PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Multimodal machine learning model effective at predicting response to CDK4/6 inhibitors in HR-positive, HER2-negative breast cancer patients

Combining real-world clinical and genomic data resulted in a more accurate prediction of outcomes compared to examining clinical and genomic data separately

2024-12-13
(Press-News.org) SAN ANTONIO – A machine learning (ML) model incorporating both clinical and genomic factors outperformed models based solely on either clinical or genomic data in predicting which patients with hormone receptor (HR)-positive, HER2-negative metastatic breast cancer would have better outcomes from adding CDK4/6 inhibitors to endocrine therapy as first-line treatment, according to results presented at the San Antonio Breast Cancer Symposium (SABCS), held December 10-13, 2024.

While the use of CDK4/6 inhibitors combined with endocrine therapy have significantly improved outcomes in patients with HR-positive, HER2-negative metastatic breast cancer, Pedram Razavi, MD, PhD, the scientific director of the Global Research Program at Memorial Sloan Kettering Cancer Center and presenter of the study, noted that the responses to CDK4/6 inhibitors vary widely; some patients do markedly well, while others develop treatment resistance over time, and some derive no benefit at all.

“There’s a huge need in clinic to identify patients who may or may not benefit from adding CDK4/6 inhibitors at the time of metastatic diagnosis so that we can think about escalation and de-escalation strategies in advance,” Razavi said. “More accurate prediction of outcomes could also help some patients avoid unnecessary side effects and financial toxicity from escalated upfront approaches.”

Currently, Razavi explained, certain clinical features such as treatment-free interval (TFI), the time between the last dose of adjuvant endocrine therapy and the development of metastatic disease and measurable disease, are the main factors used to identify patients who may be at high risk of early progression on first-line CDK4/6 inhibitor combinations to identify candidates for escalation therapy. Razavi and his colleagues wanted to explore whether a multimodal ML model that included additional clinical and genomic factors could more accurately stratify patients.

Using OncoCast-MPM, a ML tool developed at Memorial Sloan Kettering, they generated three models to predict progression-free survival (PFS) with CDK4/6 inhibitors: one based on clinicopathological features (CF), another on genomic features (GF), and one integrating CF and GF (CGF). The models were developed using a training cohort of 761 patients with HR-positive, HER2-negative metastatic breast cancer who received first-line endocrine therapy with CDK4/6 inhibitor combinations and had tumor sequencing performed prior to treatment or within two months of the start of treatment with MSK-IMPACT, a test designed to detect gene mutations and match patients to treatments or clinical trials for actionable cancer targets. The performance of the model was tested on a holdout test cohort of 326 patients.

The models trained on CF and GF each identified three risk groups: high, intermediate, and low, with median PFS of 6.3, 15.2, and 24.5 months for CF, and 9.9, 18.1, and 23.1 months for GF, respectively.

The CGF integrated model identified four risk groups including two intermediate groups positioned between low- and high-risk categories. The median PFS was 5.3 months in the high-risk group and 29 months in low-risk group, with the intermediate groups showing median PFS of 10.7 and 19.8 months. Notably, the hazard ratio between the high- and low-risk groups was significantly higher in the CGF model (a 6.5-fold difference) compared to CF and GF models (3- to 4-fold difference), indicating a superior stratification of patients with the CGF model. Testing the holdout test cohort yielded nearly identical PFS and hazard ratio results, confirming the robustness of the models.

“All three models performed really well, surpassing the conventional clinical risk models based on a single or a few clinical features. But the power of the analysis shone when we started combining the clinical and genomic features together,” Razavi said.

The clinical and genomic factors that were selected by the ML model were mainly those known to be associated with outcomes or resistance to either CDK4/6 inhibitors or endocrine therapy. Key genomic predictors of poor outcomes were biologically plausible alterations such as TP53 loss, MYC amplifications, PTEN loss, RTK-MAPK pathway alterations, RB1 loss, whole genome doubling, and high proportion of loss of heterozygosity. The major clinical predictors included liver metastasis, TFI less than one year, progesterone receptor negativity, low estrogen receptor expression, and presence of visceral metastasis.

“All of these variables are potentially available when the patients are diagnosed with metastatic disease, making such ML models broadly applicable. The hope is to integrate these models in clinical trial design of escalation and de-escalation strategies potentially transforming how we approach treatment for newly diagnosed metastatic disease,” Razavi said. “Knowing that a patient on first-line CDK4/6 inhibitors is in the high-risk group could prompt the treating oncologists to implement closer disease monitoring and utilizing liquid biopsy and tumor-derived biomarkers to inform second-line treatment options and clinical trials. This could put us one step closer to staying ahead of breast cancer.”

Limitations of this study include its single-institution design, retrospective data analysis, and potential referral bias associated with specialized cancer centers. To address these challenges, Razavi and his team are validating the model using external data sets and aim to develop an online tool where physicians can input clinical and genomic data to receive patient-specific outcome predictions.

The study was indirectly and partially supported by the National Institutes of Health, U.S. Department of Defense, Susan G. Komen, Breast Cancer Research Foundation, AstraZeneca, Sophia Genetics, Novartis, and Tempus. Razavi reports consultant, advisory board, or advisor roles for AstraZeneca, Pfizer, Lilly/Loxo Oncology, Novartis, Tempus, Prelude Therapeutics, NeoGenomics, Natera, SAGA Diagnostics, Paige, Guardant Health, Myriad Genetics, and Foresight Diagnostics; and institutional grant/funding from Grail, Novartis, AstraZeneca, Biotheranostics, Tempus, NeoGenomics, Biovica International AB, Guardant Health, Personalis, Myriad Genetics, and Foresight Diagnostics.

END



ELSE PRESS RELEASES FROM THIS DATE:

Light-induced gene therapy disables cancer cells’ energy center

2024-12-13
COLUMBUS, Ohio – Researchers are shining a light on cancer cells’ energy centers – literally – to damage these power sources and trigger widespread cancer cell death. In a new study, scientists combined strategies to deliver energy-disrupting gene therapy using nanoparticles manufactured to zero in only on cancer cells. Experiments showed the targeted therapy is effective at shrinking glioblastoma brain tumors and aggressive breast cancer tumors in mice. The research team overcame a significant challenge to break ...

MLB adds lifesavers to the chain of survival at annual Winter Meetings

2024-12-13
DALLAS, December 13, 2024 — The American Heart Association and Major League Baseball (MLB) brought cardiopulmonary resuscitation (CPR) and automated external defibrillator (AED) training to the League’s annual Winter Meetings held in Dallas this week. Attendees from all 30 Major League Clubs and many organizations across the baseball industry learned lifesaving skills needed to respond confidently and capably in the event of a cardiac emergency. According to American Heart Association data, 9 out of ...

TTUHSC researcher to study protein regulation in Alzheimer’s disease

TTUHSC researcher to study protein regulation in Alzheimer’s disease
2024-12-13
More than six million Americans are affected by Alzheimer’s disease, a form of dementia marked by accumulation of amyloid-β within the brain. Amyloid-β is a relatively small protein that forms toxic plaques in the brain contributing to the harmful effects of Alzheimer's disease. Another protein, hyperphosphorylated tau (pTau), also accumulates as toxic neurofibrillary tangles. Together, amyloid-β plaques and pTau tangles result in brain damage, neuroinflammation and ultimately brain death. Gene expression studies have already identified ...

Oxidation in glacial rivers and lakes could help mitigate methane emissions

2024-12-13
(Carlisle, Pa.) — A new study in the journal Scientific Reports offers a rare glimmer of hope in the face of climate change, suggesting glacial rivers and lakes may play a crucial role in mitigating the effects of  methane, a powerful greenhouse gas that recent studies have shown emerging as glaciers melt in warming global temperatures. This new study, led by Dickinson College Associate Professor of Environmental Studies Kristin Strock, looked at what happens when glaciers melt and release trapped methane, a potent greenhouse gas that contributes to climate change. Strock, a 2019 National Geographic Explorer, led an all-female team of researchers ...

How chemical reactions deplete nutrients in plant-based drinks

How chemical reactions deplete nutrients in plant-based drinks
2024-12-13
Over the last decade, the global market for plant-based beverages has seen remarkable growth, with oat, almond, soy and rice drinks emerging as popular alternatives to cow’s milk in coffee and oatmeal during this time. One of the likely reasons for millions of liters of plant-based drinks ending up in the shopping baskets of consumers is that their climate footprint is often lower than that of cow’s milk. But consumers would be mistaken if they considered plant-based beverages healthier than cow’s milk. This is highlighted in a new study conducted by the University of Copenhagen in collaboration with the University ...

The CNIC presents iFlpMosaics, an innovative genetic toolkit for the study of gene function

The CNIC presents iFlpMosaics, an innovative genetic toolkit for the study of gene function
2024-12-13
A team at the Centro Nacional de Investigaciones Cardiovasculares (CNIC) has developed a comprehensive set of innovative genetic tools and mouse lines, called iFlpMosaics, designed to enhance the study of gene function and its implications in health and disease. The groundbreaking study, led by Dr. Rui Benedito and published in Nature Methods, presents a pioneering approach that overcomes critical limitations of existing methods for generating genetic mosaics. These innovations will enable scientists to more accurately investigate the effects of somatic mutations on cellular biology and disease. The study highlights the iFlpMosaics toolkit's utility across different experimental setups, ...

Children’s Hospital of Philadelphia, Stanford Researchers reveal and refine new immunotherapy platform with increased potential to target cancer cells

2024-12-13
Philadelphia, December 13, 2024 – Researchers from Children’s Hospital of Philadelphia (CHOP) and Stanford University have revealed the molecular structure of TRACeR-I, a protein platform for reprogramming immune responses. A better understanding of its structure may help optimize designs for the platform, which can be used to develop cancer treatments by either directly modifying immune cells or by creating proteins that help immune cells locate cancer cells. The findings were published today by the journal Nature ...

M87's powerful jet unleashes rare gamma-ray outburst

M87s powerful jet unleashes rare gamma-ray outburst
2024-12-13
Also known as Virgo A or NGC 4486, M87 is the brightest object in the Virgo cluster of galaxies, the largest gravitationally bound type of structure in the universe. It came to fame in April 2019 after scientists from EHT released the first image of a black hole in its center. Led by the EHT multi wavelength working group, a study published in Astronomy and Astrophysics Journal presents the data from the second EHT observational campaign conducted in April 2018, involving over 25 terrestrial and orbital telescopes. The authors report the first observation of a high-energy gamma-ray flare in over a decade from the supermassive black hole M87, based on nearly ...

Hippos 'vulnerable' as gaps in data hinder conservation efforts

2024-12-13
A new database of African hippo populations has revealed huge gaps in our knowledge of where the megaherbivores live and thrive, with populations fragmented and reliant on protected areas. Hippos are classified as “vulnerable to extinction” by the International Union for the Conservation of Nature (IUCN) Red List and have been called the “neglected megafauna”, with a lack of scientific attention and much less research into their lives and habitats than other large mammals. University of Leeds School of Biology Postgraduate Researcher Hannah Lacy ...

Faster, safer complex head and neck reconstruction with preserved blood supply tissue

Faster, safer complex head and neck reconstruction with preserved blood supply tissue
2024-12-13
Sometimes, moving just a few inches can go a long way. Osaka Metropolitan University researchers have developed a promising technique for head and neck reconstruction that shifts the placement of transferred tissue with blood vessels attached, offering a safer, faster option for patients with complex tissue defects, especially those at high risk. Head and neck reconstruction plays a crucial role in the treatment of patients with head and neck cancer. The goal is to preserve functions vital for breathing, ...

LAST 30 PRESS RELEASES:

New research boosts future whooping cough vaccines

Mechanistic understanding could enable better fast-charging batteries

No bones about it: new details about skeletal cell aging revealed

UNM scientists discover how nanoparticles of toxic metal used in MRI scans infiltrate human tissue

UMaine research examines best methods for growing Atlantic sea scallops

Medical cannabis could speed recovery, especially at community recovery homes

Study assesses U.S. image amid weakening of democracy

Two scientific researchers to receive 2025 Ralph L. Sacco Scholarships for Brain Health

Researchers improve chemical reaction that underpins products from foods to fuels

Texas Tech to develop semiconductor power devices through $6 million grant

Novel genomic screening tool enables precision reverse-engineering of genetic programming in cells

Hot Schrödinger cat states created

How cells repair their power plants

Oxygen is running low in inland waters—and humans are to blame

ACP’s Best Practice Advice addresses use of cannabis, cannabinoids for chronic noncancer pain

Beyond photorespiration: A systematic approach to unlocking enhanced plant productivity

How a small number of mutations can fuel outbreaks of western equine encephalitis virus

Exposure to wildfire smoke linked with worsening mental health conditions

Research uncovers hidden spread of one of the most common hospital-associated infections

Many older adults send their doctors portal messages, but who pays?

Fine particulate matter from 2020 California wildfires and mental health–related emergency department visits

Gender inequity in institutional leadership roles in US academic medical centers

Pancreatic cells ‘remember’ epigenetic precancerous marks without genetic sequence mutations

Rare combination of ovarian tumors found in one patient

AI-driven clinical recommendations may aid physician decision making to improve quality of care

Artificial intelligence has potential to aid physician decisions during virtual urgent care

ACP and Annals of Internal Medicine present breaking scientific news at ACP’s Internal Medicine Meeting 2025

New study reveals polymers with flawed fillers boost heat transfer in plastics

Signs identified that precede sudden arrhythmic death syndrome in young people

Discovery of bacteria's defence against viruses becomes a piece of the puzzle against resistance

[Press-News.org] Multimodal machine learning model effective at predicting response to CDK4/6 inhibitors in HR-positive, HER2-negative breast cancer patients
Combining real-world clinical and genomic data resulted in a more accurate prediction of outcomes compared to examining clinical and genomic data separately