Editorial

Age: Nuisance variable to be eliminated with statistical control or important concern?

Neuroimaging markers based on Magnetic Resonance Imaging (MRI) combined with various other measures (such as genetic covariates, biomarkers, vascular risk factors, neuropsychological tests etc.) might provide useful predictions of clinical outcomes during the progression towards Alzheimer’s disease (AD). The use of multiple features in predictive frameworks for clinical outcomes has become increasingly prevalent in AD research. However, many studies do not focus on systematically and accurately evaluating combinations of multiple input features. Hence, the aim of the present work is to explore and assess optimal combinations of various features for MR-based prediction of (1) cognitive status and (2) biomarker positivity with a multi-kernel learning Gaussian process framework. The explored features and parameters included (A) combinations of brain tissues, modulation, smoothing, and image resolution; (B) incorporating demographics & clinical covariates; (C) the impact of the size of the training data set; (D) the influence of dimensionality reduction and the choice of kernel types. The approach was tested in a large German cohort including 959 subjects from the multicentric longitudinal study of cognitive impairment and dementia (DELCODE). Our evaluation suggests the best prediction of memory performance was obtained for a combination of neuroimaging markers, demographics, genetic information (ApoE4) and CSF biomarkers explaining 57% of outcome variance in out-of-sample predictions. The highest performance for A$\beta$42/40 status classification was achieved for a combination of demographics, ApoE4, and a memory score while usage of structural MRI further improved the classification of individual patient’s pTau status.

Establishing brain-behavior associations that map brain organization to phenotypic measures and generalize to novel individuals remains a challenge in neuroimaging. Predictive modeling approaches that define and validate models with independent datasets offer a solution to this problem. While these methods can detect novel and generalizable brain-behavior associations, they can be daunting, which has limited their use by the wider connectivity community. Here, we offer practical advice and examples based on functional magnetic resonance imaging (fMRI) functional connectivity data for implementing these approaches. We hope these ten rules will increase the use of predictive models with neuroimaging data.

The use of kernels in machine learning methods allows the identification of an optimal hyperplane for the separation of two classes (e.g., patients with a brain disorder of interest and healthy controls). When different acquisition modalities or different types of data are available, using a single kernel for all the available data is a disadvantage because data heterogeneity cannot be fully exploited. Multiple kernel learning (MKL) addresses this issue by allowing the integration of different kernels within the same machine learning model. It has been demonstrated that MKL methods outperform single kernel methods when applied to brain disorders data, while at the same time making it possible to understand which features (e.g., brain region) are the most informative for classification. In this chapter, we provide an overview of MKL methods and illustrate their potential by reviewing recent applications to Alzheimer's disease, Parkinson's disease, and psychosis.

First episode psychosis (FEP) patients are of particular interest for neuroimaging investigations because of the absence of confounding effects due to medications and chronicity. Nonetheless, imaging data are prone to heterogeneity because for example of age, gender or parameter setting differences. With this work, we wanted to take into account possible nuisance effects of age and gender differences across dataset, not correcting the data as a pre-processing step, but including the effect of nuisance covariates in the classification phase. To this aim, we developed a method which, based on multiple kernel learning (MKL), exploits the effect of these confounding variables with a subject-depending kernel weighting procedure. We applied this method to a dataset of cortical thickness obtained from structural magnetic resonance images (MRI) of 127 FEP patients and 127 healthy controls, who underwent either a 3 Tesla (T) or a 1.5 T MRI acquisition. We obtained good accuracies, notably better than those obtained with standard SVM or MKL methods, up to more than 80% for frontal and temporal areas. To our best knowledge, this is the largest classification study in FEP population, showing that fronto-temporal cortical thickness can be used as a potential marker to classify patients with psychosis.

Age is now widely accepted as the greatest single risk factor for developing bladder cancer, and bladder cancer is considered as primarily a disease of the elderly. Because of the close link between age and incidence of bladder cancer, it can be expected that this disease will become an enormous challenge with the growth of an aging population in the years ahead.

Using MEDLINE, a search of the literature between January 1966 and July 2007 was performed to describe normative physiologic changes associated with aging, elucidate genetic and epigenetic alterations that associate aging with bladder cancer and its phenotypes; and to characterize how aging influences efficacies, risks, side effects, and potential complications of the treatments needed for the various stages of bladder cancer.

We discuss influence of aging on host physiology, genetic and epigenetic changes, environmental influences, and host factors in the development and treatment of bladder cancer. Treatments with intravesical bacille Calmette Guerin, radical cystectomy, and perioperative chemotherapy are less well tolerated and have poorer response in elderly patients compared with their younger counterparts. Elderly patients face both clinical and broader institutional barriers to appropriate treatment and may receive less aggressive treatment and sub-therapeutic dosing. However, when appropriately selected, elderly patients tolerate and respond well to cancer treatments.

The decision to undergo treatment for cancer is a tradeoff between loss of function and/or independence and extension of life, which is complicated by a host of concomitant issues such as comorbid medical conditions, functional declines and “frailty”, family dynamics, and social and psychologic issues. Chronological age should not preclude definitive surgical therapy. It is imperative that healthcare practitioners and researchers from disparate disciplines collectively focus efforts towards gaining a better understanding of what the consequences of bladder cancer and its treatments are for older adults and how to appropriately meet the multifaceted medical and psychosocial needs of this growing population.

Comparisons of heart failure (HF) patients with an unselected healthy sample in terms of quality of life (QoL) and depressive symptoms might prove misleading. We compared QoL and depressive symptoms of a HF population with an age- and gender-matched sample of community dwelling elderly.

Data were collected from 781 HF patients (36% female; age 72 ± 9; New York Heart Association II-IV) and 781 age- and gender-matched community-dwelling elderly. Participants completed the Medical Outcome Study 36-item General Health Survey, the Cantril's Ladder of life, and the Center for Epidemiological Studies-Depression scale (CES-D). Analysis of variance techniques with Welch F test and chi-square tests were used to describe differences in QoL and depressive symptoms between different groups. For both men and women with HF, QoL was reduced and depressive symptoms were elevated when compared with their elderly counterparts (CES-D ≥16: 39% vs. 21%, P < .001). HF patients had more chronic conditions—specifically diabetes and asthma/chronic obstructive pulmonary disease. Impaired QoL and depressive symptoms were most prevalent among HF patients with comorbidities. Prevalence was also higher in HF patients in the absence of these conditions.

HF has a large impact on QoL and depressive symptoms, especially in women with HF. Differences persist, even in the absence of common comorbidities. Results demonstrate the need for studies of representative HF patients with direct comparisons to age- and gender-matched controls.