Development and validation of a web-based prediction tool on minor physical anomalies for schizophrenia

Mandibular morphology in schizophrenia patients compared with non-psychiatric controls using digital panoramic radiography: a retrospective cross-sectional study from Istanbul, Türkiye

BACKGROUND

Schizophrenia is a chronic severe mental disorder characterized by impairment in cognition, emotion, perception, and other aspects of behavior. In light of the association of craniofacial dysmorphology with schizophrenia, mandibular morphology may provide clues about the role of neurodevelopment in the pathophysiology of schizophrenia. This retrospective cross-sectional study aimed to compare the mandibular morphology of patients with schizophrenia with controls using digital panoramic radiography (DPR).

METHODS

302 recorded diagnostic panoramic images obtained from 143 schizophrenia patients (98 males, 45 females), and 159 controls (73 males, 86 females), aged 18-45 years, were evaluated. Seven mandibular measurements consisting of ramus height, condylar height, gonial angle, antegonial angle, antegonial notch depth, ramal notch depth and bigonial width were measured from the DPRs in a double-blinded manner. Bivariate comparisons were carried out using the Independent t-test and Mann-Whitney U test. Logistic regression analysis was used for multivariate comparisons.

RESULTS

Linear measurements were higher while angular measurements were lower in schizophrenia patients. Regression analyses indicated that female patients had greater ramus height (OR = 1.243; P = 0.001), condylar height (OR = 1.463; P = 0.048) and bigonial width (OR = 1.082; P < 0.001); male patients had greater ramus heights (OR = 1.216; P = 0.001) and bigonial width (OR = 1.076; P < 0.001) as well as lower antegonial angle (OR = 0.908; P = 0.012) compared to their respective controls.

CONCLUSION

Quantitative differences in mandibular morphology in schizophrenia patients versus controls deserve attention and corroborate with the concept of abnormal neurodevelopment in schizophrenia.

Machine learning for prediction of schizophrenia based on identifying the primary and interaction effects of minor physical anomalies

In the neurodevelopmental model of schizophrenia, minor physical anomalies (MPAs) are considered neurodevelopmental markers of schizophrenia. To date, there has been no research to evaluate the interaction between MPAs. Our study built and used a machine learning model to predict the risk of schizophrenia based on measurements of MPA items and to investigate the potential primary and interaction effects of MPAs. The study included 470 patients with schizophrenia and 354 healthy controls. The models used are classical statistical model, Logistic Regression (LR), and machine leaning models, Decision Tree (DT) and Random Forest (RF). We also plotted two-dimensional scatter diagrams and three-dimensional linear/quadratic discriminant analysis (LDA/QDA) graphs for comparison with the DT dendritic structure. We found that RF had the highest predictive power for schizophrenia (Full-training AUC = 0.97 and 5-fold cross-validation AUC = 0.75). We identified several primary MPAs, such as the mouth region, high palate, furrowed tongue, skull height and mouth width. Quantitative MPA analysis indicated that the higher skull height and the narrower mouth width, the higher the risk of schizophrenia. In the interaction, we further identified that skull height and mouth width, furrowed tongue and skull height, high palate and skull height, and high palate and furrowed tongue, showed significant two-item interactions with schizophrenia. A weak three-item interaction was found between high palate, skull height, and mouth width. In conclusion, we found that the two machine learning methods showed good predictive ability in assessing the risk of schizophrenia using the primary and interaction effects of MPAs.

Living alone is associated with a higher prevalence of psychiatric morbidity in a population-based cross-sectional study

Background

Living alone has been linked to poor mental health, however large-scale epidemiological studies on the association between living alone and psychiatric morbidity including depression and anxiety are lacking. The aim of this study was to investigate this issue in a large Taiwanese cohort.

Methods

In this cross-sectional study, we enrolled 121,601 volunteers from 29 community recruitment stations in Taiwan and divided them into two groups based on whether or not they lived alone. Psychiatric morbidity was defined as a Generalized Anxiety Disorder 2-item score ≥ 3, Patient Health Questionnaire 2-item score ≥ 3, or self-reported depression. Logistic regression was used to explore the associations between living alone and psychiatric morbidity.

Results

The participants who lived alone had a higher prevalence of psychiatric morbidity [odds ratio (OR) = 1.608, 95% confidence interval (CI) = 1.473 to 1.755] after adjusting for potential confounders. In a subgroup analysis, married subjects who lived alone and divorce/separation (OR = 2.013, 95% CI = 1.763 to 2.299) or widowing (OR = 1.750, 95% CI = 1.373 to 2.229) were more likely to have psychiatric morbidity than those who were married and not living alone.

Conclusions

Our findings suggest that living alone is a risk factor for psychiatric morbidity, especially for married subjects who live alone in concordance with divorce, separation, or the death of a spouse.