Researchers Use Machine Learning Algorithms To Uncover New Diabetes Sub-Groups

Researchers from the Departments of Endocrinology, Personalized Medicine, Genomic Sciences, and Health Policy at the Icahn School of Medicine have collectively published interesting new findings from a computer science-based approach to researching type 2 diabetes. The team used machine-learning algorithms to sift through thousands of patient records, analyzing hundreds of individual data points within each record, to help them learn more about the underlying workings of type 2 diabetes. While researchers have been studying diabetes for decades, the depth and speed at which advanced algorithms are able to analyze large datasets is helping researchers uncover new information about the disease.

Researchers Use Machine Learning Algorithms To Uncover New Diabetes Sub-Groups

The team employed a machine learning-based sorting technique to create a patient similarity network in which patients with like symptoms or conditions were grouped together in a network map representing the dataset. This algorithm worked its way through the records of 2,500 diabetic patients, sorting them based on hundreds of data points in their chart. The resulting scatter plot, seen above, clearly shows three distinct sub-groups within the overall type 2 diabetes patient population. Endocrinologists had long known through observation that type 2 diabetes seemed to present in a number of distinct groups, but until now these groups were undefined and unstudied.

Read more...

Fitbit Devices Can Now Automatically Identify Exercises and Track Workouts

Fitbit has released a software upgrade for its Surge and Charge HR activity trackers that adds functionality allowing the devices to automatically detect when users begin a workout, and even discern what type of exercises were done. Prior to the update, Fitbit users needed to manually tell their devices that they were about to start a workout, after which they were prompted to enter details on the type of exercise they would be doing. This information was subsequently used to trend workout habits and calculate daily caloric burn.

Fitbit Devices Can Now Automatically Identify Exercises and Track Workouts

To help reduce manual workout logging, Fitbit has enhanced its activity trackers with software that will detect an increase in activity levels, and then analyze the details of that activity to identify what exercise is being performed. The extent to which Fitbit will identify activities is limited. In a press release, the company reports that its trackers can now automatically identify biking, running, walking, and elliptical use. Beyond this, exercise will be sorted into one of two generic categories: aerobic workouts or sports workouts. By default, Fitbit will not count the activity as a workout until the user spends 30 minutes exercising, but this threshold can be reduced to as low as 10 minutes, or increased all the way to 90 minutes.

Read more...

Robert Wood Johnson Partners With Cornell To Develop An Android-based ResearchKit Framework

The Robert Wood Johnson Foundation is funding a large-scale development initiative that will help researchers port their iOS ResearchKit apps into the Android marketplace with minimal effort or duplicate coding. The project is being funded by RWJF, while development of the new framework is being handled by the Small Data Lab at Cornell University, as well as Open mHealth and Touchlab.

Robert Wood Johnson Partners With Cornell To Develop An Android-based ResearchKit Framework

The overarching goal of the initiative is to “help developers and researchers with existing apps on iOS more easily adapt those apps for Android.” Apple launched ResearchKit in March 2015, and mainstream adoption has come quickly. Since its launch, researchers from prestigious academic facilities have flocked to ResearchKit, including Johns Hopkins University, Massachusetts General Hospital, Dana-Farber Cancer Institute, Duke University, Yale University, Stanford Medicine, the University of Oxford, and Cornell University. The framework is currently being used to collect data on autism, epilepsy, melanoma, pregnancy complications, asthma, Parkinson’s disease, diabetes, breast cancer, and cardiovascular disease.

Read more...

MIT Researchers Unveil SmartPill That Monitors Vital Signs

MIT researchers working from the university’s Lincoln Laboratory and Koch Institute for Integrative Cancer Research have co-developed a new ingestible smartpill that monitors core body temperature, respiration rate, and heart rate as it travels through a patient’s digestive system. The team’s progress was published in this month’s PLOS One journal. Researchers hope to see the technology rolled out to improve patient monitoring in hospitals, as well as to support soldiers and athletes.

MIT Researchers Unveil SmartPill That Monitors Vital Signs

The pill contains a miniaturized thermometer as well as a microphone and a small antenna. The thermometer tracks core temperature, while the microphone is used to record and analyze heart and lung sounds. An antenna then transmits the temperature and raw audio data to an external receiver, boasting a communications range of 10 feet, impressive given that the entire device is smaller than an almond. Once the information has left the body, researchers are able to process the audio data to calculate both respiration rate and heart rate. The device itself is only expected to remain in the digestive track for a day or two before being passed, making it optimal for patients that would benefit from short-term monitoring, but not ideal for patients that require long-term monitoring.

Read more...

Andreessen Horowitz Launches $200 Million Digital Health Investment Fund

Venture capital firm Andreessen Horowitz announces a new $200 million investment fund that it will direct entirely toward biotechnology startups. The fund will be led by Vijay Pande, a new general partner at Andreessen Horowitz. Pande comes to Andreessen Horowitz from Stanford University, where he was the director of the biophysics program and taught chemistry, computer science, and biology. During his tenure, he oversaw computer science-based research on Alzheimer’s Disease, Huntington’s Disease, and cancer. He also won a Guinness Book of World Records title for building the world’s most powerful supercomputer, hitting processing speeds of up to one petaflop.

Andreessen Horowitz Launches $200 Million Digital Health Investment Fund

Under Pande’s leadership, Andreessen Horowitz will target startups operating at the intersection of biology and machine learning, an area the company is calling “computational biomedicine.”  He explains, “Because the cost of sensors are going to zero, the cost of things like genomic sequencing are going to zero…. It creates an interesting situation where so much is available to us right now. What’s left is the software to put it all together.” Pande cites deep learning-based image analysis applications that support radiology, pathology, dermatology, and ophthalmology as prime examples of startups working at the intersection he is interested in investing.

Read more...
↑ Back to top

Founding Sponsors

Platinum Sponsors