Engineering | Health and medicine | News releases | Public Health | Research | Technology

June 21, 2023

A team led by researchers at the University of Washington has created an app FeverPhone that transforms smartphones into thermometers without adding new hardware. To take someones temperature, the screen of a smartphone is held to a patients forehead. Shown here is lead author Joseph Breda (left), a UW doctoral student in the Paul G. Allen School of Computer Science & Engineering, measuring Richard Lis temperature.Dennis Wise/University of Washington

If youve ever thought you may be running a temperature yet couldnt find a thermometer, you arent alone. A fever is the most commonly cited symptom of COVID-19 and an early sign of many other viral infections. For quick diagnoses and to prevent viral spread, a temperature check can be crucial. Yet accurate at-home thermometers arent commonplace, despite the rise of telehealth consultations.

There are a few potential reasons for that. The devices can range from $15 to $300, and many people need them only a few times a year. In times of sudden demand such as the early days of the COVID-19 pandemic thermometers can sell out. Many people, particularly those in under-resourced areas, can end up without a vital medical device when they need it most.

To address this issue, a team led by researchers at the University of Washington has created an app called FeverPhone, which transforms smartphones into thermometers without adding new hardware. Instead, it uses the phones touchscreen and repurposes the existing battery temperature sensors to gather data that a machine learning model uses to estimate peoples core body temperatures. When the researchers tested FeverPhone on 37 patients in an emergency department, the app estimated core body temperatures with accuracy comparable to some consumer thermometers. The team published its findings March 28 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies.

In undergrad, I was doing research in a lab where we wanted to show that you could use the temperature sensor in a smartphone to measure air temperature, said lead author Joseph Breda, a UW doctoral student in the Paul G. Allen School of Computer Science & Engineering.When I came to the UW, my adviser and I wondered how we could apply a similar technique for health. We decided to measure fever in an accessible way. The primary concern with temperature isnt that its a difficult signal to measure; its just that people dont have thermometers.

Lead author Joseph Breda.Dennis Wise/University of Washington

The app is the first to use existing phone sensors to estimate whether people have fevers. It needs more training data to be widely used, Breda said, but for doctors, the potential of such technology is exciting.

People come to the ER all the time saying, I think I was running a fever. And thats very different than saying I was running a fever, said Dr. Mastafa Springston, a co-author on the study and a UW clinical instructor at the Department of Emergency Medicine in the UW School of Medicine.In a wave of influenza, for instance, people running to the ER can take five days, or even a week sometimes. So if people were to share fever results with public health agencies through the app, similar to how we signed up for COVID exposure warnings, this earlier sign could help us intervene much sooner.

Clinical-grade thermometers use tiny sensors known as thermistors to estimate body temperature. Off-the-shelf smartphones also happen to contain thermistors; theyre mostly used to monitor the temperature of the battery. But the UW researchers realized they could use these sensors to track heat transfer between a person and a phone. The phone touchscreen could sense skin-to-phone contact, and the thermistors could gauge the air temperature and the rise in heat when the phone touched a body.

To test this idea, the team started by gathering data in a lab. To simulate a warm forehead, the researchers heated a plastic bag of water with a sous-vide machine and pressed phone screens against the bag. To account for variations in circumstances, such as different people using different phones, the researchers tested three phone models. They also added accessories such as a screen protector and a case and changed the pressure on the phone.

The researchers used the data from different test cases to train a machine learning model that used the complex interactions to estimate body temperature. Since the sensors are supposed to gauge the phones battery heat, the app tracks how quickly the phone heats up and then uses the touchscreen data to account for how much of that comes from a person touching it. As they added more test cases, the researchers were able to calibrate the model to account for the variations in things such as phone accessories.

Then the team was ready to test the app on people. The researchers took FeverPhone to the UW School of Medicines Emergency Department for a clinical trial where they compared its temperature estimates against an oral thermometer reading. They recruited 37 participants, 16 of whom had at least a mild fever.

To use FeverPhone, the participants held the phones like point-and-shoot cameras with forefingers and thumbs touching the corner edges to reduce heat from the hands being sensed (some had the researcher hold the phone for them). Then participants pressed the touchscreen against their foreheads for about 90 seconds, which the researchers found to be the ideal time to sense body heat transferring to the phone.

Overall, FeverPhone estimated patient core body temperatures with an average error of about 0.41 degrees Fahrenheit (0.23 degrees Celsius), which is in the clinically acceptable range of 0.5 C.

The researchers have highlighted a few areas for further investigation. The study didnt include participants with severe fevers above 101.5 F (38.6 C), because these temperatures are easy to diagnose and because sweaty skin tends to confound other skin-contact thermometers, according to the team. Also, FeverPhone was tested on only three phone models. Training it to run on other smartphones, as well as devices such as smartwatches, would increase its potential for public health applications, the team said.

We started with smartphones since theyre ubiquitous and easy to get data from, Breda said. I am already working on seeing if we can get a similar signal with a smartwatch. Whats nice, because watches are much smaller, is their temperature will change more quickly. So you could imagine having a user put a Fitbit to their forehead and measure in 10 seconds whether they have a fever or not.

Shwetak Patel, a UW professor in the Allen School and the electrical and computer engineering department, was a senior author on the paper, and Alex Mariakakis, an assistant professor in the University of Torontos computer science department, was a co-author. This research was supported by the University of Washington Gift Fund.

For more information, contact Breda at joebreda@cs.washington.edu. Hell be traveling for research starting June 23; his availability for interviews will be limited after that.

For questions specifically for Dr. Mastafa Springston, please contact Susan Gregg at sghanson@uw.edu.

Originally posted here:

An app can transform smartphones into thermometers that ... - University of Washington

Researchers at MIT and Tufts University have developed a new AI model called ConPLex that vastly accelerates drug discovery by predicting drug-protein interactions without the need to calculate the molecules structures. The model can screen over 100 million compounds in a single day, which could significantly reduce drug development failure rates and costs.

By applying a language model to protein-drug interactions, researchers can quickly screen large libraries of potential drug compounds.

Huge libraries of drug compounds may hold potential treatments for a variety of diseases, such as cancer or heart disease. Ideally, scientists would like to experimentally test each of these compounds against all possible targets, but doing that kind of screen is prohibitively time-consuming.

In recent years, researchers have begun using computational methods to screen those libraries in hopes of speeding up drug discovery. However, many of those methods also take a long time, as most of them calculate each target proteins three-dimensional structure from its amino-acid sequence, then use those structures to predict which drug molecules it will interact with.

Researchers at MIT and Tufts University have now devised an alternative computational approach based on a type of artificial intelligence algorithm known as a large language model. These models one well-known example is ChatGPT can analyze huge amounts of text and figure out which words (or, in this case, amino acids) are most likely to appear together. The new model, known as ConPLex, can match target proteins with potential drug molecules without having to perform the computationally intensive step of calculating the molecules structures.

Using this method, the researchers can screen more than 100 million compounds in a single day much more than any existing model.

This work addresses the need for efficient and accurate in silico screening of potential drug candidates, and the scalability of the model enables large-scale screens for assessing off-target effects, drug repurposing, and determining the impact of mutations on drug binding, says Bonnie Berger, the Simons Professor of Mathematics, head of the Computation and Biology group in MITs Computer Science and Artificial Intelligence Laboratory (CSAIL), and one of the senior authors of the new study.

Lenore Cowen, a professor of computer science at Tufts University, is also a senior author of the paper, which was published on June 8 in the Proceedings of the National Academy of Sciences. Rohit Singh, a CSAIL research scientist, and Samuel Sledzieski, an MIT graduate student, are the lead authors of the paper, and Bryan Bryson, an associate professor of biological engineering at MIT and a member of the Ragon Institute of MGH, MIT, and Harvard, is also an author. In addition to the paper, the researchers have made their model available online for other scientists to use.

In recent years, computational scientists have made great advances in developing models that can predict the structures of proteins based on their amino-acid sequences. However, using these models to predict how a large library of potential drugs might interact with a cancerous protein, for example, has proven challenging, mainly because calculating the three-dimensional structures of the proteins requires a great deal of time and computing power.

An additional obstacle is that these kinds of models dont have a good track record for eliminating compounds known as decoys, which are very similar to a successful drug but dont actually interact well with the target.

One of the longstanding challenges in the field has been that these methods are fragile, in the sense that if I gave the model a drug or a small molecule that looked almost like the true thing, but it was slightly different in some subtle way, the model might still predict that they will interact, even though it should not, Singh says.

Researchers have designed models that can overcome this kind of fragility, but they are usually tailored to just one class of drug molecules, and they arent well-suited to large-scale screens because the computations take too long.

The MIT team decided to take an alternative approach, based on a protein model they first developed in 2019. Working with a database of more than 20,000 proteins, the language model encodes this information into meaningful numerical representations of each amino-acid sequence that capture associations between sequence and structure.

With these language models, even proteins that have very different sequences but potentially have similar structures or similar functions can be represented in a similar way in this language space, and were able to take advantage of that to make our predictions, Sledzieski says.

In their new study, the researchers applied the protein model to the task of figuring out which protein sequences will interact with specific drug molecules, both of which have numerical representations that are transformed into a common, shared space by a neural network. They trained the network on known protein-drug interactions, which allowed it to learn to associate specific features of the proteins with drug-binding ability, without having to calculate the 3D structure of any of the molecules.

With this high-quality numerical representation, the model can short-circuit the atomic representation entirely, and from these numbers predict whether or not this drug will bind, Singh says. The advantage of this is that you avoid the need to go through an atomic representation, but the numbers still have all of the information that you need.

Another advantage of this approach is that it takes into account the flexibility of protein structures, which can be wiggly and take on slightly different shapes when interacting with a drug molecule.

To make their model less likely to be fooled by decoy drug molecules, the researchers also incorporated a training stage based on the concept of contrastive learning. Under this approach, the researchers give the model examples of real drugs and imposters and teach it to distinguish between them.

The researchers then tested their model by screening a library of about 4,700 candidate drug molecules for their ability to bind to a set of 51 enzymes known as protein kinases.

From the top hits, the researchers chose 19 drug-protein pairs to test experimentally. The experiments revealed that of the 19 hits, 12 had strong binding affinity (in the nanomolar range), whereas nearly all of the many other possible drug-protein pairs would have no affinity. Four of these pairs bound with extremely high, sub-nanomolar affinity (so strong that a tiny drug concentration, on the order of parts per billion, will inhibit the protein).

While the researchers focused mainly on screening small-molecule drugs in this study, they are now working on applying this approach to other types of drugs, such as therapeutic antibodies. This kind of modeling could also prove useful for running toxicity screens of potential drug compounds, to make sure they dont have any unwanted side effects before testing them in animal models.

Part of the reason why drug discovery is so expensive is because it has high failure rates. If we can reduce those failure rates by saying upfront that this drug is not likely to work out, that could go a long way in lowering the cost of drug discovery, Singh says.

This new approach represents a significant breakthrough in drug-target interaction prediction and opens up additional opportunities for future research to further enhance its capabilities, says Eytan Ruppin, chief of the Cancer Data Science Laboratory at the National Cancer Institute, who was not involved in the study. For example, incorporating structural information into the latent space or exploring molecular generation methods for generating decoys could further improve predictions.

Reference: Contrastive learning in protein language space predicts interactions between drugs and protein targets by Rohit Singh, Samuel Sledzieski, Bryan Bryson, Lenore Cowen and Bonnie Berger, 8 June 2023, Proceedings of the National Academy of Sciences.DOI: 10.1073/pnas.2220778120

The research was funded by the National Institutes of Health, the National Science Foundation, and the Phillip and Susan Ragon Foundation.

View post:

Accelerating Drug Discovery With the AI Behind ChatGPT ... - SciTechDaily

(June 16, 2023 / JNS)

The Hebrew University of Jerusalem (HU) presented world-renowned computer science researcher and co-founder of database theory, Professor Jeffrey D. Ullman, with a prestigious Honorary Doctorate degree during the 86th Board of Governors Meeting on June 12 in Jerusalem.

Professor Ullman, the Stanford W. AschermanProfessor of Computer Science (Emeritus),has been a leader in the database theory field. His highly influential textbooks revolutionized the content of database courses that have educated generations of distinguished computer scientists. Professor Ullman was the Ph.D. advisor for Google Co-Founder Sergey Brin and served on Googles technical advisory board.

He is also a Co-Founder& Chief Executive Officer of Gradiance Corporation, which designs homework and labs that encourage students to learn from their mistakes and complete assignments correctly.

At the ceremony, HU President Professor Asher Cohen conferred upon Professor Ullman the degree of Doctor Philosophiae Honoris Causa, In recognition of his tremendous contributions to the field of computer science, in tribute to his academic achievements, including the prestigious A.M. Turing Award; and with immense gratitude for his and Hollys close friendship with the Hebrew University of Jerusalem, including their support of teaching assistants and an endowed lectureship.

Acknowledging the accolade, Professor Ullman said, I am honored to receive this degree and have been pleased to witness Hebrew Universitys success encouraging researcher cooperation and applying computer science big data and evaluative techniques to new fields of study. This helps break down academic silos, encourages new directions in research, and advances the Hebrew Universitys mission to expand the boundaries of knowledge in service to Israel and the world.

Professor Ullman and his wife, Holly, have been involved with Hebrew University for many years. They have pledged a $1 million gift to the university for the Scharf-Ullman Endowed Lectureship in Data and Computing Research and the Scharf-Ullman Graduate Scholarship Fund for Data and Computing Research. This gift also encourages cooperation between computer scientists and researchers in fields as diverse as medicine, political science, agriculture, and archaeology.

In 2020, he was a co-recipient of the Association of Computing Machinerys A.M. Turing Award, the highest distinction in computer science. It celebrated Professor Ullmans contributions of lasting and major technical importance to computer science.

Other prizes and awards include the Donald E. Knuth Prize, the SIGMOD Edgar F. Codd Innovations Award, and the IEEE John von Neumann Medal. He has received Honorary Doctorates from the Free University of Brussels (1975); the University of Paris-Dauphine (1992); and Ben-Gurion University of the Negev (2016).

Professor Ullman has served on numerous technical and scientific advisory boards, editorial boards, and corporate boards of directors, sharing his expertise with government agencies, commercial companies, and start-ups. He has also contributed to committees at academic and government institutions across the United States, Canada, Israel, Australia, Singapore, and Japan.

He is a member of the American Academy of Arts and Sciences and the National Academy of Engineering and Science and a fellow of the Association for Computing Machinery.

Professor Ullman received a Doctor of Philosophy in Electrical Engineering from Princeton University in 1966 and a Bachelor of Science in Engineering Mathematics from Columbia University in 1963.

He lives with his wife, Holly, in Stanford, California.

About the Hebrew University of Jerusalem

The Hebrew University of Jerusalem is Israels premier academic and research institution. Serving over 23,000 students from 80 countries, the university produces nearly 40% of Israels civilian scientific research and has received over 11,000 patents. Faculty and alumni of the Hebrew University have won eight Nobel Prizes and a Fields Medal. For more information about the Hebrew University, visit: http://new.huji.ac.il/en.

About American Friends of the Hebrew University

American Friends of the Hebrew University (AFHU) is a national, not-for-profit organization based in the United States. AFHU is headquartered in New York and has seven regional offices working in close partnership with the Hebrew University of Jerusalem. AFHU provides supporters, Hebrew University alumni, and the public with stimulating programs and events and organizes missions to Israel. The organizations activities support scholarly and scientific achievement at HU, create scholarships, fund new facilities, and assist the universitys efforts to recruit outstanding new faculty.

For more information, visit http://www.afhu.org.

JNS serves as the central hub for a thriving community of readers who appreciate the invaluable context our coverage offers on Israel and their Jewish world.

Please join our community and help support our unique brand of Jewish journalism that makes sense.

Link:

Hebrew University confers Honorary Doctorate degree on Professor ... - JNS.org

JEE Advanced 2023:The Indian Institute of Technology (IIT), Goa is one of the six new IITs that was incorporated by amending the The Institutes of Technology Act, 1961 by the Union Cabinet. The institute comes under the aegis of Ministry of Education, Government of India. The admissions to various BTech courses at IIT Goa are done on the basis of the ranks scored in JEE Advanced.

You have exhausted your monthly limit of free stories.

To continue reading,simply register or sign in

Subscribe to read on

Select your plan

All-Access

Digital Only

This premium article is free for now.

Register to continue reading this story.

This content is exclusive for our subscribers.

Subscribe to get unlimited access to The Indian Express exclusive and premium stories.

This content is exclusive for our subscribers.

Subscribe now to get unlimited access to The Indian Express exclusive and premium stories.

IE Online Media Services Pvt Ltd

First published on: 03-06-2023 at 09:52 IST

Read more:

JEE Advanced 2023: Last 5 years BTech Computer Science cut-off for admission in IIT Goa - The Indian Express

Programming will be obsolete, Matt Welsh, a former engineer at Google and Apple, predicted recently. Welsh now runs an A.I. start-up, but his prediction, while perhaps self-serving, doesnt sound implausible:

I believe the conventional idea of writing a program is headed for extinction, and indeed, for all but very specialized applications, most software, as we know it, will be replaced by A.I. systems that are trained rather than programmed. In situations where one needs a simple program those programs will, themselves, be generated by an A.I. rather than coded by hand.

Welshs argument, which ran earlier this year in the house organ of the Association for Computing Machinery, carried the headline The End of Programming, but theres also a way in which A.I. could mark the beginning of a new kind of programming one that doesnt require us to learn code but instead transforms human-language instructions into software. An A.I. doesnt care how you program it it will try to understand what you mean, Jensen Huang, the chief executive of the chip-making company Nvidia, said in a speech this week at the Computex conference in Taiwan. He added: We have closed the digital divide. Everyone is a programmer now you just have to say something to the computer.

Wait a second, though wasnt coding supposed to be one of the cant-miss careers of the digital age? In the decades since I puttered around with my Spectrum, computer programming grew from a nerdy hobby into a vocational near-imperative, the one skill to acquire to survive technological dislocation, no matter how absurd or callous-sounding the advice. Joe Biden to coal miners: Learn to code! Twitter trolls to laid-off journalists: Learn to code! Tim Cook to French kids: Apprenez programmer!

Programming might still be a worthwhile skill to learn, if only as an intellectual exercise, but it would have been silly to think of it as an endeavor insulated from the very automation it was enabling. Over much of the history of computing, coding has been on a path toward increasing simplicity. Once, only the small priesthood of scientists who understood binary bits of 1s or 0s could manipulate computers. Over time, from the development of assembly language through more human-readable languages like C and Python and Java, programming has climbed what computer scientists call increasing levels of abstraction at each step growing more removed from the electronic guts of computing and more approachable to the people who use them.

A.I. might now be enabling the final layer of abstraction: the level on which you can tell a computer to do something the same way youd tell another human.

So far, programmers seem to be on board with how A.I. is changing their jobs. GitHub, the coders repository owned by Microsoft, surveyed 2,000 programmers last year about how theyre using GitHubs A.I. coding assistant, Copilot. A majority said Copilot helped them feel less frustrated and more fulfilled in their jobs; 88 percent said it improved their productivity. Researchers at Google found that among the companys programmers, A.I. reduced coding iteration time by 6 percent.

The rest is here:

Opinion | It's the End of Computer Programming as We Know It. (And I Feel Fine.) - The New York Times