Journal of Clinical Medicine Research, ISSN 1918-3003 print, 1918-3011 online, Open Access
Article copyright, the authors; Journal compilation copyright, J Clin Med Res and Elmer Press Inc
Journal website https://www.jocmr.org

Short Communication

Volume 16, Number 5, May 2024, pages 251-255

Predicting Dropout From Cognitive Behavioral Therapy for Panic Disorder Using Machine Learning Algorithms

Figures

Figure 1.
Figure 1. Process flow diagram for predictive models. LightGBM: light gradient boosting machine; SMOTE: synthetic minority oversampling technique.
Figure 2.
Figure 2. The predictive performance of machine learning models. LightGBM: light gradient boosting machine.
Figure 3.
Figure 3. The feature importance of machine learning models. LightGBM: light gradient boosting machine; NEO-FFI: NEO Five Factor Index; PD: panic disorder.

Table

Table 1. Demographics and Baseline Characteristics
 
CharacteristicsCompleter (n = 189)Dropout (n = 19)P
Values are presented as mean and standard deviation (SD). NEO-FFI: NEO Five Factor Index; PDSS: Panic Disorder Severity Scale; SCL-90-R: Symptom Checklist-90 Revised.
Sex (% female)67.263.6> 0.05
Mean age36.3 (10.9)34.3 (12.1)> 0.05
Onset29.1 (10.2)29.1 (11.8)> 0.05
NEO-FFI
  Neuroticism26.7 (9.0)27.5 (7.1)> 0.05
  Extraversion25.9 (8.1)27.0 (8.0)> 0.05
  Openness28.3 (6.1)27.9 (7.4)> 0.05
  Agreeableness32.7 (6.8)32.0 (6.2)> 0.05
  Conscientiousness27.4 (7.7)27.8 (8.1)> 0.05
PDSS13.1 (4.8)12.7 (5.2)> 0.05
SCL-90-R depression subscale1.14 (0.8)1.15 (1.0)> 0.05