Multimodal deep learning for Alzheimer's disease dementia assessment.

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Original Research: Nurses' Perspectives on Caring for Patients with Do-Not-Resuscitate Orders.

BACKGROUND: Confusion about what a do-not-resuscitate (DNR) order means, including its misinterpretation as "do not treat," has been extensively documented in the literature. Yet there is a paucity of research concerning nurses' perspectives on DNR orders. PURPOSE AND DESIGN: This mixed-methods study was designed to explore nurses' perspectives on the meaning and interpretation of DNR orders in relation to caring for hospitalized adults with such orders. METHODS: Direct care nurses on three units in a large urban hospital were asked to respond online to a case study by indicating how they would prioritize care based on the patient's DNR designation. These nurses were then invited to participate in open-ended interviews with a nurse researcher. Interviews were audiotaped, transcribed, and analyzed. FINDINGS: A total of 35 nurses responded to the case study survey. The majority chose to prioritize palliative care, despite no indication that any plan of care was in place. Thirteen nurses also completed a one-on-one interview. Analysis of interview data revealed this overarching theme: varying interpretations of DNR orders among nurses were common, resulting in unintended consequences. Participants also reported perceived variances among health care team members, patients, and family members. Such misinterpretations resulted in shifts in care, varying responses to deteriorating status, tension, and differences in role expectations for health care team members. CONCLUSIONS: Nurses have opportunities to address misconceptions about care for patients with DNR orders through practice, education, advocacy and policy, and research.

Correlates of comorbid anxiety and externalizing disorders in childhood obsessive compulsive disorder.

The present study examines the influence of diagnostic comorbidity on the demographic, psychiatric, and functional status of youth with a primary diagnosis of obsessive compulsive disorder (OCD). Two hundred and fifteen children (ages 5-17) referred to a university-based OCD specialty clinic were compared based on DSM-IV diagnostic profile: OCD without comorbid anxiety or externalizing disorder, OCD plus anxiety disorder, and OCD plus externalizing disorder. No age or gender differences were found across groups. Higher OCD severity was found for the OCD + ANX group, while the OCD + EXT group reported greater functional impairment than the other two groups. Lower family cohesion was reported by the OCD + EXT group compared to the OCD group and the OCD + ANX group reported higher family conflict compared to the OCD + EXT group. The OCD + ANX group had significantly lower rates of tic disorders while rates of depressive disorders did not differ among the three groups. The presence of comorbid anxiety and externalizing psychopathology are associated with greater symptom severity and functional and family impairment and underscores the importance of a better understanding of the relationship of OCD characteristics and associated disorders. Results and clinical implications are further discussed.