Comparing Data-Driven and Psychological Personality Temperaments in Psychiatry
Author Information
Author(s): Sawalma Abdelrahman S., Sehwail Mahmud A., Dammers Jürgen, Herzallah Mohammad M.
Primary Institution: Palestinian Neuroscience Initiative, Al-Quds University
Hypothesis
This study aims to validate an Arabic version of the tri-dimensional personality questionnaire and compare the clinical utility of data-driven personality components with Cloninger’s psychological temperaments in patients with major depressive disorder.
Conclusion
Data-driven personality components significantly outperformed psychological temperaments in identifying medication-naïve patients with major depressive disorder.
Supporting Evidence
- Data-driven personality components showed very little overlap with Cloninger’s original temperaments.
- Both Cloninger’s temperaments and data-driven components revealed low internal consistency but high test-retest reliability.
- Data-driven components significantly outperformed psychological TPQ temperaments with higher accuracy and recall.
Takeaway
The study found that using data-driven methods to understand personality can help doctors better identify depression in patients compared to traditional methods.
Methodology
The study used independent component analysis (ICA) to analyze the tri-dimensional personality questionnaire (TPQ) and support vector machine (SVM) for classification.
Potential Biases
Potential biases may arise from the exclusion of participants with prior psychotropic drug exposure and other psychiatric disorders.
Limitations
The study's findings may not generalize beyond the specific population of Arabic-speaking individuals in the West Bank.
Participant Demographics
{"age":{"HC":"22.3 ± 9.2","MDD":"28.6 ± 9.7"},"education":{"HC":"14.0 ± 3.6","MDD":"12.7 ± 3.0"},"female_percentage":{"HC":"59.6","MDD":"60.7"}}
Statistical Information
P-Value
<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website