(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.”
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
ELSE PRESS RELEASES FROM THIS DATE:
Potential therapeutic target found to combat tuberculosis, a disrupted NAD(H) homeostasis
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
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
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
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
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
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
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
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
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
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:
ASH: Novel combination therapy significantly reduces spleen volume in patients with myelofibrosis
ASH: Novel menin inhibitors show promise for patients with advanced acute myeloid leukemias
ASH: Targeted oral therapy reduced disease burden and improved symptoms for patients with rare blood disorder
New Sylvester cancer study provides insight into underlying gene mutations in myelodysplastic syndromes
First-in-human clinical trial of CAR T cell therapy with new binding mechanism shows promising early responses
Long-term results show combination treatment that skips chemotherapy is effective for older patients with Ph+ ALL
Mindfulness could help women with opioid use disorder better control drug urges
TTUHSC’s ARPA-H membership will spur innovation, improve access for West Texas patients
Global annual finance flows of $7 trillion fueling climate, biodiversity, and land degradation crises
Tracing how the infant brain responds to touch with near-infrared spectroscopy
These are the world's most effective charities
When is an aurora not an aurora?
Advisory panel issues field-defining recommendations for US government investments in particle physics research
Doctors discover many patients at UNC’s Inflammatory Bowel Disease Clinic screen positive for malnutrition
BNL: Advisory panel issues field-defining recommendations for U.S. government investments in particle physics research
International collaboration uses faculty member’s research on ancient Roman migration, seeks to understand Balkan genomic history
USF Health Heart Institute doctors are upbeat about cardiac regeneration
AI-driven breakthroughs in cells study: SFU-UBC collaboration introduces "MCS-detect" for advancements in super-resolution microscopy
Advisory panel issues field-defining recommendations for investments in particle physics research
$3.8 million NIH grant to fund Southwest Center on Resilience for Climate Change and Health
What happens when the brain loses a hub?
Study reveals Zika’s shape-shifting machinery—and a possible vulnerability
RIT leading STEM co-mentoring network
Genetic mutations that promote reproduction tend to shorten human lifespan, study shows
CAMH develops potential new drug treatment for multiple sclerosis
Polyethylene waste could be a thing of the past
A dynamic picture of how we respond to high or low oxygen levels
University of Toronto researchers discover new lipid nanoparticle that shows muscle-specific mRNA delivery, reduces off-target effects.
Evolving insights in blood-based liquid biopsies for prostate cancer interrogation
Finding the most heat-resistant substances ever made[Press-News.org] 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