Identification of Determinants of Progression to Type 2 Diabetes Using Electronic Health Records and “Big Data” Analytics

|

article image
20 million U.S. adults are living with type 2 diabetes (T2D), and are at elevated risk of complications including cardiovascular disease and death. Prevalence of diabetes has more than tripled since 19901.Total estimated financial burden of T2D: $245 billion2. atients progress from low-risk (normal) glycemic state to prediabetes (intermediate hyperglycemia) to T2D diagnosis, over 3–6 years3. Application of a novel machine learning analytic platform to an extensive.

Spotlight

LiveStories

LiveStories drives outreach and better decisions using civic data—how communities live, learn, work, and play. Our data communication platform makes it easy to analyze local data, get benchmarks, and create interactive stories. Our customers span public and private sectors including the Gates Foundation, California Health and Human Services Agency, ShotSpotter, UCLA, Maricopa County, and many local health departments.

OTHER ARTICLES

Straight to the Top: Why Incorta Beats Top Cloud Vendors in Dresner Advisory’s 2020 Market Study

Article | March 19, 2020

Business agility is the name of the game in 2020. Last year, the US-China trade wars gave business leaders around the world a preview of what it looks like when change and uncertainty become the new normal in the global economy—and for those caught flatfooted, it wasn’t pretty. Here we are nearly one year later and the world has changed dramatically once again. The trade war fiasco? That was just a dress rehearsal compared to what we are living through today with the recent outbreak of COVID-19. At times like these, few things matter more than having visibility into and the freedom to innovate with data to address the necessary business agility.

Read More

A Tale of Two Data-Centric Services

Article | March 19, 2020

The acronym DMaaS can refer to two related but separate things: data center management-as-a-service referred to here by its other acronym, DCMaaS and data management-as-a-service. The former looks at infrastructure-level questions such as optimization of data flows in a cloud service, the latter refers to master data management and data preparation as applied to federated cloud services.DCMaaS has been under development for some years; DMaaS is slightly younger and is a product of the growing interest in machine learning and big data analytics, along with increasing concern over privacy, security, and compliance in a cloud environment.DMaaS responds to a developing concern over data quality in machine learning due to the large amount of data that must be used for training and the inherent dangers posed by divergence in data structure from multiple sources. To use the rapidly growing array of cloud data, including public cloud information and corporate internal information from hybrid clouds, you must aggregate data in a normalized way so it can be available for model training and processing with ML algorithms. As data volumes and data diversity increase, this becomes increasingly difficult.

Read More

New Spain data center becomes test bed for Microsoft and Telefonica’s expanded partnership

Article | March 19, 2020

Microsoft recently announced that it’s leveraging a new global strategic partnership with Telefonica to jointly develop “go-to-market plans for regions the company does business.Last year during Mobile World Congress 2019, Microsoft took the veil off its newfound relationship with the international telecommunications giant, Telefonica.Highlighted during this year’s announcement was Microsoft’s opening of a new datacenter region in Spain. Microsoft’s new data center comes at a time where the company looks to help expedite Spain’s digital transformation.

Read More

How can we democratize machine learning on IoT devices

Article | March 19, 2020

TinyML, as a concept, concerns the running of ML inference on Ultra Low-Power (ULP 1mW) microcontrollers found on IoT devices. Yet today, various challenges still limit the effective execution of TinyML in the embedded IoT world. As both a concept and community, it is still under development.Here at Ericsson, the focus of our TinyML as-a-Service (TinyMLaaS) activity is to democratize TinyML, enabling manufacturers to start their AI businesses using TinyML, which runs on 8, 16 and 32 bit microcontrollers.Our goal is to make the execution of ML tasks possible and easy in a specific class of devices. These devices are characterized by very constrained hardware and software resources such as sensor and actuator nodes based on these microcontrollers.Below, we present how we can bind the as-a-service model to TinyML. We will provide a high-level technical overview of our concept and introduce the design requirements and building blocks which characterize this emerging paradigm.

Read More

Spotlight

LiveStories

LiveStories drives outreach and better decisions using civic data—how communities live, learn, work, and play. Our data communication platform makes it easy to analyze local data, get benchmarks, and create interactive stories. Our customers span public and private sectors including the Gates Foundation, California Health and Human Services Agency, ShotSpotter, UCLA, Maricopa County, and many local health departments.

Events