In a three-wave 6 yrs longitudinal study we investigated if the expansion of lateral ventricle (LV) volumes (regarded as a proxy for brain tissue loss) predicts third wave performance on a test of ...response inhibition (RI).
Trajectories of left and right lateral ventricle volumes across the three waves were quantified using the longitudinal stream in Freesurfer. All participants (N = 74;48 females;mean age 66.0 yrs at the third wave) performed the Color-Word Interference Test (CWIT). Response time on the third condition of CWIT, divided into fast, medium and slow, was used as outcome measure in a machine learning framework. Initially, we performed a linear mixed-effect (LME) analysis to describe subject-specific trajectories of the left and right LV volumes (LVV). These features were input to a multinomial logistic regression classification procedure, predicting individual belongings to one of the three RI classes. To obtain results that might generalize, we evaluated the significance of a k-fold cross-validated f1-score with a permutation test, providing a p-value that approximates the probability that the score would be obtained by chance. We also calculated a corresponding confusion matrix.
The LME-model showed an annual ∼ 3.0% LVV increase. Evaluation of a cross-validated score using 500 permutations gave an f1-score of 0.462 that was above chance level (p = 0.014). 56% of the fast performers were successfully classified. All these were females, and typically older than 65 yrs at inclusion. For the true slow performers, those being correctly classified had higher LVVs than those being misclassified, and their ages at inclusion were also higher.
Major contributions were: (i) a longitudinal design, (ii) advanced brain imaging and segmentation procedures with longitudinal data analysis, and (iii) a data driven machine learning approach including cross-validation and permutation testing to predict behaviour, solely from the individual's brain "signatures" (LVV trajectories).
The concept of Mild Cognitive Impairment (MCI) is used to describe the early stages of Alzheimer's disease (AD), and identification and treatment before further decline is an important clinical task. ...We selected longitudinal data from the ADNI database to investigate how well normal function (HC, n= 134) vs. conversion to MCI (cMCI, n= 134) and stable MCI (sMCI, n=333) vs. conversion to AD (cAD, n= 333) could be predicted from cognitive tests, and whether the predictions improve by adding information from magnetic resonance imaging (MRI) examinations. Features representing trajectories of change in the selected cognitive and MRI measures were derived from mixed effects models and used to train ensemble machine learning models to classify the pairs of subgroups based on a subset of the data set. Evaluation in an independent test set showed that the predictions for HC vs. cMCI improved substantially when MRI features were added, with an increase in Formula: see text-score from 60 to 77%. The Formula: see text-scores for sMCI vs. cAD were 77% without and 78% with inclusion of MRI features. The results are in-line with findings showing that cognitive changes tend to manifest themselves several years after the Alzheimer's disease is well-established in the brain.
Loss of autonomy in day-to-day functioning is one of the feared outcomes of Alzheimer's disease (AD), and relatives may have been worried by subtle behavioral changes in ordinary life situations long ...before these changes are given medical attention. In the present study, we ask if such subtle changes should be given weight as an early predictor of a future AD diagnosis.
Longitudinal data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to define a group of adults with a mild cognitive impairment (MCI) diagnosis remaining stable across several visits (sMCI, n=360; 55-91 years at baseline), and a group of adults who over time converted from having an MCI diagnosis to an AD diagnosis (cAD, n=320; 55-88 years at baseline). Eleven features were used as input in a Random Forest (RF) binary classifier (sMCI vs. cAD) model. This model was tested on an unseen holdout part of the dataset, and further explored by three different permutation-driven importance estimates and a comprehensive post hoc machine learning exploration.
The results consistently showed that measures of daily life functioning, verbal memory function, and a volume measure of hippocampus were the most important predictors of conversion from an MCI to an AD diagnosis. Results from the RF classification model showed a prediction accuracy of around 70% in the test set. Importantly, the post hoc analyses showed that even subtle changes in everyday functioning noticed by a close informant put MCI patients at increased risk for being on a path toward the major cognitive impairment of an AD diagnosis.
The results showed that even subtle changes in everyday functioning should be noticed when reported by relatives in a clinical evaluation of patients with MCI. Information of these changes should also be included in future longitudinal studies to investigate different pathways from normal cognitive aging to the cognitive decline characterizing different stages of AD and other neurodegenerative disorders.
Patients with Mild Cognitive Impairment (MCI) have an increased risk of Alzheimer's disease (AD). Early identification of underlying neurodegenerative processes is essential to provide treatment ...before the disease is well established in the brain. Here we used longitudinal data from the ADNI database to investigate prediction of a trajectory towards AD in a group of patients defined as MCI at a baseline examination. One group remained stable over time (sMCI, n = 357) and one converted to AD (cAD, n = 321). By running two independent classification methods within a machine learning framework, with cognitive function, hippocampal volume and genetic APOE status as features, we obtained a cross-validation classification accuracy of about 70%. This level of accuracy was confirmed across different classification methods and validation procedures. Moreover, the sets of misclassified subjects had a large overlap between the two models. Impaired memory function was consistently found to be one of the core symptoms of MCI patients on a trajectory towards AD. The prediction above chance level shown in the present study should inspire further work to develop tools that can aid clinicians in making prognostic decisions.
Objectives Adolescents spend increasingly more time on electronic devices, and sleep deficiency rising in adolescents constitutes a major public health concern. The aim of the present study was to ...investigate daytime screen use and use of electronic devices before bedtime in relation to sleep. Design A large cross-sectional population-based survey study from 2012, the youth@hordaland study, in Hordaland County in Norway. Setting Cross-sectional general community-based study. Participants 9846 adolescents from three age cohorts aged 16–19. The main independent variables were type and frequency of electronic devices at bedtime and hours of screen-time during leisure time. Outcomes Sleep variables calculated based on self-report including bedtime, rise time, time in bed, sleep duration, sleep onset latency and wake after sleep onset. Results Adolescents spent a large amount of time during the day and at bedtime using electronic devices. Daytime and bedtime use of electronic devices were both related to sleep measures, with an increased risk of short sleep duration, long sleep onset latency and increased sleep deficiency. A dose–response relationship emerged between sleep duration and use of electronic devices, exemplified by the association between PC use and risk of less than 5 h of sleep (OR=2.70, 95% CI 2.14 to 3.39), and comparable lower odds for 7–8 h of sleep (OR=1.64, 95% CI 1.38 to 1.96). Conclusions Use of electronic devices is frequent in adolescence, during the day as well as at bedtime. The results demonstrate a negative relation between use of technology and sleep, suggesting that recommendations on healthy media use could include restrictions on electronic devices.
Summary
The aim of the current study was to examine sleep patterns and rates of insomnia in a population‐based study of adolescents aged 16–19 years. Gender differences in sleep patterns and ...insomnia, as well as a comparison of insomnia rates according to DSM‐IV, DSM‐V and quantitative criteria for insomnia (Behav. Res. Ther., 41, 2003, 427), were explored. We used a large population‐based study in Hordaland county in Norway, conducted in 2012. The sample included 10 220 adolescents aged 16–18 years (54% girls). Self‐reported sleep measurements included bedtime, rise time, time in bed, sleep duration, sleep efficiency, sleep onset latency, wake after sleep onset, rate and frequency and duration of difficulties initiating and maintaining sleep and rate and frequency of tiredness and sleepiness. The adolescents reported short sleep duration on weekdays (mean 6:25 hours), resulting in a sleep deficiency of about 2 h. A majority of the adolescents (65%) reported sleep onset latency exceeding 30 min. Girls reported longer sleep onset latency and a higher rate of insomnia than boys, while boys reported later bedtimes and a larger weekday–weekend discrepancy on several sleep parameters. Insomnia prevalence rates ranged from a total prevalence of 23.8 (DSM‐IV criteria), 18.5 (DSM‐V criteria) and 13.6% (quantitative criteria for insomnia). We conclude that short sleep duration, long sleep onset latency and insomnia were prevalent in adolescents. This warrants attention as a public health concern in this age group.
Purpose
It is generally accepted that mental health problems are unequally distributed across population strata defined by socioeconomic status (SES), with more problems for those with lower SES. ...However, studies of this association in children and adolescents are often restricted by the use of global measures of mental health problems and aggregation of SES-indicators. We aim to further elucidate the relationship between childhood mental health problems and SES by including more detailed information about mental health and individual SES-indicators.
Methods
The participants (
N
= 5,781, age 11–13) were part of the Bergen Child Study (BCS). Mental health was assessed using the teacher, parent and self-report versions of the Strengths and Difficulties Questionnaire (SDQ), including an impact section, used to measure symptom dimensions and probability of psychiatric disorders. Parent reports of family economy and parental education were used as SES measures.
Results
For each SES indicator we confirmed an inverse relationship across all the symptom dimensions. Poor family economy consistently predicted mental health problems, while parental education level predicted externalizing disorders stronger than internalizing disorders.
Conclusion
In this Norwegian sample of children, family economy was a significant predictor of mental health problems as measured across a wide range of symptom dimensions and poor economy predicted a high probability of a psychiatric disorder. Longitudinal studies of the impact of low family income as well as other SES factors on externalizing and internalizing symptom dimensions and disorders are called for.
Inattention in childhood is associated with academic problems later in life. The contribution of specific aspects of inattentive behaviour is, however, less known. We investigated feature importance ...of primary school teachers' reports on nine aspects of inattentive behaviour, gender and age in predicting future academic achievement. Primary school teachers of n = 2491 children (7-9 years) rated nine items reflecting different aspects of inattentive behaviour in 2002. A mean academic achievement score from the previous semester in high school (2012) was available for each youth from an official school register. All scores were at a categorical level. Feature importances were assessed by using multinominal logistic regression, classification and regression trees analysis, and a random forest algorithm. Finally, a comprehensive pattern classification procedure using k-fold cross-validation was implemented. Overall, inattention was rated as more severe in boys, who also obtained lower academic achievement scores in high school than girls. Problems related to sustained attention and distractibility were together with age and gender defined as the most important features to predict future achievement scores. Using these four features as input to a collection of classifiers employing k-fold cross-validation for prediction of academic achievement level, we obtained classification accuracy, precision and recall that were clearly better than chance levels. Primary school teachers' reports of problems related to sustained attention and distractibility were identified as the two most important features of inattentive behaviour predicting academic achievement in high school. Identification and follow-up procedures of primary school children showing these characteristics should be prioritised to prevent future academic failure.
Imaging research into age-related changes in episodic memory has mainly focused on changes in cortical areas in the medial temporal lobe and the hippocampus. However, several lines of evidence ...indicate that subcortical structures such as the basal ganglia and the thalamus are also involved in episodic memory function. Recent studies have revealed age-related changes in functional connectivity between different brain areas, as measured by resting state fMRI. It remains to be shown whether functional connectivity measures in the basal ganglia and the thalamus can be associated with age-related changes in memory function. Here, we investigate this question by applying high model order spatial independent component analysis to resting state fMRI data in a cohort of 100 healthy elderly and relate connectivity features to verbal episodic memory function as assessed by the California Verbal Learning Test (CVLT). We identified five components that were located within different parts of the thalamus and the basal ganglia. Two of these components demonstrated negative correlations between their functional connectivity level and CVLT performance. We also found negative correlations between connectional strength within subcortical structures and CVLT performance. These results indicate a previously undocumented role for the putamen and the thalamus in verbal episodic memory function in aging.
Cortical surface area has tremendously expanded during human evolution, and similar patterns of cortical expansion have been observed during childhood development. An intriguing hypothesis is that ...the high-expanding cortical regions also show the strongest correlations with intellectual function in humans. However, we do not know how the regional distribution of correlations between intellectual function and cortical area maps onto expansion in development and evolution. Here, in a sample of 1048 participants, we show that regions in which cortical area correlates with visuospatial reasoning abilities are generally high expanding in both development and evolution. Several regions in the frontal cortex, especially the anterior cingulate, showed high expansion in both development and evolution. The area of these regions was related to intellectual functions in humans. Low-expanding areas were not related to cognitive scores. These findings suggest that cortical regions involved in higher intellectual functions have expanded the most during development and evolution. The radial unit hypothesis provides a common framework for interpretation of the findings in the context of evolution and prenatal development, while additional cellular mechanisms, such as synaptogenesis, gliogenesis, dendritic arborization, and intracortical myelination, likely impact area expansion in later childhood.