OBJECTIVE: Studies show partial improvements in some core symptoms of Autism Spectrum Disorders (ASD) in time. However, the predictive factors (e.g. pretreatment IQ, comorbid psychiatric disorders, adaptive, and language skills, etc.) for a better the outcome was not studied with machine learning methods. We aimed to examine the predictors of outcome with machine learning methods, which are novel computational methods including statistical estimation, information theories and mathematical learning automatically discovering useful patterns in large amounts of data. METHOD: The study the group comprised 433 children (mean age: 72.3 ± 45.9 months) with ASD diagnosis. The ASD symptoms were assessed by the Autism Behavior Checklist, Aberrant Behavior Checklist, Clinical Global Impression scales at baseline (T0) and 12th (T1), 24th (T2), and 36th (T3) months. We tested the performance of for machine learning algorithms (Naive Bayes, Generalized Linear Model, Logistic Regression, Decision Tree) on our data, including the 254 items in the baseline forms. Patients with ≤2 CGI points in ASD symptoms at in 36 months were accepted as the group who has "better outcome" as the prediction class. RESULTS: The significant proportion of the cases showed significant improvement in ASD symptoms (39.7% in T1, 60.7% in T2; 77.8% in T3). Our machine learning model in T3 showed that diagnosis group affected the prognosis. In the autism group, older father and mother age; in PDD-NOS group, MR comorbidity, less birth weight and older age at diagnosis have a worse outcome. In Asperger's Disorder age at diagnosis, age at first evaluation and developmental cornerstones has affected prognosis. CONCLUSION: In accordance with other studies we found early age diagnosis, early start rehabilitation, the severity of ASD symptoms at baseline assessment predicted outcome. Also, we found comorbid psychiatric diagnoses are affecting the outcome of ASD symptoms in clinical observation. The machine learning models reveal several others are more significant (e.g. parental age, birth weight, sociodemographic variables, etc.) in terms of prognostic information and also planning treatment of children with ASD.

No abstract

Objective: This study aims to examine the psychopathology, quality of life perception, eating behaviors and self-image of children and adolescents who are diagnosed with obesity; as well as their parents' behaviour, coping skills and the relations between these conditions. Methods: In this study, 30 patients between the ages of 8 -18 who have consulted the University of Akdeniz Pediatric Endocrinology Department and had BMI standard deviation above 2 and had no mental retardation or received no previous psychiatric consultations on the obesity were enrolled. Our control group included 30 healthy children and adolescents who were matching on the same demographic information (gender and age) with the treatment (patient) group, and they had no previous medical or psychiatric illnesses. The Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version was administered to both groups, and the Rosenberg Self Image Scale was used to determine their self-images. The Quality of Life Scale for Children was administered to the children and adolescents as well as to their parents. To determine the methods of child rearing and coping strategies with stress, parents were administered the Family Life and Child Rearing Demeanours Scale and the Coping Strategies Scale. Results: There were no significant sociodemographic differences between the two groups except for parents' educational level and socioeconomic status. As we found no differences on parenting styles and coping strategies, a higher percentage of psychiatric illnesses were detected in our study and the quality of life perception of parents was found lower in the obese group. Self-image scores were not varied between obese children and healthy controls. İt was observed that obese group children's mother have more likley high obesity rates than the mothers in the control group children. Conclusions: As a result of this study, psychiatric disorders were observed more frequently in obese children and adolescents. The perception of quality of life for obese children and adolescents seem alike with control groups' perception. However, the fact that obese children and adolescents' parents claim that their children's quality of life is not equal to other groups shows that obese children and adolescents are less aware of health condition and following problems they have and might possible attain in the future.[Abstract:0106][Addiction]

We aimed to determine the predictive factors for psychiatric problem severity and/or clinical approval 10 years after first assessment between ages 1-4 years. Methods: The children that were assessed with the CBCL and the BITSEA in their 1-4 years of age were included. The follow-up assessments were made by telephone interviews 10 years later by child psychiatry residents. The primary caregivers responded the follow-up questionnaire items, such as social/academic/behavioral functioning and self-esteem and the items regarding the psychiatric approval, diagnosis, and treatment history. Results: The CBCL-Internalizing scores in toddlerhood were found to be significantly inversely correlated with social and behavioral functioning level and self-esteem scores. The paternal and maternal BITSEA-Competence scores were found to be positively correlated with social and academic functioning. The CBCL Withdrawn/Depressed points at first evaluation were determined to be statistically significantly predictive for psychiatric diagnosis. Conclusions:The study revealed that some measures including CBCL and BITSEA completed in toddlerhood significantly indicate the children under risk of psychiatric morbidity in adolescence. Therefore, we conclude that the widespread use of this assessment measures in toddlers and the referral of the group under risk to the psychiatry units for further investigations could be useful preventive interventions.

Bu çalışma, Ondokuz Mayıs Üniversitesi Tıp Fakültesi Klinik Çalışmalar Etik Kurulu tarafından 08.04.2020 tarihinde 2020/55 karar numarası ile onaylanmıştır. Öz Amaç: Kompleks etiyolojisi ve çekirdek semptomlarına etkili bir tedavinin henüz olmaması nedeniyle birçok kültürde OSB'nin oluşum nedenlerine dair farklı görüşler bulunmaktadır.Bu çalışmada ailelerin OSB'nin nedenlerine ait görüşleri, tedavi seçimleri ve beklentilerinin araştırması amaçlanmıştır. Materyal ve Metot: Çalışmaya 2015-2019 yılları arasında Ondokuz Mayıs Üniversitesi Çocuk Psikiyatri kliniğine başvuran ve OSB tanısı olan çocukların aileleri dahil edilmiş olup veriler geriye dönük olarak taranmıştır. Kliniğimize başvuran her hasta için ailelere görüşme öncesinde "Ön Görüşme Formu" doldurtulmuş, bilgileri tam olan hastalar çalışmaya alınmıştır. Ön görüşme formunda çocuğun yaşı, cinsiyeti, daha önce aldığı tedavi, hastalığın ya da bozukluğun neden kaynaklandığı ve tedavi beklentisine dair sorular bulunmaktadır. Klinik global izlem-hastalık şiddeti çocuk psikiyatri uzmanı tarafından doldurulmuştur. Bulgular: Çalışma grubunda 241 çocuk ve bakım vereninin verisi incelenmiştir. Erkek ve kız hastaların klinik özellikleri, aile görüşleri ve çocuk psikiyatri uzmanı tarafından belirlenen hastalık şiddeti karşılaştırıldığında kız hastaların klinik global izlem puanlarının daha yüksek olduğu (p=0.022) ve "Çocuğun kendinden" şıkkının daha yüksek oranda işaretlendiği (p=0.014) gözlenmiştir. İki Adımlı Kümeleme Analizi sonrasında iki küme oluşmuş ve kümeler için en belirleyici özellik "Çocuğa ait nedenler" olmuştur. İki küme arasında "daha önce psikiyatrik muayene", "ilaç tedavisi" ve "yaş" özelliklerinin belirleyici olduğu gözlenmiştir. Sonuç: Ailenin tedavi seçiminde, otizmin oluşum nedenlerine ait görüşleri, bozukluğun süresi ve daha önce çocuğun görmüş olduğu psikiyatrik muayeneler etkili olmaktadır. Bu bulgular OSB ile ilgilenen klinisyenlerin ailelere rehberlik etme ve kararlarına yardımcı olması açısından önem taşımaktadır.