Longevity Papers

We derive and test a CT-based biological age model for predicting longevity, using an automated pipeline of explainable AI algorithms that quantifies skeletal muscle, abdominal fat, aortic calcification, bone density, and solid abdominal organs. We apply these AI tools to abdominal CT scans from 123,281 adults (mean age, 53.6 years; 47% women; median follow-up, 5.3 years). The final weighted CT biomarker selection was based on the index of prediction accuracy. The CT model significantly outperforms standard demographic data for predicting longevity (IPA = 29.2 vs. 21.7; 10-year AUC = 0.880 vs. 0.779; p < 0.001). Age- and sex-corrected survival hazard ratio for the highest-vs-lowest risk quartile was 8.73 (95% CI,8.14-9.36) for the CT biological age model, and increased to 24.79 after excluding cancer diagnoses within 5 years of CT. Muscle density, aortic plaque burden, visceral fat density, and bone density contributed the most. Here we show a personalized phenotypic CT biological age model that can be opportunistically-derived, regardless of clinical indication, to better inform risk assessment.

Current deep-learning-based image-analysis solutions exhibit limitations in holistically capturing spatiotemporal cellular changes, particularly during aging. We present scCamAge, an advanced context-aware multimodal prediction engine that co-leverages image-based cellular spatiotemporal features at single-cell resolution alongside cellular morphometrics and aging-associated bioactivities such as genomic instability, mitochondrial dysfunction, vacuolar dynamics, reactive oxygen species levels, and epigenetic and proteasomal dysfunctions. scCamAge employed heterogeneous datasets comprising ∼1 million single yeast cells and was validated using pro-longevity drugs, genetic mutants, and stress-induced models. scCamAge also predicted a pro-longevity response in yeast cells under iterative thermal stress, confirmed using integrative omics analyses. Interestingly, scCamAge, trained solely on yeast images, without additional learning, surpasses generic models in predicting chemical and replication-induced senescence in human fibroblasts, indicating evolutionary conservation of aging-related morphometrics. Finally, we enhanced the generalizability of scCamAge by retraining it on human fibroblast senescence datasets, which improved its ability to predict senescent cells.

Sleep is a fundamental biological process with profound implications for physical and mental health, yet our understanding of its complex patterns and their relationships to a broad spectrum of diseases remains limited. While polysomnography (PSG), the gold standard for sleep analysis, captures rich multimodal physiological data, analyzing these measurements has been challenging due to limited flexibility across recording environments, poor generalizability across cohorts, and difficulty in leveraging information from multiple signals simultaneously. To address this gap, we curated over 585,000 hours of high-quality sleep recordings from approximately 65,000 participants across multiple cohorts and developed SleepFM, a multimodal sleep foundation model trained with a novel contrastive learning approach, designed to accommodate any PSG montage. SleepFM produces informative sleep embeddings that enable predictions of future diseases. We systematically demonstrate that SleepFM embeddings can predict 130 future diseases, as modeled by Phecodes, with C-Index and AUROC of at least 0.75 on held-out participants (Bonferroni-corrected p < 0.01). This includes accurate predictions for death (C-Index: 0.84 [95% CI: 0.81-0.87]), heart failure (C-Index: 0.80 [95% CI: 0.77-0.83]), chronic kidney disease (C-Index: 0.79 [95% CI: 0.77-0.81]), dementia (C-Index: 0.85 [95% CI: 0.82-0.87]), stroke (C-Index: 0.78 [95% CI: 0.76-0.81]), atrial fibrillation (C-Index: 0.78 [95% CI: 0.75-0.81]), and myocardial infarction (C-Index: 0.81 [95% CI: 0.78-0.84]). The model's generalizability was further validated through strong performance on the Sleep Heart Health Study (SHHS), a dataset unseen during pre-training. Additionally, SleepFM demonstrates strong performance on traditional sleep analysis tasks, achieving competitive results in both sleep staging (mean F1 scores: 0.70-0.78) and sleep apnea diagnosis (AUROC: 0.90-0.94). Beyond these standard applications, our analysis reveals that specific sleep stages and physiological signals carry distinct predictive power for different diseases. This work demonstrates how foundation models can leverage sleep polysomnography data to uncover the extensive relationship between sleep physiology and future disease risk.

Nicotinamide adenine dinucleotide (NAD

The molecular mechanisms of aging are not fully understood. Here, we used label-free Stimulated Raman scattering (SRS) microscopy to investigate changes in proteins and lipids throughout the lifespan of C. elegans. We observed a dramatic buildup of proteins within the body cavity or pseudocoelom of aged adults that was blunted by interventions that extend lifespan: caloric restriction (CR) and the reduced insulin/insulin-like growth factor signaling (IIS) pathway. Using a combination of microscopy, proteomic analysis, and validation with mutant strains, we identified vitellogenins as the key molecular components of the protein buildup in the pseudocoelom. Vitellogenins shuttle nutrients from intestine to embryos and are homologous to human apolipoprotein B, the causal driver of cardiovascular disease. We then showed that CR and knockdown of vitellogenins both extend lifespan by >60%, but their combination has no additional effect on lifespan, suggesting that CR extends the lifespan of C. elegans in part by inhibiting vitellogenesis. The extensive dataset of more than 12,000 images stitched into over 350 whole-animal SRS images of C. elegans at different ages and subjected to different longevity intervention will be a valuable resource for researchers interested in aging.