Search

Background: Our objective was to assess the performance of machine learning methods to predict post-operative delirium using a prospective clinical cohort.Methods: We analyzed data from an observational cohort study of 560 older adults (≥ 70 years) without dementia undergoing major elective non-cardiac surgery. Post-operative delirium was determined by the Confusion Assessment Method supplemented by a medical chart review (N = 134, 24%). Five machine learning algorithms and a standard stepwise logistic regression model were developed in a training sample (80% of participants) and evaluated in the remaining hold-out testing sample. We evaluated three overlapping feature sets, restricted to variables that are readily available or minimally burdensome to collect in clinical settings, including interview and medical record data. A large feature set included 71 potential predictors. A smaller set of 18 features was selected by an expert panel using a consensus process, and this smaller feature set was considered with and without a measure of pre-operative mental status.Results: The area under the receiver operating characteristic curve (AUC) was higher in the large feature set conditions (range of AUC, 0.62-0.71 across algorithms) versus the selected feature set conditions (AUC range, 0.53-0.57). The restricted feature set with mental status had intermediate AUC values (range, 0.53-0.68). In the full feature set condition, algorithms such as gradient boosting, cross-validated logistic regression, and neural network (AUC = 0.71, 95% CI 0.58-0.83) were comparable with a model developed using traditional stepwise logistic regression (AUC = 0.69, 95% CI 0.57-0.82). Calibration for all models and feature sets was poor.Conclusions: We developed machine learning prediction models for post-operative delirium that performed better than chance and are comparable with traditional stepwise logistic regression. Delirium proved to be a phenotype that was difficult to predict with appreciable accuracy. [ABSTRACT FROM AUTHOR]

BACKGROUND/OBJECTIVES: Delirium manifests clinically in varying ways across settings. More than 40 instruments currently exist for characterizing the different manifestations of delirium. We evaluated all delirium identification instruments according to their psychometric properties and frequency of citation in published research. DESIGN: We conducted the systematic review by searching Cumulative Index to Nursing and Allied Health Literature (CINAHL), Cochrane Library, Excerpta Medica Database (Embase), PsycINFO, PubMed, and Web of Science from January 1, 1974, to January 31, 2020, with the keywords "delirium" and "instruments," along with their known synonyms. We selected only systematic reviews, meta‐analyses, or narrative literature reviews including multiple delirium identification instruments. MEASUREMENTS: Two reviewers assessed the eligibility of articles and extracted data on all potential delirium identification instruments. Using the original publication on each instrument, the psychometric properties were examined using the Consensus‐based Standards for the Selection of Health Measurement Instruments (COSMIN) framework. RESULTS: Of 2,542 articles identified, 75 met eligibility criteria, yielding 30 different delirium identification instruments. A count of citations was determined using Scopus for the original publication for each instrument. Each instrument underwent methodological quality review of psychometric properties using COSMIN definitions. An expert panel categorized key domains for delirium identification based on criteria from the Diagnostic and Statistical Manual of Mental Disorders (DSM)‐III through DSM‐5. Four instruments were notable for having at least two of three of the following: citation count of 200 or more, strong validation methodology in their original publication, and fulfillment of DSM‐5 criteria. These were, alphabetically, Confusion Assessment Method, Delirium Observation Screening Scale, Delirium Rating Scale‐Revised‐98, and Memorial Delirium Assessment Scale. CONCLUSION: Four commonly used and well‐validated instruments can be recommended for clinical and research use. An important area for future investigation is to harmonize these measures to compare and combine studies on delirium. [ABSTRACT FROM AUTHOR]

Background: Delirium is a common and preventable geriatric syndrome. Moving beyond the binary classification of delirium present/absent, delirium severity represents a potentially important outcome for evaluating preventive and treatment interventions and tracking the course of patients. Although several delirium severity assessment tools currently exist, most have been developed in the absence of advanced measurement methodology and have not been evaluated with rigorous validation studies. Objective: We aimed to report our development of new delirium severity items and the results of item reduction and selection activities guided by psychometric analysis of data derived from a field study. Methods: Building on our literature review of delirium instruments and expert panel process to identify domains of delirium severity, we adapted items from existing delirium severity instruments and generated new items. We then fielded these items among a sample of 352 older hospitalized patients. Results: We used an expert panel process and psychometric data analysis techniques to narrow a set of 303 potential items to 17 items for use in a new delirium severity instrument. The 17-item set demonstrated good internal validity and favorable psychometric characteristics relative to comparator instruments, including the Confusion Assessment Method – Severity (CAM-S) score, the Delirium Rating Scale Revised 98, and the Memorial Delirium Assessment Scale. Conclusion: We more fully conceptualized delirium severity and identified characteristics of an ideal delirium severity instrument. These characteristics include an instrument that is relatively quick to administer, is easy to use by raters with minimal training, and provides a severity rating with good content validity, high internal consistency reliability, and broad domain coverage across delirium symptoms. We anticipate these characteristics to be represented in the subsequent development of our final delirium severity instrument. [ABSTRACT FROM AUTHOR]

Background and Objectives While there are qualitative studies examining the delirium-related experiences of patients, family caregivers, and nurses separately, little is known about common aspects of delirium burden among all three groups. We describe common delirium burdens from the perspectives of patients, family caregivers, and nurses. Research Design and Methods We conducted semistructured qualitative interviews about delirium burden with 18 patients who had recently experienced a delirium episode, with 16 family caregivers, and with 15 nurses who routinely cared for patients with delirium. We recruited participants from a large, urban teaching hospital in Boston, Massachusetts. Interviews were recorded and transcribed. We used interpretive description as the approach to data analysis. Results We identified three common burden themes of the delirium experience: Symptom Burden (Disorientation, Hallucinations/Delusions, Impaired Communication, Memory Problems, Personality Changes, Sleep Disturbances); Emotional Burden (Anger/Frustration, Emotional Distress, Fear, Guilt, Helplessness); and Situational Burden (Loss of Control, Lack of Attention, Lack of Knowledge, Lack of Resources, Safety Concerns, Unpredictability, Unpreparedness). These burdens arise from different sources among patients, family caregivers, and nurses, with markedly differing perspectives on the burden experience. Discussion and Implications Our findings advance the understanding of common burdens of the delirium experience for all groups and offer structure for instrument development and distinct interventions to address the burden of delirium as an individual or group experience. Our work reinforces that no one group experiences delirium in isolation. Delirium is a shared experience that will respond best to systemwide approaches to reduce associated burden. [ABSTRACT FROM AUTHOR]

Among elderly people who do not present with complaints of memory impairment, dementia is often missed by physicians, and time-consuming screening tests requiring expertise to administer and interpret are rarely done. Easily administered, reliable and cost effective dementia screening tests are needed for elderly individuals. The "pencil and paper" Cognitive Assessment Screening Test (CAST) takes minimal examiner time/training, and is both sensitive and specific in discriminating demented patients from healthy controls. The objectives of this study were to: (1) confirm the validity of the CAST in identifying individuals with dementia in a real-world setting (nonassisted living retirement community); (2) compare the sensitivity and specificity with other screening tests and extensive psychometric tests; and (3) assess the reliability of the CAST in test-retest conditions over time. The CAST was both sensitive and specific and showed reliability on retesting. The CAST is both simpler to administer and more accurate than other screening tests for elderly subjects. [ABSTRACT FROM AUTHOR]

This study examines the use of music as a strategy to decrease agitated behavior in cognitively impaired nursing home residents. Twenty agitated subjects, 68 to 84 years of age, were exposed to 15 minutes of calming music on two occasions. Agitated behavior scores were recorded before, during and after the musical intervention using the Agitated Behavior Scale. Results indicate that a statistically significant reduction in agitated behavior occurs both during (p. <0]) and after the musical intervention (p. <05). Calming music was shown to be an effective, nonpharmacologic strategy which nurses and other caregivers may use to reduce agitated behavior in the nursing home. [ABSTRACT FROM PUBLISHER]

Editor's note: This article is by 22 nursing gerontology experts who are all advocates of nursing home reform. They are listed at the end of this article., (Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.)

Background: Our objective was to assess the performance of machine learning methods to predict post-operative delirium using a prospective clinical cohort., Methods: We analyzed data from an observational cohort study of 560 older adults (≥ 70 years) without dementia undergoing major elective non-cardiac surgery. Post-operative delirium was determined by the Confusion Assessment Method supplemented by a medical chart review (N = 134, 24%). Five machine learning algorithms and a standard stepwise logistic regression model were developed in a training sample (80% of participants) and evaluated in the remaining hold-out testing sample. We evaluated three overlapping feature sets, restricted to variables that are readily available or minimally burdensome to collect in clinical settings, including interview and medical record data. A large feature set included 71 potential predictors. A smaller set of 18 features was selected by an expert panel using a consensus process, and this smaller feature set was considered with and without a measure of pre-operative mental status., Results: The area under the receiver operating characteristic curve (AUC) was higher in the large feature set conditions (range of AUC, 0.62-0.71 across algorithms) versus the selected feature set conditions (AUC range, 0.53-0.57). The restricted feature set with mental status had intermediate AUC values (range, 0.53-0.68). In the full feature set condition, algorithms such as gradient boosting, cross-validated logistic regression, and neural network (AUC = 0.71, 95% CI 0.58-0.83) were comparable with a model developed using traditional stepwise logistic regression (AUC = 0.69, 95% CI 0.57-0.82). Calibration for all models and feature sets was poor., Conclusions: We developed machine learning prediction models for post-operative delirium that performed better than chance and are comparable with traditional stepwise logistic regression. Delirium proved to be a phenotype that was difficult to predict with appreciable accuracy.