强迫症病程的预测因素：针对复发事件的逻辑回归与Cox回归分析
Predictors of course in obsessive-compulsive disorder: logistic regression versus Cox regression for recurrent events.
作者信息
Kempe P T, van Oppen P, de Haan E, Twisk J W R, Sluis A, Smit J H, van Dyck R, van Balkom A J L M
机构信息
Department of Psychiatry and Institute for Research in Extramural Medicine, VU University Medical Center, GGZ Buitenamstel, The Netherlands.
出版信息
Acta Psychiatr Scand. 2007 Sep;116(3):201-10. doi: 10.1111/j.1600-0447.2007.00997.x.
OBJECTIVE
Two methods for predicting remissions in obsessive-compulsive disorder (OCD) treatment are evaluated. Y-BOCS measurements of 88 patients with a primary OCD (DSM-III-R) diagnosis were performed over a 16-week treatment period, and during three follow-ups.
METHOD
Remission at any measurement was defined as a Y-BOCS score lower than thirteen combined with a reduction of seven points when compared with baseline. Logistic regression models were compared with a Cox regression for recurrent events model.
RESULTS
Logistic regression yielded different models at different evaluation times. The recurrent events model remained stable when fewer measurements were used. Higher baseline levels of neuroticism and more severe OCD symptoms were associated with a lower chance of remission, early age of onset and more depressive symptoms with a higher chance.
CONCLUSION
Choice of outcome time affects logistic regression prediction models. Recurrent events analysis uses all information on remissions and relapses. Short- and long-term predictors for OCD remission show overlap.
目的
评估两种预测强迫症（OCD）治疗缓解情况的方法。在16周的治疗期间及三次随访期间，对88例原发性强迫症（DSM-III-R）诊断患者进行了耶鲁布朗强迫症量表（Y-BOCS）测量。
方法
任何一次测量时的缓解定义为Y-BOCS评分低于13分，且与基线相比降低7分。将逻辑回归模型与用于复发事件模型的Cox回归进行比较。
结果
逻辑回归在不同评估时间产生不同模型。当使用较少测量值时，复发事件模型保持稳定。神经质的较高基线水平和更严重的强迫症症状与较低的缓解机会相关，发病年龄较早和抑郁症状较多则与较高的缓解机会相关。
结论
结局时间的选择会影响逻辑回归预测模型。复发事件分析使用了关于缓解和复发的所有信息。强迫症缓解的短期和长期预测因素存在重叠。
Zotero 插件