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.

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

In support of the neurodevelopmental model of schizophrenia, minor physical anomalies (MPAs) have been suggested as biomarkers and potential pathophysiological significance for schizophrenia. However, an integrated, clinically useful tool that used qualitative and quantitative MPAs to visualize and predict schizophrenia risk while characterizing the degree of importance of MPA items was lacking. We recruited a training set and a validation set, including 463 schizophrenia patients and 281 healthy controls to conduct logistic regression and the least absolute shrinkage and selection operator (Lasso) regression to select the best parameters of MPAs and constructed nomograms. Two nomograms were built to show the weights of these predictors. In the logistic regression model, 11 out of a total of 68 parameters were identified as the best MPA items for distinguishing between patients with schizophrenia and controls, including hair whorls, epicanthus, adherent ear lobes, high palate, furrowed tongue, hyperconvex fingernails, a large gap between first and second toes, skull height, nasal width, mouth width, and palate width. The Lasso regression model included the same variables of the logistic regression model, except for nasal width, and further included two items (interpupillary distance and soft ears) to assess the risk of schizophrenia. The results of the validation dataset verified the efficacy of the nomograms with the area under the curve 0.84 and 0.85 in the logistic regression model and lasso regression model, respectively. This study provides an easy-to-use tool based on validated risk models of schizophrenia and reflects a divergence in development between schizophrenia patients and healthy controls ( https://www.szprediction.net/ ).

Neurodevelopment regulators miR-137 and miR-34 family as biomarkers for early and adult onset schizophrenia.

Early-onset schizophrenia (EOS) may have stronger familial aggregation and a more severe outcome than adult-onset schizophrenia (AOS). MicroRNA (miRNA) takes on dual roles as a genetic and epigenetic modulator, which may mediate the influence of genetic risk. Neurological soft signs (NSS) are neurological abnormalities that may be intermediate phenotypes or endophenotypes for schizophrenia. Our previous study found poorer performance on NSS tests from patients with EOS and their unaffected first-degree relatives. Thus, we aimed to identify a set of aberrant neurodevelopmental-related miRNAs that could serve as potential biomarkers for EOS or schizophrenia with NSS. This study included 215 schizophrenia patients (104 EOS and 111 AOS), 72 unaffected first-degree relatives, 31 patients with bipolar disorder, and 100 healthy controls. Differential expression analysis revealed that miR-137, miR-34b, and miR-34c were significantly up-regulated in patients with schizophrenia and their unaffected first-degree relatives compared to healthy controls. Receiver operating characteristic (ROC) analysis showed that the miR-137 expression signature could be used to discriminate between patients with EOS and healthy controls (AUC = 0.911). Additionally, miR-34b had the highest ability to discriminate between EOS and AOS (AUC = 0.810), which may indicate different aetiological pathways to disease onset. Moreover, miR-137 dysregulation was correlated with almost all NSS subscales (i.e., sensory integration, motor sequencing, etc.) and, when EOS patients with NSS, miR-137 expression discriminated these patients from healthy controls to a greater extent (AUC = 0.957). These findings support the potential for neurodevelopmental-related miRNAs to be used as indicators of vulnerability to EOS.

Alterations of plasma cytokine biomarkers for identifying age at onset of schizophrenia with neurological soft signs.

Several studies have been suggested that immunity plays a part in neurodevelopment and schizophrenia pathogenesis. Early age of onset in schizophrenia is associated with genetic factors which affect neurodevelopment. This study aims to identify immune abnormalities associated with neurodevelopmental impairments in early-onset schizophrenia (EOS) and adult-onset schizophrenia (AOS) patients. We determined the plasma levels of six cytokines (IL-1ß, IL-4, IL-6, IL-10, IL-12 and TNF-α) in schizophrenia patients and healthy controls. Measurements included neurological soft signs (NSS) to distinguish and subgroup those with neurodevelopmental impairments. The study included 210 schizophrenia patients, which were divided into 84 EOS and 126 AOS patients, as well as 122 healthy controls. We observed significant differences in levels of IL-4, IL-6 and IL-10 between EOS and AOS patients. The results demonstrated the area under ROC curve (AUC) of the IL-4 in EOS and healthy controls was 0.81. Moreover, these results indicated that AUC of the IL-4 and the combination of IL-4, IL-6 and IL-12 in EOS with NSS and healthy controls were 0.91 and 0.95. These cytokines are altered in EOS and schizophrenia patients with neurodevelopmental impairments and demonstrated good classification abilities. These findings manifested that both pro- and anti-inflammatory cytokines are contributed to the clinical and pathophysiological features of schizophrenia. Future works are expected to explore potential genetic effectors and predictors as well as therapeutic directions in personalized medicine for early-onset schizophrenia.

Risk Model Assessment in Early-Onset and Adult-Onset Schizophrenia Using Neurological Soft Signs.

Age at onset is one of the most important clinical features of schizophrenia that could indicate greater genetic loadings. Neurological soft signs (NSS) are considered as a potential endophenotype for schizophrenia. However, the association between NSS and different age-onset schizophrenia still remains unclear. We aimed to compare risk model in patients with early-onset schizophrenia (EOS) and adult-onset schizophrenia (AOS) with NSS. This study included 262 schizophrenia patients, 177 unaffected first-degree relatives and 243 healthy controls. We estimated the discriminant abilities of NSS models for early-onset schizophrenia (onset age < 20) and adult-onset schizophrenia (onset age ≥ 20) using three data mining methods: artificial neural networks (ANN), decision trees (DT) and logistic regression (LR). We then assessed the magnitude of NSS performance in EOS and AOS families. For the four NSS subscales, the NSS performance were greater in EOS and AOS families compared with healthy individuals. More interestingly, there were significant differences found between patients' families and control group in the four subscales of NSS. These findings support the potential for neurodevelopmental markers to be used as schizophrenia vulnerability indicators. The NSS models had higher discriminant abilities for EOS than for AOS. NSS were more accurate in distinguishing EOS patients from healthy controls compared to AOS patients. Our results support the neurodevelopmental hypothesis that EOS has poorer performance of NSS than AOS. Hence, poorer NSS performance may be imply trait-related NSS feature in EOS.

Sleep apnea is associated with an increased risk of mood disorders: a population-based cohort study.

PURPOSE: The symptoms of sleep apnea, such as sleep fragmentation and oxygen desaturation, might be risk factors for subsequent mood disorder (MD), but associations between sleep apnea and MD remain unclear. This nationwide population-based study thus aimed to identify the risk of MD in patients with vs. without sleep apnea. METHODS: This cohort study used data from the National Health Insurance database. In total, 5415 patients diagnosed with sleep apnea between 2000 and 2010 were evaluated, and 27,075 matched non-sleep apnea enrollees were included as a comparison cohort. All subjects were followed until 2011. The Cox proportional hazard ratio (HR) was used to investigate the relationship between MD and sleep apnea while controlling covariates and comorbidities of sleep apnea. RESULTS: Of 5415, 154 patients with sleep apnea (2.84 %) were diagnosed with MD during the follow-up period in comparison with 306 of 27,075 individuals (1.13 %) without antecedent sleep apnea. After adjusting for the selected factors and comorbidities, we found that patients with sleep apnea were from 1.82- to 2.07-fold greater risk of MD than the comparisons. Of the three subcategories of MD (major depressive disorder, bipolar disorder, and unspecified MD), sleep apnea had the highest predisposing risk with respect to major depressive disorder (adjusted HR from 1.82 to 2.07) and bipolar disorder (adjusted HR from 2.15 to 3.24). CONCLUSIONS: There is a greater likelihood of MD manifesting in patients with a history of sleep apnea. Health professionals are thus advised to carefully monitor the psychological impacts of sleep apnea.

Improving risk assessment and familial aggregation of age at onset in schizophrenia using minor physical anomalies and craniofacial measures.

Age at onset is the most important feature of schizophrenia that could indicate its origin. Minor physical anomalies (MPAs) characterize potential marker indices of disturbances in early neurodevelopment. However, the association between MPAs and age at onset of schizophrenia is still unclear. We aimed to compare risk assessment and familial aggregation in patients with early-onset schizophrenia (EOS) and adult-onset schizophrenia (AOS) with MPAs and craniofacial measures.We estimated the risk assessment of MPAs among patients with EOS (n = 68), patients with AOS (n = 183), nonpsychotic relatives (n = 147), and healthy controls (n = 241) using 3 data-mining algorithms. In addition, we assessed the magnitude of familial aggregation of MPAs with respect to the age at onset of schizophrenia.The performance of EOS was superior to that of AOS, with discrimination accuracies of 89% and 76%, respectively. Combined MPA scores as the risk assessment were significantly higher in all schizophrenia subgroups and the nonpsychotic relatives of EOS patients than in the healthy controls. The recurrence risk ratio for familial aggregation of the MPA scores of EOS families (odds ratio 9.27) was substantially higher than that of AOS families (odds ratio 2.47).The results highlight that EOS improves risk assessment and has a severe magnitude of familial aggregation of MPAs. These findings indicate that EOS might result from a stronger genetic susceptibility to neurodevelopmental deficits.

Effect of nortriptyline on Ca²âº handling in SIRC rabbit corneal epithelial cells.

To explore the effect of nortriptyline, a tricyclic antidepressant, on cytosolic free Ca²âº concentrations ([Ca²âº]i) in corneal epithelial cells, [Ca²âº]i levels in suspended SIRC rabbit corneal epithelial cells were measured by using fura-2 as a Ca²âº-sensitive fluorescent dye. Nortriptyline at concentrations between 20-200 microM increased [Ca²âº]i in a concentration-dependent manner. The Ca²âº signal was reduced partly by removing extracellular Ca²âº. Nortriptyline-induced Ca²âº influx was inhibited by the store-operated Ca²âº channel blockers econazole and SK&F96365, the phospholipase A2 inhibitor aristolochic acid, and alteration of activity of protein kinase C. In Ca²âº-free medium, 200 microM nortriptyline pretreatment greatly inhibited the rise of [Ca²âº]i induced by the endoplasmic reticulum Ca²âº pump inhibitor thapsigargin. Conversely, pretreatment with thapsigargin or 2,5-di-tert-butylhydroquinone (BHQ; another endoplasmic reticulum Ca²âº pump inhibitor) nearly abolished nortriptyline-induced [Ca²âº]i rise. Inhibition of phospholipase C with U73122 decreased nortriptyline-induced [Ca²âº]i rise by 75%. Taken together, nortriptyline induced [Ca²âº]i rises in SIRC cells by causing phospholipase C-dependent Ca²âº release from the endoplasmic reticulum and Ca²âº influx via store-operated Ca²âº channels.