Michigan IT Symposium 2019 View Other Sessions

Do you ever wonder whether there are others across campus that have similar business use cases where technology is required to address the need? Does it cross your mind that there are probably others who are also defining requirements, working through vendor selection, implementing and then working through how to find a sustainable way to support the very technology solutions you are working on? 

In this session we will discuss best practices and lessons learned from several efforts to build consortiums across campus for applications to meet technology needs. The session will also look at risks and issues to consider, hurdles to overcome, and how to engage others across campus. We will use real life examples of cross campus cooperative projects both completed and in progress, some of which have worked pretty well and others that have encountered issues. Projects examples will include efforts such as Tableau (data visualization tool), Salesforce (CRM), Interfolio (Faculty 360), and Digital Asset Management.  

Come and join the conversation on how together we can leverage our collective resources to address campus wide technology needs, particularly in regard to enterprise level applications.

The University of Michigan generates an incredible amount of data each day, informing ground-breaking research and discovery, teaching and learning, and patient care. With advances in machine learning, advanced sensor technology, robotics, automation, and the Internet of Things, our accumulation of data—as well as the outcomes that can be drawn from it—is expected to grow exponentially.   

Data consumers are often tasked with being experts in databases, data stewardship, and complex analytical tools to access and draw insights from their desired information. In a rapidly changing environment, this limits our ability to make timely and effective decisions. Moreover, our current methods of sharing data often compel campus partners to create copies of institutional data in local databases for individual reporting and decision support needs. This duplication leads to increased IT security, privacy, and compliance risks, poor quality, and different interpretations of the same data. It also creates multiple sources of truth.   

But there is a better way for the future. Join us to hear about some of the innovations that are being pursued to provide easy access to intuitive, consistent and accurate data. We also welcome your ideas on how to advance the use of data at U-M.

The U-M School of Dentistry has employed natural language processing, machine learning, and graph database technology to parse our plain-text patient histories and connect them to the patient's treatment history and a standard tree of health care concepts, the Unified Medical Language System (UMLS). By associating free text with computable knowledge, we have unlocked a trove of previously unusable information about our patient population.

Applications of this tool include identifying communities of patients with similar health and dental care patterns for more targeted precision care, searching for populations of patients for research, identifying gaps in the medical record, improvements to our history-collection processes and forms, and reconciling patient histories at the School of Dentistry with those at Michigan Medicine.

This talk will describe the process and tools used to build the knowledge graph and demonstrate example applications of the tool. We will also discuss our plans for continuing improvement and extension. Technologies used include: Neo4j, MetaMap, MySQL, CLAMP, and Python with scikit-learn.

Are you worried about being sued because your videos don’t have captions? Have you ever wanted a text transcript of a media recording to help with your research or a blog post? Maybe you’re just wondering what all the fuss is about. Don’t know how to get started? If you this sounds like you, we have the answers you are looking for!   

In this hands-on and discussion session we will experiment with free and easy captioning tools, discuss best practices (like what it means to be ADA compliant), and uncover other benefits for captions besides accessibility compliance.

In this interactive session, explore and collaborate with others working to improve business relationships. 

We will cover:

• Good conversations
• Trust
• Meeting people from their perspective
• Good questions for better solutions 

Each section will have an activity and a practice moment in groups of 3 with the roles: observer, relationship manager and client. There will be time in each section for all to collaborate and coordinate best practices.

Participants need to register for Part 1 and Part 2.

Learning how to ask for and offer help has been proven to build positive culture, increase employee engagement, and improve productivity. In this two hour session, attendees can hear from business process owners who will present brief summaries of challenges they face in their departments, including topics such as tracking visiting scholars and managing budget commitments. We will then break out into groups to collaborate with peers on different ways to leverage technology and our experience to solve the issues presented.