The Team Behind the Tool

Moore has spent much of his career looking for ways to battle sepsis. Recognizing the diagnostic potential of AI, he sought to collaborate with UVA experts.

He phoned a friend, UVA Engineerings Rich Nguyen.

Nguyen, an assistant professor in the Department of Computer Science, who also has an appointment in the School of Data Science, specializes in AI. He put together the cross-disciplinary team.

Were aiming in this collaboration for the computer scientists and the data scientists to be embedded into the clinical settings, Nguyen said.

The two fourth-year students have served as his research assistants.

Edwards, the statistics major, is minoring in computer science and social entrepreneurship. Boner, a Rodman Scholar, gained experience as a software research intern and as an extern with Cisco before starting on the sepsis project.

As part of their work, the students spent time in the medical ICU, making rounds with medical teams under the direction of Drs. Taison Bell and Kyle Enfield.

Behind the computer, The team has developed a data engineering pipeline, Nguyen said. They perform statistical and computational analysis on large-scale clinical data, which allows for fast experimentation with different machine learning models.

The team also includes Joy Qiu, a 2020 School of Data Science alumna, who works at the Center for Advanced Medical Analytics in the UVA School of Medicine.

Computer science alumni Matthew Pillari, a 2022 graduate, and Navid Jahromi, a 2021 graduate, were previously on the project. Pillari is now a machine learning engineer at Imagen, while Jahromi is a software engineer at Palantir Technologies.

Its important to note that no health care decisions have yet been made based on the tool.

Thats because the AI is still learning. And in order to learn, the AI is dipping into a vast archive of biometrics. The data is essentially played back, as if in real time, starting with the beginning of a patients stay.

Were feeding the AI a bunch of datasets, Boner said. The model is learning to match those data to tell us either, yes, the patient had bloodstream infection, or no, they didnt have bloodstream infection. We have that ground truth from the medical records. And, so, the AI is learning patterns in the time series that we have, and patterns in the way that a patients condition is changing over time, that might suggest bloodstream infection.

The effort is looking closely at specific types of patients, such as transplant recipients, because they can have differing physiological responses to infection, Moore said.

Thats resulted in some new discoveries.

Transplant patients are immunocompromised, the doctor explained. Thats due to receiving anti-rejection medicines. They are thought to not mount the same clinical signature of physiological response to infection as immunocompetent patients.

Our data suggest that they do, in fact, mount a robust response. But its likely not the same response as an immunocompetent patient. This finding may help us better identify bloodstream infections in this patient population.

One dilemma for doctors caring for transplant patients is intervention versus risk. Overuse of antibiotics, for example, can lead to antibiotic resistance and other unintended effects.

Having AI that can read the nuanced differences among individuals would allow for better-informed, more personalized care.

Like the technology itself, the students have been doing a lot of deep learning.

Edwards said she learned about the challenges associated with using AI in medicine. Being able to gain the direct insights of doctors and other medical professionals boosted her own understanding, she said. In turn, she hopes that translates to the tool.

Within our research, I focus specifically on explainable artificial intelligence, she said. Explainability refers to an AI models ability to explain its behavior in human terms. Many of the most powerful machine learning models are so complex that the way they make predictions isnt clearly understood. Explainability is critical for building trust in a machine learning model, and its especially important in a clinical setting where lives are at stake.

She added that, no matter where her career ends up taking her, she hopes to continue working at the intersection of technology and social impact.

Boner, in addition to contributing to the AIs deep-learning layers, wrote a conference paper with Nguyen and Moore as part of an undergraduate consortium.

Through this project, Ive learned, first and foremost, how to do research, Boner said. Ive collaborated with both technical and non-technical researchers toward a common goal, which has been very valuable.

He plans to pursue a doctorate in computer science at Duke University, where hell be focusing on interpretable AI for health care applications.

Moore praised both students many contributions to the project.

Louisa and Zack have been integral members of our research team, Moore said. Not only are they extremely talented and technically gifted in computer science and AI, but they are also intellectually curious and bring a fresh set of eyes and ideas to the problem of infection detection in the ICU. They have been a pleasure to work with, and Ive learned a lot from them.

Currently, the AI has the combined wisdom of 40,500 anonymized patient records, consisting of 4.1 million laboratory measurements, from which to draw.

Continued here:

Class of '23: UVA Developed AI To Spot Early Sepsis. 2 Undergrads ... - UVA Today

Google announced on Thursday a $150,000 grant to South Carolina 4-H to help promote computer science education in Greenville.

GREENVILLE, S.C. (WSPA) Google announced on Thursday a $150,000 grant to South Carolina 4-H to help promote computer science education.

The grant was announced during a youth coding event at Berea Middle School, during which students learned basic coding skills and heard from Rep. William Timmons, of Greenville.

South Carolina and the Upstate have seen a growing demand for computer science jobs, making it essential that we provide access and encouragement for K-12 students to pursue this important field, said Timmons.I am thrilled to see that Google has partnered with 4-H to provide greater access to computer science education in our state, setting these students up for growth and giving them the tools they need to succeed.

According to Code.org, 96% of South Carolina high school students attend a school that offers foundational computer science, yet only 26% of students are enrolled in a computer science course.

In 2022, South Carolina averaged 6,349 open computing jobs each month, with an average salary of $77,383, yet the state had only 806 graduates in computer science in 2019.

Thursdays grant aims to help promote computer science education through CLOVER by 4-H, an e-learning platform and the Clemson University Cooperative Extensions 4-H program.

The new funding, Google said, would increase the reach of the CS Career Pathway Program for students from 57,000 students to around 70,000 students.

By creating opportunities for all young people regardless of circumstance, Clemson Extension and 4-H play a vital role in preparing todays youth for the careers of tomorrow, saidAshley Burns, 4-H Youth Development Program Team Director, Clemson University Cooperative Extension. Google.orgs investment in the 4-H CS Pathway Program has greatly increased our capacity to deliver high-impact CS programming across the state, setting students on a trajectory to unlock their potential and thrive.

View original post here:

Google gives $150,000 to promote youth coding in Upstate - WSPA 7News

Google.org announced a $150,000 grant to South Carolina 4-H during a coding event for local middle school students in Greenville, South Carolina, as part of a statewide effort to help expand access to computer science education in the state.

With the new funding from Google.org, 4-H will increase the reach of the CS Career Pathway program for students in the state by 20 percent, from 57,000 to around 70,000 students. As a result, young people across the state will now have expanded access to CS education through Clemson University Cooperative Extensions 4-H program and the e-learning platform CLOVER by 4-H.

Students at Berea Middle School participated in the event, during which they learned basic coding skills and heard remarks from U.S. Rep. William Timmons of Greenville about the importance of computer science education.

South Carolina and the Upstate have seen a growing demand for computer science jobs, making it essential that we provide access and encouragement for K-12 students to pursue this important field, said U.S. Rep. William Timmons of Greenville. I am thrilled to see that Google has partnered with 4-H to provide greater access to computer science education in our state, setting these students up for growth and giving them the tools they need to succeed.

According to the 2022 State of Computer Science Education from Code.org, 96 percent of South Carolina high school students attend a school that offers foundational computer science, yet only 26 percent of students are enrolled in a computer science course. In 2022, South Carolina averaged 6,349 open computing jobs each month, with an average salary of $77,383, yet the state had only 806 graduates in computer science in 2019.

By creating opportunities for all young people regardless of circumstance, Clemson Extension and 4-H play a vital role in preparing todays youth for the careers of tomorrow, said Ashley Burns, 4-H Youth Development Program Team Director, Clemson University Cooperative Extension. Google.orgs investment in the 4-H CS Pathway Program has greatly increased our capacity to deliver high-impact CS programming across the state, setting students on a trajectory to unlock their potential and thrive.

In 2022, Google.org announced a $5 million grant to the National 4-H Council to extend CS education access to six million 4-Hers across the country. In South Carolina, this new funding will help continue and expand previous work related to CS and computational thinking skills.

Google.org has supported 4-H to expand access to CS education since 2017.

Here is the original post:

Google invests $150K in 4-H computer science in S.C. - AGDAILY

Infographic by Anna Chung

By Bonnie Zhao 4/4/23 11:42pm

The computer science department held a town hall announcing the redesigned COMP curriculum to students on Tuesday, March 21. The new curriculum includes many changes to the major requirements for both Bachelor of Arts and Bachelor of Science degrees, according to a document shared with COMP majors.

Alan Cox, the Associate Department Chair and chair of the COMP working group reevaluating the major, said the working group was created last fall to review the existing curriculum and to develop the proposed changes. According to Cox, the group consists of seven faculty members across different areas of the department.

It had been over a decade since we had done a top-to-bottom review of our curriculum. Computer science is a rapidly evolving field, and so we felt that the time had come, Cox wrote in an email to the Thresher. The university has placed a renewed emphasis on achieving a better balance between the major and general education. In support of this university-wide goal, we reduced the major requirements for the B.S. degree so that the total credit hours to earn the degree is reduced from 128-129 down to 120.

For both B.A. and B.S. degrees, three new courses are being introduced to the new curriculum as major requirements including COMP 312, replacing the previous major requirement COMP 411/412; COMP 318, replacing the previous major requirement COMP 322, which might not be offered as a course after spring 2024; and COMP 221.

In addition, ELEC 220 and COMP 421 will no longer be major requirements, with the latter becoming an elective course instead. COMP 310 is no longer required and might not be offered as a course after fall 2023.

Specific to the B.S. degree, the COMP capstone will be replaced by COMP breadth courses, and PHYS 101 and 102 will no longer be major requirements.

Enjoy what you're reading?Sign up for our newsletter

The working group aims to include changes to the degree requirements in the General Announcements for the fall 2023 and spring 2024 academic year. If the plan materializes, current students who plan to graduate in fall 2023 and beyond will have the option to choose to graduate under either the old requirements or the new requirements.

Sarah Yao, a Baker College junior, said she has already taken most of her major requirement courses, so it makes more sense for her to follow the old COMP curriculum. However, she believes the new changes could be beneficial for underclassmen.

They made COMP 310 into COMP 318, which has updated contents in order to teach the students programming design and object-oriented programming. Another good change is making physics not required for the B.S. curriculum, since that was something that impeded people from [pursuing the] B.S. CS, Yao said. Before the change in curriculum, due to the strict class prerequisites, it would be very hard to transition to COMP major starting in sophomore spring semester. But now, logistically, it can be possible.

Ian Carroll, a Brown College junior, said he likes the new B.A. requirements for many reasons, one of which is how they shift away from some of the higher level courses in favor of lower-level equivalents. He also mentioned an appreciation for ethics as a core requirement since he believes it is an essential aspect of the field, prompting students to consider topics like data privacy and misuse of software.

I think it allows for a nicer introduction for a lot of the topics and reduces a lot of the stress classes like 310 and 421 put with their faster paced or larger projects, Carroll said. I really like the idea of changing the B.A. to require a design capstone, since that gives a lot more experience like a real world project in terms of scale and scope.

Carroll said he similarly appreciates the removal of physics requirements and the changes to the capstone requirement for the B.S.

I think everyone is happy physics is gone, as most of us didnt know why it was there in the first place, and it definitely makes the B.S. a lot more manageable for students, Carroll said. The new requirements make it much clearer, in that youre getting experience in a range of higher level topics. I wish I had these B.S. requirements coming into Rice, as I would definitely pursue them if I had more time.

Aaron Wang, a Baker senior, said he believes the new COMP curriculum is more flexible, yet also less rigorous.

The reality is that 80% of COMP majors aim for a good paying job, not to become a computer scientist, Wang said. Those who do want to go into academia can still take the electives. Its a shame COMP 310 might be canceled. Most people I know just wanted it to be separated into two courses again.

Stephen Wong, a lecturer of computer science and the instructor for COMP 310, said that he believes the department has decided to completely remove the course from the curriculum after the fall semester of 2023.

Its not even an option, Wong said. [Itll lead to] this glaring hole in terms of the object-oriented programming and design in the curriculum. And the problem there is that object-oriented design is the major programming paradigm in use today in the world People going out into the world absolutely have to have this training. We cannot send them out into the world without it.

Wong said that a lack of a strong object-oriented programming design course will impede students ability to prepare for both upper-level design courses such as COMP 410 and the industry.

I worry that the department is bowing to pressures of perceived difficulty, Wong said. Were falling behind. Other people are increasing what theyre doing this year, and were decreasing Youve got these tech companies laying off left and right right now Reducing the critical skills and knowledge of our students is the last thing we should be doing at this point. We should be doing everything we can to make our students more competitive, not less competitive.

Continue reading here:

Computer Science debuts redesigned curriculum - The Rice Thresher

Nilanjana Raychawdhary, a second-year graduate student in computer science and software engineering, or CSSE, has an opportunity to expand existing research ideas through networking and learning from others by earning an invitation to the Computing Research Association- Widening Participating Graduate Cohort for Women, April 20-22 in San Francisco. Attendees have the opportunity to interact with senior female computing-related researchers and professionals who will share pertinent information on graduate school survival skills and personal insights.

By attending the special CRA-WP cohort, I hope to learn about the latest advancements and trends in the field of computer science research, particularly in my area of focus, said Raychawdhary, who will join CSSE classmate and graduate student Prashamsa Pandey at the conference. I would also like to connect with other researchers and experts in the field to expand my network and gain insights into different approaches and methodologies. Ultimately, I hope to bring back new knowledge and perspectives that I can apply to my research and education, helping me to further develop my skills and make meaningful contributions to the field.

Full story onRaychawdhary.

Read the original post:

Student in computer science and software engineering awarded ... - Office of Communications and Marketing