The influence of temperament and character profiles on specialty choice and well-being in medical residents

Abstract

Background: Multiple factors influence the decision to enter a career in medicine and choose a specialty. Previous studies have looked at personality differences in medicine but often were unable to describe the heterogeneity that exists within each specialty. Our study used a person-centered approach to characterize the complex relations between the personality profiles of resident physicians and their choice of specialty.

Methods: 169 resident physicians at a large Midwestern US training hospital completed the Temperament and Character Inventory (TCI) and the Satisfaction with Life Scale (SWLS). Clusters of personality profiles were identified without regard to medical specialty, and then the personality clusters were tested for association with their choice of specialty by co-clustering analysis. Life satisfaction was tested for association with personality traits and medical specialty by linear regression and analysis of variance.

Results: We identified five clusters of people with distinct personality profiles, and found that these were associated with particular medical specialties Physicians with an "investigative" personality profile often chose pathology or internal medicine, those with a "commanding" personality often chose general surgery, "rescuers" often chose emergency medicine, the "dependable" often chose pediatrics, and the "compassionate" often chose psychiatry. Life satisfaction scores were not enhanced by personality-specialty congruence, but were related strongly to self-directedness regardless of specialty.

Conclusions: The personality profiles of physicians were strongly associated with their medical specialty choices. Nevertheless, the relationships were complex: physicians with each personality profile went into a variety of medical specialties, and physicians in each medical specialty had variable personality profiles. The plasticity and resilience of physicians were more important for their life satisfaction than was matching personality to the prototype of a particular specialty.

Keywords: Career choice; Character; Medical specialization; Personality; Temperament; Well-being.

Figure 1. Identifying clusters of subjects sharing similar TCI subscale scores.

Clusters 1–5 appear in sequence from top (cluster 1) to bottom (cluster 5). Ward’s clustering method was used and calculated the incremental sum of squares. The similarity measure was the Half square Euclidean distance. The optimal number of 5 clusters was calculated using the Davies–Bouldin validity index.

Figure 2. The match between TCI clusters and physician’s specialties.

The cluster interaction was calculated using Hypergeometric statistics. P-values < 0.05 were reported and color coded (red: low, blue: high), so the red circle indicated the strongest association (i.e., lowest p value) was between cluster 5 and psychiatrists. The size of the circles indicates the number of subjects in the intersection.

Figure 3. Prototypes (centroid, i.e., profile of average values) of the TCI clusters in comparison to those of associated specialties.

The X-axis corresponds to the TCI subscales. Y-axis corresponds to the TCI in its 5 point Likert scale on which 1 indicates definitely false and 5 indicates definitely true. (A) Prototype of cluster 1. The centroid calculated using all subjects in the cluster is color-coded in blue. The centroid calculated from the intersection of subjects in cluster 1 and the specialty of pathology is color-coded in red. The centroid calculated from the intersection of subjects in cluster 1 and internal medicine is color-coded in green. (B) Prototype of cluster 2. The centroid calculated using all subjects in the cluster is color-coded in blue. The centroid calculated from the intersection of subjects in cluster 2 and General Surgery is color-coded in red. (C) Prototype of cluster 3. The centroid calculated using all subjects in the cluster is color-coded in blue. The centroid calculated from the intersection of subjects in cluster 3 and Emergency Medicine is color-coded in red. (D) Prototype of cluster 4. The centroid calculated using all subjects in the cluster is color-coded in blue. The centroid calculated from the intersection of subjects in cluster 4 and Pediatrics is color-coded in red. (E) Prototype of cluster 5. The centroid calculated using all subjects in the cluster is color-coded in blue. The centroid calculated from the intersection of subjects in cluster 5 and Psychiatry is color-coded in red.

Figure 4. Box plots of the distribution of average Satisfaction with Life Scale (SWLS) scores in physicians comprising each of the 5 TCI clusters.

In each box, the central mark is the median, the edges of the box are the 25th and 75th percentiles, the whiskers extend to the most extreme data points not considered outliers, and outliers are plotted individually (Statistical Toolbox, Matlab 2007b). According to ANOVA (Statistical Toolbox, Matlab 2007b), Clusters 2, 4 and 5 have means significantly different than Cluster 1 (p < 0.05). Clusters 2 and 4 have means significantly different than Cluster 3 (p < 0.05). Finally Clusters 2, 4 and 5 have similar means.

Figure 5. Boxplots of the distribution of average Satisfaction with Life Scale scores for physicians in pathology who have various TCI profiles.

Pathologists in cluster 1 (“investigative”) were significantly (p < 0.05) lower than those in cluster 4 (“dependable”).

Figure 6. Pie chart showing the occurrences of specialties (%) in each TCI cluster. Specialties corresponding to TCI cluster (A) 1, (B) 2, (C) 3, (D) 4, and (E) 5.