Roy Arunima, Nikolitch Katerina, McGinn Rachel, Jinah Safiya, Klement William, Kaminsky Zachary A
The Royal's Institute of Mental Health Research, University of Ottawa, Ottawa, ON Canada.
Division of Thoracic Surgery, The Ottawa Research Hospital Research Institute and Ottawa University, Ottawa, ON Canada.
NPJ Digit Med. 2020 May 26;3:78. doi: 10.1038/s41746-020-0287-6. eCollection 2020.
Machine learning analysis of social media data represents a promising way to capture longitudinal environmental influences contributing to individual risk for suicidal thoughts and behaviors. Our objective was to generate an algorithm termed "Suicide Artificial Intelligence Prediction Heuristic (SAIPH)" capable of predicting future risk to suicidal thought by analyzing publicly available Twitter data. We trained a series of neural networks on Twitter data queried against suicide associated psychological constructs including burden, stress, loneliness, hopelessness, insomnia, depression, and anxiety. Using 512,526 tweets from = 283 suicidal ideation (SI) cases and 3,518,494 tweets from 2655 controls, we then trained a random forest model using neural network outputs to predict binary SI status. The model predicted = 830 SI events derived from an independent set of 277 suicidal ideators relative to = 3159 control events in all non-SI individuals with an AUC of 0.88 (95% CI 0.86-0.90). Using an alternative approach, our model generates temporal prediction of risk such that peak occurrences above an individual specific threshold denote a ~7 fold increased risk for SI within the following 10 days (OR = 6.7 ± 1.1, = 9 × 10). We validated our model using regionally obtained Twitter data and observed significant associations of algorithm SI scores with county-wide suicide death rates across 16 days in August and in October, 2019, most significantly in younger individuals. Algorithmic approaches like SAIPH have the potential to identify individual future SI risk and could be easily adapted as clinical decision tools aiding suicide screening and risk monitoring using available technologies.
对社交媒体数据进行机器学习分析是一种很有前景的方法，可用于捕捉对个体自杀念头和行为风险有影响的纵向环境因素。我们的目标是生成一种名为“自杀人工智能预测启发式算法（SAIPH）”的算法，该算法能够通过分析公开可用的推特数据来预测未来自杀念头的风险。我们在针对与自杀相关的心理结构（包括负担、压力、孤独、绝望、失眠、抑郁和焦虑）查询的推特数据上训练了一系列神经网络。我们使用来自283例自杀意念（SI）病例的512,526条推文和来自2655名对照的3,518,494条推文，然后使用神经网络输出训练了一个随机森林模型，以预测二元SI状态。该模型在所有非SI个体中预测了来自277名自杀意念者独立组的830起SI事件，相对于3159起对照事件，曲线下面积（AUC）为0.88（95%置信区间0.86 - 0.90）。使用另一种方法，我们的模型生成风险的时间预测，使得高于个体特定阈值的峰值出现表示在接下来的10天内SI风险增加约7倍（比值比[OR]=6.7±1.1，P = 9×10⁻⁹）。我们使用区域获取的推特数据验证了我们的模型，并观察到算法SI分数与2019年8月和10月16天内全县自杀死亡率之间存在显著关联，在年轻个体中最为显著。像SAIPH这样的算法方法有潜力识别个体未来的SI风险，并且可以很容易地改编为临床决策工具，利用现有技术辅助自杀筛查和风险监测。
