Cancer screening, leading to early detection, saves lives. Unfortunately, existing screening techniques require expensive and intrusive medical procedures, not globally available, resulting in too many lost would-be-saved lives. We present CATCH-FM, CATch Cancer early with Healthcare Foundation Models, a cancer pre-screening methodology that identifies high-risk patients for further screening solely based on their historical medical records. With millions of electronic healthcare records (EHR), we establish the scaling law of EHR foundation models pretrained on medical code sequences, pretrain compute-optimal foundation models of up to 2.4 billion parameters, and finetune them on clinician-curated cancer risk prediction cohorts. In our retrospective evaluation comprising of thirty thousand patients, CATCH-FM achieves strong efficacy, with 50% sensitivity in predicting first cancer risks at 99% specificity cutoff, and outperforming feature-based tree models and both general and medical LLMs by up to 20% AUPRC. Despite significant demographic, healthcare system, and EHR coding differences, CATCH-FM achieves state-of-the-art pancreatic cancer risk prediction on the EHRSHOT few-shot leaderboard, outperforming EHR foundation models pretrained using on-site patient data. Our analysis demonstrates the robustness of CATCH-FM in various patient distributions, the benefits of operating in the ICD code space, and its ability to capture non-trivial cancer risk factors. Our code will be open-sourced.

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest c ancers, and early detection remains a major clinical challenge due to the absence of spec ific symptoms and reliable biomarkers. In this work, we propose a new multimodal appro ach that integrates longitudinal diagnosis code histories and routinely collected laborato ry measurements from electronic health records to detect PDAC up to one year prior to clin ical diagnosis. Our method combines neural controlled differential equations to model irregular lab time series, pretrained language models and recurrent networks to learn diagnosis code trajectory representations, and cross-attention mechanisms to capture in teractions between the two modalities. We develop and evaluate our approach on a real-world dat aset of nearly 4,700 patients and achieve significant improvements in AUC ranging from 6.5 % to 15.5% over state-of-the-art methods. Furthermore, our model identifies diagnosis codes and laboratory panels associated with elevated PDAC risk, including both established and new biomarkers.

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive cancer, with most cases diagnosed at stage IV and a five-year overall survival rate below 5%. Early detection and prognosis modeling are crucial for improving patient outcomes and guiding early intervention strategies. In this study, we developed and evaluated a deep learning fusion model that integrates radiology reports and CT imaging to predict PDAC risk. The model achieved a concordance index (C-index) of 0.6750 (95% CI: 0.6429, 0.7121) and 0.6435 (95% CI: 0.6055, 0.6789) on the internal and external dataset, respectively, for 5-year survival risk estimation. Kaplan-Meier analysis demonstrated significant separation (p<0.0001) between the low and high risk groups predicted by the fusion model. These findings highlight the potential of deep learning-based survival models in leveraging clinical and imaging data for pancreatic cancer.

Purpose: Retrieval-augmented generation (RAG) is a technology to enhance the functionality and reliability of large language models (LLMs) by retrieving relevant information from reliable external knowledge (REK). RAG has gained interest in radiology, and we previously reported the utility of NotebookLM, an LLM with RAG (RAG-LLM), for lung cancer staging. However, since the comparator LLM differed from NotebookLM's internal model, it remained unclear whether its advantage stemmed from RAG or inherent model differences. To better isolate RAG's impact and assess its utility across different cancers, we compared NotebookLM with its internal LLM, Gemini 2.0 Flash, in a pancreatic cancer staging experiment. Materials and Methods: A summary of Japan's pancreatic cancer staging guidelines was used as REK. We compared three groups - REK+/RAG+ (NotebookLM with REK), REK+/RAG- (Gemini 2.0 Flash with REK), and REK-/RAG- (Gemini 2.0 Flash without REK) - in staging 100 fictional pancreatic cancer cases based on CT findings. Staging criteria included TNM classification, local invasion factors, and resectability classification. In REK+/RAG+, retrieval accuracy was quantified based on the sufficiency of retrieved REK excerpts. Results: REK+/RAG+ achieved a staging accuracy of 70%, outperforming REK+/RAG- (38%) and REK-/RAG- (35%). For TNM classification, REK+/RAG+ attained 80% accuracy, exceeding REK+/RAG- (55%) and REK-/RAG- (50%). Additionally, REK+/RAG+ explicitly presented retrieved REK excerpts, achieving a retrieval accuracy of 92%. Conclusion: NotebookLM, a RAG-LLM, outperformed its internal LLM, Gemini 2.0 Flash, in a pancreatic cancer staging experiment, suggesting that RAG may improve LLM's staging accuracy. Furthermore, its ability to retrieve and present REK excerpts provides transparency for physicians, highlighting its applicability for clinical diagnosis and classification.

A kind of pancreatic cancer called Pancreatic Ductal Adenocarcinoma (PDAC) is anticipated to be one of the main causes of mortality during past years. Evidence from several researches supported the concept that the oncogenic KRAS (Ki-ras2 Kirsten rat sarcoma viral oncogene) mutation is the major cause of pancreatic cancer. KRAS acts as an on-off switch that promotes cell growth. But when the KRAS gene is mutated, it will be in one position, allowing the cell growth uncontrollably. This uncontrollable multiplication of cells causes cancer growth. Therefore, KRAS was selected as the target protein in the study. Fifty plant-derived compounds are selected for the study. To determine whether the examined drugs could bind to the KRAS complex's binding pocket, molecular docking was performed. Computational analyses were used to assess the possible ability of tested substances to pass the Blood Brain Barrier (BBB). To predict the bioactivity of ligands a machine learning model was created. Five machine learning models were created and have chosen the best one among them for analyzing the bioactivity of each ligand. From the fifty plant-derived compounds the compounds with the least binding energies are selected. Then bioactivity of these six compounds is analyzed using Random Forest Regression model. Adsorption, Distribution, Metabolism, Excretion (ADME) properties of compounds are analyzed. The results showed that borneol has powerful effects and acts as a promising agent for the treatment of pancreatic cancer. This suggests that borneol found in plants like mint, ginger, rosemary, etc., is a successful compound for the treatment of pancreatic cancer.

The advancement of artificial intelligence algorithms has expanded their application to several fields such as the biomedical domain. Artificial intelligence systems, including Large Language Models (LLMs), can be particularly advantageous in drug discovery, which is a very long and expensive process. However, LLMs by themselves lack in-depth knowledge about specific domains and can generate factually incorrect information. Moreover, they are not able to perform more complex actions that imply the usage of external tools. Our work is focused on these two issues. Firstly, we show how the implementation of an advanced RAG system can help the LLM to generate more accurate answers to drug-discovery-related questions. The results show that the answers generated by the LLM with the RAG system surpass in quality the answers produced by the model without RAG. Secondly, we show how to create an automatic target dossier using LLMs and incorporating them with external tools that they can use to execute more intricate tasks to gather data such as accessing databases and executing code. The result is a production-ready target dossier containing the acquired information summarized into a PDF and a PowerPoint presentation.

Like millions of people in the US, artificial intelligence was just something Dianne Balon read about on the news. Little did she know the tech would come to save her life. Despite being a picture of health, an AI-powered blood test in 2022 revealed that one of the world's deadliest cancers was silently forming in Ms Balon's pancreas. It caught the tumor in its earliest form, before it had the chance to grow and spread, which is when the vast majority of pancreatic cancers are caught - at which point it's too late. The results of the test provided a key'piece of the puzzle'.

Explainable AI (XAI) [1] is a research field focused on making Artificial Intelligence (AI) systems in general, and Machine Learning (ML) systems in particular, more understandable to humans. Explainable AI offers several advantages, to name a few: it fosters confidence in the prediction of the model by making the decision-making process more transparent, promotes responsible AI development, aids in debugging and identifying issues, and allows auditing of AI models and checking if they adhere to regulatory standards. The inherent explainability of AI systems has not remained static but has changed considerably as a result of technological progress. In fact, explainability has become an increasingly difficult issue to tackle, as the internal functioning of AI systems has become less intelligible as they have become more complex [2]. Initially, symbolic AI models were explainable per se, e.g., rule-based expert systems could easily show to their users which rules they had followed to make a given decision, even though the rules can incorporate measures of uncertainty and imprecision as, for example, in fuzzy systems. These type of AI models are considered transparent, which means that the model itself is understandable [3], being understandability the characteristic of a model to make a human understand its function without any need for explaining its internal structure or the algorithmic means by which the model processes data internally [4].

Machine learning has emerged as a powerful tool for scientific discovery, enabling researchers to extract meaningful insights from complex datasets. For instance, it has facilitated the identification of disease-predictive genes from gene expression data, significantly advancing healthcare. However, the traditional process for analyzing such datasets demands substantial human effort and expertise for the data selection, processing, and analysis. To address this challenge, we introduce a novel framework, a Team of AI-made Scientists (TAIS), designed to streamline the scientific discovery pipeline. TAIS comprises simulated roles, including a project manager, data engineer, and domain expert, each represented by a Large Language Model (LLM). These roles collaborate to replicate the tasks typically performed by data scientists, with a specific focus on identifying disease-predictive genes. Furthermore, we have curated a benchmark dataset to assess TAIS's effectiveness in gene identification, demonstrating our system's potential to significantly enhance the efficiency and scope of scientific exploration. Our findings represent a solid step towards automating scientific discovery through large language models.

As a result, it's essential to try to catch pancreatic cancer at the earliest stage possible. A team of researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) worked with Limor Appelbaum, a staff scientist in the department of radiation oncology at the Beth Israel Deaconess Medical Center in Boston, to develop an AI system that predicts a patient's likelihood of developing pancreatic ductal adenocarcinoma (PDAC), the most common form of the cancer. The system outperformed current diagnostic standards and could someday be used in a clinical setting to identify patients who could benefit from early screening or testing, helping catch the disease earlier and save lives. The research was published in the journal eBioMedicine last month. The researchers' goal was a model capable of predicting a patient's risk of being diagnosed with PDAC in the next six to 18 months, making early-stage detection and cure more likely.