life sciences

Second annual Women in Data Science conference showcases research, explores challenges

MIT News

Two hundred students, industry professionals, and academic leaders convened at the Microsoft NERD Center in Cambridge, Massachusetts for the second annual Women in Data Science (WiDS) conference on March 5. The conference grew from 150 participants last year, and highlighted local strength in academics and health care. "The WiDS conference highlighted female leadership in data science in the Boston area," said Caroline Uhler, a member of the WiDS steering committee who is an IDSS core faculty member and assistant professor of electrical engineering and computer science (EECS) at MIT. "This event is particularly important to encourage more female scientists in related areas to join this emerging area that has such broad societal impact." Regina Barzilay, Delta Electronics Professor of EECS, gave the first presentation on how data science and machine learning approaches are improving cancer research. Barzilay said her experiences as a breast cancer survivor motivates her work.

IIoT, Digital Transformation, Smart Manufacturing, Life Sciences


The Life Sciences industry is leveraging IIoT, digital transformation, and smart manufacturing to address some of its primary manufacturing concerns, including improving productivity and reducing costs, the ability to document and secure everything from raw materials to process changes and software version control, and serialization and track and trace capabilities to meet local regulations while ensuring the highest levels of security. The ability to move from batch processes to continuous processes, particularly for bulk pharmaceuticals, is critical, especially with the use of disposable and modular production increasing. As with all industries in an IIoT connected world, cybersecurity continues to be a significant issue and an area that requires further investments. There are a number of market trends shaping the life sciences industry. Global population and life expectancies are increasing.

Diagnosing Heart Disease with A.I.


Google and Verily Life Sciences shared the latest advance in computer vision to identify signs of heart disease. With an accuracy of 70 percent, early results from the AI trained on retinal scan images from more than 200,000 patients is as precise as methods that require blood tests for cholesterol, said Google Brain product manager Lily Peng.

See How This Robotic Arm Brace Uses Neurological Signals To Restore Movement

Forbes Europe

Air Force veteran (1968-1975) Angel Camareno is fitted with a MyoPro device. Angel suffered a brachial plexus injury 40 years ago which led to reduced motion in his arm. Myomo, a spinout from Massachusetts Institute of Technology (MIT) has created a robotic arm brace for people with limb paralysis from neurological disorders such as Amyotrophic Lateral Sclerosis (ALS), Multiple Sclerosis (MS) or stroke to help them regain movement with their hands and arms. The robotic arm brace, MyoPro, senses the patient's electromyography (EMG) signals through non-invasive sensors and restores function to their paralyzed arms. Patients who use the device are able to do things they were unable to do or found difficult to do before such as feeding themselves, doing laundry, carrying objects or even returning to work.

Industry Verticals READY for Artificial Intelligence in 2018 - Direct2DellEMC


Imagine what the world would be like if we could harness the multitude of data generated each day to catalyze positive change. What if we had the ability to predict and stop crimes before they happened, or could apply these same methodologies to save lives with better healthcare? With recent advances in artificial intelligence, these outcomes are not only possible, but an exciting reality!

Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care Artificial Intelligence

Patients in the intensive care unit (ICU) require constant and close supervision. To assist clinical staff in this task, hospitals use monitoring systems that trigger audiovisual alarms if their algorithms indicate that a patient's condition may be worsening. However, current monitoring systems are extremely sensitive to movement artefacts and technical errors. As a result, they typically trigger hundreds to thousands of false alarms per patient per day - drowning the important alarms in noise and adding to the exhaustion of clinical staff. In this setting, data is abundantly available, but obtaining trustworthy annotations by experts is laborious and expensive. We frame the problem of false alarm reduction from multivariate time series as a machine-learning task and address it with a novel multitask network architecture that utilises distant supervision through multiple related auxiliary tasks in order to reduce the number of expensive labels required for training. We show that our approach leads to significant improvements over several state-of-the-art baselines on real-world ICU data and provide new insights on the importance of task selection and architectural choices in distantly supervised multitask learning.