Search

Summary Background Mortality risk stratification based on dichotomising a physiological indicator with a cutoff point might not adequately capture increased mortality risk and might not account for non-linear associations. We aimed to characterise the linear and non-linear relationships of 27 physiological indicators with all-cause mortality to evaluate whether the current clinical thresholds are suitable in distinguishing patients at high risk for mortality from those at low risk. Methods For this observational cohort study of the US non-institutionalised population, we used data from adults (≥18 years) included in the 1999–2014 National Health and Nutrition Examination Survey (NHANES) linked with National Death Index mortality data collected from Jan 1, 1999, up until Dec 31, 2015. We used Cox proportional hazards regression models adjusted for age, sex, and race or ethnicity to assess associations of physiological indicators with all-cause mortality. We assessed non-linear associations by discretising the physiological indicator into nine quantiles (termed novemtiles) and by using a weighted sum of cubic polynomials (spline). We used ten-fold cross validation to select the most appropriate model using the concordance index, Nagelkerke R2, and Akaike Information Criterion. We identified the level of each physiological indicator that led to a 10% increase in mortality risk to define our cutoffs used to compare with the current clinical thresholds. Findings We included 47 266 adults of 82 091 assessed for eligibility. 25 (93%) of 27 indicators showed non-linear associations with substantial increases compared with linear models in mortality risk (1·5–2·5-times increase). Height and 60 s pulse were the only physiological indicators to show linear associations. For example, participants with an estimated glomerular filtration rate (GFR) of less than 65 mL/min per 1·73 m2 or between 90–116 mL/min per 1·73 m2 are at moderate (hazard ratio 1–2) mortality risk. Those with a GFR greater than 117 mL/min per 1·73 m2 show substantial (hazard ratio ≥2) mortality risk. Both lower and higher values of cholesterol are associated with increased mortality risk. The current clinical thresholds do not align with our mortality-based cutoffs for fat deposition indices, 60 s pulse, triglycerides, cholesterol-related indicators, alkaline phosphatase, glycohaemoglobin, homoeostatic model assessment of insulin resistance, and GFR. For these indicators, the misalignment suggests the need to consider an additional bound when only one is provided. Interpretation Most clinical indicators were shown to have non-linear associations with all-cause mortality. Furthermore, considering these non-linear associations can help derive reliable cutoffs to complement risk stratification and help inform clinical care delivery. Given the poor alignment with our proposed cutoffs, the current clinical thresholds might not adequately capture mortality risk. Funding Ravitz Family Foundation, Forbes Institute for Cancer Discovery, and National Institutes of Health.

With the aging of the world population, age-related hearing loss (presbycusis) and other hearing disorders such as tinnitus become more prevalent, leading to reduced quality of life and social isolation. Unveiling the genetic and environmental factors leading to age-related auditory disorders could suggest lifestyle and therapeutic interventions to slow auditory aging. In the following, we built the first machine learning-based hearing age predictor by training models to predict chronological age from hearing test results (root mean squared error=7.10±0.07 years; R-Squared=31.4±0.8%). We defined hearing age as the prediction outputted by the model on unseen samples, and accelerated auditory aging as the difference between a participant’s hearing age and age. We then performed a genome wide association study [GWAS] and found that accelerated hearing aging is 14.1±0.4% GWAS-heritable. Specifically, accelerated auditory aging is associated with 662 single nucleotide polymorphisms in 243 genes (e.g OR2B4P, involved in smell perception). Similarly, it is associated with biomarkers (e.g cognitive tests), clinical phenotypes (e.g chest pain), diseases (e.g depression), environmental (e.g smoking, sleep) and socioeconomic (e.g income, education, social support) variables. The hearing age predictor could be used to evaluate the efficiency of emerging rejuvenation therapies on hearing.

With age, the prevalence of diseases such as fatty liver disease, cirrhosis, and type two diabetes increases. Approaches to both predict abdominal age and identify risk factors for accelerated abdominal age may ultimately lead to advances that will delay the onset of these diseases. We build an abdominal age predictor by training convolutional neural networks to predict abdominal age (or “AbdAge”) from 45,552 liver magnetic resonance images [MRIs] and 36,784 pancreas MRIs (R-Squared = 73.3 ± 0.6; mean absolute error = 2.94 ± 0.03 years). Attention maps show that the prediction is driven by both liver and pancreas anatomical features, and surrounding organs and tissue. Abdominal aging is a complex trait, partially heritable (h_g2 = 26.3 ± 1.9%), and associated with 16 genetic loci (e.g. in PLEKHA1 and EFEMP1), biomarkers (e.g body impedance), clinical phenotypes (e.g, chest pain), diseases (e.g. hypertension), environmental (e.g smoking), and socioeconomic (e.g education, income) factors.

Phenotypic biomarkers (e.g. cholesterol, weight, and glucose) are important to diagnose and treat diseases associated with aging. However, while many biomarkers are co-dependent (e.g. glycohemoglobin and glucose), it is generally unknown how age influences their co-dependence. In the following, we analyzed 50 biomarkers in 27,508 National Health and Nutrition Examination Survey (NHANES) participants (age range: 20 to 80, mean age: 46.3 years old, sexes: 48.9% males, 51.1% females, ethnicities: 46.0% Whites, 27.8% Hispanics, 20.0% non-Hispanic Blacks, 6.1% others) to investigate how the co-dependency structure of common biomarkers evolves with age and whether differences exist between sexes and ethnicities. First, we associated the change in correlations between biomarkers with chronological age. We identified six trends and replicated our top finding (height vs. systolic blood pressure) in participants of the UK Biobank (N=470,895). We found that, on average, correlations tend to decrease with age. Secondly, we examined how biomarkers predict other biomarkers in participants of different age groups. We found 17 (34%) biomarkers whose predictability decreases with age and 5 (10%) biomarkers whose predictability increases with age. A limitation of this study is that it cannot distinguish between biological changes related to aging and generational effects. Our results can be interactively explored here: http://apps.chiragjpgroup.org/Aging_Biomarkers_Co-Dependencies/.

The microbiome is a new frontier for building predictors of human phenotypes. However, machine learning in the microbiome is fraught with issues of reproducibility, driven in large part by the wide range of analytic models and metagenomic data types available. We aimed to build robust metagenomic predictors of host phenotype by comparing prediction performances and biological interpretation across 8 machine learning methods and 4 different types of metagenomic data. Using 1,570 samples from 300 infants, we fit 7,865 models for 6 host phenotypes. We demonstrate the dependence of accuracy on algorithm choice and feature definition in microbiome data and propose a framework for building microbiome-derived indicators of host phenotype. We additionally identify biological features predictive of age, sex, breastfeeding status, historical antibiotic usage, country of origin, and delivery type. Our complete results can be viewed at http://apps.chiragjpgroup.org/ubiome_predictions/., Author summary The human microbiome is hypothesized to influence human phenotype. However, many published host-microbe associations may not be reproducible. A number of reasons could be behind irreproducible results, including a wide array of methods for measuring the microbiome through genetic sequence, annotation pipelines, and analytical models/prediction approaches. Therefore, there is a need to compare different modeling strategies and microbiome data types (i.e. species abundance versus metabolic pathway abundance) to determine how to build robust and reproducible host-microbiome predictions. In this work, we executed a broad comparison of different predictive methods as a function of microbiome data types to effectively predict host characteristics. Our pipeline was able uncover robust microbial associations with phenotype. We additionally recommended considerations for reproducible microbiome-host association pipeline development. We claim our work is a necessary stepping stone in increasing the utility of emerging cohort data and enabling the next generation of efficient microbiome association studies in human health.