Photo Illustration by The Daily Beast / Getty
Source: Scientists Found a Way to Predict Your Death by How You Walk
Critics by Nature.com
Predicting all-cause mortality risk is challenging and requires extensive medical data. Recently, large-scale proteomics datasets have proven useful for predicting health-related outcomes. Here, we use measurements of levels of 4,684 plasma proteins in 22,913 Icelanders to develop all-cause mortality predictors both for short- and long-term risk. The participants were 18-101 years old with a mean follow up of 13.7 (sd. 4.7) years. During the study period, 7,061 participants died.
Our proposed predictor outperformed, in survival prediction, a predictor based on conventional mortality risk factors. We could identify the 5% at highest risk in a group of 60-80 years old, where 88% died within ten years and 5% at the lowest risk where only 1% died. Furthermore, the predicted risk of death correlates with measures of frailty in an independent dataset. Our results show that the plasma proteome can be used to assess general health and estimate the risk of death.
The ability to predict when someone will die is not something you would wish upon yourself or your friends. It could, however, prove useful in the delivery of healthcare and biomedical research. It is often possible to give a meaningful prediction of how long individuals with specific diagnoses will live1, but predicting when an individual will die from any cause is altogether a different matter.
Several diseases, lifestyle2,3,4, social and psychological factors5 associate with all-cause mortality. Commonly used risk factors for all-cause mortality are age, sex, traditional cardiovascular risk factors such as systolic blood pressure, cholesterol levels, smoking, and diabetes, cardiovascular disease, cancer, alcohol consumption, body mass index (BMI), and creatinine levels6,7,8. Among other biomarkers of all-cause mortality are brain age estimated from structural magnetic resonance images9, DNA methylation10, and telomere length11.
Recently, circulating metabolic biomarkers have been found to associate with the risk of all-cause mortality. In a study of 44,168 individuals, where 5512 died during follow-up, 14 metabolic biomarkers were found to improve 5 and 10-year all-cause mortality predictions over conventional risk factors8. Another study of 17,345 participants identified 106 metabolic biomarkers that improved short-term all-cause mortality risk prediction over established risk factors7.
In a study of 3523 participants from the Framingham Heart Study, 38 of 85 preselected circulating protein biomarkers associated with all-cause mortality and improved all-cause mortality prediction over cardiovascular risk factors12. Similarly, 56 peptides (31 proteins) correlated with 5-year mortality in a study of 2473 older men. A panel of those peptides improved the predictive value of a commonly used clinical predictor of mortality.
With the advent of new technology such as SOMAmers14 or proximity extension assays15, it is possible to simultaneously measure levels of thousands of proteins efficiently. Several studies using this technology have shown the plasma proteome to be heavily associated with age and life span16,17,18,19,20. A study of 997 participants associated 651 out of 1301 proteins with age, found that a 76-protein proteomic age signature associated with all-cause mortality independent of chronological age, and created a seven-protein mortality predictor18.
In a study of 1025 older adults, 754 of 4265 proteins were associated with age. A proteomic age model using the age-associated proteins predicted mortality better than chronological age19. Another study of 4263 participants measured 2925 proteins to evaluate how circulating protein profile changes over the life span20. Some studies have used large proteomics datasets to predict other health-related factors. A protein-based risk score for cardiovascular outcomes in a high-risk group was developed using 1130 candidate plasma proteins21.
In addition, ~5000 plasma proteins were used to predict health states, behavior, and incident diseases, with performance comparable to traditional risk factors, in 16,894 participants22. These studies underscore the value of using plasma levels of a large number of proteins to search for biomarkers in health and diseases..…To be continued….
Hippisley-Cox, J. & Coupland, C. Development and validation of QMortality risk prediction algorithm to estimate short term risk of death and assess frailty: cohort study. BMJ 358, j4208 (2017).Article PubMed PubMed Central Google Scholar
Flegal, K. M., Kit, B. K., Orpana, H. & Graubard, B. I. Association of all-cause mortality with overweight and obesity using standard body mass index categories: a systematic review and meta-analysis. JAMA 309, 1–82 (2013).Article CAS PubMed PubMed Central Google Scholar
Danaei, G. et al. The preventable causes of death in the United States: comparative risk assessment of dietary, lifestyle, and metabolic risk factors. PLoS Med. 6, e1000058 (2009).Article PubMed PubMed Central Google Scholar
Puterman, E. et al. Predicting mortality from 57 economic, behavioral, social, and psychological factors. Proc. Natl. Acad. Sci. https://doi.org/10.1073/pnas.1918455117 (2020).
Wang, T. J. et al. Multiple biomarkers for the prediction of first major cardiovascular events and death. N. Engl. J. Med. 355, 2631–2639 (2006).Article CAS PubMed Google Scholar
Fischer, K. et al. Biomarker profiling by nuclear magnetic resonance spectroscopy for the prediction of all-cause mortality: an observational study of 17,345 persons. PLoS Med. 11, e1001606 (2014).Article PubMed PubMed Central Google Scholar
Deelen, J. et al. A metabolic profile of all-cause mortality risk identified in an observational study of 44,168 individuals. Nat. Commun. 10, 3346 (2019).Article PubMed PubMed Central CAS Google Scholar
Cole, J. H. et al. Brain age predicts mortality. Mol. Psychiatry 23, 1385–1392 (2018).Article CAS PubMed Google Scholar
Zhang, Y. et al. DNA methylation signatures in peripheral blood strongly predict all-cause mortality. Nat. Commun. 8, 14617 (2017).Article CAS PubMed PubMed Central Google Scholar
Cawthon, R. M., Smith, K. R., O’Brien, E., Sivatchenko, A. & Kerber, R. A. Association between telomere length in blood and mortality in people aged 60 years or older. Lancet 361, 393–395 (2003).Article CAS PubMed Google Scholar
Ho, J. E. et al. Protein biomarkers of cardiovascular disease and mortality in the community. J. Am. Heart Assoc. 7, e008108 (2018).Article CAS PubMed PubMed Central Google Scholar
Orwoll, E. S. et al. High-throughput serum proteomics for the identification of protein biomarkers of mortality in older men. Aging Cell 17, e12717 (2018).Article PubMed Central CAS Google Scholar
Rohloff, J. C. et al. Nucleic acid ligands with protein-like side chains: modified aptamers and their use as diagnostic and therapeutic agents. Mol. Ther. Nucleic Acids 3, e201 (2014).Article CAS PubMed PubMed Central Google Scholar
Assarsson, E. et al. Homogenous 96-Plex PEA immunoassay exhibiting high sensitivity, specificity, and excellent scalability. PLoS ONE 9, e95192 (2014).Article PubMed PubMed Central CAS Google Scholar
Menni, C. et al. Circulating proteomic signatures of chronological age. J. Gerontol. A. Biol. Sci. Med. Sci. 70, 809–816 (2015).Article CAS PubMed Google Scholar
Tanaka, T. et al. Plasma proteomic signature of age in healthy humans. Aging Cell 17, e12799 (2018).Article PubMed PubMed Central CAS Google Scholar
Tanaka, T. et al. Plasma proteomic biomarker signature of age predicts health and life span. eLife 9, e61073 (2020).Article CAS PubMed PubMed Central Google Scholar
Sathyan, S. et al. Plasma proteomic profile of age, health span, and all-cause mortality in older adults. Aging Cell 19, e13250 (2020).CAS PubMed PubMed Central Google Scholar
Lehallier, B. et al. Undulating changes in human plasma proteome profiles across the lifespan. Nat. Med. 25, 1843–1850 (2019).Article CAS PubMed PubMed Central Google Scholar
Ganz, P. et al. Development and validation of a protein-based risk score for cardiovascular outcomes among patients with stable coronary heart disease. JAMA 315, 2532–2541 (2016).Article CAS PubMed Google Scholar
Williams, S. A. et al. Plasma protein patterns as comprehensive indicators of health. Nat. Med. 25, 1851–1857 (2019).Article CAS PubMed PubMed Central Google Scholar
Rafnar, T. et al. The Icelandic Cancer Project—a population-wide approach to studying cancer. Nat. Rev. Cancer 4, 488–492 (2004).Article CAS PubMed Google Scholar
Ivarsdottir, E. V. et al. Sequence variation at ANAPC1 accounts for 24% of the variability in corneal endothelial cell density. Nat. Commun. 10, 1284 (2019).Article PubMed PubMed Central CAS Google Scholar
Kursa, M. B. & Rudnicki, W. R. Feature selection with the Boruta Package. JSS J. Stat. Softw. 36, 1–13 (2010).Google ScholarTibshirani, R. Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. Ser. B Methodol. 58, 267–288 (1996).Google Scholar
Jassal, B. et al. The reactome pathway knowledgebase. Nucleic Acids Res. 48, D498–D503 (2020).CAS PubMed Google ScholarEbaid, D., Crewther, S. G., MacCalman, K., Brown, A. & Crewther, D. P. Cognitive processing speed across the lifespan: beyond the influence of motor speed. Front. Aging Neurosci. 9, 62 (2017).Article PubMed PubMed Central Google Scholar
Reitan, R. M. Validity of the trail making test as an indicator of organic brain damage. Percept. Mot. Skills 8, 271–276 (1958).Article Google Scholar
Wiklund, F. E. et al. Macrophage inhibitory cytokine-1 (MIC-1/GDF15): a new marker of all-cause mortality: Serum MIC-1/GDF15 and mortality risk. Aging Cell 9, 1057–1064 (2010).Article CAS PubMed Google Scholar
Baek, S. J. & Eling, T. Growth differentiation factor 15 (GDF15): a survival protein with therapeutic potential in metabolic diseases. Pharmacol. Ther. 198, 46–58 (2019).Article CAS PubMed PubMed Central Google Scholar
Coll, A. P. et al. GDF15 mediates the effects of metformin on body weight and energy balance. Nature 578, 444–448 (2020).Article CAS PubMed Google Scholar Moon, J. S. et al. Growth differentiation factor 15 protects against the aging-mediated systemic inflammatory response in humans and mice. Aging Cell 19, e13195 (2020).Article CAS PubMed PubMed Central Google Scholar
Lara, J. et al. Towards measurement of the healthy ageing phenotype in lifestyle-based intervention studies. Maturitas 76, 189–199 (2013).Article PubMed Google Scholar Nishiwaki, Y. et al. Association of thoracic kyphosis with subjective poor health, functional activity and blood pressure in the community-dwelling elderly. Environ. Health Prev. Med. 12, 246–250 (2007).Article PubMed PubMed Central Google Scholar
Hynes, R. O. The extracellular matrix: not just pretty fibrils. Science 326, 1216–1219 (2009).Article CAS PubMed PubMed Central Google Scholar Le Roith, D. Insulin-like growth factors. N. Engl. J. Med. 336, 633–640 (1997).Article PubMed Google Scholar
Helgadottir, A. et al. Genetic variability in the absorption of dietary sterols affects the risk of coronary artery disease. Eur. Heart J. 41, 2618–2628 (2020).Article CAS PubMed PubMed Central Google Scholar Brody, E. et al. Life’s simple measures: unlocking the proteome. J. Mol. Biol. 422, 595–606 (2012).Article CAS PubMed Google Scholar
Gold, L. et al. Aptamer-based multiplexed proteomic technology for biomarker discovery. PLoS ONE 5, e15004 (2010).Article CAS PubMed PubMed Central Google Scholar Kim, C. H. et al. Stability and reproducibility of proteomic profiles measured with an aptamer-based platform. Sci. Rep. 8, 8382 (2018).Article PubMed PubMed Central CAS Google Scholar
Candia, J. et al. Assessment of variability in the SOMAscan assay. Sci. Rep. 7, 14248 (2017).Article PubMed PubMed Central CAS Google Scholar The Emerging Risk Factors Collaboration. Major lipids, apolipoproteins, and risk of vascular disease. JAMA 302, 1993–2000 (2009).Article PubMed Central Google Scholar
Pencina, M. J., D’Agostino, R. B., D’Agostino, R. B. & Vasan, R. S. Evaluating the added predictive ability of a new marker: From area under the ROC curve to reclassification and beyond. Stat. Med. 27, 157–172 (2008).Article PubMed Google Scholar
Harrell, F. E., Califf, R. M., Pryor, D. B., Lee, K. L. & Rosati, R. A. Evaluating the yield of medical tests. JAMA 247, 2543–2546 (1982).Article PubMed Google Scholar DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44, 837–845 (1988).Article CAS PubMed Google Scholar
Zou, H. & Hastie, T. Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B Stat. Methodol. 67, 301–320 (2005).Article Google Scholar Chen, T. & Guestrin, C. XGBoost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785–794 (Association for Computing Machinery, 2016). https://doi.org/10.1145/2939672.2939785.
Mi, H. et al. PANTHER version 16: a revised family classification, tree-based classification tool, enhancer regions and extensive API. Nucleic Acids Res. 49, D394–D403 (2021).Article CAS PubMed Google Scholar Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).Google Scholar Robin, X. et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform. 12, 77 (2011).
Marketing Programs To Buy: