Analysis of Health Care Databases | three credits
Biomedical Software Engineering | two credits
Applied Linear Models | three credits
Intro to Artificial Intelligence/Deep Learning in Biomedical Research | one credit
Introduction to R Programming | two credits
Programming in Systems Biomedicine | two credits
Analysis of Longitudinal Data | three credits
Applied Linear Models II (Prereq ALM 1) | three credits

Students in the MSDSAI program perform original mentored research, culminating in a capstone report. These research projects are performed using a wide range of approaches, with a variety of biomedical applications, as illustrated by the following projects.

Year	Student	Full title	Mentor
2021	Chloe Ling	Comprehensive analysis of electronic medical records improves prediction and classification of autism spectrum disorder	Avner Schlessinger
2022	John Miller	Self-supervised Deep Learning for Computer Aided Detection of Breast Cancer	Li Shen
2023	Raj Vaza	Repository of Alzheimer’s Disease and Related Dementia Variants (RADR) and Application to diverse populations	Kuan-lin Huang
2024	Tanuja Gobbur	Evaluating Methods to Extract Features from Clinical Notes for Rare Disease Identification	Vikas Pejaver