Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior.
Ontology highlight
ABSTRACT:
SUBMITTER: Velupillai S
PROVIDER: S-EPMC6381841 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior.
Velupillai Sumithra S Hadlaczky Gergö G Baca-Garcia Enrique E Gorrell Genevieve M GM Werbeloff Nomi N Nguyen Dong D Patel Rashmi R Leightley Daniel D Downs Johnny J Hotopf Matthew M Dutta Rina R
Frontiers in psychiatry 20190213
Risk assessment of suicidal behavior is a time-consuming but notoriously inaccurate activity for mental health services globally. In the last 50 years a large number of tools have been designed for suicide risk assessment, and tested in a wide variety of populations, but studies show that these tools suffer from low positive predictive values. More recently, advances in research fields such as machine learning and natural language processing applied on large datasets have shown promising results ...[more]
Similar Datasets
Project description:Resistance to small molecule drugs often emerges in cancer cells, viruses, and bacteria as a result of the evolutionary pressure exerted by the therapy. Protein mutations that directly impair drug binding are frequently involved in resistance, and the ability to anticipate these mutations would be beneficial in drug development and clinical practice. Here, we evaluate the ability of three distinct computational methods to predict ligand binding affinity changes upon protein mutation for the cancer target Abl kinase. These structure-based approaches rely on first-principle statistical mechanics, mixed physics- and knowledge-based potentials, and machine learning, and were able to estimate binding affinity changes and identify resistant mutations with remarkable accuracy. We expect that these complementary approaches will enable the routine prediction of resistance-causing mutations in a variety of other target proteins.
| S-EPMC6716344 | biostudies-literature
Project description:OBJECTIVE:This systematic review aimed to evaluate the ability of risk tools to predict the future episodes of suicide/self-harm in adolescents. DESIGN:Systematic review. DATA SOURCES:MEDLINE, EMBASE, CINAHL and PsycINFO were searched from inception to 3 March 2018. ELIGIBILITY CRITERIA FOR SELECTING STUDIES:Cohort studies, case-control studies and randomised controlled trials of adolescents aged 10-25 who had undergone risk assessment in a clinical setting following an episode of self-harm were included. DATA EXTRACTION AND SYNTHESIS:Two independent reviewers extracted data and assessed risk of bias. Data were grouped by tool and narrative synthesis undertaken, with studies appraised using a checklist combining the QUIPS (Quality In Prognosis Studies) and QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies) tools. RESULTS:Of the 17 137 articles initially identified, 11 studies evaluating 10 separate tools were included. The studies varied in setting, population and outcome measure. The majority of the studies were rated as having an unclear risk of bias, and meta-analysis was not possible due to high variability between studies.The ability of the tools to correctly identify those adolescents going on to make a self-harm/suicide attempt ranged from 27% (95% CI 10.7% to 50.2%) to 95.8% (95% CI 78.9% to 99.9%). A variety of metrics were provided for 1-10 points increases in various tools, for example, odds and HRs. CONCLUSIONS:This systematic review is the first to explore the use of assessment tools in adolescents. The predictive ability of these tools varies greatly. No single tool is suitable for predicting a higher risk of suicide or self-harm in adolescent populations. PROSPERO REGISTRATION NUMBER:CRD42017058686.
| S-EPMC6731844 | biostudies-other
Project description:BackgroundMobile technology offers unique opportunities for monitoring short-term suicide risk in daily life. In this study of suicidal adolescent inpatients, theoretically informed risk factors were assessed daily following discharge to predict near-term suicidal ideation and inform decision algorithms for identifying elevations in daily level risk, with implications for real-time suicide-focused interventions.MethodsAdolescents (N = 78; 67.9% female) completed brief surveys texted daily for 4 weeks after discharge (n = 1621 observations). Using multi-level classification and regression trees (CARTSs) with repeated 5-fold cross-validation, we tested (a) a simple prediction model incorporating previous-day scores for each of 10 risk factors, and (b) a more complex model incorporating, for each of these factors, a time-varying person-specific mean over prior days together with deviation from that mean. Models also incorporated missingness and contextual (study week, day of the week) indicators. The outcome was the presence/absence of next-day suicidal ideation.ResultsThe best-performing model (cross-validated AUC = 0.86) was a complex model that included ideation duration, hopelessness, burdensomeness, and self-efficacy to refrain from suicidal action. An equivalent model that excluded ideation duration had acceptable overall performance (cross-validated AUC = 0.78). Models incorporating only previous-day scores, with and without ideation duration (cross-validated AUC of 0.82 and 0.75, respectively), showed relatively weaker performance.ConclusionsResults suggest that specific combinations of dynamic risk factors assessed in adolescents' daily life have promising utility in predicting next-day suicidal thoughts. Findings represent an important step in the development of decision tools identifying short-term risk as well as guiding timely interventions sensitive to proximal elevations in suicide risk in daily life.
| S-EPMC9814182 | biostudies-literature
Project description:INTRODUCTION:The AARR task force on suicidal ideation and behavior (SI/SB) in dementia conducted an online survey on the extent of SI/SB in individuals diagnosed with mild cognitive impairment (MCI) or dementia who were participating in clinical trials. METHODS:Investigators with experience in conducting SI/SB assessments in clinical trial subjects with MCI or dementia were invited to complete a global 19-item online survey. RESULTS:A total of 204 evaluable responses were collected with the majority from North America and Europe (83.4%) and the remainder from Asia, Latin America, and Mideast/Africa. The mean (SD) number of subjects personally assessed by the respondents in the past year with MCI, mild-moderate dementia, or severe dementia was 12.8 (26.2), 31.2 (39.6), and 10.1 (34.7), respectively. The mean number of subjects in each diagnostic group with suicidal ideation (SI), suicidal behavior (SB), or completed suicide (CS) was on average quite low (0.3 to 1.1 for SI, 0.1 to 0.2 for SB, and 0.0 to 0.2 for CS). Confidence in subject self-reports of SI/SB over different time periods declined with increasing severity of cognitive impairment and with increasing duration of the recall time period assessed. Of respondents, 56% and 75% had low confidence in self-ratings of SI/SB from subjects with severe dementia over the past 24 hours and the past week to 1 month, respectively. Ratings of the reliability of information collected on SI/SB also decreased with increasing severity of cognitive impairment. Approximately 70% of respondents rated the reliability of the information they obtained from all sources (patient, caregiver, and others) for subjects with MCI as high, but only about half (42.0% to 55.3%) and less than a quarter (17.4% to 24.3%) rated the reliability of information obtained for subjects with mild to moderate dementia or severe dementia as high, respectively. DISCUSSION:These results support the usefulness of prospective SI/SB assessments in MCI and mild dementia, raise questions about the reliability of assessments in moderate dementia, and confirm their lack of clinical utility in severe dementia. The results highlight the need for development of validated assessment instruments adapted to the stage of cognitive decline of the patients under study and may be the most effective in the earliest stages of the disease.
| S-EPMC5644276 | biostudies-literature
Project description:BackgroundRates of suicide and self-harm are elevated in carceral institutions. Inmates are a vulnerable group since they are exposed to multiple risk factors. This paper critically reviews empirical research on programs to prevent suicidal and self-harmful behaviors in correctional facilities and summarizes effect sizes across studies.MethodsWe searched PsychINFO, PubMed, IEEEXPLORE and the CRISE Documentation Centre Database to identify relevant articles published before June 2022. Inclusion criteria were: peer-reviewed and with outcome data on effectiveness of prevention activities. Two reviewers independently assessed 905 articles to determine inclusion eligibility. Quality was assessed by two independent reviewers using the Quality Assessment Tool for Quantitative Studies. Meta-analyses using random-effect models were used to pool effect sizes for each outcome. This review was conducted in accordance with PRISMA guidelines.FindingsTwenty-four of the 905 articles, published between 1980 and 2022, were included. Studies were frequently conducted in the United States (n=13; 54%) and used varying study designs; most frequently pre-post with no control group (n=9; 38%). Sample sizes and interventions varied considerably. Most were of moderate quality (n=21; 88%). On average, prevention programs in correctional facilities were effective in decreasing suicide deaths (pooled rate ratio of 0·35 [95% CI 0·23 to 0·55; p<0·001]; I2=68·01%), incidents of self-harm (pooled Hedges'g of -0·54 (95% CI: -1·03 to -0·05; p=0·031]; I2=81·34%), and suicidal ideation (pooled Hedges'g of -0·39 [95% CI: -0·65 to -0·14; p=0·003]; I2=47·09%).InterpretationPrevention activities are effective in reducing suicide death, self-harm and suicidal ideation in correctional settings. Multicomponent programs, which include several preventive activities, seem to be most effective in reducing suicide deaths. Future evaluation studies should control for confounding variables by including control groups, having larger samples and limiting attrition. Standards for suicide prevention in jails and prisons should be included in National suicide prevention strategies.FundingNone.
| S-EPMC9309412 | biostudies-literature
Project description:Suicide is a leading cause of death in the young adult population, with few biological markers identified thus far to be associated with suicidality. Cytokines (including IL-6 and TNFα) may contribute to increased risk for depression and suicidality. Few studies have examined the associations of cytokine mRNA expression with depression and suicidal ideation and behavior. This study examines these associations and whether cytokine signaling networks differentiate suicide attempters (SA), suicide ideators (SI), and healthy controls (HC). Cytokine pathway marker (CPM; e.g. cytokines and proteins in cytokine signaling pathways) mRNA gene expression in whole blood was examined in suicide attempters (n = 38), suicide ideators (n = 38), and healthy controls (n = 36). Between-group differences in CPM gene expression were examined. We also examined association of the mRNA of these genes with the severity of depression and suicidal ideation. Novel Gaussian Graphical Model (GGM) techniques were utilized to examine between-network partial correlation differences in cytokine signaling networks relevant to IL-6 and TNFα signaling pathways. The severity of depression symptoms was positively associated with TNFα mRNA levels and negatively associated with IL-10 mRNA levels, but CPM expression was not associated with suicidal ideation severity. There were no between-group differences in CPM markers among healthy controls, SI and SA groups after correcting for multiple comparisons. In network analyses, we found suggestive results of between-group network differences between SI and control groups in gene pairs with IL-6R and STAT3 as common nodes. In a cohort of suicide attempters and ideators, TNFα and IL-10 mRNA levels appear to be associated with depressive symptomology, consistent with elevation of pro-inflammatory cytokine production and reduction of anti-inflammatory cytokine production. Additionally, cytokine signaling networks may differentiate suicide ideators from healthy controls based on between-network differences, with differences possibly related to relationships of IL6R or STAT3 with other components of cytokine signaling networks.
| S-EPMC8009526 | biostudies-literature
Project description:Suicide and suicide attempts are complex behaviors that result from the interaction of different factors, including genetic variants that increase the predisposition to suicidal behaviors. Copy number variations (CNVs) are deletions or duplications of a segment of DNA usually larger than one kilobase. These structural genetic changes, although quite rare, have been associated with genetic liability to mental disorders, such as autism, schizophrenia, and bipolar disorder. No genome-wide level studies have been published investigating the potential role of CNVs in suicidal behaviors. Based on single-nucleotide polymorphism array data, we followed the Penn-CNV standards to detect CNVs in 1,608 subjects, comprising 475 suicide and suicide attempt cases and 1,133 controls. Although the initial algorithms determined the presence of CNVs on chromosomes 6 and 12 in seven and eight cases, respectively, compared with none of the controls, visual inspection of the raw data did not support this finding. Furthermore we were unable to validate these findings by CNV-specific real-time polymerase chain reaction. Additionally, rare CNV burden analysis did not find an association between the frequency or length of rare CNVs and suicidal behavior in our sample population. Although our findings suggest CNVs do not play an important role in the etiology of suicidal behaviors, they are not inconsistent with the strong evidence from the literature suggesting that other genetic variants account for a portion of the total phenotypic variability in suicidal behavior.
2015-04-17 | E-MTAB-3519 | biostudies-arrayexpress
Project description:The convergence of smart technologies and predictive modelling in prisons presents an exciting opportunity to revolutionize the monitoring of inmate behaviour, allowing for the early detection of signs of distress and the effective mitigation of suicide risks. While machine learning algorithms have been extensively employed in predicting suicidal behaviour, a critical aspect that has often been overlooked is the interoperability of these models. Most of the work done on model interpretations for suicide predictions often limits itself to feature reduction and highlighting important contributing features only. To address this research gap, we used Anchor explanations for creating human-readable statements based on simple rules, which, to our knowledge, have never been used before for suicide prediction models. We also overcome the limitation of anchor explanations, which create weak rules on high-dimensionality datasets, by first reducing data features with the help of SHapley Additive exPlanations (SHAP). We further reduce data features through anchor interpretations for the final ensemble model of XGBoost and random forest. Our results indicate significant improvement when compared with state-of-the-art models, having an accuracy and precision of 98.6% and 98.9%, respectively. The F1-score for the best suicide ideation model appeared to be 96.7%.
| S-EPMC11232594 | biostudies-literature
Project description:Computer vision and classification methods have become increasingly wide-spread in recent years due to ever-increasing access to computation power. Advances in semiconductor devices are the basis for this growth, but few publications have probed the benefits of data-driven methods for improving a critical component of semiconductor manufacturing, the detection and inspection of defects for such devices. As defects become smaller, intensity threshold-based approaches eventually fail to adequately discern differences between faulty and non-faulty structures. To overcome these challenges we present machine learning methods including convolutional neural networks (CNN) applied to image-based defect detection. These images are formed from the simulated scattering of realistic geometries with and without key defects while also taking into account line edge roughness (LER). LER is a known and challenging problem in fabrication as it yields additional scattering that further complicates defect inspection. Simulating images of an intentional defect array, a CNN approach is applied to extend detectability and enhance classification to these defects, even those that are more than 20 times smaller than the inspection wavelength.
| S-EPMC6902446 | biostudies-literature
Project description:Numerous breast cancer risk assessment tools that allow users to input personal risk information and obtain a personalized breast cancer risk estimate are available on the Internet. The goal of these tools is to increase screening awareness and identify modifiable health behaviors; however, the utility of this risk information is limited by the readability of the material. We undertook this study to assess the overall readability of breast cancer risk assessment tools and accompanying information, as well as to identify areas of suggested improvement. We searched for breast cancer risk assessment tools, using five search terms, on three search engines. All searches were performed on June 12, 2014. Sites that met inclusion criteria were then assessed for readability using the suitability assessment of materials (SAM) and the SMOG readability formula (July 1, 2014–January 31, 2015). The primary outcomes are the frequency distribution of overall SAM readability category (superior, adequate, or not suitable) and mean SMOG reading grade level. The search returned 42 sites were eligible for assessment, only 9 (21.4 %) of which achieved an overall SAM superior rating, and 27 (64.3 %) were deemed adequate. The average SMOG reading grade level was grade 12.1 (SD 1.6, range 9–15). The readability of breast cancer risk assessment tools and the sites that host them is an important barrier to risk communication. This study demonstrates that most breast cancer risk assessment tools are not accessible to individuals with limited health literacy skills. More importantly, this study identifies potential areas of improvement and has the potential to heighten a physician’s awareness of the Internet resources a patient might navigate in their quest for breast cancer risk information.
| S-EPMC4621697 | biostudies-other