Author: admin

Posted on

Signatera™ as a Pan-Cancer Decision-Making Tool to Illuminate the Care Pathway

Sponsored content brought to you by

Natera logo

To date, precision oncology has largely focused on selecting therapies based on tumor genomics. One of the most persistent challenges in clinical practice remains knowing what to do next. After surgery, during systemic therapy or in surveillance, clinicians are often navigating uncertainty, balancing overtreatment against the risk of recurrence.

Reshaping patient management

Circulating tumor DNA (ctDNA)–based minimal residual disease (MRD) assessment with tumor-informed Signatera™ is reshaping this paradigm by providing a dynamic, patient-specific signal that can illuminate next steps across the continuum of care. Unlike conventional imaging or clinicopathologic risk factors, ctDNA offers a real-time measure of tumor burden at the molecular level. Signatera is designed using the patient’s tumor, enabling highly sensitive and specific detection of residual disease at levels far below radiographic visibility. This creates a new layer of clinical intelligence that is actionable across neoadjuvant, adjuvant, surveillance, metastatic, and treatment response settings.

Neoadjuvant setting: early readouts to adapt therapy

In the neoadjuvant setting, clinicians often need to wait until the time of surgery to determine whether therapy was effective. Assessing ctDNA dynamics during neoadjuvant therapy can provide an early indication of treatment response; ctDNA clearance has been associated with improved outcomes while conversely, persistent ctDNA may signal resistance, prompting consideration of treatment escalation, clinical trial enrollment, or alternative regimens.1 This creates an opportunity to move beyond static endpoints toward adaptive treatment strategies. Clinicians can watch ctDNA trends to refine therapy in real time. This is especially relevant in aggressive tumor types where early response assessment is critical.

Adjuvant setting: refining who may benefit from additional therapy

MRD testing may provide immediate clinical impact in the adjuvant setting. Current decision-making relies heavily on population-level risk factors, often leading to overtreatment in some patients and undertreatment in others. Postoperative ctDNA positivity is a strong, independent predictor of recurrence across multiple tumor types. Signatera data demonstrates that ctDNA-positive patients after surgery can have dramatically higher recurrence risk compared with ctDNA-negative patients.2 More importantly, Signatera ctDNA status can help predict who benefits from adjuvant therapy. Evidence suggests that ctDNA-positive patients derive meaningful benefit from additional systemic treatment, while ctDNA-negative patients may not.3

stratify patients after surgery

Surveillance: detecting recurrence earlier

Surveillance after curative-intent therapy remains a gray zone as imaging can often be intermittent and insensitive to early recurrence. While many biomarkers like CEA, CA-19-9, CA-125 generally have limitations in both sensitivity and specificity, Signatera ctDNA testing offers a more sensitive approach to detect molecular relapse earlier than imaging and other blood biomarkers. Studies have shown that Signatera can identify recurrence months before it becomes radiographically apparent with high sensitivity and specificity and substantial lead times.4 Earlier detection opens the door to intervention at a lower disease burden, when therapies may be more effective. It also enables more tailored surveillance strategies to intensify monitoring or imaging when ctDNA becomes positive, provides reassurance, and potentially reduces imaging frequency in persistently negative patients. Rather than a fixed surveillance schedule, ctDNA enables a response-guided follow-up strategy.

Treatment on MRD (TOMR)

TOMR is a new paradigm in precision oncology that is used to guide earlier, more proactive therapy decisions to escalate treatment in MRD-positive patients at high risk of relapse and de-escalate or avoid unnecessary toxicity in MRD-negative patients. For clinicians, this moves decision-making from prognostic to personalized, anchored by the presence of residual disease at an earlier and potentially curable stage.

Metastatic setting: real-time disease monitoring

In metastatic disease, treatment decisions are often based on imaging intervals that may lag behind molecular changes in disease burden. A newer technology like ctDNA introduces a more immediate and dynamic tool. Because ctDNA reflects tumor burden and molecular activity, it can be used to monitor treatment response earlier than imaging and identify emerging resistance to inform timely switches in therapy. In practice, this allows clinicians to avoid prolonged exposure to ineffective therapies and pivot more quickly. Additionally, Signatera is being used to monitor response to immunotherapy across tumor types, providing a pan-cancer application in advanced disease.

Treatment response monitoring: a continuous feedback Loop

Across all stages, one of the most powerful aspects of ctDNA is its ability to create a longitudinal feedback loop. Serial testing enables clinicians to track ctDNA trends over time:

  • Clearance means favorable response and improved prognosis
  • ctDNA dynamics have been shown to correlate strongly with outcomes. Patients who remain ctDNA negative demonstrate significantly better survival than those who become or remain ctDNA positive which could mean there is a higher risk of disease progression

This transforms monitoring from episodic snapshots into a continuous signal, providing actionable insight at each decision point.

A pan-cancer framework for clinical decision-making

What makes Signatera particularly compelling is its pan-cancer applicability. Its tumor-informed design allows it to be used across multiple solid tumors, including colorectal, breast, lung, bladder, ovarian, and melanoma. This consistency enables a unified framework for integrating MRD into clinical workflows:

  1. At diagnosis or pre-treatment—establish baseline and design assay
  2. During neoadjuvant therapy—assess early response
  3. Post-surgery—evaluate MRD and guide adjuvant decisions
  4. During surveillance—detect molecular relapse early
  5. In advanced disease—monitor response and resistance

Rather than being confined to a single decision point, ctDNA becomes a longitudinal biomarker embedded throughout the care pathway.

From uncertainty to actionability

Signatera ctDNA testing bridges the gap from uncertainty to actionability by answering clinically meaningful questions at each stage of the patient’s journey: Is there still disease present, and is it changing? By doing so, ctDNA doesn’t just add another biomarker. It redefines how clinicians navigate the care pathway, moving from reactive to proactive care.

 

References

  1. Chakrabarti S, Cohen S, Tin A, et al. Utility of Circulating Tumor DNA to Assess Tumor Response in Patients with Locally Advanced Rectal Cancer Undergoing Neoadjuvant Therapy. Cancers. 2026; 18(4):589.
  2. Reinert T, Henriksen TV, Christensen E, et al. Analysis of Plasma Cell-Free DNA by Ultradeep Sequencing in Patients With Stages I to III Colorectal Cancer. JAMA Oncol. 2019.
  3. Nakamura Y, Watanabe J, et al. ctDNA-based molecular residual disease and survival in resectable colorectal cancer. Nature Medicine. 2024. doi: 10.1038/s41591-024-03254-6.

 

For additional information: www.natera.com.

The post Signatera™ as a Pan-Cancer Decision-Making Tool to Illuminate the Care Pathway appeared first on Inside Precision Medicine.

Posted on

Supervised Fine-Tuning of Large Language Models With Chain-of-Thought Reasoning for Pediatric Heart Disease Detection in Unstructured Echocardiogram Reports: Algorithm Development and Validation

Background: Pediatric heart disease (PHD), including congenital heart defects, is often incompletely captured in electronic health records, particularly when clinical significance must be inferred from unstructured echocardiogram reports. Automated methods capable of extracting clinically meaningful PHD from narrative reports could improve clinical decision support and research applications. Objective: The aim of the study is to evaluate the feasibility of using supervised fine-tuning of large language models (LLMs), with and without chain-of-thought (CoT) reasoning, to characterize patients with clinically significant or historical PHD from unstructured echocardiogram reports. Methods: We developed a PHD detection algorithm using fine-tuned open-source LLMs, including LLaMA (Meta) and Qwen (Alibaba), to analyze 9749 echocardiogram reports. A subset of 712 reports was adjudicated by 2 pediatric cardiac anesthesiologists, classifying 506 (71.1%) as clinically significant PHD and 206 (28.9%) as not significant. While DeepSeek R1 has shown improved performance with CoT reasoning, its application in medical contexts is underexplored. We incorporated R1-generated CoT into model prompts and fine-tuned backbone LLMs. Results: The fine-tuned Qwen-7B-10k-overthink-CoT achieved the highest accuracy (92.4%), outperforming Qwen-7B-without-CoT (90%), LLaMA-3B-without-CoT (87.9%), Qwen-3B-without-CoT (85.6%), Qwen-3B-10k-overthink-CoT (68.5%), and LLaMA-3B-10k-overthink-CoT (46.2%). In a second dataset, an external validation was performed (n=113; 64 positive, 49 negative), Qwen-7B-10k-overthink-CoT sustained a strong, balanced performance (82.7%), followed by Qwen-7B-without-CoT (88.4%), LLaMA-3B-without-CoT (86.8%), Qwen-3B-without-CoT (84.5%), Qwen-3B-10k-overthink-CoT (58.9%), and LLaMA-3B-10k-overthink-CoT (46.2%). The fine-tuned Qwen-7B model with overthinking CoT (10,000 tokens) achieved the highest internal accuracy (92.4%), with balanced sensitivity and specificity. Across repeated runs, CoT-enhanced models demonstrated improved classification consistency compared to non-CoT models (Qwen-7B-without-CoT: 90%, LLaMA-3B-without-CoT: 87.9%, Qwen-3B-without-CoT: 85.6%). In external validation (n=113), non-CoT variants achieved higher accuracy (up to 88.4%), whereas the Qwen-7B CoT model demonstrated more balanced class performance (accuracy=82.7%). Conclusions: Supervised fine-tuning of LLMs with CoT offers an effective approach for automated PHD detection within unstructured data in the electronic medical record. While CoT-enhanced models demonstrated improved internal performance and more balanced classification, they did not consistently achieve higher accuracy in external validation, highlighting trade-offs between accuracy and class balance. These findings highlight the promise of LLM-based approaches for clinical text phenotyping while underscoring the need for larger, multicenter validation and careful calibration for real-world deployment. Continued validation and integration into the electronic medical record are essential for real-world, artificial intelligence–driven clinical decision support.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/65aeb9ead7dafad2f061f602c5cfe3ed" />

Posted on

Comparing the Accuracy of ChatGPT-4o, DeepSeek-V3, and Gemini 2.5 Flash in Answering Frequently Asked Questions About Systemic Lupus Erythematosus: Quantitative Study

Background: Systemic lupus erythematosus (SLE) is a complex, fluctuating disease, creating a continuous need for reliable patient information. A prior study concluded that patients with SLE often turn to the internet, including artificial intelligence (AI) chatbots, for information regarding SLE. The rise of AI chatbots as a primary information source presents a critical challenge regarding the accuracy of the information they provide. Objective: This study aimed to evaluate the performance of the latest generation of AI chatbots (ChatGPT-4o, DeepSeek-V3, and Gemini 2.5 Flash) in answering frequently asked questions about SLE. Methods: Twenty-two frequently asked questions about SLE in Bahasa Indonesia (the Indonesian language) were posed to each chatbot. Responses were independently and blindly evaluated for accuracy by 5 clinical immunologists using a 4-point Likert scale. Readability was assessed using the Flesch reading ease score formula. Statistical comparisons for accuracy and readability were performed using repeated-measures ANOVA or the Friedman test, followed by the Bonferroni test for pairwise comparisons. The Spearman ρ was used to evaluate correlations among accuracy, readability, and word count. Results: Gemini 2.5 Flash demonstrated the highest accuracy, with a mean score of 1.25 (SD 0.53), significantly outperforming ChatGPT-4o (mean 1.71, SD 0.61; <.001). Gemini 2.5 Flash significantly outperformed ChatGPT-4o in 2 evaluated domains. The interreliability analysis revealed a statistically significant level of agreement among the 5 evaluators across all responses (Kendall =0.389; <.001). Readability for all 3 chatbots was low (median Flesch reading ease score 42.22‐46.66). Gemini 2.5 Flash produced the longest responses (8509 total words), followed by DeepSeek-V3 (5410 words) and ChatGPT-4o (3632 words). A significant negative correlation was found between word count and lower accuracy (ρ=−0.401; =.001). Conclusions: Our study found that ChatGPT-4o, DeepSeek-V3, and Gemini 2.5 Flash provided overall satisfactory responses to SLE-related questions. The highest accuracy was demonstrated by Gemini 2.5 Flash; however, the absolute differences in scores among the 3 AI chatbots were relatively small. All 3 AI chatbots demonstrated low readability, which may limit accessibility for patient use. This finding highlights a critical “blind spot” in which clinical accuracy, as rated by experts, does not equate to patient accessibility. Thus, further research is required to develop more comprehensive evaluation frameworks incorporating safety, factuality, and calibration of AI chatbots across different medical fields and topics.
Posted on

TARGA Imager Enables High-Resolution Imaging of Neurodevelopmental Models

Sponsored content brought to you by

Lumencor logo

Neurodevelopment in schizophrenia poses major challenges for experimental study due at least in part to the brain’s genetic complexity, cellular diversity, and limitations in accessing living human tissue. To overcome such barriers, researchers often use complementary human stem cell–derived models: adherent cortical organoids and Neurogenin-2 (NGN2) induced neurons. Adherent cortical organoids form three-dimensional cultures containing diverse cortical neuron types, enabling analysis of network development and long-term maturation over months.1 In contrast, NGN2 neurons generate rapid, two-dimensional, homogeneous populations of excitatory neurons that display robust activity within weeks, making them well suited for scalable, functional assays, and high-throughput screening.2

With the added insight that stem cell models offer into the neural development of the schizophrenic brain, the quantification of patient-derived neurons’ collective function is a priority.3 At Columbia University’s Mortimer B. Zuckerman Mind Brain and Behavior Institute, researchers use NGN2 neurons, yielding reproducible populations of excitatory cortical neurons that scale reliably across experiments.

Calcium imaging provides a powerful functional readout in these NGN2 neuron networks. When a neuron fires an action potential, voltage-gated calcium channels open and intracellular calcium rises sharply.4 Fluorescence calcium indicators convert transient, ionic changes into fluorescence emission that can be quantitatively detected via light microscopy across thousands of cells simultaneously. Coupling calcium-sensitive reporters with high-speed optical microscopy enables noninvasive, population-level measurement of neural activity, synchrony, and network dynamics. Interpreting these rich image sequences requires sophisticated theoretical and numerical approaches.5

Building on the ability to measure neural activity with calcium imaging at scale, Lumencor’s TARGA Imager represents a transformative step in the development of optical imaging hardware for the study of neurodevelopmental conditions such as schizophrenia. It is well suited to workflows where NGN2-neuron cultures are studied across multiple conditions in parallel (Figure 1). In these contexts, TARGA delivers calcium fluorescence images over millimeter-scale fields of view within standard 96-well plates, entire well areas, while maintaining high-speed, faster-than video rate imaging with precision resolution.

Lumencor NGN2-neurons calcium imaging workflow
Figure 1. TARGA implementation for NGN2-neurons calcium imaging workflow

These capabilities allow researchers to observe chemical communications across large neuronal networks rather than isolated cells in real time. Images can be acquired at frequencies up to 100 Hz, enabling capture of fast calcium transients of collective neuronal dynamics. Rapid switching of multicolor excitation light supports multiplexed fluorescence dyes, linking functional activity with cellular structure and organization.

Overall, TARGA achieves high spatial, temporal, and spectral resolution simultaneously with precise, automated opto-mechanical architecture. These data are well matched to modern image analysis and AI algorithms, generating robust fluorescence traces from complex neuronal populations (Figure 2). In combination, these features make the TARGA Imager a revelatory neuroscience tool, uniquely enabling visualization of emergent collective behavior at millimeter scale with exceptional resolution. Such integrated performance accelerates discovery by bridging cellular mechanisms and systems-level phenotypes relevant to schizophrenia pathophysiology and therapeutic screening. By uniting scale, speed, and precision in a single optical platform, TARGA empowers researchers to probe experimental neuroscience and strengthens translational studies of complex psychiatric disease at population scale.

NGN2-neurons calcium imaging workflow
Figure 1. TARGA implementation for NGN2-neurons calcium imaging workflow

 

References

  1. Van der Kroeg et al. Human adherent cortical organoids in a multiwell format. eLife. 2024. 13:e98340.
  2. Shan et al. Fully defined NGN2 neuron protocol reveals diverse signatures of neuronal maturation. Cell Reports Methods. 2024. 4:100858.
  3. Rao et al. Aberrant pace of cortical neuron development in brain organoids from patients with 22q11.2 deletion syndrome‑associated schizophrenia. Nature Communications. 2025. 16:6986.
  4. Zhang et al. Fast and sensitive GCaMP calcium indicators for imaging neural populations. Nature. 2023. 615:884–891.
  5. Pasarkar et al. maskNMF: A denoise‑sparsen‑detect approach for extracting neural signals from dense imaging data. bioRxiv. 2023. 2023.09.14.557777.

 

Lumencor_June 2026 sponsored content QRCode

 

To learn more, visit: lumencor.com or contact our team at: info@lumencor.com.

The post TARGA Imager Enables High-Resolution Imaging of Neurodevelopmental Models appeared first on Inside Precision Medicine.

Posted on

360° Video-Based Virtual Reality for Preparing Medical Students for Body Donor Dissection: Randomized Controlled Trial

Background: Body donor dissection is fundamental to medical education but often induces anxiety and emotional distress in students, potentially impacting learning outcomes and well-being. Traditional preparation methods emphasize technical and procedural elements while inadequately addressing students’ emotional challenges. Recent advances in educational technology, particularly 360° video-based virtual reality (VR), may enhance students’ emotional readiness by providing immersive previews of dissection environments. However, the application of this technology specifically for emotional preparation for body donor dissection remains largely unexplored. Objective: This study aimed to develop and evaluate a 360° video-based VR application designed to enhance medical students’ emotional preparedness for their first body donor dissection experience. Methods: A randomized controlled longitudinal study was conducted with 43 first-year medical students (26/43, 60.5% female, mean age 20.9, SD 0.57 years) at Weill Cornell Medicine-Qatar in Fall 2025. Participants completed a baseline survey including the 40-item State-Trait Anxiety Inventory and were randomly assigned to intervention (n=22) or control (n=21) groups using computer-generated permuted block randomization. Before their first dissection session, the intervention group viewed a custom-designed 360° video-based VR experience that featured a virtual tour of the anatomy laboratory and a simulated first encounter with a body donor. The control group received no intervention. State-Trait Anxiety Inventory surveys were administered at baseline (survey 1, all participants), post-VR intervention (survey 2, intervention group only), and postfirst dissection (survey 3, all participants). A follow-up perception survey (survey 4) was administered to the intervention group 1 week into the dissection course. Data were analyzed using 2-tailed paired-samples and independent-samples tests, with qualitative responses analyzed using artificial intelligence–assisted thematic analysis. Results: The intervention group demonstrated a statistically significant reduction in trait anxiety (TA) immediately following the VR experience (mean difference 2.32, SD 4.95; =2.20; =.04), while the reduction in state anxiety (SA) was not significant (mean difference 2.41, SD 8.55; =1.32; =.20). No significant differences in SA or TA were found between intervention and control groups immediately before the first dissection session (SA: =0.03; =.98 and TA: =0.70; =.49) or in anxiety trajectories from baseline to postdissection (SA: =0.85; =.41 and TA: =0.46; =.65). Female students reported higher baseline TA compared to normative college populations (45.42 vs 40.40; mean difference 5.02, SD 7.72; =3.32; =.003). Qualitative analysis revealed positive perceptions, with 91% (10/11) reporting clear content and 82% (9/11) recommending it to future cohorts. Key perceived benefits included environmental familiarization, procedural understanding, and psychological preparation. Conclusions: The 360° video-based VR intervention significantly reduced TA and was perceived as valuable for emotional and procedural preparation. The intervention shows promise as a preparatory tool for enhancing emotional and procedural readiness; however, its impact on objective educational outcomes was not assessed and warrants further investigation. Trial Registration: ClinicalTrials.gov NCT07521033; https://clinicaltrials.gov/study/NCT07521033
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/2d931f56b90b14ca89868171f23345e7" />

Posted on

Social Partner Effects on Type 2 Diabetes Prevention, Management, and Spillover Health Outcomes: Single-Arm Pre-Post Pilot Intervention

Background: South Asian Americans are at high risk of prediabetes and type 2 diabetes mellitus (T2DM). South Asian populations are typically close-knit communities, with support networks that could be leveraged in lifestyle interventions. Objective: This study was a single-arm, pre-post pilot study to evaluate the feasibility and efficacy of a culturally tailored telehealth intervention for South Asian adults with prediabetes or T2DM and their social partners (trusted household members) who agreed to complete preintervention and postintervention surveys. Methods: Participants attended 5-hour-long health education sessions delivered in English and Bengali. Participant outcomes included pre-post changes in hemoglobin A1c (HbA), BMI, blood pressure (BP), self-reported minutes of physical activity, and dietary choices at baseline and at the 6-month follow-up. For social partners, outcomes included pre-post survey changes in physical activity and dietary choices. We used Pearson chi-square tests and paired 2-tailed tests to compare baseline measures with postintervention outcomes. Results: This pilot study included 54 participants and 106 social partners in Atlanta, Georgia, between March 2021 and November 2023. All participants were Bangladeshi and spoke native Bengali. Social partners were most commonly participants’ children (39/106, 36.8%) or spouses (34/106, 32.1%). The participant baseline HbA level was 7.5% (SD 1.48%), which decreased by −0.83% (95% CI 0.42%-1.30%; <.001). Participants also improved systolic BP by −5.8 mm Hg (95% CI 0.196-11.37; =.04) with no change in diastolic BP (−0.451 mm Hg, 95% CI −1.49 to 2.39; =.60) or BMI (−0.642 kg/m, 95% CI −1.87 to 0.59; =.17). Compared with baseline, 39% more participants exercised at least 150 minutes weekly (<.001), but there was no difference in self-reported fruit and vegetable intake. However, the social partners increased fruit and vegetable intake (=.02), decreased soda intake (<.001), and increased daily moderate exercise (=.003). Conclusions: Including social partners in T2DM prevention and management is feasible and potentially beneficial, but comparative studies are needed to determine the incremental effects of social partners’ participation vs individual-focused lifestyle interventions. Trial Registration: ClinicalTrials.gov NCT05275231; https://clinicaltrials.gov/study/NCT05275231
Posted on
<![CDATA[Lawsuits, research, and clinicians clash over youth screen addiction—learn more about how problematic social platform use evades diagnosis and how we can curb harm.]]>
Posted on
<![CDATA[Post hoc SUSTAIN-1 data reveal who relapses after stopping intranasal esketamine in TRD—key risk factors guide personalized relapse-prevention plans.]]>
Posted on

CiteSentinel Launched to Detect and Prevent AI Hallucinations in Legal Citations

Legal tech startup BrentWorks reports that it has launched CiteSentinel, a dedicated platform built specifically to detect and prevent AI hallucinations in legal citations, including those related to biotechnology. The tool scans legal documents and flags case law, statutes, and legal authorities that may be fabricated, misstated, or otherwise erroneous, before they reach a judge, according to the company.

Courts across the country are increasingly sanctioning attorneys who submit briefs containing invented case citations, a well-documented byproduct of generative AI drafting tools that produce authoritative-sounding, but entirely fictional, legal authority, says BrentWorks co-founder Brent Britton, a technology attorney and MIT-trained engineer. CiteSentinel was designed to close that verification gap, giving attorneys a fast and easy way to confirm that every citation in a filing corresponds to a real case, a real statute, and a real legal authority, he adds.

“The legal profession is learning, in very public ways, that AI doesn’t just make mistakes, it confidently lies to your face,” continues Britton. “CiteSentinel is about restoring trust. It lets lawyers move fast with the irresistible efficiencies of generative AI while still filing documents reciting authorities they can stand behind. It also enables them to scan opposing counsel’s documents, giving them a competitive edge in the courtroom.”

AI hallucinations
When a brief containing fabricated citations reaches the court, the question of who drafted it quickly becomes secondary to the question of whose name is on it. [BestForBest/Getty Images]

Many attorneys who do not personally use AI to draft documents are discovering they have a problem anyway, Britton points out. Opposing counsel may have used AI. Co-counsel may have. Contract attorneys and paralegals almost certainly have access to it and may be using it without disclosing that fact. When a brief containing fabricated citations reaches the court, the question of who drafted it quickly becomes secondary to the question of whose name is on it, he explains.

CiteSentinel lets attorneys scan any document, their own, a colleague’s, or an adversary’s, for citation errors before those errors become their problem, notes Britton. Attorneys who review opposing counsel’s filings with CiteSentinel gain an additional advantage: the ability to identify and challenge citations to authorities that simply do not exist, he says.

Unlike traditional research platforms that focus on finding more information, states Britton, CiteSentinel was created to confirm that the law cited in a document is real. Attorneys can scan:

  • Their own AI-assisted drafts, before filing
  • Submissions from co-counsel, contract attorneys, and support staff
  • Opposing counsel’s filings, for strategic advantage
  • Any document where citation accuracy carries professional or ethical weight

BrentWorks’ other co-founder is Brent Hunter, a technologist who applied neural networks to finance in 1993. He cites CiteSentinel as the first in a series of products the company will be releasing for the practice of law in the age of AI.

Both BrentWorks’ co-founders agree that AI hallucinations pose particular risks in biotechnology-related legal matters because cases often depend on highly technical evidence, including patent claims, prior art, clinical trial data, FDA regulatory history, scientific publications, expert witness testimony, freedom-to-operate analyses, and licensing agreements. In this context, an AI system could invent scientific references that do not exist, mischaracterize FDA guidance documents, fabricate patent precedents, incorrectly summarize clinical trial results, or generate inaccurate prior-art searches. Such errors can undermine legal arguments, regulatory submissions, and intellectual property strategies.

“Biotech litigation is where AI hallucinations turn genuinely dangerous. You have a system trained to sound authoritative now injecting phantom patent precedents and counterfeit clinical data into documents that determine whether a drug reaches patients or a patent survives challenge,” explains Brent Britton. “In this domain, where the technical record is everything, a ghost FDA guidance document or a fabricated prior art reference can unravel an entire legal strategy and years of work along with it. The law has always been a high-stakes information game, and right now the machines are playing it with synthetic cards.”

As CiteSentinel expands beyond just case citation verification, “it will be the truth layer that keeps all players honest,” he predicts.

 

The post CiteSentinel Launched to Detect and Prevent AI Hallucinations in Legal Citations appeared first on GEN – Genetic Engineering and Biotechnology News.

Posted on

CRISPR Shreds Undruggable Cancer Cells with Precision

When Jingkun Zeng, PhD, joined the lab of Nobel laureate, Jennifer Doudna, PhD, as a postdoctoral researcher in 2024, he was not interested in applying CRISPR for gene editing.

The molecular scissors had demonstrated extraordinary clinical promise in correcting single-point mutations, most strikingly in Baby KJ’s case, where a rare metabolic disorder once presented a 50% mortality rate in infancy.  

Yet, Zeng had his ambitious sights on stopping cancer progression, where the biology “became messy.” Cancer can be driven by hundreds of thousands of mutations, making it nearly impossible to correct each mutation one-by-one to restore healthy function. 

Zeng, who completed his PhD training in cancer evolution at The Francis Crick Institute, aimed to develop new CRISPR-based technology that could therapeutically access the undruggable tumor suppressor protein, p53. Mutations in this “guardian of the genome” are found in nearly half of all cancers, and up to 70–90% of cases of the most deadly tumors, including ovarian, pancreatic, and non-small cell lung cancer. 

In a new study published in Nature titled, “Targeting Cancer-Specific Mutations with RNA-Triggered Chromatin Shredding,” Zeng and colleagues from Innovative Genomics Institute (IGI), University of California (UC) Berkeley, UC San Francisco (UCSF), and Gladstone Institutes, have now engineered a CRISPR system to selectively trigger cancer cell death by chromatin shredding. 

The approach recognizes cancer cells using the RNA-guided nuclease, CRISPR-Cas12a2, to recognize mutant p53 mRNA transcripts. Therapeutic effectiveness was demonstrated in mouse models of lung and liver tumors. 

Bacterial roots 

Mutations in p53 are early drivers in the cancer-causing cascade, making the tumor suppressor one of the most sought-after targets in cancer therapy. Yet despite decades of effort, no approved p53 drugs exist on the market. 

Unlike many druggable proteins, p53 lacks a well-defined binding pocket traditionally required by established modalities, such as small molecules or antibodies. Additionally, most cancer therapeutics are designed to inhibit disease-driving proteins, whereas restoring p53 function demands precise, controlled activation of a tumor suppressor. 

“It’s the first time we managed to target p53 with such precision,” Zeng told GEN, emphasizing that CRISPR-Cas12a2 can distinguish healthy and disease cells that differed by just one nucleotide.

The novel drug modality takes advantage of CRISPR’s bacterial roots as a defense system that protects against infection by cutting the genetic material of invading viruses, preventing replication and spread.

Zeng also emphasizes that the guide RNA is easily programmable for additional therapeutic areas, such as destroying viral infected cells or abnormal cells due to aging. The technology can also be multiplexed to recognize multiple cancer mutations simultaneously.

The work joins a growing industry effort to develop scalable and generalizable genetic medicines. 

Looking ahead, the authors aim to improve the delivery efficiency to cancer cells, a longstanding challenge across CRISPR therapies. The team is also undergoing collaborations to apply the technology across diverse cancer types, including brain, prostate, and ovarian cancer. 

The post CRISPR Shreds Undruggable Cancer Cells with Precision appeared first on GEN – Genetic Engineering and Biotechnology News.