Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of the stored samples. Current Rehearsal-based CL methods typically construct the memory buffer by selecting a representative subset (referred to as coresets), aiming to approximate the training efficacy of the full dataset with minimal storage overhead. However, mainstream Coreset Selection (CS) methods generally formulate the CS problem as a bi-level optimization problem that relies on numerous inner and outer iterations to solve, leading to substantial computational cost thus limiting their practical efficiency. In this paper, we aim to provide a more efficient selection logic and scheme for coreset construction. To this end, we first analyze the Mean Squared Error (MSE) between the buffer-trained model and the Bayes-optimal model through the perspective of localized error decomposition to investigate the contribution of samples from different regions to MSE suppression. Further theoretical and experimental analyses demonstrate that samples with high probability density play a dominant role in error suppression. Inspired by this, we propose the Probability Density-Aware Coreset (PDAC) method. PDAC leverages the Projected Gaussian Mixture (PGM) model to estimate each sample's joint density, enabling efficient density-prioritized buffer selection. Finally, we introduce the streaming Expectation Maximization (EM) algorithm to enhance the adaptability of PGM parameters to streaming data, yielding Streaming PDAC (SPDAC) for streaming scenarios. Extensive comparative experiments show that our methods outperforms other baselines across various CL settings while ensuring favorable efficiency.

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.

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.

Artificial intelligence (AI), deep learning (DL), and machine learning (ML) have transformed many industries and areas of science. Now, these tools are being applied to address the challenges of cancer biomarker discovery, where the analysis of vast amounts of imaging and molecular data is beyond the ability of traditional statistical analyses and tools. In a special issue of Cancer Biomarkers, researchers propose various approaches and explore some of the unique challenges of using AI, DL, and ML to improve the accuracy and predictive power of biomarkers for cancer and other diseases. "The biomarker field is blessed with a plethora of imaging and molecular-based data, and at the same time, plagued with so much data that no one individual can comprehend it all," explained Guest Editor Karin Rodland, PhD, Pacific Northwest National Laboratory, Richland; and Oregon Health and Science University, Portland, OR, USA. "AI offers a solution to that problem, and it has the potential to uncover novel interactions that more accurately reflect the biology of cancer and other diseases."

BERG, a clinical-stage biotech that employs artificial intelligence (AI) to investigate diseases and develop innovative treatments, today announced two major medical/clinical research developments on pancreatic ductal adenocarcinoma (PDAC) to be presented virtually at the European Society for Medical Oncology (ESMO) 2020 Congress taking place from September 19-21, 2020. The first study entitled "Project Survival: High Fidelity Longitudinal Phenotypic and Multi-omic Characterization of Pancreatic Ductal Adenocarcinoma (PDAC) for Biomarker Discovery", is the culmination of the largest existing high-fidelity characterization of pancreatic cancer from a phenotypic/adaptive multi-omic perspective. BERG's Interrogative Biology platform was employed to identify causal relationships between existing pancreatic cancer therapies and changes in proteomic, metabolic and lipidomic responses to 253 treatment interventions and 211 progression events. The research cohort included PDAC patients across different stages including early, locally advanced and metastatic to yield the most accurate characterization of the evolution of the disease. Throughout the course of the study, 470,000 clinical data points were gathered.