-
Mashup Score: 4
This extensive description of a unique cohort of paediatric patients with Cushing syndrome has the potential to inform diagnostic workup, preventative actions, and follow-up of children with this rare endocrine condition.
Source: www.thelancet.comCategories: General Medicine News, Hem/OncsTweet
-
Mashup Score: 7
Background: Artificial intelligence is increasingly being applied to many workflows. Large language models (LLMs) are publicly accessible platforms trained to understand, interact with, and…
Source: preprints.jmir.orgCategories: General Medicine News, Oncologists1Tweet-
Sharing a preprint from Elisabetta Xue, our talented @NCICCR_MOS Immunotherapy fellow: can #LLMs reliably answer Qs abt the complex HSCT field; can they facilitate comprehension for non-specialists & patients? https://t.co/4zKi8lazkA @DBrackenClarke @GMIannantuonoMD @gulleyj1
-
-
Mashup Score: 2Mutation of NOTCH1 is selected within normal esophageal tissues, yet leads to selective epistasis suppressive of further evolution into cancer - 1 year(s) ago
Sequencing of tissues from histologically normal esophagus, among other organs, has revealed that normal tissues harbor somatic variants that are also found in cancers arising from the same tissue types. Our understanding of how somatic mutations commonly found in normal tissue can contribute to tumorigenesis is limited: common somatic mutations may or may not confer phenotypes compatible with oncogenesis. However, the strength of selection for somatic variants that appear in both normal and cancer tissues can be quantified in each context using evolutionary modeling approaches. We studied the evolutionary trajectory from normal esophageal tissue to esophageal squamous-cell carcinoma (ESCC) by analysis of 2171 sequenced samples from previous studies on normal esophageal epithelium and ESCC to reveal the stepwise contributions of somatic mutations to increased cellular division and survival. We also analyzed pairwise selective epistasis between somatically mutated genes that may lead to
Source: www.biorxiv.orgCategories: General Medicine News, Hem/OncsTweet-
Mutation of NOTCH1 is selected within normal esophageal tissues, yet leads to selective epistasis suppressive of further evolution into cancer https://t.co/cXGYv2A7VO
-
-
Mashup Score: 2Building Transparent ML/AI Solutions to Advance Biological Research Codeathon - NCBI Insights - 1 year(s) ago
Machine Learning and Artificial Intelligence (ML/AI) Codeathon to Advance Biological Research- This codeathon invites developers and tech enthusiasts with a passion for social good to build equitable and transparent ML/AI solutions that tackle various problems in healthcare, research, education, and more. The event will be held virtually from February 26th to March 1st, 2024 (11 AM- 5 PM ET). Participants will have the opportunity to network with fellow participants and learn from experts in industry, academia, and government. The codeathon will be cooperative rather than competitive, and teams will share ideas and technical expertise. At the end of the event, teams will present their work to each other, representatives from the NIH, and the public. After the codeathon, the team products will be made publicly available through the NCBI Codeathons GitHub Organization and may be featured on NCBI sites. Participants are encouraged to co-author a joint manuscript and share their work onlin
Source: ncbiinsights.ncbi.nlm.nih.govCategories: General Medicine News, Hem/OncsTweet-
NCBI Codeathon: "Building Transparent ML/AI Solutions to Advance Biological Research Codeathon" 02-26-2024 @ 11:00 AM (EDT) to 03-01-2024 @ 05:00 PM (EDT) https://t.co/JA5R1fmkwg
-
-
Mashup Score: 20Comparison of Large Language Models in Answering Immuno-Oncology Questions: A Cross-Sectional Study - 1 year(s) ago
Background: The capability of large language models (LLMs) to understand and generate human-readable text has prompted the investigation of their potential as educational and management tools for cancer patients and healthcare providers. Materials and Methods: We conducted a cross-sectional study aimed at evaluating the ability of ChatGPT-4, ChatGPT-3.5, and Google Bard to answer questions related to four domains of immuno-oncology (Mechanisms, Indications, Toxicities, and Prognosis). We generated 60 open-ended questions (15 for each section). Questions were manually submitted to LLMs, and responses were collected on June 30th, 2023. Two reviewers evaluated the answers independently. Results: ChatGPT-4 and ChatGPT-3.5 answered all questions, whereas Google Bard answered only 53.3% (p <0.0001). The number of questions with reproducible answers was higher for ChatGPT-4 (95%) and ChatGPT3.5 (88.3%) than for Google Bard (50%) (p <0.0001). In terms of accuracy, the number of answers deemed
Source: www.medrxiv.orgCategories: General Medicine News, Hem/OncsTweet-
Sharing preprint led by the brilliant @GMIannantuonoMD with team incl. @DBrackenClarke, @FatimaKarzai, Hyoyoung Choo-Wosoba, @gulleyj1: can #LLMs answer expert curated, graded difficulty Qs abt #Cancer #Immunotherapy? Which one is best? Can we trust them? https://t.co/1vFJFoJW0q
-
-
Mashup Score: 38Pan-Cancer Analysis of Postdiagnosis Exercise and Mortality - 1 year(s) ago
PURPOSE The impact of postdiagnosis exercise on cause-specific mortality in cancer survivors and whether this differs on the basis of cancer site is unclear. METHODS We performed an analysis of 11,480 patients with cancer enrolled in the Prostate, Lung, Colorectal, and Ovarian cancer screening trial. Patients with a confirmed diagnosis of cancer completing a standardized survey quantifying exercise after diagnosis were included. The primary outcome was all-cause mortality (ACM); secondary end points were cancer mortality and mortality from other causes. Cox models were used to estimate the cause-specific hazard ratios (HRs) for ACM, cancer, and noncancer mortality as a function of meeting exercise guidelines versus not meeting guidelines with adjustment for important clinical covariates. RESULTS After a median follow-up of 16 years from diagnosis, 4,665 deaths were documented (1,940 due to cancer and 2,725 due to other causes). In multivariable analyses, exercise consistent with guidel
Source: ascopubs.orgCategories: Latest Headlines, Partners & KOLsTweet-
RT @RyanNipp: Pan-Cancer Analysis of Postdiagnosis Exercise and Mortality. https://t.co/ppGG4RY3pO @ASCO @JCO_ASCO @JCOOP_ASCO @DrBetofM…
-
RT @RyanNipp: Pan-Cancer Analysis of Postdiagnosis Exercise and Mortality. https://t.co/ppGG4RY3pO @ASCO @JCO_ASCO @JCOOP_ASCO @DrBetofM…
-
-
Mashup Score: 3Applications of large language models in cancer care: current evidence and future perspectives - 1 year(s) ago
The development of large language models (LLMs) is a recent success in the field of generative artificial intelligence (AI). They are computer models able to perform a wide range of natural language processing tasks, including content generation, question answering, or language translation. In recent months, a growing number of studies aimed to assess their potential applications in the field of medicine, including cancer care. In this mini review, we described the present published evidence for using LLMs in oncology. All the available studies assessed ChatGPT, an advanced language model developed by OpenAI, alone or compared to other LLMs, such as Google Bard, Chatsonic, and Perplexity. Although ChatGPT could provide adequate information on the screening or the management of specific solid tumors, it also demonstrated a significant error rate and a tendency toward providing obsolete data. Therefore, an accurate, expert-driven verification process remains mandatory to avoid the potent
Source: www.frontiersin.orgCategories: Hem/Oncs, Latest HeadlinesTweet-
Our brief review of research (as opposed to blogposts/social media posts) on applications of #LLM chatbots in #oncology care, with @GMIannantuonoMD @DBrackenClarke @gulleyj1 and @FatimaKarzai. I expect a lot more to come as use cases get identified. https://t.co/75ohTBgw4W
-
-
Mashup Score: 1Spatial Transcriptomic Analysis of Pituitary Corticotroph Tumors Unveils Intratumor Heterogeneity - 1 year(s) ago
Spatial transcriptomic (ST) analysis of tumors provides a novel approach on studying gene expression along with the localization of tumor cells in their environment to uncover spatial interactions. Herein, we present ST analysis of corticotroph pituitary neuroendocrine tumors (PitNETs) from formalin-fixed, paraffin-embedded (FFPE) tissues. We report that the in situ annotation of tumor tissue can be inferred from the gene expression profiles and is in concordance with the annotation made by a pathologist. Furthermore, relative gene expression in the tumor corresponds to common protein staining used in the evaluation of PitNETs, such as reticulin and Ki-67 index. Finally, we identify intratumor heterogeneity; clusters within the same tumor may present with different secretory capacity and transcriptomic profiles, unveiling potential intratumor cell variability with possible therapeutic interest. Together, our results provide the first attempt to clarify the spatial cell profile in PitNE
Source: www.medrxiv.orgCategories: Latest Headlines, Oncologists1Tweet-
Excited for participating in this #spatialtranscriptomics #Visium platform study with an expert team from @NICHD_NIH, in the first step of studying the spatial biology of #pituitary corticotroph tumors, revealing their heterogeneity. https://t.co/SANbr315Iz
-
-
Mashup Score: 0In vivo hematopoietic stem cell modification by mRNA delivery - 1 year(s) ago
Targeting specific messenger RNA–encapsulating lipid nanoparticles to hematopoietic stem cells permits in vivo bone marrow transplantation.
Source: www.science.orgCategories: Hem/Oncs, Latest HeadlinesTweet-
https://t.co/OpvVFYGzQc @DBrackenClarke
-
-
Mashup Score: 0Language trees with sampled ancestors support a hybrid model for the origin of Indo-European languages - 1 year(s) ago
Indo-European languages emerged south of the Caucasus around 8300 years ago, followed by an expansion northward to the Steppe regions.
Source: www.science.orgCategories: Latest Headlines, Oncologists1Tweet-
Convergence of paleogenomics and linguistics methods for IE languages supporting hybrid model between Steppe and Anatolian hypotheses. https://t.co/8IQyjIskJX
-
This must be the largest series of #pediatric Cushing syndrome: single-center (title to be corrected), from #NICHD. #endocrine Paediatric Cushing syndrome: a prospective, multisite, observational cohort study - The Lancet Child & Adolescent Health https://t.co/71nSk91PKk