Brain Aneurysm Study Identifies Structural, Immune Markers of Rupture Risk

According to some estimates, stroke is the second leading cause of death globally. One of the causes of a severe type of stroke are brain aneurysms. Now data from a new study suggests that certain cells in the brain may cause aneurysms to weaken and rupture. And it helps explain why some aneurysms burst while others do not. It also opens a door to new ways of potentially predicting and preventing strokes. All of the findings are covered in a new Nature Neuroscience paper titled “Cerebrovascular vulnerability and fibrosis in human brain aneurysms.”

Brain aneurysms, which are bulges in blood vessels in the brain, can go unnoticed for years before rupturing causing a severe, often deadly type of stroke. About one in 50 people in the U.S. has a brain aneurysm but predicting which ones are most dangerous remains challenging. Aneurysms can be repaired surgically or using other minimally invasive procedures but those decisions depend on the size and location of the aneurysm as well as patient specific risk factors. With the current study, “we’ve made major steps toward solving the mystery of how aneurysms form,” said Ethan Winkler, MD, PhD, assistant professor of neurological surgeon and senior author of the Nature Neuroscience study. “We’ve identified the cast of characters involved and seen which ones are implicated at different phases of disease.”

To get to those answers, Winkler and his team analyzed more than 100,000 individual cells from human aneurysms and healthy brain arteries. From these data, they identified 19 transcriptionally distinct cell types and determined which genes were active in each. They also mapped how the cells were organized within the blood vessel wall.

“Our atlas of human brain aneurysms, as well as cell-resolution spatial transcriptomics, revealed that pathological cerebrovascular remodeling occurs with the loss of structurally supportive smooth muscle cells and the emergence of activated perivascular fibroblasts, which re-populate the vascular wall and express multiple genes linked to aneurysm risk,” the scientists wrote. 

Specifically, they found that vessels in aneurysm tissue had disorganized layers, and that many of the smooth muscle cells that allows the vessel walls to expand and contract had disappeared. In their place were scar-forming fibroblasts, which the team dubbed “activated fibroblasts.” These stiffened the arterial wall, making it less able to flex as blood flowed through. These cells also expressed genes that are linked to an inherited risk of aneurysm. The scientists also identified a type of macrophage that accumulated inside the arterial wall near the fibroblasts. The data showed that these specialized macrophages express a gene that is typically associated with bone tissue. 

Further testing revealed the presence of a feedback look between the two cell types. Specifically, the activated fibroblasts release a signal that triggers the macrophages to produce enzymes that degrade the blood vessel’s structural support. The scientists confirmed that this was the case by blocking the signals sent to the macrophages. They observed that the macrophages were less likely to produce the destructive enzymes when the signal was blocked. 

This process where vessel walls lose muscle cells followed by the buildup of scar tissue and immune cell activation helps explain why smaller aneurysms, which are often considered low risk, can still rupture. It jibes with Winkler’s own clinical experiences. He noted that more than half of the ruptures that he treated early in his career occurred in aneurysms below the typical surgical threshold of seven millimeters.  

This study brings scientists and clinicians one step closer to understanding how aneurysms form and perhaps being able to intervene earlier to prevent them. As the scientists note in the paper, “the molecular blueprint provided by this study substantially extends our mechanistic understanding of brain aneurysms and nominates new cells and pathways with translational promise for the development of therapeutic options.” This could involve blocking the signals that fibroblasts send or by inhibiting the immune response to those signals.               

The post Brain Aneurysm Study Identifies Structural, Immune Markers of Rupture Risk appeared first on GEN – Genetic Engineering and Biotechnology News.

AI Tool Classifies 102 CNS Tumor Subtypes in Minutes

Researchers German Cancer Research Center (DKFZ), Heidelberg University’s Medical Faculty, Heidelberg University Hospital developed AI system called Hetairos classify central nervous system (CNS) tumors using routinely prepared stained sections. research, published Nature Cancer, showed system classify 102 molecular tumor subtypes CNS cancers using digitized H&E slides, delivering diagnostic findings minutes rather than days or weeks often required molecular testing.

“ shows artificial intelligence is capable deriving molecular information directly routine sections thus fundamentally changing cancer diagnostics,” said lead author Darui Jin, PhD, postdoctoral fellow DKFZ.

CNS tumors encompass broad range diseases substantial molecular morphological diversity. methylation profiling is currently gold standard classifying many brain tumors, tests require specialized labs employing expensive analytical tools require sufficient amount tumor material, which difficult obtain some instances. these tests typically take two weeks return . reliance on molecular testing also created barriers some settings.

“Faster more widely accessible methods therefore needed,” researchers wrote. Existing alternatives such nanopore also require specialized instruments preparation. Routine H&E histopathology remains most widely available diagnostic material worldwide.

development Hetairos made possible advances computer vision digital pathology. Prior research established AI algorithms detect molecular features classify tumors molecularly defined categories. researchers noted previous research shown AI models estimate methylation signals standard H&E slides predict specific molecular alterations, “ artificial intelligence (AI)-based diagnostic solution H&E slides covers entire spectrum CNS tumors, currently only possible methylation testing, is still missing.”

develop Hetairos, team trained validated system using more than 11,000 digitized sections 9,606 treated 11 medical centers across four continents. Diagnoses used training were primarily established through methylation diagnostics. resulting model was designed classify tumors 102 molecular subtypes span nearly entire WHO classification spectrum CNS tumors.

important element system is it estimate confidence its predictions.

“Crucial Hetairos’s applicability across cohorts its realistic confidence estimates, which help judge its prediction accuracy,” researcher wrote. “Depending on cohort, Hetairos made high-confidence predictions 50–70% cases, those predictions were found correct nearly 90% instances.”

it become custom, system was also tested directly experts. Five board-certified neuropathologists reviewed 210 cases using only sections. Hetairos achieved accuracy rate 68%, compared 30% specialists. When three most likely diagnoses were considered, AI tool was 84% accurate versus 50% neuropathologists.

“ show modern AI systems now capable recognizing extremely subtle morphological patterns difficult even experienced specialists distinguish,” said Felix Sahm, project leader DKFZ.

prospective evaluation Hetairos practice analyzed 210 tumor alongside routine diagnostics without, its weren’t used influence management. While complete molecular testing required average 12 days, Hetairos generated approximately 12 minutes digitized slides were available. Including slide preparation scanning, findings often produced within 24 hours two days.

much speedier help clinicians initiate targeted treatments sooner guide additional testing, rather than replacing molecular testing, developers envision Hetairos triage decision-support tool.

“We developed Hetairos primarily tool support diagnostics,” Sahm said. “It is not intended replace molecular analyses, rather specifically complement accelerate them. technology make important contribution, particularly countries or regions limited resources, it is based on standard sections used worldwide.”

The post AI Tool Classifies 102 CNS Tumor Subtypes in Minutes appeared first on Inside Precision Medicine.

Usability, Relevance, and User Engagement of a Government-Sponsored and Community Co-Designed Digital Mental Health Website During the COVID-19 Pandemic: A Pilot Study on Latino/a/x Adults

Background: Latino/a/x adults have higher rates of unmet mental health needs than other racial and ethnic groups. One promising solution to help bridge this gap in care is digital mental health tools. Digital tools, such as self-help websites, have demonstrated the ability to enhance mental health literacy, reduce stigma, and improve mental health symptoms. Despite the potential benefits, engagement remains a critical challenge, and there has been a large oversight of unique considerations for Latino/a/x adults as end users. Objective: Guided by the Technology Acceptance Model and the Behavioral Model for Vulnerable Populations, the study’s overarching objective is to characterize within-group variation of Latino/a/x adults’ engagement with a government-funded, prevention-focused mental health website that was co-designed with community partners during the COVID-19 pandemic. Methods: The Together for Wellness/Juntos Por Nuestro Bienestar (T4W/Juntos) website offered free digital mental health resources to help Californians cope with the COVID-19 pandemic. A pilot evaluation of the website involved baseline and 4-week follow-up surveys about demographics, behavioral health needs, and overall website user experience. This current subanalysis focused on a stratified sample of Latino/a/x adult participants (baseline N=131; baseline and follow-up n=68). The baseline sample was mostly female (106/130, 81.5%); 66.9% (87/130) preferred to use the website in English and 30% (39/130) preferred Spanish. Behavioral health needs were assessed using the Patient Health Questionnaire-2, Generalized Anxiety Disorder 2-item scale, and a COVID-19 stressors checklist. We measured usability, comfort using the website, relevance of the website, and past-month use of resources. Data were analyzed using ordered and standard logistic regression methods. Results: Latino/a/x adults who preferred using the website in English (odds ratio [OR] 13.76, <.001) compared with Spanish were more comfortable using the website. Compared with adults aged 18‐30 years, adults aged 41‐50 years had significantly lower odds of agreeing that the website was easy to use. Sensitivity analyses revealed that participants who found the website easier to use (OR 2.22, =.001) and those with greater behavioral health needs (OR 1.22, =.045) were more likely to perceive the website’s topics as relevant. Participants with higher behavioral health needs at baseline were more likely to use the website and engage with resources for anxiety or stress at follow-up (OR 1.42, =.047). Conclusions: This study addresses gaps in understanding Latino/a/x adults’ experiences with a prevention-focused mental health website. The language-based disparity in comfort highlights the need to significantly improve the user experience for Latino/a/x Spanish speakers. Still, the website can be a helpful resource for Latino/a/x adults with high behavioral health needs, bridging a critical gap in support. A collaborative approach to developing resource-rich websites with trusted community organizations is vital for effectively reaching Latino/a/x communities and tailoring resources to address their unique needs.

Symeres Expands Spray Drying Capabilities at Its U.S. New Jersey Site

Netherlands CRDMO Symeres expanded its spray drying capabilities at its Cranbury, NJ CMC development site to support formulation development for poorly soluble and development-challenged small-molecule drug candidates.

The expanded capability is designed to support bioavailability enhancement strategies, including amorphous solid dispersions (ASDs), particle engineering and solubility optimization for compounds progressing from preclinical development through Phase II clinical activities.

The investment strengthens the company’s integrated CMC offering by combining spray drying, formulation sciences, analytical characterization, solid-state sciences, and process development within a single development environment, according to Henning Steinhagen, CEO of Symeres. This enables sponsors to progress from early formulation screening through to clinical-ready material within one coordinated scientific framework, reducing tech-transfer risk, accelerating decision-making, and improving development continuity, he adds.

By expanding spray drying capabilities within its integrated Cranbury CMC site, Symeres says it can help clients address developability challenges earlier, reduce operational complexity, and support faster progression into clinical development. [Symeres]
By expanding spray drying capabilities within its integrated Cranbury CMC site, Symeres says it can help clients address developability challenges earlier, reduce operational complexity, and support faster progression into clinical development. [Symeres]

“Our investment in spray drying reflects our commitment to supporting customers across the entire drug development journey,” continues Steinhagen. “While Symeres is widely recognized for its discovery expertise, this expanded capability further strengthens our ability to support complex molecules through development and into the clinic.”

“An increasing proportion of modern small molecule drug candidates require advanced formulation approaches to achieve acceptable bioavailability and clinical performance,” explains Paul O’Shea, managing director at Exemplify BioPharma, a Symeres company. “By expanding our spray drying capabilities within our integrated Cranbury CMC site, we can help clients address developability challenges earlier, reduce operational complexity, and support faster progression into clinical development.”

A Symeres spokesperson, who says the Cranbury site now supports laboratory-scale and pilot-scale spray drying workflows for a range of formulation development activities, including rapid material screening, process optimization and scalable process development, notes that the platform is particularly suited to Biopharmaceutical Classification System (BCS) Class II and IV compounds, highly lipophilic molecules and targeted therapies requiring enhanced oral exposure.

The post Symeres Expands Spray Drying Capabilities at Its U.S. New Jersey Site appeared first on GEN – Genetic Engineering and Biotechnology News.

Implementation of a Web-Based Application (Wellhealth) for Osteoporosis Medication Management in Older Adults: Prospective Feasibility Study

<strong>Background:</strong> Osteoporosis is a major global health challenge, but treatment uptake and long-term adherence remain low, raising the risk of future fractures. Barriers to effective care include low patient awareness, financial constraints, and challenges with ongoing monitoring and follow-up. Although mobile health and telemedicine tools can support chronic disease management, many osteoporosis apps lack clinical validation and structured medication management features. <strong>Objective:</strong> This study aimed to evaluate the feasibility of implementing a newly developed web-based application, Wellhealth, to support osteoporosis treatment management. A secondary objective was to explore potential associations between patient demographic characteristics and the frequency of in-app medication logging over a 1-year period. <strong>Methods:</strong> We conducted a feasibility study at the Golden Jubilee Medical Center, Mahidol University, between January 2023 and March 2025. Participants were recruited using convenience sampling during routine outpatient osteoporosis clinic visits. Eligible patients with a primary osteoporosis diagnosis used the Wellhealth web-based system, including the Assisted Liaison Service feature, over a 1-year period. Weekly in-app reports of medication use, satisfaction, and related outcomes were analyzed. Feasibility outcomes were summarized using descriptive statistics. Potential associations between participant characteristics and consistent in-app medication logging were explored using univariable and multivariable logistic regression analyses. Differences between in-app medication logging rates and medication possession ratio values were summarized using medians and IQRs. <strong>Results:</strong> We enrolled 32 participants with a mean age of 71 (range 58-91) years. The average in-app medication logging rate was 62.38% (SD 27.4%) for antiosteoporosis medications and 64.67% (SD 34.5%) for calcium supplementation. Vitamin D logging data were available for 27 participants, with an average logging rate of 68.23% (SD 31.6%). Overall satisfaction with the application was high, with 49% (15/32) of participants reporting high satisfaction, 42% (14/32) good, and 9% (3/32) average. User interaction increased markedly between the first and third quarters of 2023 before stabilizing through the second quarter of 2024. In multivariable analysis, consistent calcium logging was the only factor independently associated with higher antiosteoporosis logging rates (<i>P</i>=.02). Although younger age was associated with higher logging in univariable analysis (<i>P</i>=.01), this was no longer significant after multivariable adjustment (<i>P</i>=.12). <strong>Conclusions:</strong> Use of the Wellhealth system was feasible in this small cohort, with consistent medication logging, high user acceptability, and sustained digital engagement. Only consistent calcium logging was independently associated with higher antiosteoporosis medication tracking rates. Larger studies are needed to assess the app’s clinical effectiveness and impact on long-term outcomes.

Fast-Acting Malaria Drug Shows Promise in First-in-Human Study

A small-scale clinical study has shown that a new class of antimalarial drug can safely and quickly kill malaria parasites in the blood. Published today in Science Translational Medicine, these early clinical results open the door to much-needed treatment options to fight against malaria infections as cases of drug resistance continue to rise.  

“Malaria continues to be responsible for a large global health burden, with an estimated 282 million cases and 610,000 deaths in 2024,” write the authors of the study, led by Stephan Chalon, MD, PhD, vice president of experimental medicine and clinical pharmacology at the nonprofit organization Medicines for Malaria Venture. “Fast-acting antimalarial drugs are needed to address the emergence of artemisinin resistance in Plasmodium falciparum, the major cause of severe malaria worldwide.” 

Malaria infections caused by P. falciparum are typically treated with artemisinin-based combination therapy (ACT). As part of this first-line treatment, an artemisinin-derived drug dramatically reduces the numbers of malaria parasites circulating in the blood within a few hours while a companion drug with a slower mode of action eliminates the remaining parasites. 

However, artemisinin-resistant malaria infections have been steadily increasing in Southeast Asia, and more recently in East Africa. As resistance spreads, the efficacy of first-line ACT progressively declines, driving an urgent need for fast-acting alternatives to artemisinin-based drugs. 

The clinical trial evaluated the safety and tolerability of MMV367, an oral antimalarial drug candidate under development at Medicines for Malaria Venture. The drug belongs to the pyrrolidinamide class, a novel group of fast-acting antimalarials that interfere with two enzymes that are essential for malaria parasites to synthesize long-chain fatty acids.  

As part of the study, 12 healthy volunteers were inoculated with P. falciparum and then treated with MMV367 after eight days. Results showed that doses of 20mg or above were able to quickly kill the parasites, with half of them being eliminated within 4.3 hours. The drug also proved safe in all participants, showing only mild side effects in some of them.

No evidence of emerging drug resistance against this novel drug class was found during the study. However, this will need to be confirmed in future studies with a larger patient population and longer follow-up period. While more research will be needed before this drug can reach people affected by malaria worldwide, these early clinical results support its potential as an alternative to artemisinins in antimalarial combination therapies as they increasingly lose efficacy in the face of escalating drug resistance.  

As a product development partnership (PDP), Medicines for Malaria Venture works together with major pharmaceutical companies and academic institutions to promote the development of accessible and affordable medicines to treat and prevent malaria with a major focus on addressing the needs of children and pregnant women. Since its inception in 1999, the nonprofit has delivered 19 approved medicines, with many other candidates currently at various stages of clinical development. 

The post Fast-Acting Malaria Drug Shows Promise in First-in-Human Study appeared first on Inside Precision Medicine.

Ultrasensitive HPV DNA Blood Test Could Help Personalize Head and Neck Cancer Treatment

Researchers from Mass General Brigham Cancer Institute have shown that HPV-DeepSeek, an ultrasensitive blood test that detects human papillomavirus (HPV) DNA, could predict which patients with HPV-associated head and neck cancer are most likely to benefit from adjuvant treatment after surgery.

“Right now, the decision to give adjuvant radiation or chemoradiation after surgery hinges almost entirely on TNM staging and surgical pathology,” explained senior author Daniel Faden, MD, director of the Head and Neck Cancer Genomics and Liquid Biopsy Program at Mass General Brigham Cancer Institute.

This means that surgeons and oncologists look at features like the number of involved lymph nodes, whether there’s extranodal extension, surgical margin status, and perineural invasion or lymphovascular invasion.

“The problem is, these are static, backward-looking variables,” Faden told Inside Precision Medicine. “They tell us what was in the tumor specimen, but they don’t tell us whether the patient has microscopic disease left behind after surgery.”

This can result in some patients receiving more treatment than they need, with potential unnecessary side effects, and others receiving less treatment than they should and later having their cancer come back.

Previous work has shown that circulating tumor (ct)HPV DNA is a promising biomarker for predicting head and neck cancer recurrence, but current assays, using droplet digital polymerase chain reaction (ddPCR), lack the sensitivity needed for detecting minimal residual disease (MRD) after surgery.

Faden and team therefore used their experience of studying HPV to build HPV-DeepSeek, a whole genome sequencing (WGS) assay that detects ctHPV DNA in blood samples.

He noted that the assay differs from most currently available MRD assays as it is not tumor-informed and does not require building a bespoke panel from each patient’s tumor. This makes HPV-DeepSeek tissue agnostic, and means the assay has a lower cost and faster turnaround times than tumor-informed WGS approaches.

Faden and team evaluated the performance of HPV-DeepSeek in the Clear-HPVca study, which included 103 patients (mean age 62 years, 89% men) with stage I to IV HPV-positive head and neck cancer who were treated with surgery.

The authors report in Science Translational Medicine that among 74 patients with ctHPV DNA status available during the postsurgery period (four days to six months after surgery, before adjuvant therapy), 23% were MRD-positive.

After a median follow-up of 27 months, patients with ctHPV DNA detected had worse outcomes than those with no ctHPV DNA. Specifically, the two-year disease-free survival rate was 60% among the patients who were MRD-positive, compared with 100% for those who were MRD-negative, and the two-year overall survival rates were 73% and 98%, respectively.

The researchers also found that HPV-DeepSeek could predict which patients benefit from adjuvant treatment; the recurrence rate was 27% among 15 MRD-positive patients who received adjuvant treatment compared with 100% among the two MRD positive patients who did not receive adjuvant treatment.

Conversely, there was no benefit of adjuvant treatment among MRD-negative patients; in this group, the recurrence rate was 3% among the 37 MRD-negative patients who received adjuvant therapy and 0% among the 21 MRD-negative patients who did not receive adjuvant therapy.

Furthermore, the assay identified molecular recurrence an average of seven months, and up to 17.5 months, earlier than clinical recurrence. With ddPCR, molecular recurrence was only detected four months earlier than clinical recurrence.

Although the team knew that HPV-DeepSeek was more sensitive than ddPCR, Faden described the size of the lead-time as striking.

“It tells us we’re detecting recurrence at a disease burden that’s genuinely clinically meaningful and actionable,” he said. “We had some patients where molecular detection preceded clinical detection by over a year. That kind of window creates real opportunities—time to discuss salvage surgery or systemic therapy before a patient ever develops symptomatic recurrence.”

Faden and team are now planning interventional trials that will investigate whether using HPV-DeepSeek to guide adjuvant therapy decisions improves outcomes and reduces toxicity.

Faden hopes that the assay will eventually be used to guide personalized treatment decisions.

“As a surgeon who treats this disease, not just a scientist who studies it, this is where I get genuinely excited—because it’s a shift in philosophy, not just methodology,” he said. “What HPV-DeepSeek does is make disease biology—specifically, whether there’s residual disease—visible in real time.”

He added: “If you can accurately detect MRD early after surgery, you can make treatment decisions based on that biology [and] the downstream implications are significant. You reduce unnecessary toxicity in patients who don’t need more treatment. You potentially intensify treatment in patients with residual disease. And you can rethink surveillance—if a patient remains MRD-negative after treatment, can we move to less frequent imaging and potentially spare them years of follow-up CT scans?”

“We’re not there yet clinically, but this is a first step—a research finding with real promise. It’s the beginning of a conversation about how to personalize care.”

The post Ultrasensitive HPV DNA Blood Test Could Help Personalize Head and Neck Cancer Treatment appeared first on Inside Precision Medicine.

Digital Portal Strengthens Patient Engagement in Cancer Clinical Trials

A digital platform designed to strengthen communication helped keep clinical trial participants engaged in a national oncology study, according to findings published in the journal JNCI Cancer Spectrum. The Participant Engagement Portal (PEP), developed by the Alliance for Clinical Trials in Oncology, was tested as part of the National Cancer Institute-sponsored Multi-Cancer Early Detection Biobank Study (A212102). Among participants who enrolled to use PEP, 84% reported a positive experience, 96% said it was easy to access, 93% found surveys easy to complete, and 93% agreed to be contacted about future research opportunities.

The findings provide a positive snapshot that digital tools designed to address participant needs can help improve their engagement throughout the term of a clinical trail, and aid in the the collection of data that can improve the efficiency and long-term value of oncology trials.

“We were eager to offer trial participants a format to allow connection to the study team,” said Suzanne George, MD, senior author of the study project and professor of medicine at Harvard Medical School. “Nearly all participants who engaged with the tool opted in for recontact for future research which allows the ability to build a research community. PEP gives patients a direct way [to] self-report key data elements, such as specific social and economic factors which may impact a person’s cancer journey.”

The intent in developing PEP was to find new ways to improve the experience of patients enrolled in clinical trials. Digital tools have the ability to simplify access to study materials, streamline data collection, aid in remote patient monitoring, and improve communication between researchers and trial participants. Specifically, PEP was created to improve engagement, which the researchers defined as sustained and beneficial interaction between participants and researchers over the course of the study. Unlike many digital tools focused on recruitment, PEP was designed to help researchers learn directly from patient experiences and maintain communication after trial enrollment.

“Historically, there are very few, if any, instances of trials providing consistent, longitudinal communication back to the patient about the overall clinical trial,” George told Inside Precision Medicine. “The large percentage of people reporting positive experience suggests PEP’s content and delivery methods resonate with them.”

To develop PEP, The Alliance used an iterative user-centered process that included advisory board input, usability testing with 19 patients, including 12 Spanish-speaking participants, and refinement using plain-language and health-literacy principles. Rather than requiring usernames and passwords, participants received secure links by text or email that allowed direct access to portal content and surveys.

The pilot was conducted within the MCED Biobank Study, an ongoing national clinical trial investigating future blood tests for the early detection of cancer. Of the total 2,221 study people enrolled in the trial, 40% chose to use PEP. Of the 899 users, 361 completed demographic questionnaires and 310 completed surveys addressing social determinants of health.

One of the portal’s central features was bidirectional communication that included trial participants receiving study updates, newsletters, and research information. PEP users could also provide feedback and report personal information that could help researchers better understand their experiences. According to George, participant feedback has influenced both the platform’s design and future patient engagement strategies.

“As noted in our manuscript, we conducted one-on-one focused interviews with people to evaluate the PEP on all levels, from communication methods and content to data security and privacy,” she said. “Through these findings, we were able to understand the need to transcreate documents into Spanish for cultural meaning and contextual relevance, rather than just translate them word-for-word.”

Feedback also led researchers to reconsider maintaining study-specific websites.

“Participant feedback substantiated our decision to eliminate dedicated study-specific PEP website(s),” George said. “Instead, we are transitioning to an IRB-approved newsletter format delivered directly to study participants for ongoing communication and education.”

The study also showed that people using PEP were willing to provide information about social determinants of health (SDoH), such as education, insurance status, housing stability, food insecurity, and financial concerns.

“If a trial chooses to formally integrate SDoH metrics, they could be included as protocol-directed surveys done via PEP, making results directly available to the protocol investigators,” George said. “Self-reported information is critical because it allows researchers to look beyond the actual study biology.”

Collecting this kind of information can help identify barriers that may affect treatment adherence, including transportation challenges, childcare responsibilities, and financial stress.

Another notable finding was that community-based practices enrolled a higher proportion of eligible participants into PEP than academic medical centers. The reasons remain under evaluation, but George suggested that established relationships between patients and local care teams may contribute to greater acceptance of the platform.

Further, the researchers found that 98% of participants were open to health-related follow-up communications. The research team believe this is an important outcome because it creates opportunities for future re-engagement and continued participation in research activities.

While the data from the pilot showed meaningful patient engagement, there were some limitations. Participants who enrolled in PEP were more likely to be female and White than the broader study population, raising questions about whether the data would be representative across diverse populations.

“Looking forward, PEP would ideally become a standard core functionality in all oncology studies,” George noted. “However, we will need to continue to expand outreach and continue to engage the participant community, to ensure we are indeed reaching all of those who would like to be part of such a platform.”

The post Digital Portal Strengthens Patient Engagement in Cancer Clinical Trials appeared first on Inside Precision Medicine.

AI Detects Breast Cancer Much Earlier than Radiologists Alone

Using AI, radiologists can see signs of breast cancer up to ten years earlier in the mammograms of patients later diagnosed with the disease, according to new research published this week in Radiology. These findings could help greatly accelerate diagnosis and improve decisions about who to screen sooner and with more regularity—questions that are increasingly important as more younger women are diagnosed with the disease. 

The researchers tested three commercially available AI-based computer-assisted detection (AI-CAD) systems on mammogram data from a large screening population. Cancer prediction scores issued by AI-CAD were elevated for a significant number of patients later diagnosed with breast cancer compared to those who remained cancer-free. The team was led by researchers at the Karolinska University Hospital in Stockholm.

“Approximately 20% of breast cancer cases demonstrate mammographic signs that are already visible to AI around six years before diagnosis,” said senior coauthor Fredrik Strand, MD, PhD, of Karolinska. “Our study confirms the potential of AI to, in some cases, find signs of cancer in the mammograms much earlier than when radiologists detected it.”

Earlier diagnosis is crucial in breast cancer, as it is for most malignancies. Although annual breast screening, using mammography, is recommended for women in the U.S. aged 40 to 74, it is known that approximately 20-25% of women show early signs of breast cancer on their scans before they are diagnosed. 

Strand’s team investigated AI’s potential to flag mammographic signs that were present up to 10 years in retrospect. The study included a total of 88,963 mammograms performed on 31,394 patients over 10 years—between January 2008 and April 2019. Of these participants, 12,072, or 38.5%, were diagnosed with cancer.

The data came from the Validation of Artificial Intelligence for Breast Imaging (VAI-B) database, which collects breast imaging data from volunteers across four regions of Sweden. The Swedish national breast screening program invites women between the ages of 40 and 74 to participate in screening examinations every two years, and each mammogram has traditionally been read by two radiologists. The average age of screening was 57.6 years.

The AI-CAD systems found many of those cancers at earlier screening points, achieving 90% specificity—distinguishing between a true positive and a true negative result—in up to 17% of patients at 10 years before diagnosis, up to 19.7% six years before diagnosis, up to 25.2% four years before diagnosis, and up to 39.3% two years before diagnosis.

“This study aims to add to the growing literature regarding the application of AI in breast cancer screening and how it can help play a role in earlier detection of breast cancer,” said Strand. “Analyzing the AI scores of screened individuals over time could provide insight into how early detectable changes arise, potentially allowing for earlier intervention.”

Breast cancer is the most commonly diagnosed cancer worldwide. It accounts for roughly 30% of all new female cancer diagnoses. In the U.S., AI-based systems have shown promise for predicting five-year risk of breast cancer and identifying women at risk of cancers that arise between regular screening mammograms. 

 

The post AI Detects Breast Cancer Much Earlier than Radiologists Alone appeared first on Inside Precision Medicine.

In Silico Devices May Improve Drug Manufacturability

Using in silico tools to augment physical experiments can help identify manufacturability issues early in development. That’s according to an AI technology company that spoke on a recent panel.

BigHat Biosciences, which was among the companies presenting at PEGS Boston, explained that developing in silico models of antibody yields using a cell-free expression system allows the exploration of a wider range of mutations.

And this, in turn, lets companies better optimize their product for manufacturability.

“There’s only so many experiments you can do by putting an antibody into CHO [Chinese Hamster Ovary] cells,” explains Hunter Elliott, PhD, vice president of machine learning at BigHat Biosciences.

“With in silico tools augmenting that exploration side, we can build models that make predictions for improved sequences, screening many more antibodies in silico than we need to send to the lab.”

Elliott’s talk came alongside a panelist who argued it was important for preclinical researchers to communicate with the manufacturing departments of their companies to make a success of the latest generation of harder-to-manufacture drugs.

Speaking about his own products, Elliott argues that using in silico tools to explore a wider range of possible antibody mutations means it’s possible to select the handful with the highest possible yields as well as other improved biophysical properties.

“You’re derisking your processes because you’re combining your experiments with the in silico tools you’re using,” he says.

Talking about the panel, Elliott adds that discussion around the limitations of models included the lack of publicly available data on manufacturability and developability, especially for potential products that have failed to make it to the clinic.

Some have expressed concern that using in silico tools might also accidentally screen out the best-performing antibodies. Although, he says, “my personal opinion is that the ability to predict properties of sequences without sending them into the lab makes it easier for us to optimize from a suboptimal starting sequence.”

“With these models, we can keep this imperfect antibody in the loop and take it forward through several rounds of optimization, and then, instead of a candidate molecule being killed early on, it might be engineered into manufacturability.”

The post <i>In Silico</i> Devices May Improve Drug Manufacturability appeared first on GEN – Genetic Engineering and Biotechnology News.