(Press-News.org) With the rapid development in computing power over the past few decades, machine-learning (ML) techniques have become popular in medical settings as a way to predict survival rates and life expectancies among patients diagnosed with diseases such as cancer, heart disease, stroke, and, more recently, COVID-19. Such statistical modeling helps patients and caregivers balance treatment that offers the highest chance of a cure while minimizing the consequences of potential side effects.
A professor and his doctoral student at The University of Texas at Arlington have published a new model of predicting survival from cancer that they say is 30% more effective than previous models in predicting who will be cured of disease. This model can help patients avoid treatments they don’t need while allowing treatment teams to focus instead on others who need additional interventions.
“Previous studies modeling the probability of a cure, also called the cure rate, used a generalized linear model with a known parametric link function such as the logistic link function. However, this type of research doesn’t capture non-linear or complex relationships between the cure probability and important covariates, such as the age of the patient or the age of a bone marrow donor,” said principal investigator Suvra Pal, associate professor of statistics in the Department of Mathematics. “Our research takes the previously tested promotion time cure model (PCM) and combines it with a supervised type of ML algorithm called a support vector machine (SVM) that is used to capture non-linear relationships between covariates and cure probability.”
Supported by a grant from the National Institute of General Medical Sciences, the new SVM-integrated PCM model (PCM-SVM) is developed in a way that builds upon a simple interpretation of covariables to predict which patients will be uncured at the end of their initial treatment and need additional medical interventions.
To test the technique, Pal and his student Wisdom Aselisewine took real survival data for patients with leukemia, a type of blood cancer that is often treated with a bone marrow transplant. The researchers chose leukemia because it is caused by the rapid production of abnormal cancerous, white blood cells. Since this does not happen in healthy people, they were able to clearly see which patients in the historic data set were cured by treatments and which were not.
Both statistical models were tested and the newer PCM-SVM technique was found to be 30% more effective at predicting who would be cured by the treatments compared to the previous technique.
“These findings clearly demonstrate the superiority of the proposed model,” Pal said. “With our improved predictive accuracy of cure, patients with significantly high cure rates can be protected from the additional risks of high-intensity treatments. Similarly, patients with low cure rates can be recommended timely treatment so that the disease does not progress to an advanced stage for which therapeutic options are limited. The proposed model will play an important role in defining the optimal treatment strategy.”
END
New machine learning technique 30% better at predicting cancer cure rates
UTA study is first to integrate two types of modeling techniques to predict cancer recurrences
2023-11-20
ELSE PRESS RELEASES FROM THIS DATE:
Potential therapeutic target found to combat tuberculosis, a disrupted NAD(H) homeostasis
2023-11-20
BIRMINGHAM, Ala. – It has been uncertain how Mycobacterium tuberculosis deflects the immune response in humans, though evidence has pointed to host immunometabolism — the intrinsic link between metabolism in immune cells and their immune function. The pathogen M. tuberculosis is known to disrupt a metabolic pathway called glycolysis in infected myeloid cells, which include macrophages, through an unclear mechanism.
A more accurate understanding of this pathogenic mechanism could provide a target against the bacterium that caused 1.6 million deaths in 2021, along with 10 million new cases of tuberculosis every year.
Now a study published ...
Global Neuroanatomy Network (GNN): Creating a new resource for neuro educators
2023-11-20
In a leap forward for neuroanatomy education, the Global Neuroanatomy Network (GNN) is about to launch, creating a new, accessible, peer-reviewed collection of resources for instructors around the world. Developed as a response to the challenges faced in transitioning neuroanatomy education to an online format during the pandemic, the GNN represents a collaborative effort by educators globally.
The initiative began as a conversation on social media, recognizing the need for better resources and support for teaching neuroanatomy online. As educators ...
New research demonstrates more effective method for measuring impact of scientific publications
2023-11-20
Newly published research reexamines the evaluation of scientific findings, proposing a network-based methodology for contextualizing a publication’s impact.
This new method, which is laid out in an article co-authored by Alex Gates, an assistant professor with the University of Virginia’s School of Data Science, will allow the scientific community to more fairly measure the impact of interdisciplinary scientific discoveries across different fields and time periods. The article was published ...
UCSB scientists will eliminate bottlenecks to breakthroughs with a newly acquired synthetic biology robotics system
2023-11-20
Researchers in UC Santa Barbara’s newly designated Biological Engineering (BioE) Department have received a significant boost from the U.S. Army, which awarded the university a $9.85 million grant to design and purchase state-of-the-art equipment that project leader Michelle O’Malley, a professor of chemical engineering and biological engineering, says “allows UCSB scientists to do things that we never thought were possible.” The funding, awarded through the Department of Defense’s Defense University Research ...
NASA’s Webb reveals new features in heart of Milky Way
2023-11-20
The latest image from NASA’s James Webb Space Telescope shows a portion of the dense center of our galaxy in unprecedented detail, including never-before-seen features astronomers have yet to explain. The star-forming region, named Sagittarius C (Sgr C), is about 300 light-years from the Milky Way’s central supermassive black hole, Sagittarius A*.
“There’s never been any infrared data on this region with the level of resolution and sensitivity we get with Webb, so we are seeing lots of features here for the first time,” said the observation team’s principal investigator Samuel Crowe, an undergraduate student at the University ...
UC Irvine-led study is first to find brain hemorrhage cause other than injured blood vessels
2023-11-20
Irvine, Calif., Nov. 20, 2023 — A first-of-its-kind study led by the University of California, Irvine has revealed a new culprit in the formation of brain hemorrhages that does not involve injury to the blood vessels, as previously believed. Researchers discovered that interactions between aged red blood cells and brain capillaries can lead to cerebral microbleeds, offering deeper insights into how they occur and identifying potential new therapeutic targets for treatment and prevention.
The ...
AI outperforms expert plastic surgeon in rhinoplasty consultations
2023-11-20
In a new study, artificial intelligence in the form of ChatGPT outperformed an expert rhinoplasty surgeon in answering preoperative and postoperative patient questions related to nasal surgery. ChatGPT earned significantly higher ratings in accuracy, completeness, and overall quality, according to the study published in Facial Plastic Surgery & Aesthetic Medicine. Click here to read the article now.
Kay Durairaj, MD, and Omer Baker, from Pasadena, California , Dario Bertossi, MD, from University of Verona, Steven Dayan, MD, from University of Illinois, Chicago, Kian Karimi, MD, from Los Angeles California, Roy Kim, MD, from San Francisco, California, Sam ...
People watched other people shake boxes for science. Here’s why
2023-11-20
When researchers asked hundreds of people to watch other people shake boxes, it took just seconds for almost all of them to figure out what the shaking was for.
The deceptively simple work by Johns Hopkins University perception researchers is the first to demonstrate that people can tell what others are trying to learn just by watching their actions. Published today in the journal Proceedings of the National Academy of Sciences, the study reveals a key yet neglected aspect of human cognition, and one with implications for artificial intelligence.
“Just by looking ...
AI finds formula on how to predict monster waves
2023-11-20
Long considered myth, freakishly large rogue waves are very real and can split apart ships and even damage oil rigs. Using 700 years’ worth of wave data from more than a billion waves, scientists at the University of Copenhagen and University of Victoria have used artificial intelligence to find a formula for how to predict the occurrence of these maritime monsters. The new knowledge can make shipping safer.
EMBARGOED CONTENT UNTIL MONDAY 20 NOVEMBER 2023 3 PM US EASTERN TIME
Stories about monster waves, called rogue waves, have been the lore of sailors for centuries. But when a 26-metre-high rogue wave slammed into the Norwegian oil ...
Study reveals bias in AI tools when diagnosing women’s health issue
2023-11-20
Machine learning algorithms designed to diagnose a common infection that affects women showed a diagnostic bias among ethnic groups, University of Florida researchers found.
While artificial intelligence tools offer great potential for improving health care delivery, practitioners and scientists warn of their risk for perpetuating racial inequities. Published Friday in the Nature journal Digital Medicine, this is the first paper to evaluate fairness among these tools in connection to a women’s health issue.
“Machine learning can be a great tool in medical diagnostics, but we found it can show bias toward different ethnic groups,” said Ruogu Fang, an associate ...
LAST 30 PRESS RELEASES:
Intra-arterial tenecteplase for acute stroke after successful endovascular therapy
Study reveals beneficial microbes that can sustain yields in unfertilized fields
Robotic probe quickly measures key properties of new materials
Climate change cuts milk production, even when farmers cool their cows
Frozen, but not sealed: Arctic Ocean remained open to life during ice ages
Some like it cold: Cryorhodopsins
Demystifying gut bacteria with AI
Human wellbeing on a finite planet towards 2100: new study shows humanity at a crossroads
Unlocking the hidden biodiversity of Europe’s villages
Planned hydrogen refuelling stations may lead to millions of euros in yearly losses
Planned C-sections increase the risk of certain childhood cancers
Adults who have survived childhood cancer are at increased risk of severe COVID-19
Drones reveal extreme coral mortality after bleaching
New genetic finding uncovers hidden cause of arsenic resistance in acute promyelocytic leukemia
Native habitats hold the key to the much-loved smashed avocado’s future
Using lightning to make ammonia out of thin air
Machine learning potential-driven insights into pH-dependent CO₂ reduction
Physician associates provide safe care for diagnosed patients when directly supervised by a doctor
How game-play with robots can bring out their human side
Asthma: patient expectations influence the course of the disease
UNM physician tests drug that causes nerve tissue to emit light, enabling faster, safer surgery
New study identifies EMP1 as a key driver of pancreatic cancer progression and poor prognosis
XPR1 identified as a key regulator of ovarian cancer growth through autophagy and immune evasion
Flexible, eco-friendly electronic plastic for wearable tech, sensors
Can the Large Hadron Collider snap string theory?
Stuckeman professor’s new book explores ‘socially sustainable’ architecture
Synthetic DNA nanoparticles for gene therapy
New model to find treatments for an aggressive blood cancer
Special issue of Journal of Intensive Medicine analyzes non-invasive respiratory support
T cells take aim at Chikungunya virus
[Press-News.org] New machine learning technique 30% better at predicting cancer cure ratesUTA study is first to integrate two types of modeling techniques to predict cancer recurrences