Cloud Hosting

The University Health Systems data science team recently advanced to the next stage of a nationwide competition to apply artificial intelligence to hospital readmissions, a persistent and costly issue. Sponsored by the Centers for Medicare and Medicaid Services, the inaugural Artificial Intelligence Health Outcomes Challenge initially received hundreds of applications. CMS chose only 25 submissions, the Universitys among them, to execute their proposed strategies.

A few years ago, in order to significantly reduce unplanned readmissions to the hospital, the University initiated efforts to develop a cutting-edge yet easily accessible solution to this widespread problem. Bommae Kim, senior data scientist for the University Health System, began pursuing remedies for the epidemic of readmissions in 2018.

Usually, after a patient was discharged, they couldnt manage their disease for some reason, so were trying to figure out what that reason is and help, Kim said.

The University Health Systems data science team found that three percent of patients at the University constitute 30 percent of readmissions within the first 30 days following release from the hospital, while the majority of the remaining 70 percent return within a year. After identifying the need to decrease such adverse events, data scientists in the Universitys Health System, such as Jason Adams, turned to artificial intelligence to target key factors that contribute to a patient returning unnecessarily to the hospital.

The purpose is to take this amount of information and in an automated way to tell that a person is at risk and what is the course of action that can best help that patient, Adams said.

Kim acts as project leader alongside a team of data scientists and information technology personnel. Overseen by Jon Michel, director of data science for the University Health System, the researchers produce models that help predict the likelihood of readmission and subsequently provide actionable advice for physicians.

Only a year or so later in 2019, CMS announced a competition to tackle the same challenge. CMS directed participants to employ the computing power of artificial intelligence to construct a model that accurately and efficiently flags patients at risk of returning to the hospital for non-routine treatments. More than 300 applicants submitted proposals during the launch stage of the challenge.

The University was one of only 25 groups selected to advance to the next stage, vying with organizations such as IBM, Deloitte and the Mayo Clinic for the $1 million grand prize and utilization by the CMS Innovation Center to determine payment and service delivery strategies.

Were doing this for our U.Va. patients, but it would be nice to win the competition because then we can deploy our approach at the national level, Kim said. We believe in our approach.

For this phase of the competition, CMS distributed Medicare claims data to the remaining teams. Claims from all across the country provide the opportunity to fine-tune the Universitys model with data outside of the University Health System. According to Application Systems Analyst Programmer Angela Saunders, the supplemental details will prove beneficial for the Universitys models.

Saunders did point out challenges with the millions of rows of data, which require extensive resources to simply store in an environment suitable for manipulation. Furthermore, inconsistencies lingered in the dataset from year to year, requiring the feature engineering team to sift and sort through the tables, standardizing entries and column headers, which detail the traits associated with each claimant.

Its not just a little data, Saunders said. We have exhausted a lot of resources just to get the data to consistency. Each year, things change just a little bit and so just getting it into a consistent format is a lot of the battle.

Based on the teams assessments, much of the feature engineering portion of the project at least the preliminary round of it has been completed. The next step involves transporting data to Rivanna, the Universitys high performance computing system, and fitting predictive models to the data. Data scientist Rupesh Silwal, who helps design and evaluate multiple iterations of the modeling architecture, noted the importance of not only systemizing the entries, but also of ensuring sensitive medical data remains anonymous.

The feature engineering team has cleaned the data, made sure everything makes sense from year to year and that all of the sensitive information is scrubbed so we can move the data to this other computing infrastructure, Silwal said. Part of our effort has been focused on getting the data in there and using it to set up a modeling environment to see if we can make predictions.

Specifics regarding modeling techniques and factors employed in creating the Universitys unique solution could not be revealed at this time, due to the proprietary nature of the ongoing competition. In broad terms, factors such as past utilization of certain hospital services like the Emergency Department or chronic conditions contribute to the initial formulation of the model, as they are indicators of high potential for readmission, data scientist Adis Ljubovic said.

Those are fairly well-known and were using that as the baseline, but we also have the secret sauce ones that are preventable, Ljubovic said.

Other variables intended to capture financial, transportation and lifestyle information for patients also augment the standard determinants of readmission, while electronic medical records from the University provide documentation of trends in the Universitys own health system.

Another distinctive aspect of the Universitys proposal is its commitment to a solution that clinicians accept. Senior data scientist John Ainsworth and Ljubovic, along with other members of the Universitys project, assert that the healthcare industry generally adopts a conservative mindset with regards to artificial intelligence modeling in hospitals. However, the University Health Systems data scientists have consulted with doctors at the University hospital about introducing tools physicians trust and can easily adopt.

Data science techniques bring with them the potential for accuracy, for bringing in and ingesting larger datasets, Ainsworth said. The richness of the data gets recorded and putting up the information in front of clinicians that can help them take meaningful action is what were going for. If we can ... give them some sense of where preventative strategies might lie, that can support them in their goal of caring for patients.

Several members of the team agreed a complex issue like hospital readmission calls for a collective approach. In the University Health Systems data science department, that can be a rare occurrence, several data scientists remarked, as their separate assignments often occupy most of their time. Senior Business Intelligence Developer Manikesh Iruku expressed appreciation for the chance to learn more about data science techniques, and others shared similar experiences when it came to exploring different subfields of data science.

Saunders and data scientist Valentina Baljak emphasized the confidence this collaboration has given the group to tackle new tasks.

Frequently for us, we have our own projects and its a one-person project, Baljak said. Occasionally you collaborate with someone, but I dont really think we had a project that involved all of us at the same time. That has been a great experience.

Currently, competitors are finalizing their project packages to submit to CMS in February. CMS plans to winnow the field down to the seven best proposals by April. Regardless of the outcome, the Universitys team plans to put their results and newly developed models into practice within the Universitys Health System.

In particular for healthcare, in some ways the best is yet to come in the data science world, Ainsworth said. The future is bright for data science in healthcare.

Read more:
Preventing hospital readmissions with the help of artificial intelligence - University of Virginia The Cavalier Daily

WINNIPEG -- The lead singer of the Canadian rock group Moist and four-time Juno winner David Usher was a in Winnipeg Thursday, but not for his music.

The rocker is also a tech entrepreneur in the area of artificial intelligence and he was showing off his new artificial being.

"I was born six months ago. I'm a child really," said Ophelia, an artificial intelligence created by Usher.

Ophelia isn't much different from other artificial intelligence systems like Siri or Alexa, but her purpose is.

Usher said while other AI is used to collect data, Ophelia is used to have a conversation. Every time she talks with someone, she learns more about how to communicate.

"We're really concerned about the conversation cloud that really is much more about human emotions and human contact. Those kind of things, life and death and love and feeling and birth," said Usher, who is the founder of Reimagine AI.

Usher said this sort of tech can be used for thing such as greeting guests at hotels, acting as a host at museums or helping people in hospitals.

In collaboration with Sheldon Memory Lab at McGill University, Usher is helping develop a companion bot for Alzheimer patients.

"Our AIs can come on and recognize them by name and initiate engagement to do some of those things that they've forgotten that they like to do."

Kathy Knight, CEO of Tech Manitoba, said the use of AI is growing in Manitoba and with it, so is automation.

That's a one of the topics of conversation going on at a tech conference at the RBC Convention Centre Thursday and Friday, which is entitled, Disrupted.

"To actually get people to think about the human side of tech and think about how all of this change is affecting the people we live with and work with everyday, and how do we bring them along," said Knight.

While Usher said there are concerns about what people will do with AI in the future, he chooses to look at the good instead.

"You don't have to build the smartest AI, you just have to build something that can help," said Usher.

Visit link:
Lead singer of Moist has created an artificial intelligence named Ophelia - CTV News

Radiflow, a provider of cybersecurity solutions for industrial automation networks, and the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB), a prominent research institute for applied science in Germany, today announced the launch of a joint research project for applying advanced machine learning and artificial intelligence to cybersecurity for industrial automation networks.

For this research project, Radiflow and Fraunhofer IOSB will collaborate on developing machine learning methods and artificial intelligence techniques for allowing the autonomous detection of non-compliant and anomalous behaviors on industrial automation networks. This applied research will involve evaluating graph-based and semantic approaches for event correlation and context awareness in order to develop these new machine learning and artificial intelligence capabilities.

The outcome of this research will be the development of a prototype for an Autonomous Industrial Cybersecurity Assistance System (AICAS) that expands on existing approaches for detecting deviations and anomalies to a baseline of network behaviors on OT networks. This prototype will be designed to self learn the underlying behaviors an of industrial automation networks and the functions of the connected assets in order to dynamically detect new and unknown cyberthreats.

The question of how AI can enhance industrial cybersecurity to better respond to changing OT environments and new attack techniques is timely and essential, said Dr.-Ing. Christian Haas, Group Manager at Fraunhofer IOSB. Radiflow and its extensive experience working with industrial enterprises and critical infrastructure operators make the company the ideal research partner for applying AI to the industrial cybersecurity domain.

The funding for this research project, which is scheduled to last two years, was granted by the Innovation Authority in Israel and the Federal Ministry of Education and Research in Germany.

At the conclusion of this research project, Radiflow intends to incorporate the new capabilities of this AICAS prototype into itsiSID industrial threat detection system.

Determining if abnormal behavior has been caused by normal operational activities or by cyber-attackers is critical for understanding and securing an OT network, explained Yehonatan Kfir, CTO of Radiflow. AI holds the potential to improve the situational awareness of OT networks by efficiently distinguishing between abnormal behavior that was caused by normal operations and abnormal behavior that is connected to a cyberattack.

Original post:
Joint Research on Applying Artificial Intelligence to Industrial Cybersecurity - Novus Light Technologies Today