Predicting the probability of death using proteomics

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. Eiriksdottir et al. use a temporal proteomic dataset from over 22,000 Icelandic individuals to identify predictors and predict all-cause mortality. Their findings suggest that the plasma proteome may be of value in general health screening for risk of death.

Automated summary

The study developed predictors for all-cause mortality using large-scale proteomics datasets, indicating that the plasma proteome may be valuable in assessing overall health status and estimating the risk of death.