Department of Psychiatry, University of Pittsburgh, Pittsburgh, PA, USA.
Graduate School of Applied and Professional Psychology, Rutgers University, New Brunswick, NJ, USA.
J Child Psychol Psychiatry. 2021 Feb;62(2):223-231. doi: 10.1111/jcpp.13269. Epub 2020 May 25.
Research has yielded factors considered critical to risk for borderline personality disorder (BPD). Yet, these factors overlap and are relevant to other disorders, like depression and conduct disorder (CD). Regularized regression, a machine learning approach, was developed to allow identification of the most important variables in large datasets with correlated predictors. We aimed to identify critical predictors of BPD symptoms in late adolescence (ages 16-18) and determine the specificity of factors to BPD versus disorders with putatively similar etiology.
We used a prospective longitudinal dataset (n = 2,450) of adolescent girls assessed on a range of clinical, psychosocial, and demographic factors, highlighted by previous research on BPD. Predictors were grouped by developmental periods: late childhood (8-10) and early (11-13) and mid-adolescence (14-15), yielding 128 variables from 41 constructs. The same variables were used in models predicting depression and CD symptoms.
The best-fitting model for BPD symptoms included 19 predictors and explained 33.2% of the variance. Five constructs - depressive and anxiety symptoms, self-control, harsh punishment, and poor social and school functioning - accounted for most of the variance explained. BPD was differentiated from CD by greater problems with mood and anxiety in BPD and differences in parenting risk factors. Whereas the biggest parenting risk for BPD was a punitive style of parenting, CD was predicted by both punitive and disengaged styles. BPD was differentiated from MDD by greater social problems and poor behavioral control in BPD.
The best predictors of BPD symptoms in adolescence are features suggesting complex comorbidity, affective activation, and problems with self-control. Though some risk factors were non-specific (e.g., inattention), the disorders were distinguished in clinically significant ways.
研究已经产生了被认为是边缘型人格障碍（BPD）风险关键的因素。然而，这些因素与其他疾病（如抑郁症和品行障碍（CD））重叠且相关。正则化回归是一种机器学习方法，旨在识别大数据集中与相关预测因素相关的最重要变量。我们旨在确定青春期后期（16-18 岁）BPD 症状的关键预测因素，并确定这些因素对 BPD 与具有假定相似病因的疾病的特异性。
我们使用了一个前瞻性纵向数据集（n=2450），对一系列临床、心理社会和人口统计学因素进行了评估，这些因素突出了以前关于 BPD 的研究。预测因素按发育阶段分组：晚期儿童（8-10 岁）和早期（11-13 岁）和中期青少年（14-15 岁），从 41 个结构中产生 128 个变量。相同的变量用于预测抑郁和 CD 症状的模型。
BPD 症状的最佳拟合模型包括 19 个预测因子，解释了 33.2%的方差。五个结构 - 抑郁和焦虑症状、自我控制、严厉惩罚以及社交和学校功能不佳 - 解释了大部分方差。BPD 与 CD 的区别在于 BPD 中情绪和焦虑问题更多，而教养风险因素不同。BPD 的最大教养风险因素是惩罚性的教养方式，而 CD 则由惩罚性和冷漠性的教养方式共同预测。BPD 与 MDD 的区别在于 BPD 中社会问题更多，行为控制能力较差。
青春期 BPD 症状的最佳预测因素是提示复杂共病、情感激活和自我控制问题的特征。尽管一些风险因素不具有特异性（例如，注意力不集中），但这些疾病在临床上有明显的区别。
