Tulane Home Tulane Shield logo linking to site home page

Biomedical Informatics Master's Program

A four-semester program designed to enrich and improve credentials of graduates to apply for Biomedical Informatics analyst, data scientist, or other healthcare-related profession career. Please follow this link to apply: applygrad.tulane.edu/apply.

 

Project Overview & Goals

The proposed program is a two-year (four-semester) thesis program leading to a Master of Science in Biomedical Informatics. The major goal of the program curriculum is to train new Biomedical Informatics (BMI) specialists. The program is primarily designed to enrich and improve the academic credentials of graduates. Our distinctive program emphasizes student development in four areas (coursework, experiential learning, presentation skills, and personal growth), and allows students to broaden and strengthen their academic foundation for further intellectual development and medical research. Each graduate will be able to use their preparation to investigate and apply information and communication technologies to advance research, practice, and solve problems in the related Biomedical fields in a comprehensive, competitive, and effective way.

The program is designed to include the following high-level competency areas:

  • Biomedically-related courses:  principal of public health informatics, biomedical imaging and process, advanced bioinformatics.
  • Data science related courses: introduction to data science, data science with cloud computing, advanced data science analytic techniques, and big data related courses.
  • The program has reciprocal relationships with specific courses in the graduate programs in Biomedical Engineering, and Biochemistry/ Molecular Biology.

The program will provide graduates with marketable skills for informatics careers in biology, medicine, public health, IT trainers, project managers, chief nursing officers, chief medical officers, or research scientists focused on the development of prescriptive analytics from big data sources. These uniquely trained master`s graduates will be critical to existing efforts to improve health outcomes. Building a stronger presence in biomedical data sciences and informatics in clinical practice, research, and education, is a high priority for the institutions. This program also prepares students to participate in research programs in academia, healthcare, public health, and industry, as well as to apply the knowledge in clinical, government, and industry settings.  

Program option: Students can take classes on campus or online.

Admission Requirements

A Bachelor’s degree (B.S. or B.A., preference majors are computer sciences, biological sciences, statistics, biostatistics, bioinformatics, public health, engineering, biomedical engineering, and mathematics) with GPA ≥ 3.1 on a 4.0 scale and one of the following:

  • GRE ≥ 300
  • MCAT ≥ 504 (28)
  • DAT ≥ 16

In addition, TOEFL ≥ 85 for applicants whose first language is not English. Language testing will be waived if student has received a degree from an accredited U.S. institution.

The following documents must be submitted for candidates to receive full consideration:

  • Transcripts: Official transcripts from all previous undergraduate and graduate studies are required. Applicants whose highest degree is from a foreign university much have their credentials evaluated course by course, even if the primary language of instruction is English and/or the school uses a 4-point grading system. Applications will not be reviewed without this evaluation. Applicants are encouraged to have their institution send credentials electronically to bms@tulane.edu.
  • Personal Statement: Applicants must prepare a personal statement, which should demonstrate how the applicant's Biomedical Informatics career goals and interests align with their selected degree program. Students will submit their personal statement through the SLATE application system.
  • Letters of Recommendation: Applicants will request three letters of recommendation through the SLATE application system. Recommenders can include professors, employers, or other academic mentors. Letters of recommendation should indicate the applicant’s academic history and potential for success in the Biomedical Informatics graduate program.
  • Test Scores: Applicants should request that testing agencies send official scores to the Graduate Program in Biomedical Sciences (6178) in addition to entering their test scores in the SLATE application. Informal score reports from the applicant will not substitute for official reports from the testing agency.
Application Information

The Fall 2021 application process opens on December 1, 2020 and closes on June 1, 2021. Applications will be reviewed as they are received, and applicants will be admitted on a competitive basis. Therefore, early submission of applications is highly encouraged.  There is no application fee.

Applications are accepted on a rolling basis. ALL application materials must be received before the closing date (see above). Rolling admission basis means there is no guarantee there will be openings in the class up until the deadlines.

For questions regarding the program, please contact Dr. Ashad Alam (Program Director, malam@tulane.edu or Hanna Räsänen (Section Administrator, hrasanen@tulane.edu).

Program Curriculum (Minimum 30 credit hours)

The core curriculum emphasizes biomedical applications of data science and big data knowledge. Students must complete a minimum of 30 credit hours from the courses listed below.

Course Number Course Name Credit Hours
Core Courses
Year 1 - Fall

BIMI - 6100

Elements in Biomedical Informatics 4

BIMI - 6200

Introduction to Data Science for Biomedical Informatics 3

BIMI - 6300

Fundamentals of Data Analytics 3
Year 1 - Spring

BIMI - 7100

Statistical Machine and Deep Learning in Biomedical Practice 3

BIMI - 7300

Biomedical Data Science with Cloud Computing 3

BIMI - 7500

Big Data Analysis in Biomedical Informatics 3
Year 1 - Summer

BIMI - 9980

Master's Thesis Research 0
Year 2 - Fall

BIMI - 8500

Research Methodology of Biomedical Informatics 1
Year 2 - Spring

BIMI - 8500

Research Methodology of Biomedical Informatics 1
Year 2 - Fall, Spring and Summer

BIMI - 9980

Master's Thesis Research 0
Electives courses (Year 1 or Year 2): All students are required to take at least one of the following biologically relevant courses (excluding GBCH-7250 Biostatistics) as an elective: BMSP 6070, Advanced Cell Biology; GBCH 6010, Biochemistry; EPID 7810, Human Molecular Genetics. Other elective courses may be substituted with permission of the Program Director.
Fall

BIMI - 8550

Computational Biology: Structure and Organization 3

BMEN - 6830

Introduction Biomed Imaging & Process 3

GBCH - 7230

Introduction to Bioinformatics 3

PATH - 7600

Cancer Biology and Pathology 3

BIMI - 6400

Health Informatics 3

GBCH - 6010

Graduate Biochemistry 4
Spring

BIMI - 8600

Advanced Data Science Analytic Techniques 3

GBCH - 7170

Principles of Genetics 3

EPID - 7810

Human Molecular Genetics 3

BMEN - 6020

Mathematical Modeling and Analysis of Biological Systems 3

GPSO - 7320

Renal Physiology 3

GBCH - 7250

Biostatistics 2

MIIM - 7065

Scientific Writing 3

Minimum of 30 credit hours (21 core and at least 9 elective credit hours)

 

Courses

Required Courses

Elements in Biomedical Informatics (BIMI-6100, Fall, 4 Credit Hours) 

Course Co-directors: Lan-Juan Zhao, Md Ashad Alam, Daniel Giles Fort

The objective of this course is to teach graduate students the necessary backgrounds of biomedical informatics with computer applications in biomedicine and health care. The biomedical data, their acquisition, storage, ethics, and use in biomedical decision making for probabilistic clinical reasoning will be introduced. The basic underlying cognitive science issues will be studied in which information is processed by the human mind and biomedical informatics. Students will acquire essential concepts for biomedical computing, system design, and engineering in health care. Application of natural language, text processing, imaging structures in biomedicine will be discussed. Finally, the challenges associated with technology assessment and the evaluation of clinical information systems, imaging systems in radiology, computers in medical education, and health care financing are introduced. Student presentation/discussion sessions following each block will allow students to present (4 times) and discuss the principles and the applications of the latest biomedical informatics technologies.

 

Introduction to Data Science for Biomedical Informatics (BIMI-6200, Fall, 3 Credit Hours)

Course Co-directors: Lan-Juan Zhao, Md Ashad Alam

Data science has become a central element of both scientific research and industry. The objective of this course is to teach graduate students the necessary backgrounds of data science biomedical informatics with MySQL, R, Phyton, and MATLAB programs. The overview of biomedical data science- introduction to database, biological database, data storage, and biomedical data showcase will be introduced. The basic underlying of data structures, algorithms, inference in biomedical informatics point of view will be studied. Students are expected to become comfortable with SQL, R, Python, and MATLAB programming along with structure and syntax of functions. Advanced coding skills, techniques, ideas, and new packages (library) management will be accomplished in a practical manner. Exploratory analysis, data visualization, report prosecution techniques, and data science and analytics in health care will be discussed. Finally, necessary concepts of imaging with multi-omics data integration are introduced. Student presentation/discussion sessions following each block will allow students to present (4 times) and discuss the problem of programming.

 

Fundamental of Data Analytics (BIMI-6300, Fall, 3 Credit Hours)

Course Director: Chuan Qiu

The objective of this course is to teach graduate students to understand the current state of multivariate and multi-view statistical analysis in an age of complex biomedical data. Overview of multivariate and multi-view data will be addressed. The basic underlying linear regression (e.g., multivariable, multivariate, logistic, and ridge recession) will be studied and practiced with biomedical data. Sparse linear models along with the elastic net, linear dimensionality reduction methods (supervised and unsupervised), linear discriminate analysis, and linear cluster analysis will be discussed with practical applications. As advanced tools, adaptive basis function models, graphical models, artificial neural networks, penalized multivariate analysis, and fusion-based approaches will be introduced to evaluate biomedical data. Finally, students will learn how to use R /Python as a tool and apply the multivariate and multi-view data processing techniques to solve some biomedical problems such as gene-gene interaction, prediction, classification, and multi-omics integration analysis. Student presentation/discussion sessions following each block will allow students to present (4 times) and discuss the principles and the applications of the latest multivariate technologies.

 

Statistical Machine and Deep learning in Biomedical Practice (BIMI-7100, Spring, 3 Credit Hours) 

Course Co-directors: Md Ashad Alam, Daniel Giles Fort

The objective of this course is to teach graduate students for a comprehensive understanding of automatically detectable patterns in data, and then to use the identified patterns to predict future data. Background of probability theory, functional analysis, and overview of statistical machine learning with data representation and features engineering will be launched. A popular machine learning tool for classification and regression, support vector machine and its variants will be studied and practiced with biomedical data. The notion of positive definite kernel and kernel-based methods will be discussed with real-world applications. Nonlinear dimensionality reduction techniques, including manifold learning (t-SNE and UMAP) will be introduced and evaluated in Biomedical data. Principle of Bayesian statistics, Gaussian processes, Markova and hidden Markova models, and Markov random fields will be discussed with applications. Deep neural networks-based learning approaches and adversarial learning approached will be considered for biomedical data. Finally, students will learn how to use Python as a tool and apply machine learning, and deep learning techniques to solve some real-world biomedical problem. Student presentation/discussion sessions following each block will allow students to present (4 times) and discuss the principles and the applications of the latest multivariate technologies.

 

Biomedical Data Science with Cloud Computing (BIMI-7300, Fall, 3 Credit Hours)

Course Director: Md Ashad Alam

The objective of this course is to teach graduate students the necessary backgrounds of programming and high-performance computing techniques in data science with cloud computing. Background of the computer inside and overview of optimization tools will be reviewed and discussed. Advanced technologies, high-performance computing, cloud computing, and MapReduce will be learned. Open-source software Hadoop and Spark and cloud service (Amazon, Google, and Microsoft) will be discussed in a step-by-step process to solve problems in Big data and computation. The relational data management, the next generation digitally enhanced science, and interactive visualization tools will be addressed and implemented with biomedical data. Finally, students will learn the latest research topics on cloud platforms and can understand some commercial cloud systems through projects.

 

Big Data Analysis in Biomedical Informatics (BIMI-7500, Spring, 3 Credit Hours)

Course Co-directors: Hui Shen, Chuan Qiu 

The objective of this course is to teach graduate students to understand why big data are assuming a crucial role in the Biomedical Informatics. Big data overview, big data in data science, and big data in biomedical informatics will be addressed. Details of big data visualization tools and a compressive results interpretation will be introduced and performed. Fundamental and advanced (machine and deep learning) big data analytics approaches will be studied for functional applications. The typical use such as disease privation, multi-omics, medical imaging, and brain imaging, will be focused to understand the efficiency of Big data. Finally, the audience will discover Big data management challenges, technologies, and leadership skills. Student presentation/discussion sessions following each block will allow students to present (4 times) and discuss the principles and the applications of the latest big data technologies.

 

Research Methodology of Biomedical Informatics (BIMI-8500, Fall & Spring, 1 Credit Hours/Semester, 2 Credit Hours per Year)

Course Director: Hong-Wen Deng

Course Objectives: This course consists of formal oral presentation and critical discussion to familiarize students, postdoctoral fellows, and outside speakers with the innovative research topics and methodology development of biomedical informatics. This course will use the combined format of a journal club as well as a research meeting. Students are required to present a seminar on a currently published peer-reviewed research paper approved by the course director, on a research idea, or on their own research work. The seminar will cover the advanced biomedical informatics topics, including bioinformatics, genome informatics, transcriptomics, metagenomics, metabolomics, proteomics, biomedical imaging, drug repurposing, health informatics and telehealth, public health informatics, etc. Students are required to participate in discussions following the presentation. In the discussion, students may also talk about their concerns regarding research, scientific paper writing, and grant writing with their peers and faculty members.

 

Master’s Thesis Research (BIMI-9980, Fall, Spring & Summer, 0 Credit Hours per Semester)

Course Director: TBD

Master’s Thesis Research is mandatory for students in the 2-year M.Sc. in BMI program to conduct research to fulfill the thesis requirement. It is the student’s responsibility to choose a thesis advisor from the faculty of the Center for Biomedical Informatics and Genomics by the end of the second semester. It is expected that the student spends a minimum of 20 hours a week working on the thesis project. Students are requested to check off biweekly/monthly meetings with the advisors and semester meetings with the committee. The thesis is expected to be completed in two semesters and must be approved by a thesis committee consisting of three faculty members.

 

Elective Courses

Health Informatics (BIMI-6400, Fall, 3 Credit Hours)

Course Director: Daniel Giles Fort

The goal of this course is to teach graduate students for the increasing necessity for computation in modern health informatics research.  Foundations of Health informatics, Health informatics database, and theoretical foundations of health informatics will be discussed. Models, Theories and Research for program evaluation, Technical Infrastructure to support healthcare, administrative application in Healthcare, clinical decision support systems in healthcare and public health informatics will be studied.  The engaged ePatinet, social media tools for practice and education, personal health records, and mHelath will be introduced. Finally, Managing the life cycle of a health information system, usability, standards, safety, analytics, governance structures, legal and regulatory issues in health informatics will be studied.

 

Computational Biology: Structure and Organization (BIMI-8550, Fall, 3 Credit Hours) 

Course Director: Hui Shen

The objective of this course is to teach graduate students the advanced approaches of compactional biology and their application. Overview statistical preliminary, computational biology, comparative genomics, genome annotation, and molecular evolution will be discussed. Coding and non-coding genes identification and modeling approaches will be addressed. Gene and genome regelation (clustering, classification, networks, and regulatory networks) tools will be addressed. Finally, advanced methods of computational biological, chromatin interactions, synthetic biology, and medical genomics will be studied.

 

Advanced Data Science Analytic Techniques (BIMI-8600, Spring, 3 Credit Hours)

Course Director: Md Ashad Alam

The objective of this course is to teach graduate students the advanced approaches with algorithms in representation learning, generative adversarial networks, and their application to imaging multi-omics data. Overview and implementation of advanced deep neural networks (deep residual, dynamics of output, deep feed forward, and regularization neural networks) will be discussed. Graphical deep neural networks with structured probabilistic models will be studied with practices. Deep reinforcement learning, interpretable deep networks, confronting the partition function, and sequence modeling will be addressed to solve problems in imaging multi-omics data. Adversarial threat models, the most common being to attack in standard machine learning models, will be examined to attempt defenses against adversarial examples. Finally, students will learn the latest research topics on advanced deep learning platforms and can display their knowledge with presentations. 

 

Additionally, the program has reciprocal relationships with specific courses in the graduate program in Biomedical Engineering, and Biochemistry & Molecular Biology. For example:

Careers

Careers in biomedical informatics continue to grow due to a population boom among senior citizens, recent public policy changes that changed the financial structure of medical science, and complex disease. Technological advances are enabling us to collect complex information at increasing depth and resolution while decreasing labor. Earning a master’s degree in Biomedical Informatics can pave the way for advanced technologies, data science, and leadership positions.

We expect that the program graduates will be accepted into desired professional at the external job listing in Biomedical Informatics:

Tuition & Fees

Full-time tuition for the 2021-2022 academic year is projected to be $28,916/year plus fees for 30 credit hours.

Students will also be charged the following estimated fees on a per-semester basis:

Academic Support Services $400 max.

Student Activities $130.

Reilly Recreation Center $190.

Student Health Services $333.

This is a discounted rate from Tulane's regular tuition of $23,163 per semester. No tuition waivers or stipends are available for this program. Information on the possibility of financial aid loans can be found at the Tulane University Office of Financial Aid website at http://www.finaidhsc.tulane.edu/