Where Industry Meets Innovation

  • Contact Us
  • sign in Sign In
  • Sign in with certificate
mit campus


Search Videos

  • View All
  • ILP Videos
  • MIT Faculty Shorts
  • Tech-TV
  • Startup Exchange

Conferences Videos

  • 1/24 Japan Conference
  • 1/7 Wuxi Symposium
  • 11/13 Research and Development
  • 11/8 Paris Symposium
  • 10/31 MIT Citi Conference
  • 10/10 Startups Silicon Valley

Featured Videos


11 Results | Last Page

45 mins
ILP Video

Startup Exchange

BioBright, Charles Fracchia
Catalia Health, Cory Kidd
Engine Bioscience, Stephen Harrison
Interpretable AI, Daisy Zhuo
Legit Patents, Matt Osmand
LuminDX, Susan Conover
PathAI, Aditya Khosla
ReviveMed, Leila Pirhaji
TwoXAR, Andrew Radin
Read More

30 mins
ILP Video

The Roles of AI in Healthcare

Ernest Fraenkel, PhD
Professor of Biological Engineering
What are the prospects for applying AI to improve healthcare? I will outline three types of problems that AI can address in healthcare, the most challenging of which is the development of new therapeutics. To address this challenge, we leverage recent advances in machine learning and high-throughput experimentation to apply the engineering cycle to drug discovery. The engineering cycle is based on iteratively measuring a system, modeling it computationally, and manipulating it. Each time the cycle is completed, the results improve. This iterative approach is fundamental to all engineering design but, until now, has had limited impact on drug discovery. I will briefly describe progress on unpublished projects relating to these efforts, including a collaborative, multi-institutional project called Answer ALS.
Read More

32 mins
ILP Video

From genomics to therapeutics: dissection and manipulation of human disease circuitry at single-cell resolution

Manolis Kellis
Professor, MIT Computer Science and Artificial Intelligence Lab
Institute Member, Broad Institute of MIT and Harvard
MIT Department of Electrical Engineering and Computer Science
Perhaps the greatest surprise of human genome-wide association studies (GWAS) is that 90% of disease-associated regions do not affect proteins directly, but instead lie in non-coding regions with putative gene-regulatory roles. This has increased the urgency of understanding the non-coding genome, as a key com-ponent of understanding the mechanistic basis of human disease. To address this challenge, we generate transcriptional and epigenomic maps of cellular circuitry across 100s of reference human tissues and cell types, 1000s of individuals in disease-relevant tissues, and 10,000s of individual cells in complex tissues, across patients and control individuals. We use the resulting datasets to infer regulatory networks linking genetic variants to their target genes, their upstream regulators, the cell types where they act, and the pathways they perturb, thus providing unbiased views of disease mechanisms, and sometimes re-shaping our understanding of common disorders. For example, we found that genetic variants contributing to Alz-heimer?s disease act primarily through immune processes, rather than neuronal processes. We also found that the strongest genetic association with obesity acts via a master switch controlling energy storage vs. energy dissipation in our adipocytes, rather than through the control of appetite or exercise in the brain. Combining genetic, epigenomic, and transcriptional variation across patients and healthy controls, we infer causal genes and regions that mediate the effect of genetic variants on disease phenotypes, pinpointing driver genes and regions in Alzheimer?s disease, heart disease, and cancer. We combine single-cell pro-files, tissue-level variation, and genetic variation across healthy and diseased individuals to deconvolve bulk profiles into single-cell profiles, to recognize changes in cell type proportion associated with disease and ag-ing, and to partition genetic effects into the individual cell types where they act. We expand these methods to electronic health records to recognize meta-phenotypes associated with combinations of clinical notes, pre-scriptions, lab tests, and billing codes, to impute missing phenotypes in sparse medical records, and to rec-ognize the molecular pathways underlying complex meta-phenotypes in genotyped individuals by integration of molecular phenotypes imputed in disease-relevant cell types. Lastly, we develop programmable and modular technologies for manipulating these pathways by high-throughput reporter assays, genome editing, and gene targeting in human cells and mice, demonstrating tissue-autonomous therapeutic avenues in Alz-heimer?s, obesity, and cancer. These results provide a roadmap for translating genetic findings into mecha-nistic insights and ultimately new therapeutic avenues for complex disease and cancer.
Read More

28 mins
ILP Video

Interpretable AI

Dimitris Bertsimas
Boeing Professor of Operations Research
Co-Director, Operations Research Center (ORC)
Faculty Director, Master of Business Analytics
MIT Sloan School of Management
This talk introduces a new generation of machine learning methods that provide state of the art performance and are very interpretable, introducing optimal classification (OCT) and regression (ORT) trees for prediction and prescription with and without hyperplanes. This talk shows that (a) Trees are very interpretable, (b) They can be calculated in large scale in practical times, and (c) In a large collection of real world data sets, they give comparable or better performance than random forests or boosted trees. Their prescriptive counterparts have a significant edge on interpretability and comparable or better performance than causal forests. Finally, we show that optimal trees with hyperplanes have at least as much modeling power as (feedforward, convolutional, and recurrent) neural networks and comparable performance in a variety of real world data sets. These results suggest that optimal trees are interpretable, practical to compute in large scale, and provide state of the art performance compared to black box methods.
Read More

28 mins
ILP Video

Identifying and rationally modulating cellular drivers of enhanced immunity

Alex Shalek
Pfizer-Laubach Career Development Assistant Professor
Institute for Medical Engineering & Science, Department of Chemistry, and Koch Institute, MIT
Ragon Institute | Broad Institute | HMS | MGH
Immune homeostasis requires constant collaboration between a diverse and dynamic set of cell types. Within our immune tissues, distinct cellular subsets must work together to defend against pathogenic threats, maintain tolerance, and establish memory. While surveying multiple healthy individuals enables exploration of potential ensemble immune solutions, contrasts against outliers of health and disease can reveal deviations that underscore diagnostic, therapeutic, and prophylactic features of enhanced function or dysfunction. Here, I will discuss how we can leverage single-cell genomic approaches ? and, in particular, single-cell RNA-Seq ? to explore the extensive functional diversity among immune cells within and across individuals, and uncover, from the bottom-up, distinct cell types and states associated with improved immunity. Moreover, I will discuss emerging experimental and computational strategies for altering ensemble cellular responses through targeted intra- or extracellular induction of these preferred types and states.
Read More

1 hr 2 mins
ILP Video

Panel Discussion: Perspectives on AI in Life Science

Andrew A. Radin
Cory Kidd
Ryan Davis
Ellie Chabi
Martha Gray
John Roberts
John Roberts, MIT Cory Kidd, Catalia Health Ryan Davis, Secure AI Labs Ellie Chabi, Santen Pharma Prof. Martha Gray
Read More

37 mins
ILP Video

AI for Passive In-Home Patient Monitoring: From Wearables to Invisibles

Dina Katabi
Andrew (1956) and Erna Viterbi Professor of Computer Science and Engineering
Director, Center for Wireless Networks and Mobile Computing (Wireless@MIT)
MIT Department of Electrical Engineering and Computer Science
This talk introduces Emerald, a novel MIT technology for in-home non-intrusive patient monitoring. The Emerald device is a WiFi-like box that runs customized machine learning algorithms to learn digital biomarkers from the wireless signals in the patient's home. It can remotely monitor the patient?s gait speed, falls, respiratory signal, heart rate, and sleep quality and stages. The sensing is completely passive ?i.e., the patient can go about her normal life without having to wear any sensors on her body, write a diary, or actively measure herself. The talk will discuss the technology, and the results from pilot studies in various therapeutic areas.
Read More

24 mins
ILP Video

Learning About Breast Cancer from Images and Text

Adam Yala
Ph.D Candidate, MIT CSAIL
Breast cancer is global problem with over 500,000 women dying from the disease every year, yet all of our decisions and insights are based on only a fraction of the information that exists at both the patient and population level. In this talk, we explore a machine learning approach to cancer that integrates rich patient information at population scale, and discuss the type of tools this enables. We have developed A.I systems for automatically reading mammograms, performing personalized risk assessment and mining medical records and implemented them clinically at Massachusetts General Hospital.
Read More

23 mins
ILP Video

Emotion AI and Future Health

Javier Hernandez
Research Scientist
Affective Computing Group
MIT Media Lab
AI and machine learning are becoming embedded in our wearables and smartphones, enabling new insights and interventions for improving lives for patients with conditions including autism, epilepsy, and depression. The latter is growing and forecast to become the #1 disease burden by 2030. How close are we to forecasting changes in mood, stress, and physical health before they happen? Could AI help us prevent future diseases such as depression, and help people stay healthy instead of becoming sick tomorrow? This talk will show the
Read More

23 mins
ILP Video

Making Images Part of Medical Record

Polina Golland
Henry Ellis Warren (1894) professor of Electrical Engineering and Computer Science
MIT Department of Electrical Engineering and Computer Science
Currently, medical images require a physician to extract clinically relevant information. I will discuss out current work towards making images part of the quantitative medical history and to enable large-scale image-based studies of disease. Although large databases of clinical images contain a wealth of information, medical acquisition constraints result in sparse scans that miss much of the anatomy. These characteristics often render computational analysis impractical as standard processing algorithms tend to fail when applied to such images. Our goal is to enable application of existing algorithms that were originally developed for high resolution research scans to severely undersampled images. We illustrate the applications of the method in the context of neurodegeneration and white matter disease studies in stroke patients.
Read More

28 mins
ILP Video

Robust Data Analytics in Biopharmaceutical Manufacturing

Richard Braartz
Department of Chemical Engineering
Read More

MIT Partners

  • mit video
    MITVideo aggregates and curates video produced by the Institute's offices, laboratories, centers and administration.
  • tech tv
    MIT Tech TV is the video-sharing site for the MIT community.