In the Original Investigation titled “Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data From Denmark,”¹ published online October 23, 2019, there were errors in the Abstract, Statistical Analysis, and Results. In the Abstract, the following sentence should have been removed: “For example, stress disorders among unmarried men older than 30 years were important factors for suicide risk in the presence of depression (risk, 0.54).”

In the second paragraph of the Statistical Analysis, the number of predictor variables given as 2554 should have been 2564. In the first and second paragraphs of the Random Forest section of the Results, predictors enumerated as “Seventeen” and “Nineteen” should have been “Eighteen” and “Twenty-one,” respectively.

In the second paragraph of the Results in CART Remodeling, the first 2 sentences were given as “Among men, the highest risk for suicide was found among those younger than 30 years who were diagnosed with schizophrenia in the past 2 years but without recorded prescriptions for antidepressants, antipsychotics, medications for addictions (eg, methadone), or hypnotics or sedatives (n = 26; risk, 0.58). Similarly, unmarried men older than 30 years who had been diagnosed with a stress disorder in the prior 4 years but did not have a recorded prescription for these medications had a risk of 0.54 (n = 37).” The sentences should have appeared as “Among men, the highest risk for suicide was found among those not being treated by pharmacotherapy (eg, antidepressants, antipsychotics, or anxiolytics) and with a prior suicide attempt in the prior 4 years, and being in the second income quartile (n = 18; risk, 1.0). Similarly, men who received a prior diagnosis of poisoning by adverse effects or underdosing of drugs but did not have a coded prescription for antidepressants, antipsychotics, medications for addictions (eg, methadone), or hypnotics/sedatives in the prior 4 years had a risk of 0.42 (n = 251).” This article was corrected online.

在原反倾销调查名为“性别特异性自杀危险性预测使用机器学习和单一付款人保健注册表数据来自丹麦，” ¹网上公布2019年10月23日，有在摘要，统计分析和结果错误。在摘要中，应删除以下句子：“例如，在存在抑郁症的情况下，年龄超过30岁的未婚男性中的压力障碍是自杀风险的重要因素（风险，0.54）。”

在统计分析的第二段中，预测变量的数量应为2554，应为2564。在结果的“随机森林”部分的第一段和第二段中，应将枚举的预测变量分别为“十七”和“十九”。分别为“十八”和“二十一”。

在CART重塑结果的第二段中，给出的前两个句子是：“在过去的2年中，被诊断为精神分裂症的30岁以下的年轻人中，自杀风险最高，但没有记录处方抗抑郁药，抗精神病药，成瘾药物（例如美沙酮）或催眠药或镇静药（n = 26；风险为0.58）。同样，在过去的4年中被诊断患有压力障碍但没有这些药物处方的30岁以上未婚男性的风险为0.54（n = 37）。” 该句子应为“在男性中，未接受药物治疗（例如抗抑郁药，抗精神病药或抗焦虑药）且在过去4年中曾尝试自杀的人中，自杀风险最高，并处于第二个收入四分位数（n = 18；风险为1.0）。同样，先前因不良反应或药物剂量不足而被诊断为中毒，但在过去4年中没有抗抑郁药，抗精神病药，成瘾药物（例如美沙酮）或催眠药/镇静剂的编码处方的男性有风险为0.42（n = 251）。” 本文已在线更正。