Machine learning algorithms revealed distorted retinal vascular branching in individuals with bipolar disorder.

BACKGROUND: Converging evidence designate vascular vulnerability in bipolar disorder. The predisposition progresses into distortion in time, thus detection of the vascular susceptibility may help reducing morbidity and mortality. It was aimed to assess retinal fundus vasculature in cardiovascular risk-free patients with bipolar disorder. METHODS: Total of 68 individuals (38 patients with bipolar disorder, 30 healthy controls) were enrolled. In order to avoid from degenerative processes, participants were between 18 and 45 years of age, vascular risk factors were eliminated. Microscopic retinal fundus images were processed with machine learning algorithms (multilayer perceptron and support vector machine) and artificial neural network approaches. RESULTS: In comparison to the healthy control group, the bipolar disorder group had lower number of breaking points (P < 0.001), lower number of curved vessel segments (P < 0.001). Total length of smooth vessels was longer (P = 0.040), and total length of curved vessel segments was significantly shorter (P < 0.001) than the control group. Vascular endothelial growth factor levels and gender were the confounders. There were significant correlations between vascular measures and serum lipid levels. LIMITATIONS: Sample size was small and patients were on various medications. CONCLUSIONS: These results indicate distortion in retinal vascular branching in bipolar disorder. Disrupted branching may reflect disturbed prosperity of retinal vascular plexus in patients with bipolar disorder. Alterations in the retinal vessels might be indicators of disruption in cerebral vascular system efficiency and thus neurovascular unit dysfunction in bipolar disorder.

Serum hepcidin / ferroportin levels in bipolar disorder and schizophrenia.

BACKGROUND: Despite several alternatives for cellular iron influx, the only mechanism for cellular iron efflux is ferroportin mediated active transport. In cases of ferroportin dysfunction, iron accumulates in the cell and causes ferroptosis. Hepcidin suppresses ferroportin levels and inflammatory activation increases hepcidin production. Mild inflammation in schizophrenia and bipolar disorder may alter hepcidin and ferroportin. METHODS: The study included a total of 137 patients aged 18-65 years, 57 diagnosed with schizophrenia and 80 with bipolar disorder, according to the DSM-IV diagnostic criteria, and a control group (HC) of 42 healthy individuals. Biochemical analyses, thyroid function tests, hemogram, serum iron level, iron-binding capacity, and ferritin levels were examined. Serum levels of hepcidin and ferroportin were measured with enzyme-linked immunosorbent assay (ELISA) method. RESULTS: A statistically significant difference was determined between the groups in terms of the serum ferroportin levels (F = 15.69, p < 0.001). Post-hoc analyses showed that the schizophrenia group had higher ferroportin levels than in the bipolar group (p < 0.001) and HCs (p < 0.001). Hepcidin levels did not differ between the groups. Chlorpromazine equivalent doses of antipsychotics correlated with ferroportin levels (p = 0.024). CONCLUSION: Ferroportin levels were increased in the schizophrenia group, although iron and hepcidin levels were within normal ranges. Antipsychotics may alter the mechanisms which control ferroportin levels. Further studies are needed to examine the relationships between antipsychotics and iron metabolism for determination of causal relationship.