How accurate are suicide risk prediction models? Asking the right questions for clinical practice.
Ontology highlight
ABSTRACT:
SUBMITTER: Whiting D
PROVIDER: S-EPMC7012643 | biostudies-literature | 2019 Aug
REPOSITORIES: biostudies-literature
Publications
How accurate are suicide risk prediction models? Asking the right questions for clinical practice.
Whiting Daniel D Fazel Seena S
Evidence-based mental health 20190627 3
Prediction models assist in stratifying and quantifying an individual's risk of developing a particular adverse outcome, and are widely used in cardiovascular and cancer medicine. Whether these approaches are accurate in predicting self-harm and suicide has been questioned. We searched for systematic reviews in the suicide risk assessment field, and identified three recent reviews that have examined current tools and models derived using machine learning approaches. In this clinical review, we p ...[more]
Similar Datasets
Project description:Assessing the mutagenicity of chemicals is an essential task in the drug development process. Usually, databases and other structured sources for AMES mutagenicity exist, which have been carefully and laboriously curated from scientific publications. As knowledge accumulates over time, updating these databases is always an overhead and impractical. In this paper, we first propose the problem of predicting the mutagenicity of chemicals from textual information in scientific publications. More simply, given a chemical and evidence in the natural language form from publications where the mutagenicity of the chemical is described, the goal of the model/algorithm is to predict if it is potentially mutagenic or not. For this, we first construct a golden standard data set and then propose MutaPredBERT, a prediction model fine-tuned on BioLinkBERT based on a question-answering formulation of the problem. We leverage transfer learning and use the help of large transformer-based models to achieve a Macro F1 score of >0.88 even with relatively small data for fine-tuning. Our work establishes the utility of large language models for the construction of structured sources of knowledge bases directly from scientific publications.
| S-EPMC10728128 | biostudies-literature
Project description:IntroductionDespite knowledge about major health effects of secondhand tobacco smoke (SHS) exposure, systematic incorporation of SHS screening and counseling in clinical settings has not occurred.MethodsA three-round modified Delphi Panel of tobacco control experts was convened to build consensus on the screening questions that should be asked and identify opportunities and barriers to SHS exposure screening and counseling. The panel considered four questions: (1) what questions should be asked about SHS exposure; (2) what are the top priorities to advance the goal of ensuring that these questions are asked; (3) what are the barriers to achieving these goals; and (4) how might these barriers be overcome. Each panel member submitted answers to the questions. Responses were summarized and successive rounds were reviewed by panel members for consolidation and prioritization.ResultsPanelists agreed that both adults and children should be screened during clinical encounters by asking if they are exposed or have ever been exposed to smoke from any tobacco products in their usual environment. The panel found that consistent clinician training, quality measurement or other accountability, and policy and electronic health records interventions were needed to successfully implement consistent screening.ConclusionsThe panel successfully generated screening questions and identified priorities to improve SHS exposure screening. Policy interventions and stakeholder engagement are needed to overcome barriers to implementing effective SHS screening.ImplicationsIn a modified Delphi panel, tobacco control and clinical prevention experts agreed that all adults and children should be screened during clinical encounters by asking if they are exposed or have ever been exposed to smoke from tobacco products. Consistent training, accountability, and policy and electronic health records interventions are needed to implement consistent screening. Increasing SHS screening will have a significant impact on public health and costs.
| S-EPMC7974019 | biostudies-literature
Project description:Most diseases arise not purely through genetic abnormalities nor purely through environmental causes, but as "complex" conditions brought about by the combined effects of genetic susceptibility factors, nongenetic experiences and exposures, and bad luck. Finding simple models capable of both characterizing such joint effects and providing new insight into pathogenesis remains an ongoing challenge in etiologic epidemiology. Additive null models can capture certain pure forms of independent etiologic effects in studies of rare conditions and can be useful for predicting possible effects of interventions. The concept of exposure modification is here proposed as useful, particularly in thinking about biologic interactions between exposures and genetic variants. Openness to parsimonious joint models and the insights they can provide is key to advancing our understanding of etiology.
| S-EPMC3324436 | biostudies-literature
Project description:The cultural keystone species theory predicts plant species that are culturally important, play a role in resource acquisition, fulfil a psycho-socio-cultural function within a given culture, have high use-value, have an associated naming and terminology in a native language, and a high level of species irreplaceability qualify for cultural keystone species designation. This theory was proposed as a framework for understanding relationships between human societies and species that are integral to their culture. A greater understanding of the dynamic roles of cultural keystones in both ecosystem processes and cultural societies is a foundation for facilitating biocultural conservation. Given such important direct conservation implications of the cultural keystone species theory, we reviewed the use of this theoretical framework across the literature to identify new directions for research. Most studies often emphasized the role of cultural keystones species in human societies but failed to provide a robust and reproducible measure of cultural keystone species status or direct test of the predictions of the theory and underemphasized their potential roles in ecosystem processes. To date, no studies that mentioned cultural keystone species tested the predictions of the theory. Only 4.4% provided a measure for cultural keystone status and 47.4% have cited or applied keystone designation to a given species without providing a reproducible measure for cultural keystone species. Studies that provided a measure for cultural keystone species primarily occurred in North America while few of these studies occurred in Australia and Europe with none occurring in Africa. As such, most cultural keystone species have been designated as such qualitatively based on researcher subjectivity while other studies have designated keystone species with quantitative indices of cultural importance, often incorporating researcher biases or measuring a few of the cultural keystone status predictors rather than all of them, indicating a lack of consensus in identifying cultural keystone species. Thus, we pose the need for a paradigm shift toward the development of serious and systematic approaches for keystone designation.
| S-EPMC7657362 | biostudies-literature
Project description:BackgroundInterest in developing machine learning models that use electronic health record data to predict patients' risk of suicidal behavior has recently proliferated. However, whether and how such models might be implemented and useful in clinical practice remain unknown. To ultimately make automated suicide risk-prediction models useful in practice, and thus better prevent patient suicides, it is critical to partner with key stakeholders, including the frontline providers who will be using such tools, at each stage of the implementation process.ObjectiveThe aim of this focus group study is to inform ongoing and future efforts to deploy suicide risk-prediction models in clinical practice. The specific goals are to better understand hospital providers' current practices for assessing and managing suicide risk; determine providers' perspectives on using automated suicide risk-prediction models in practice; and identify barriers, facilitators, recommendations, and factors to consider.MethodsWe conducted 10 two-hour focus groups with a total of 40 providers from psychiatry, internal medicine and primary care, emergency medicine, and obstetrics and gynecology departments within an urban academic medical center. Audio recordings of open-ended group discussions were transcribed and coded for relevant and recurrent themes by 2 independent study staff members. All coded text was reviewed and discrepancies were resolved in consensus meetings with doctoral-level staff.ResultsAlthough most providers reported using standardized suicide risk assessment tools in their clinical practices, existing tools were commonly described as unhelpful and providers indicated dissatisfaction with current suicide risk assessment methods. Overall, providers' general attitudes toward the practical use of automated suicide risk-prediction models and corresponding clinical decision support tools were positive. Providers were especially interested in the potential to identify high-risk patients who might be missed by traditional screening methods. Some expressed skepticism about the potential usefulness of these models in routine care; specific barriers included concerns about liability, alert fatigue, and increased demand on the health care system. Key facilitators included presenting specific patient-level features contributing to risk scores, emphasizing changes in risk over time, and developing systematic clinical workflows and provider training. Participants also recommended considering risk-prediction windows, timing of alerts, who will have access to model predictions, and variability across treatment settings.ConclusionsProviders were dissatisfied with current suicide risk assessment methods and were open to the use of a machine learning-based risk-prediction system to inform clinical decision-making. They also raised multiple concerns about potential barriers to the usefulness of this approach and suggested several possible facilitators. Future efforts in this area will benefit from incorporating systematic qualitative feedback from providers, patients, administrators, and payers on the use of these new approaches in routine care, especially given the complex, sensitive, and unfortunately still stigmatized nature of suicide risk.
| S-EPMC8956996 | biostudies-literature
Project description:BackgroundSuicide risk prediction models derived from electronic health records (EHR) are a novel innovation in suicide prevention but there is little evidence to guide their implementation.MethodsIn this qualitative study, 30 clinicians and 10 health care administrators were interviewed from one health system anticipating implementation of an automated EHR-derived suicide risk prediction model and two health systems piloting different implementation approaches. Site-tailored interview guides focused on respondents' expectations for and experiences with suicide risk prediction models in clinical practice, and suggestions for improving implementation. Interview prompts and content analysis were guided by Consolidated Framework for Implementation Research (CFIR) constructs.ResultsAdministrators and clinicians found use of the suicide risk prediction model and the two implementation approaches acceptable. Clinicians desired opportunities for early buy-in, implementation decision-making, and feedback. They wanted to better understand how this manner of risk identification enhanced existing suicide prevention efforts. They also wanted additional training to understand how the model determined risk, particularly after patients they expected to see identified by the model were not flagged at-risk and patients they did not expect to see identified were. Clinicians were concerned about having enough suicide prevention resources for potentially increased demand and about their personal liability; they wanted clear procedures for situations when they could not reach patients or when patients remained at-risk over a sustained period. Suggestions for making risk model workflows more efficient and less burdensome included consolidating suicide risk information in a dedicated module in the EHR and populating risk assessment scores and text in clinical notes.ConclusionHealth systems considering suicide risk model implementation should engage clinicians early in the process to ensure they understand how risk models estimate risk and add value to existing workflows, clarify clinician role expectations, and summarize risk information in a convenient place in the EHR to support high-quality patient care.
| S-EPMC9748385 | biostudies-literature
Project description:Background: Emerging global transformations - including a new Sustainable Development Agenda - are revealing increasingly interrelated goals and challenges, poised to be addressed by similarly integrated, multi-faceted solutions. Research to date has focused on determining the effectiveness of these approaches, yet a key question remains: are synergistic effects produced by integrating two or more sectors? We systematically reviewed impact evaluations on integrated development interventions to assess whether synergistic, amplified impacts are being measured and evaluated. Methods: The International Initiative for Impact Evaluation's (3ie) Impact Evaluation Repository comprised our sampling frame (n = 4,339). Following PRISMA guidelines, we employed a three-stage screening and review process. Results: We identified 601 journal articles that evaluated integrated interventions. Seventy percent used a randomized design to assess impact with regard to whether the intervention achieved its desired outcomes. Only 26 of these evaluations, however, used a full factorial design to statistically detect any synergistic effects produced by integrating sectors. Of those, seven showed synergistic effects. Conclusions: To date, evaluations of integrated development approaches have demonstrated positive impacts in numerous contexts, but gaps remain with regard to documenting whether integrated programming produces synergistic, amplified outcomes. Research on these program models needs to extend beyond impact only, and more explicitly examine and measure the synergies and efficiencies associated with linking two or more sectors. Doing so will be critical for identifying effective integrated development strategies that will help achieve the multi-sector SDG agenda.
| S-EPMC6034098 | biostudies-literature
Project description:In July 2010, the World Health Organization (WHO) issued formal revisions of its guidelines on the use of highly active antiretroviral therapy for HIV. The new guidelines greatly expand eligibility for treatment of adults and children, as well as for pregnant women seeking prophylaxis for vertical HIV transmission. WHO's new recommendations bring the guidelines closer to practices in developed countries, and its shift to earlier treatment alone will increase the number of treatment-eligible people by 50% or more.Scaling up access to HIV treatment is revealing important gaps in our understanding of how best to provide for all those in need. This knowledge gap is especially significant in developing countries, where women and children comprise a majority of those living with HIV infection. Given the magnitude and significance of these populations, the International AIDS Society, through its Industry Liaison Forum, prioritized HIV treatment and prophylaxis of women and children. In March 2010, the International AIDS Society and 15 partners launched a Consensus Statement outlining priority areas in which a relative lack of knowledge impedes delivery of optimal prevention of mother to child transmission (PMTCT) and treatment to women and children.The Consensus Statement, "Asking the Right Questions: Advancing an HIV Research Agenda for Women and Children", makes a special appeal for a more gender-sensitive approach to HIV research at all stages, from conception to design and implementation. It particularly emphasizes research to enhance the understanding of sex-based differences and paediatric needs in treatment uptake and response. In addition to clinical issues, the statement focuses on programmatic research that facilitates access and adherence to antiretroviral regimens. Better coordination of HIV management with sexual and reproductive healthcare delivery is one such approach.We discuss here our knowledge gaps concerning effective, safe PMTCT and treatment for women and children in light of the expansion envisioned by WHO's revised guidelines. The guideline's new goals present an opportunity for advancing the women and children's agenda outlined in the Consensus Statement.
| S-EPMC3118247 | biostudies-literature
Project description:BackgroundConversations about research priorities with members of the public are rarely designed specifically to include people who identify as Lesbian, Gay, Bisexual, Transgender and Queer (LGBTQ+) and are not researchers.MethodsGenerally, to address this gap, and specifically, to inform future research for CLS, we carried out a rapid review of published research priority sets covering LGBTQ+ topics, and an online workshop to prioritise identified themes.ResultsRapid review: results. The rapid review identified 18 LGBTQ+ research priority sets. Some focussed on specific populations such as women or men, younger or older people or people living within families. Five addressed transgender and gender non- conforming populations. All of the research priority sets originated from English-speaking, high and middle-income countries (UK, US, Canada, and Australia), and date from 2016 onwards. Prioritization approaches were wide-ranging from personal commentary to expert workshops and surveys. Participants involved in setting priorities mostly included research academics, health practitioners and advocacy organisations, two studies involved LGBTQ+ public in their process. Research priorities identified in this review were then grouped into themes which were prioritised during the workshop. Workshop: results. For the workshop, participants were recruited using local (Cambridge, UK) LGBTQ+ networks and a national advert to a public involvement in research matching website to take part in an online discussion workshop. Those that took part were offered payment for their time in preparing for the workshop and taking part. Participants personal priorities and experiences contributed to a consensus development process and a final ranked list of seven research themes and participants' experiences of healthcare, mental health advocacy, care homes, caring responsibilities, schools and family units added additional context.ConclusionsFrom the workshop the three research themes prioritised were: healthcare services delivery, prevention, and particular challenges / intersectionality of multiple challenges for people identifying as LGBTQ+. Research themes interconnected in many ways and this was demonstrated by the comments from workshop participants. This paper offers insights into why these priorities were important from participants' perspectives and detail about how to run an inclusive and respectful public involvement research exercise. On a practical level these themes will directly inform future research direction for CLS.
| S-EPMC8460395 | biostudies-literature
Project description:The current meta-analysis estimated the magnitude of the impact of asking intention and self-prediction questions on rates of subsequent behavior, and examined mediators and moderators of this question-behavior effect (QBE). Random-effects meta-analysis on 116 published tests of the effect indicated that intention/prediction questions have a small positive effect on behavior (d+ = 0.24). Little support was observed for attitude accessibility, cognitive dissonance, behavioral simulation, or processing fluency explanations of the QBE. Multivariate analyses indicated significant effects of social desirability of behavior/behavior domain (larger effects for more desirable and less risky behaviors), difficulty of behavior (larger effects for easy-to-perform behaviors), and sample type (larger effects among student samples). Although this review controls for co-occurrence of moderators in multivariate analyses, future primary research should systematically vary moderators in fully factorial designs. Further primary research is also needed to unravel the mechanisms underlying different variants of the QBE.
| S-EPMC4931712 | biostudies-literature