Bowen Daniel A, Mercer Kollar Laura M, Wu Daniel T, Fraser David A, Flood Charles E, Moore Jasmine C, Mays Elizabeth W, Sumner Steven A
a Division of Violence Prevention, National Center For Injury Prevention and Control , U.S. Centers for Disease Control and Prevention (CDC) , Atlanta , GA , USA.
b Grady Health System , Atlanta , GA , USA.
Int J Inj Contr Saf Promot. 2018 Dec;25(4):443-448. doi: 10.1080/17457300.2018.1467461. Epub 2018 May 24.
Identifying geographic areas and time periods of increased violence is of considerable importance in prevention planning. This study compared the performance of multiple data sources to prospectively forecast areas of increased interpersonal violence. We used 2011-2014 data from a large metropolitan county on interpersonal violence (homicide, assault, rape and robbery) and forecasted violence at the level of census block-groups and over a one-month moving time window. Inputs to a Random Forest model included historical crime records from the police department, demographic data from the US Census Bureau, and administrative data on licensed businesses. Among 279 block groups, a model utilizing all data sources was found to prospectively improve the identification of the top 5% most violent block-group months (positive predictive value = 52.1%; negative predictive value = 97.5%; sensitivity = 43.4%; specificity = 98.2%). Predictive modelling with simple inputs can help communities more efficiently focus violence prevention resources geographically.
确定暴力事件增加的地理区域和时间段对于预防规划至关重要。本研究比较了多个数据源的性能，以期前瞻性地预测人际暴力增加的区域。我们使用了一个大城市县2011 - 2014年关于人际暴力（杀人、袭击、强奸和抢劫）的数据，并在普查街区组层面以及一个月的移动时间窗口内预测暴力事件。随机森林模型的输入包括警察局的历史犯罪记录、美国人口普查局的人口统计数据以及持牌企业的行政数据。在279个街区组中，发现一个利用所有数据源的模型能够前瞻性地改进对最暴力街区组月份前5%的识别（阳性预测值 = 52.1%；阴性预测值 = 97.5%；灵敏度 = 43.4%；特异性 = 98.2%）。使用简单输入的预测建模可以帮助社区更有效地在地理上集中暴力预防资源。
