•Integrated machine-learning methods can predict AD severity with high accuracy.•Model validation procedure appropriate for processing individual participant data.•Highly accessible cognitive and ...functional markers more accurate than biomarkers.•Automated decision-support tool predicts individual AD severity on continuous scale.•System assesses undiagnosed patient data against an existing dataset of patients.
Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression, and k-Nearest Neighbor for regression and Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbor for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predictive performance of models incorporating CFA was shown to consistently have higher accuracy than those based solely on biomarker modalities. We found that KRR and SVM were the best performing regression and classification methods respectively. The optimal SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the best performance of the KRR model was reported with combined CFA and MRI neuroimaging data, i.e., R2 = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power of CFA and their widespread use in clinical practice, we designed a data-driven and self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating the severity of AD of an individual on a continuous spectrum. The system implemented an automated computational approach for data pre-processing, modelling, and validation and used exclusively the scores of selected cognitive measures as data entries. Taken together, we have developed an objective and practical CDSS to aid AD diagnosis.
Transgender youth are more likely than cisgender youth to report health risks related to violence victimization, substance use, mental health, and sexual health. Parental support may help foster ...resilience and better health outcomes among this population. However, limited research has characterized parental support among transgender youth. To address this gap, we conducted a thematic analysis of 33 in-depth interviews with transgender youth. We coded interviews using the dimensions of the social support framework (i.e., emotional, instrumental, appraisal, and informational) as well as inductive codes to identify emergent themes. Almost all participants described some form of general parental support (e.g., expressions of love, housing, advice, and affirmation). Parental support specific to gender identity was also noted (e.g., emotional support for coming out as transgender and chosen name and pronoun use) but was more limited. Parents may benefit from resources and programming to promote acceptance and gender-affirming behaviors.
Despite the prevalence of Internet support groups for individuals with mental illnesses little is known about the potential benefits, or harm, of participating in such groups. Therefore, this ...randomized controlled trial sought to determine the impact of unmoderated, unstructured Internet peer support, similar to what is naturally occurring on the Internet, on the well-being of individuals with psychiatric disabilities. Three hundred individuals resident in the USA diagnosed with a Schizophrenia Spectrum or an Affective Disorder were randomized into one of three conditions: experimental Internet peer support via a listserv, experimental Internet peer support via a bulletin board, or a control condition. Three measurement time points, baseline, 4- and 12 months post-baseline, assessed well-being by examining measures of recovery, quality of life, empowerment, social support, and distress. Time × group interactions in the repeated measures ANOVA showed no differences between conditions on the main outcomes. Post-hoc repeated measures ANOVAs found that those individuals who participated more in Internet peer support reported higher levels of distress than those with less or no participation (
p = 0.03). Those who reported more positive experiences with the Internet peer support group also reported higher levels of psychological distress than those reporting less positive experiences (
p = 0.01). Study results therefore do not support the hypothesis that participation in an unmoderated, unstructured Internet listserv or bulletin board peer support group for individuals with psychiatric disabilities enhances well-being. Counterintuitive findings demonstrating those who report more positive experiences also experienced higher levels of distress are discussed but we also point to the need for additional research. Future research should explore the various structures, formats, and interventions of Internet support, as well as the content and quality of interactions. Knowledge generated from such research can help to inform policies and guidelines for safely navigating online resources and supports to gain maximum benefit.
► Overall, unmoderated Internet-based peer interactions are neither helpful nor harmful. ► Individuals who participate more online report higher levels of distress. ► Individuals who report more positive experiences online also report greater distress. ► More rigorous and nuanced Internet peer support studies are needed.
The diagnosis of type 2 diabetes (T2D) at an early stage has a key role for an adequate T2D integrated management system and patient's follow-up. Recent years have witnessed an increasing amount of ...available electronic health record (EHR) data and machine learning (ML) techniques have been considerably evolving. However, managing and modeling this amount of information may lead to several challenges, such as overfitting, model interpretability, and computational cost. Starting from these motivations, we introduced an ML method called sparse balanced support vector machine (SB-SVM) for discovering T2D in a novel collected EHR dataset (named Federazione Italiana Medici di Medicina Generale dataset). In particular, among all the EHR features related to exemptions, examination, and drug prescriptions, we have selected only those collected before T2D diagnosis from an uniform age group of subjects. We demonstrated the reliability of the introduced approach with respect to other ML and deep learning approaches widely employed in the state-of-the-art for solving this task. Results evidence that the SB-SVM overcomes the other state-of-the-art competitors providing the best compromise between predictive performance and computation time. Additionally, the induced sparsity allows to increase the model interpretability, while implicitly managing high-dimensional data and the usual unbalanced class distribution.
This deeply insightful ethnography explores the healing power of caring and intimacy in a small, closely bonded Apostolic congregation during Botswana's HIV/AIDS pandemic.Death in a Church of ...Lifepaints a vivid picture of how members of the Baitshepi Church make strenuous efforts to sustain loving relationships amid widespread illness and death. Over the course of long-term fieldwork, Frederick Klaits discovered Baitshepi's distinctly maternal ethos and the "spiritual" kinship embodied in the church's nurturing fellowship practice. Klaits shows that for Baitshepi members, Christian faith is a form of moral passion that counters practices of divination and witchcraft with redemptive hymn singing, prayer, and the use of therapeutic substances. An online audio annex makes available examples of the church members' preaching and song.
Summary
Objectives
: This paper draws attention to: i) key considerations for evaluating artificial intelligence (AI) enabled clinical decision support; and ii) challenges and practical implications ...of AI design, development, selection, use, and ongoing surveillance.
Method
: A narrative review of existing research and evaluation approaches along with expert perspectives drawn from the International Medical Informatics Association (IMIA) Working Group on Technology Assessment and Quality Development in Health Informatics and the European Federation for Medical Informatics (EFMI) Working Group for Assessment of Health Information Systems.
Results
: There is a rich history and tradition of evaluating AI in healthcare. While evaluators can learn from past efforts, and build on best practice evaluation frameworks and methodologies, questions remain about how to evaluate the safety and effectiveness of AI that dynamically harness vast amounts of genomic, biomarker, phenotype, electronic record, and care delivery data from across health systems. This paper first provides a historical perspective about the evaluation of AI in healthcare. It then examines key challenges of evaluating AI-enabled clinical decision support during design, development, selection, use, and ongoing surveillance. Practical aspects of evaluating AI in healthcare, including approaches to evaluation and indicators to monitor AI are also discussed.
Conclusion
: Commitment to rigorous initial and ongoing evaluation will be critical to ensuring the safe and effective integration of AI in complex sociotechnical settings. Specific enhancements that are required for the new generation of AI-enabled clinical decision support will emerge through practical application.
Families from migrant backgrounds are found to generally underutilize mainstream child and family support services and recourse more to their social networks and community‐based actors for support. ...This article explores the role of migrant community resource persons (CRPs). Drawing on the novel concept of welfare bricolage, the study sought to unravel CRPs' take on family support and their position in the family support landscape beyond the dominant framing as instrumental intermediaries. Semi‐structured in‐depth interviews were conducted with 27 CRPs in Flanders, Belgium, to which thematic analysis was applied. This thematic analysis was guided by key principles of welfare bricolage. The findings add to the existing knowledge that CRPs creatively and flexibly shape community‐based family support outside and independent of the predefined, mainstream pathways. CRPs seek to strengthen families and their communities by purposefully assembling and deploying a wide range of resources from various support systems. The findings expand the notion of family support, what it is and who provides it, and thus provide an impetus to reconsider child and family social work in superdiverse settings. This article therefore informs government authorities and formal and informal actors working to support family welfare.
Research on online support forums has largely overlooked the quality of support provision. The present experiment examined how others' responses and a support-seeker's reply can influence ...action‐focused supportiveness, emotion‐focused supportiveness, and politeness of readers' support messages. Results showed that the supportiveness of others' comments was associated with subsequent readers' perceptions of public opinion toward the support‐seeker and readers' liking of the support‐seeker, which in turn influenced the quality of readers' support messages.
Objectives/Hypothesis
To formally document online support community (OSC) use among patients with vestibular symptoms and gain an appreciation for the perceived influence of participation on ...psychosocial outcomes and the impact on medical decision‐making.
Study Design
Self reported internet‐based questionnaire.
Methods
The Facebook search function was paired with a comprehensive list of vestibular diagnoses to systematically collect publicly available information on vestibular OSCs. Next, a survey was designed to gather clinicodemographic information, OSC characteristics, participation measures, perceived outcomes, and influence on medical decision‐making. The anonymous instrument was posted to two OSCs that provide support for patients with general vestibular symptoms.
Results
Seventy‐three OSCs were identified with >250,000 cumulative members and >10,000 posts per month. The survey was completed by 549 participants, a cohort of primarily educated middle‐aged (median = 50, interquartile range 40–60), non‐Hispanic white (84%), and female (89%) participants. The participants' most cited initial motivation and achieved goal of participants was to hear from others with the same diagnosis (89% and 88%, respectively). Daily users and those who reported seeing ≥5 providers before receiving a diagnosis indicated that OSC utilization significantly influenced their requested medical treatments (72% daily vs. 61% nondaily, P = .012; 61% <5 providers vs. 71% ≥5 providers P = .019, respectively). Most participants agreed that OSC engagement provides emotional support (74%) and helps to develop coping strategies (68%). Membership of ≥1 year was associated with a higher rate of learned coping skills (61% membership <1‐year vs. 71% ≥1‐year P = .016).
Conclusions
The use of OSCs is widespread among vestibular diagnoses. A survey of two OSCs suggests these groups provide a significant source of peer support and can influence users' ability to interface with the medical system.
Level of Evidence
NA Laryngoscope, 132:1835–1842, 2022
PDF
