Predicting an individual's aging trajectory is a central challenge in preventative medicine and bioinformatics. While machine learning models can predict chronological age from biomarkers, they often fail to capture the dynamic, longitudinal nature of the aging process. In this work, we developed and validated a machine learning pipeline to predict age using a longitudinal cohort with data from two distinct time periods (2019-2020 and 2021-2022). We demonstrate that a model using only static, cross-sectional biomarkers has limited predictive power when generalizing to future time points. However, by engineering novel features that explicitly capture the rate of change (slope) of key biomarkers over time, we significantly improved model performance. Our final LightGBM model, trained on the initial wave of data, successfully predicted age in the subsequent wave with high accuracy ($R^2 = 0.515$ for males, $R^2 = 0.498$ for females), significantly outperforming both traditional linear models and other tree-based ensembles. SHAP analysis of our successful model revealed that the engineered slope features were among the most important predictors, highlighting that an individual's health trajectory, not just their static health snapshot, is a key determinant of biological age. Our framework paves the way for clinical tools that dynamically track patient health trajectories, enabling early intervention and personalized prevention strategies for age-related diseases.

Grey matter loss in the hippocampus is a hallmark of neurobiological aging, yet understanding the corresponding changes in its functional connectivity remains limited. Seed-based functional connectivity (FC) analysis enables voxel-wise mapping of the hippocampus's synchronous activity with cortical regions, offering a window into functional reorganization during aging. In this study, we develop an interpretable deep learning framework to predict brain age from hippocampal FC using a three-dimensional convolutional neural network (3D CNN) combined with LayerCAM saliency mapping. This approach maps key hippocampal-cortical connections, particularly with the precuneus, cuneus, posterior cingulate cortex, parahippocampal cortex, left superior parietal lobule, and right superior temporal sulcus, that are highly sensitive to age. Critically, disaggregating anterior and posterior hippocampal FC reveals distinct mapping aligned with their known functional specializations. These findings provide new insights into the functional mechanisms of hippocampal aging and demonstrate the power of explainable deep learning to uncover biologically meaningful patterns in neuroimaging data.

Continuous-time systems are often represented by differential equations, including Ordinary Differential Equations (ODEs) like the motion of a pendulum and Partial Differential Equations (PDEs) such as the heat equation, which describe system behavior in response to time and other variables. For systems that evolve at discrete intervals, difference equations--using linear or nonlinear recursive functions--capture state changes over time, as seen in models of population growth. Dynamical systems can also be described geometrically via phase or state space, where each point represents a system state, and trajectories represent system evolution. Alternatively, vector fields describe time evolution as a flow, mapping system states across time steps, thereby outlining the system's path on its phase space manifold. In physics, it's more common to describe the dynamical systems using Hamiltonian or Lagrangian formalisms, which provide a more structured way of capturing the energy dynamics of a system. In systems where randomness or noise plays a role, stochastic differential equations (SDEs) are used.

Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current model editors, which modify such behaviors of pre-trained models, degrade model performance quickly across multiple, sequential edits. We propose GRACE, a \textit{lifelong} model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs. GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights.

We are now in the later stages of the first generation of life extension, which involves applying the current class of pharmaceutical and nutritional knowledge to overcoming health challenges. In the 2020s we are starting the second phase of life extension, which is the merger of biotechnology with AI. The 2030s will usher in the third phase of life extension, which will be to use nanotechnology to overcome the limitations of our biological organs altogether. As we enter this phase, we'll greatly extend our lives, allowing people to far transcend the normal human limit of 120 years. If you buy something using links in our stories, we may earn a commission.

The National Museum of Emerging Science and Innovation has made "aging" a centerpiece of its new permanent exhibitions that opened to the public on Wednesday. The museum in Tokyo's Odaiba district, popularly known as Miraikan, has completed work on four new permanent exhibitions, all of which are in line with its vision to help visitors confront various social issues and find ideas on how to overcome them, Miraikan CEO Chieko Asakawa told reporters Tuesday. In addition to the exhibition devoted to "aging," there are two new exhibitions that let people experience life with "robots," and one that showcases "planetary crisis," brought on by climate change and other global issues. "Aging is a rare topic to be handled by a science museum, but we have worked hard on creating an exhibit on this theme, thinking it's important for Japan," said Asakawa, a former IBM engineer and accessibility technology expert who assumed the current role at the museum in April 2021. "We want to convey the message that Japan's superaging society can lead the world by making the best of technologies and social systems to deal with aging."

Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current model editors, which modify such behaviors of pre-trained models, degrade model performance quickly across multiple, sequential edits. We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs. GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights. This is the first method enabling thousands of sequential edits using only streaming errors. Our experiments on T5, BERT, and GPT models show GRACE's state-of-the-art performance in making and retaining edits, while generalizing to unseen inputs. Our code is available at https://www.github.com/thartvigsen/grace}.

Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input. Most existing methods often produce one deterministic estimation. This paper proposes a novel CLIP-driven Pluralistic Aging Diffusion Autoencoder (PADA) to enhance the diversity of aging patterns. First, we employ diffusion models to generate diverse low-level aging details via a sequential denoising reverse process. Second, we present Probabilistic Aging Embedding (PAE) to capture diverse high-level aging patterns, which represents age information as probabilistic distributions in the common CLIP latent space. A text-guided KL-divergence loss is designed to guide this learning. Our method can achieve pluralistic face aging conditioned on open-world aging texts and arbitrary unseen face images. Qualitative and quantitative experiments demonstrate that our method can generate more diverse and high-quality plausible aging results.

The future has arrived in Bakersfield, and I'm not sure I'm ready for it. For nearly three hours, the conversation was nonstop at the home of Audrey and Ken Mattlin, who happen to live with several robots. There's ElliQ, who resembles a table lamp and speaks mainly to Audrey, 84, whom the robot refers to by a nickname. As in, "How did you sleep, Jelly Bean?" Goo-goo-eyed Astro looks like a short-handled vacuum cleaner with an electronic tablet for a face. He scoots around the house on wheels and follows people on command.

The application of artificial intelligence to the study of aging in 2013 led to the development of tools for measuring biological age and predicting mortality, which is defined as the frequency of death in a defined population during a specified interval [1]. Public access to these tools creates the opportunity for self-studies, allowing individuals to gain insights into how their bodies would respond to diet, lifestyle, exercise, and supplementation interventions aimed at changing their biological ages or risks of death. In 2013, Steve Horvath developed a highly accurate artificial intelligence-driven method of determining biological age [2]. This long-awaited development ushered in a new era of aging research. For the first time, it enabled researchers in academia and industry to measure the results of their work in terms of changes in biological age. For example, in 2019, Dr. Greg Fahy and his colleagues carried out an experiment aimed at regenerating the thymus.