There are over 40,000 suicide deaths per year in the United States. Predicting suicide is a priority for the field, but remains a challenge. A 2019 paper in the research journal JAMA Psychiatry noted that most models have a predictive accuracy of less than 1%. But just because it is hard to predict suicide with a model does not mean there is nothing that can be done to know when a single person may be at highest risk. Risk prediction is highly personalized, and just because a model cannot predict it for one person does not mean that you or a family member cannot. Right now, your knowledge of your own or family member’s mental health is likely a better tool to predict risk than any model.