Using categorical data analyses in suicide research: Considering clinical utility and practicality.
Ontology highlight
ABSTRACT: Objective
Categorical data analysis is relevant to suicide risk and prevention research that focuses on discrete outcomes (e.g., suicide attempt status). Unfortunately, results from these analyses are often misinterpreted and not presented in a clinically tangible manner. We aimed to address these issues and highlight the relevance and utility of categorical methods in suicide research and clinical assessment. Additionally, we introduce relevant basic machine learning methods concepts and address the distinct utility of the current methods.Method
We review relevant background concepts and pertinent issues with references to helpful resources. We also provide non-technical descriptions and tutorials of how to convey categorical statistical results (logistic regression, receiver operating characteristic [ROC] curves, area under the curve [AUC] statistics, clinical cutoff scores) for clinical context and more intuitive use.Results
We provide comprehensive examples, using simulated data, and interpret results. We also note important considerations for conducting and interpreting these analyses. We provide a walk-through demonstrating how to convert logistic regression estimates into predicted probability values, which is accompanied by Appendices demonstrating how to produce publication-ready figures in R and Microsoft Excel.Conclusion
Improving the translation of statistical estimates to practical, clinically tangible information may narrow the divide between research and clinical practice.
SUBMITTER: Mitchell SM
PROVIDER: S-EPMC7995491 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND:Data standardization is essential in electronic health records (EHRs) for both clinical practice and retrospective research. However, it is still not easy to standardize EHR data because of nonidentical duplicates, typographical errors, or inconsistencies. To overcome this drawback, standardization efforts have been undertaken for collecting data in a standardized format as well as for curating the stored data in EHRs. To perform clinical big data research, the stored data in EHR should be standardized, starting from laboratory results, given their importance. However, most of the previous efforts have been based on labor-intensive manual methods. OBJECTIVE:We aimed to develop an automatic standardization method for eliminating the noises of categorical laboratory data, grouping, and mapping of cleaned data using standard terminology. METHODS:We developed a method called standardization algorithm for laboratory test-categorical result (SALT-C) that can process categorical laboratory data, such as pos +, 250 4+ (urinalysis results), and reddish (urinalysis color results). SALT-C consists of five steps. First, it applies data cleaning rules to categorical laboratory data. Second, it categorizes the cleaned data into 5 predefined groups (urine color, urine dipstick, blood type, presence-finding, and pathogenesis tests). Third, all data in each group are vectorized. Fourth, similarity is calculated between the vectors of data and those of each value in the predefined value sets. Finally, the value closest to the data is assigned. RESULTS:The performance of SALT-C was validated using 59,213,696 data points (167,938 unique values) generated over 23 years from a tertiary hospital. Apart from the data whose original meaning could not be interpreted correctly (eg, ** and _^), SALT-C mapped unique raw data to the correct reference value for each group with accuracy of 97.6% (123/126; urine color tests), 97.5% (198/203; (urine dipstick tests), 95% (53/56; blood type tests), 99.68% (162,291/162,805; presence-finding tests), and 99.61% (4643/4661; pathogenesis tests). CONCLUSIONS:The proposed SALT-C successfully standardized the categorical laboratory test results with high reliability. SALT-C can be beneficial for clinical big data research by reducing laborious manual standardization efforts.
| S-EPMC6740165 | biostudies-literature
Project description:ObjectivesDespite the common use of contagion to analogize the spread of suicide, there is a lack of rigorous assessment of the underlying concept or theory supporting the use of this term. The present study aims to examine the varied definitions and potential utility of the term contagion in suicide-related research.Methods100 initial records and 240 reference records in English were identified as relevant with our research objectives, through systematic literature screening. We then conducted narrative syntheses of various definitions and assessed their potential value for generating new research.Results20.3% of the 340 records used contagion as equivalent to clustering (contagion-as-cluster); 68.5% used it to refer to various, often related mechanisms underlying the clustering phenomenon (contagion-as-mechanism); and 11.2% without clear definition. Under the category of contagion-as-mechanism, four mechanisms have been proposed to explain how suicide clusters occurred: transmission (contagion-as-transmission), imitation (contagion-as-imitation), contextual influence (contagion-as-context), and affiliation (contagion-as-affiliation). Contagion-as-cluster both confounds and constrains inquiry into suicide clustering by blending proposed mechanism with the phenomenon to be studied. Contagion-as-transmission is, in essence, a double or internally redundant metaphor. Contagion-as-affiliation and contagion-as-context involve mechanisms that are common mechanisms that often occur independently of apparent contagion, or may serve as a facilitating background. When used indiscriminately, these terms may create research blind spots. Contagion-as-imitation combines perspectives from psychology, sociology, and public health research and provides the greatest heuristic utility for examining whether and how suicide and suicidal behaviors may spread among persons at both individual and population levels.ConclusionClarifying the concept of "suicide contagion" is an essential step for more thoroughly investigating its mechanisms. Developing a clearer understanding of the apparent spread of suicide-promoting influences can, in turn, offer insights necessary to build the scientific foundation for prevention and intervention strategies that can be applied at both individual and community levels.
| S-EPMC4178222 | biostudies-literature
Project description:OBJECTIVE:The objective of this study was to assess the potential of combining graph learning methods with latent variable estimation methods for mining clinically useful information from observational clinical data sets. MATERIALS AND METHODS:The data set contained self-reported measures of psychopathology symptoms from a clinical sample receiving treatment for alcohol use disorder. We used the traditional graph learning methods: Graphical Least Absolute Shrinkage and Selection Operator, and Friedman's hill climbing algorithm; traditional latent variable estimation method factor analysis; recently developed graph learning method Greedy Fast Causal Inference; and recently developed latent variable estimation method Find One Factor Clusters. Methods were assessed qualitatively by the content of their findings. RESULTS:Recently developed graphical methods identified potential latent variables (ie, not represented in the model) influencing particular scores. Recently developed latent effect estimation methods identified plausible cross-score loadings that were not found with factor analysis. A graphical analysis of individual items identified a mistake in wording on 1 questionnaire and provided further evidence that certain scores are not reflective of indirectly measured common causes. DISCUSSION AND CONCLUSION:Our findings suggest that a combination of Greedy Fast Causal Inference and Find One Factor Clusters can enhance the evidence-based information yield from psychopathological constructs and questionnaires. Traditional methods provided some of the same information but missed other important findings. These conclusions point the way toward more informative interrogations of existing and future data sets than are commonly employed at present.
| S-EPMC6748805 | biostudies-literature
Project description:Mobile phone location data is a newly emerging data source of great potential to support human mobility research. However, recent studies have indicated that many users can be easily re-identified based on their unique activity patterns. Privacy protection procedures will usually change the original data and cause a loss of data utility for analysis purposes. Therefore, the need for detailed data for activity analysis while avoiding potential privacy risks presents a challenge. The aim of this study is to reveal the re-identification risks from a Chinese city's mobile users and to examine the quantitative relationship between re-identification risk and data utility for an aggregated mobility analysis. The first step is to apply two reported attack models, the top N locations and the spatio-temporal points, to evaluate the re-identification risks in Shenzhen City, a metropolis in China. A spatial generalization approach to protecting privacy is then proposed and implemented, and spatially aggregated analysis is used to assess the loss of data utility after privacy protection. The results demonstrate that the re-identification risks in Shenzhen City are clearly different from those in regions reported in Western countries, which prove the spatial heterogeneity of re-identification risks in mobile phone location data. A uniform mathematical relationship has also been found between re-identification risk (x) and data (y) utility for both attack models: y = -axb+c, (a, b, c>0; 0<x<1), where the exponent b increases with the background knowledge of the attackers. The discovered mathematical relationship provides data publishers with useful guidance on choosing the right tradeoff between privacy and utility. Overall, this study contributes to a better understanding of re-identification risks and a privacy-utility tradeoff benchmark for improving privacy protection when sharing detailed trajectory data.
| S-EPMC4607417 | biostudies-literature
Project description:In population pharmacokinetic analyses, missing categorical data are often encountered. We evaluated several methods of performing covariate analyses with partially missing categorical covariate data. Missing data methods consisted of discarding data (DROP), additional effect parameter for the group with missing data (EXTRA), and mixture methods in which the mixing probability was fixed to the observed fraction of categories (MIX(obs)), based on the likelihood of the concentration data (MIX(conc)), or combined likelihood of observed covariate data and concentration data (MIX(joint)). Simulations were implemented to study bias and imprecision of the methods in datasets with equal-sized and unbalanced category ratios for a binary covariate as well as datasets with non-random missingness (MNAR). Additionally, the performance and feasibility of implementation was assessed in two real datasets. At either low (10%) or high (50%) levels of missingness, all methods performed similarly well. Performance was similar for situations with unbalanced datasets (3:1 covariate distribution) and balanced datasets. In the MNAR scenario, the MIX methods showed a higher bias in the estimation of CL and covariate effect than EXTRA. All methods could be applied to real datasets, except DROP. All methods perform similarly at the studied levels of missingness, but the DROP and EXTRA methods provided less bias than the mixture methods in the case of MNAR. However, EXTRA was associated with inflated type I error rates of covariate selection, while DROP handled data inefficiently.
| S-EPMC3385822 | biostudies-other
Project description:BackgroundPrediction and classification algorithms are commonly used in clinical research for identifying patients susceptible to clinical conditions such as diabetes, colon cancer, and Alzheimer's disease. Developing accurate prediction and classification methods benefits personalized medicine. Building an excellent predictive model involves selecting the features that are most significantly associated with the outcome. These features can include several biological and demographic characteristics, such as genomic biomarkers and health history. Such variable selection becomes challenging when the number of potential predictors is large. Bayesian shrinkage models have emerged as popular and flexible methods of variable selection in regression settings. This work discusses variable selection with three shrinkage priors and illustrates its application to clinical data such as Pima Indians Diabetes, Colon cancer, ADNI, and OASIS Alzheimer's real-world data.MethodsA unified Bayesian hierarchical framework that implements and compares shrinkage priors in binary and multinomial logistic regression models is presented. The key feature is the representation of the likelihood by a Polya-Gamma data augmentation, which admits a natural integration with a family of shrinkage priors, specifically focusing on Horseshoe, Dirichlet Laplace, and Double Pareto priors. Extensive simulation studies are conducted to assess the performances under different data dimensions and parameter settings. Measures of accuracy, AUC, brier score, L1 error, cross-entropy, and ROC surface plots are used as evaluation criteria comparing the priors with frequentist methods as Lasso, Elastic-Net, and Ridge regression.ResultsAll three priors can be used for robust prediction on significant metrics, irrespective of their categorical response model choices. Simulation studies could achieve the mean prediction accuracy of 91.6% (95% CI: 88.5, 94.7) and 76.5% (95% CI: 69.3, 83.8) for logistic regression and multinomial logistic models, respectively. The model can identify significant variables for disease risk prediction and is computationally efficient.ConclusionsThe models are robust enough to conduct both variable selection and prediction because of their high shrinkage properties and applicability to a broad range of classification problems.
| S-EPMC9046716 | biostudies-literature
Project description:IntroductionSuicide has a complex aetiology and is a result of the interaction among the risk and protective factors at the individual, healthcare system and population levels. Therefore, policy and decision makers and mental health service planners can play an important role in suicide prevention. Although a number of suicide risk predictive tools have been developed, these tools were designed to be used by clinicians for assessing individual risk of suicide. There have been no risk predictive models to be used by policy and decision makers for predicting population risk of suicide at the national, provincial and regional levels. This paper aimed to describe the rationale and methodology for developing risk predictive models for population risk of suicide.Methods and analysisA case-control study design will be used to develop sex-specific risk predictive models for population risk of suicide, using statistical regression and machine learning techniques. Routinely collected health administrative data in Quebec, Canada, and community-level social deprivation and marginalisation data will be used. The developed models will be transformed into the models that can be readily used by policy and decision makers. Two rounds of qualitative interviews with end-users and other stakeholders were proposed to understand their views about the developed models and potential systematic, social and ethical issues for implementation; the first round of qualitative interviews has been completed. We included 9440 suicide cases (7234 males and 2206 females) and 661 780 controls for model development. Three hundred and forty-seven variables at individual, healthcare system and community levels have been identified and will be included in least absolute shrinkage and selection operator regression for feature selection.Ethics and disseminationThis study is approved by the Health Research Ethnics Committee of Dalhousie University, Canada. This study takes an integrated knowledge translation approach, involving knowledge users from the beginning of the process.
| S-EPMC9972456 | biostudies-literature
Project description:A general utility-based testing methodology for design and conduct of randomized comparative clinical trials with categorical outcomes is presented. Numerical utilities of all elementary events are elicited to quantify their desirabilities. These numerical values are used to map the categorical outcome probability vector of each treatment to a mean utility, which is used as a one-dimensional criterion for constructing comparative tests. Bayesian tests are presented, including fixed sample and group sequential procedures, assuming Dirichlet-multinomial models for the priors and likelihoods. Guidelines are provided for establishing priors, eliciting utilities, and specifying hypotheses. Efficient posterior computation is discussed, and algorithms are provided for jointly calibrating test cutoffs and sample size to control overall type I error and achieve specified power. Asymptotic approximations for the power curve are used to initialize the algorithms. The methodology is applied to re-design a completed trial that compared two chemotherapy regimens for chronic lymphocytic leukemia, in which an ordinal efficacy outcome was dichotomized, and toxicity was ignored to construct the trial's design. The Bayesian tests also are illustrated by several types of categorical outcomes arising in common clinical settings. Freely available computer software for implementation is provided. Copyright © 2016 John Wiley & Sons, Ltd.
| S-EPMC5048520 | biostudies-literature
Project description:It is essential that investigators in clinical research settings follow ethical guidelines for monitoring, assessing, and responding to suicide risk. Given the unique considerations associated with suicide risk assessment in a research context, resources informing the development of research-specific suicide risk management procedures are needed. With decades of collective experience across heterogeneous contexts, we discuss approaches to monitoring, assessing, and responding to suicide risk as a function of study sample (e.g., students, psychiatric inpatients), data collection methodologies (e.g., interview, self-report, or ecological momentary assessment), and study design (e.g., treatment research). Additional considerations include training and supervision of staff to identify suicide risk, coordination of others to respond to risk, and documentation of procedures. Finally, we attend to the impact of these procedures on the external validity of outcome data. (PsycINFO Database Record (c) 2019 APA, all rights reserved).
| S-EPMC7227801 | biostudies-literature
Project description:ObjectiveThe purpose of this research is to identify how data science is applied in suicide prevention literature, describe the current landscape of this literature and highlight areas where data science may be useful for future injury prevention research.DesignWe conducted a literature review of injury prevention and data science in April 2020 and January 2021 in three databases.MethodsFor the included 99 articles, we extracted the following: (1) author(s) and year; (2) title; (3) study approach (4) reason for applying data science method; (5) data science method type; (6) study description; (7) data source and (8) focus on a disproportionately affected population.ResultsResults showed the literature on data science and suicide more than doubled from 2019 to 2020, with articles with individual-level approaches more prevalent than population-level approaches. Most population-level articles applied data science methods to describe (n=10) outcomes, while most individual-level articles identified risk factors (n=27). Machine learning was the most common data science method applied in the studies (n=48). A wide array of data sources was used for suicide research, with most articles (n=45) using social media and web-based behaviour data. Eleven studies demonstrated the value of applying data science to suicide prevention literature for disproportionately affected groups.ConclusionData science techniques proved to be effective tools in describing suicidal thoughts or behaviour, identifying individual risk factors and predicting outcomes. Future research should focus on identifying how data science can be applied in other injury-related topics.
| S-EPMC9161307 | biostudies-literature