MRI radiomics based machine learning model of the periaqueductal gray matter in migraine patients.

Background and purpose:

The aim of the study was to investigate the question: Can MRI radiomics analysis of the periaqueductal gray region elucidate the pathophysiological mechanisms underlying various migraine subtypes, and can a machine learning model using these radiomics features accurately differentiate between migraine patients and healthy individuals, as well as between migraine subtypes, including atypical cases with overlapping symptoms?

The study analyzed initial MRI images of individuals taken after their first migraine diagnosis, and additional MRI scans were acquired from healthy subjects. Radiomics modeling was applied to analyze all the MRI images in the periaqueductal gray region. The dataset was randomized, and oversampling was used if there was class imbalance between groups. The optimal algorithm-based feature selection method was employed to select the most important 5-10 features to differentiate between the two groups. The classification performance of AI algorithms was evaluated using receiver operating characteristic analysis to calculate the area under the curve, classification accuracy, sensitivity, and specificity values. Participants were required to have a confirmed diagnosis of either episodic migraine, probable migraine, or chronic migraine. Patients with aura, those who used migraine-preventive medication within the past six months, or had chronic illnesses, psychiatric disorders, cerebrovascular conditions, neoplastic diseases, or other headache types were excluded from the study. Additionally, 102 healthy subjects who met the inclusion and exclusion criteria were included. 

The algorithm-based information gain method for feature reduction had the best performance among all methods, with the first-order, gray-level size zone matrix, and gray-level co-occurrence matrix classes being the dominant feature classes. The machine learning model correctly classified 82.4% of migraine patients from healthy subjects. Within the migraine group, 74.1% of the episodic migraine-probable migraine patients and 90.5% of the chronic migraine patients were accurately classified. No significant difference was found between probable migraine and episodic migraine patients in terms of the periaqueductal gray region radiomics features. The kNN algorithm showed the best performance for classifying episodic migraine-probable migraine subtypes, while the Random Forest algorithm demonstrated the best performance for classifying the migraine group and chronic migraine subtype.

A radiomics-based machine learning model, utilizing standard MR images obtained during the diagnosis and follow-up of migraine patients, shows promise not only in aiding migraine diagnosis and classification for clinical approach, but also in understanding the neurological mechanisms underlying migraines. 

An atypical case of corticobasal syndrome with psychotic depression and delusional jealousy.

Corticobasal syndrome (CBS) is one of the Parkinson-plus disorders. While initially defined as a movement disorder rather than cognition, it is now known that CBS is related to various psychiatric symptoms. We describe a patient clinically diagnosed with CBS whose initial presentation was psychiatric and rather atypical. His clinical picture included psychotic depression and delusional jealousy. Misdiagnosing these syndromes may delay the initiation of the treatment and worsen the patients' condition, as well as increase the burden of the caretakers. Finally, COVID-19-related changes in the organization of health services complicated the diagnosis and follow-up processes of this patient.

Serum vitamin D status does not correlate with the severity of obstructive sleep apnea in male adults: A controlled study design with minimized factors influencing serum vitamin D levels.

Observational studies performed in homogeneous groups to objectively investigate the cause and effect relationship between vitamin D deficiency and sleep disorders are scarce. In this study, it was aimed to analyze the relationship between the severity of OSAS and vitamin-D levels among the participants whose features affecting serum vit-D levels were minimised. Serum 25-OH vitamin-D levels in 121 OSAS Male patients diagnosed by polysomnography without any systemic disease or vitamin-D supplement that may effect the vitamin-D metabolism were measured. The study was conducted in winter (latitude: 41°). Anthropometric measures and biochemical tests were also performed. The distribution of vitamin-D levels was determined as severe deficiency, deficiency, insufficiency and sufficiency. Apnea-hypopne index (AHI) < 5 was considered as a control group. Patients were categorized into four groups according to AHI as control, mild, moderate and severe. The groups were similar in terms of age, BMI, lipid profile, serum calcium, anthropometric measures and smoking. There was no significant difference in the distribution of vitamin-D levels between the patient and control groups and also within OSAS subgroups (p = 0.57, p = 0.86, respectively). Odds ratio to have OSAS in patients with vitamin-D deficiency was found as 0.745 (95 %CI: 0.33-1.7). Multinominal regression analysis showed no significant relationship between the OSAS severity and the extent of vitamin-D status. Correlation analysis showed no significant relationship between vitamin-D and AHI (r = 0.017, p = 0.877). Vitamin-D status does not alter the severity of OSAS. Vitamin-D deficiency might be the result of lifestyle changes due to OSAS rather than a cause.

Different VDR, VDBP genotypes and vitamin D levels may effect obstructive sleep apnea syndrome.

Obstructive sleep apnea syndrome (OSAS) is a highly prevalent disorder which results in markedly reduced (hypopnea) or absent (apnea) airflow at the nose/mouth. Since vitamin D deficiency has found in an association with some disorders it is thought to be related with OSAS progression. The aim of this study is to investigate the association between VDR, VDBP mutations, vitamin D level and some environmental risk factors with OSAS. Fifty individuals who were diagnosed as OSAS were selected as patients, 50 healthy volunteers without any disease were selected as controls. FokI (rs2228570) and BsmI (rs1544410) mutations in VDR; rs4588 and rs7041 mutations in VDBP were investigated with quantitative real-time polymerase chain reaction (qPCR). Other risk factors were also investigated. Results were evaluated statistically. Statistically significant differences were observed according to the baseline characteristics between the groups, When groups were compared with each other, CA genotype in rs4588, CC genotype in rs2228570 and AA genotype in rs1544410 mutations were found statistically significant in patients whereas TC genotype in rs2228570 and GA genotype in rs1544410 mutations were found statistically significant in controls. When the relation between risk factors and genotypes were investigated, statistically significant associations were detected for body mass index (BMI), waist circumference, Apnea-Hypopnea Index (AHI), excessive daytime sleepiness (EDS), vitamin D and triglyceride levels. VDR and VDBP mutations were found highly related with OSAS. Possible tracking of these mutations and risk factors may help to understand the metabolism as well as the progression of the disease.