Machine learning for identifying Randomized Controlled Trials: An evaluation and practitioner's guide.
Ontology highlight
ABSTRACT:
SUBMITTER: Marshall IJ
PROVIDER: S-EPMC6030513 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We focused on building models that incorporated transcription factor (TF)-DNA interaction data for 12 members of the Auxin Response Factor (ARF) family from soybean as assessed by DNA Affinity Purification and sequencing (DAP-seq).
2023-06-01 | GSE193400 | GEO
Project description:ObjectiveWe help identify subpopulations underrepresented in randomized clinical trials (RCTs) cohorts with respect to national, community-based or health system target populations by formulating population representativeness of RCTs as a machine learning (ML) fairness problem, deriving new representation metrics, and deploying them in easy-to-understand interactive visualization tools.Materials and methodsWe represent RCT cohort enrollment as random binary classification fairness problems, and then show how ML fairness metrics based on enrollment fraction can be efficiently calculated using easily computed rates of subpopulations in RCT cohorts and target populations. We propose standardized versions of these metrics and deploy them in an interactive tool to analyze 3 RCTs with respect to type 2 diabetes and hypertension target populations in the National Health and Nutrition Examination Survey.ResultsWe demonstrate how the proposed metrics and associated statistics enable users to rapidly examine representativeness of all subpopulations in the RCT defined by a set of categorical traits (eg, gender, race, ethnicity, smoking status, and blood pressure) with respect to target populations.DiscussionThe normalized metrics provide an intuitive standardized scale for evaluating representation across subgroups, which may have vastly different enrollment fractions and rates in RCT study cohorts. The metrics are beneficial complements to other approaches (eg, enrollment fractions) used to identify generalizability and health equity of RCTs.ConclusionBy quantifying the gaps between RCT and target populations, the proposed methods can support generalizability evaluation of existing RCT cohorts. The interactive visualization tool can be readily applied to identified underrepresented subgroups with respect to any desired source or target populations.
| S-EPMC8460438 | biostudies-literature
Project description:Biomarkers associated with treatment-effect heterogeneity can be used to make treatment recommendations that optimize individual clinical outcomes. To accomplish this, statistical methods are needed to generate marker-based treatment-selection rules that can most effectively reduce the population burden due to disease and treatment. Compared to the standard approach of risk modeling to derive treatment-selection rules, a more robust approach is to directly minimize an unbiased estimate of total disease and treatment burden among a pre-specified class of rules. This problem is one of minimizing a weighted sum of 0-1 loss function, which is computationally challenging to solve due to the nonsmoothness of 0-1 loss. Huang and Fong, among others, proposed a method that uses the Ramp loss to approximate the 0-1 loss and solves the minimization problem through repetitive constrained optimizations. The algorithm was shown to have comparable or better performance than other comparative estimators in various settings. Our aim in this article is to further extend the algorithm to allow for variable selection in the presence of a large number of candidate markers.We develop an alternative method to derive marker combinations to minimize the weighted sum of Ramp loss in Huang and Fong, based on data from randomized trials. The new algorithm estimates treatment-selection rules by repetitively minimizing a smooth and differentiable objective function. Through the use of an L1 penalty, we expand the method to allow for feature selection and develop an algorithm based on the coordinate descent method to build the treatment-selection rule.Through extensive simulation studies, we compared performance of the proposed estimator to four existing approaches: (1) a logistic regression risk modeling approach, and three other "direct optimizing" approaches including (2) the estimator in Huang and Fong, (3) the weighted support vector machine, and (4) the weighted logistic regression. The proposed estimator performs comparably to that of Huang and Fong, and comparably or better than other estimators. Allowing for variable selection using the proposed estimator in the presence of a large number of markers further improves treatment-selection performance. The proposed estimator is also advantageous for selecting variables relevant to treatment selection compared to L1 penalized logistic regression and weighted logistic regression. We illustrate the application of the proposed methods in host-genetics data from an HIV vaccine trial.The proposed estimator is appealing considering its effectiveness and conceptual simplicity. It has significant potential to contribute to the selection and combination of biomarkers for treatment selection in clinical practice.
| S-EPMC4506270 | biostudies-literature
Project description:IntroductionHealth disparities arise from biological-environmental interactions. Neuroimaging cohorts are reaching sufficiently large sample sizes such that analyses could evaluate how the environment affects the brain. We present a practical guide for applying geospatial methods to a neuroimaging cohort.MethodsWe estimated brain age gap (BAG) from structural magnetic resonance imaging (MRI) from 239 city-dwelling participants in St. Louis, Missouri. We compared these participants to population-level estimates from the American Community Survey (ACS). We used geospatial analysis to identify neighborhoods associated with patterns of altered brain structure. We also evaluated the relationship between Area Deprivation Index (ADI) and BAG.ResultsWe identify areas in St. Louis, Missouri that were significantly associated with higher BAG from a spatially representative cohort. We provide replication code.ConclusionWe observe a relationship between neighborhoods and brain health, which suggests that neighborhood-based interventions could be appropriate. We encourage other studies to geocode participant information to evaluate biological-environmental interaction.
| S-EPMC10019584 | biostudies-literature
Project description:One-size-fits-all interventions that aim to change behavior are a missed opportunity to improve human health and well-being, as they do not target the different reasons that drive people's choices and behaviors. Psycho-behavioral segmentation is an approach to uncover such differences and enable the design of targeted interventions, but is rarely implemented at scale in global development. In part, this may be due to the many choices program designers and data scientists face, and the lack of available guidance through the process. Effective segmentation encompasses conceptualization and selection of the dimensions to segment on, which often requires the design of suitable qualitative and quantitative primary research. The choice of algorithm and its parameters also profoundly shape the resulting output and how useful the results are in the field. Analytical outputs are not self-explanatory and need to be subjectively evaluated and described. Finally, segments can be prioritized and targeted with matching interventions via appropriate channels. Here, we provide an end-to-end overview of all the stages from planning, designing field-based research, analyzing, and implementing a psycho-behavioral segmentation solution. We illustrate the choices and critical steps along the way, and discuss a case study of segmentation for voluntary medical male circumcision that implemented the method described here. Though our examples mostly draw on health interventions in the developing world, the principles in this approach can be used in any context where understanding human heterogeneity in driving behavior change is valuable.
| S-EPMC6820452 | biostudies-literature
Project description:BackgroundCluster randomized trials (CRTs) are becoming an increasingly important design. However, authors of CRTs do not always adhere to requirements to explicitly identify the design as cluster randomized in titles and abstracts, making retrieval from bibliographic databases difficult. Machine learning algorithms may improve their identification and retrieval. Therefore, we aimed to develop machine learning algorithms that accurately determine whether a bibliographic citation is a CRT report.MethodsWe trained, internally validated, and externally validated two convolutional neural networks and one support vector machine (SVM) algorithm to predict whether a citation is a CRT report or not. We exclusively used the information in an article citation, including the title, abstract, keywords, and subject headings. The algorithms' output was a probability from 0 to 1. We assessed algorithm performance using the area under the receiver operating characteristic (AUC) curves. Each algorithm's performance was evaluated individually and together as an ensemble. We randomly selected 5000 from 87,633 citations to train and internally validate our algorithms. Of the 5000 selected citations, 589 (12%) were confirmed CRT reports. We then externally validated our algorithms on an independent set of 1916 randomized trial citations, with 665 (35%) confirmed CRT reports.ResultsIn internal validation, the ensemble algorithm discriminated best for identifying CRT reports with an AUC of 98.6% (95% confidence interval: 97.8%, 99.4%), sensitivity of 97.7% (94.3%, 100%), and specificity of 85.0% (81.8%, 88.1%). In external validation, the ensemble algorithm had an AUC of 97.8% (97.0%, 98.5%), sensitivity of 97.6% (96.4%, 98.6%), and specificity of 78.2% (75.9%, 80.4%)). All three individual algorithms performed well, but less so than the ensemble.ConclusionsWe successfully developed high-performance algorithms that identified whether a citation was a CRT report with high sensitivity and moderately high specificity. We provide open-source software to facilitate the use of our algorithms in practice.
| S-EPMC9594883 | biostudies-literature
Project description:Machine learning is a field of computer science that builds algorithms that learn. In many cases, machine learning algorithms are used to recreate a human ability like adding a caption to a photo, driving a car, or playing a game. While the human brain has long served as a source of inspiration for machine learning, little effort has been made to directly use data collected from working brains as a guide for machine learning algorithms. Here we demonstrate a new paradigm of "neurally-weighted" machine learning, which takes fMRI measurements of human brain activity from subjects viewing images, and infuses these data into the training process of an object recognition learning algorithm to make it more consistent with the human brain. After training, these neurally-weighted classifiers are able to classify images without requiring any additional neural data. We show that our neural-weighting approach can lead to large performance gains when used with traditional machine vision features, as well as to significant improvements with already high-performing convolutional neural network features. The effectiveness of this approach points to a path forward for a new class of hybrid machine learning algorithms which take both inspiration and direct constraints from neuronal data.
| S-EPMC5876362 | biostudies-literature
Project description:To answer frequently asked questions surrounding the use of the new herpes zoster (HZ) vaccine.Published results of clinical trials and other studies, recommendations from the Canadian National Advisory Committee on Immunization, and the US Advisory Committee on Immunization Practices; data were also obtained from the vaccine's Health Canada-approved product monograph.Herpes zoster results from reactivation of the varicella-zoster virus; postherpetic neuralgia (PHN) is its most common and serious complication. The incidence of PHN after HZ is directly related to age, with 50% of affected individuals older than 60 years experiencing persistent and unrelieved pain. The live virus HZ vaccine reduces the incidence of HZ by about 50% and the occurrence of PHN by two-thirds, with vaccinated individuals experiencing attenuated or shortened symptoms. The vaccine is contraindicated in many immunocompromised patients and might not be effective in patients taking antiviral medications active against the HZ virus. Physicians should be aware of the different recommendations for these groups.The HZ vaccine is a safe and effective preventive measure for reducing the overall burden and severity of HZ in older adults. The vaccine appears to be cost-effective when administered to adults aged 60 years and older.
| S-EPMC3192074 | biostudies-other
Project description:Latent class analysis is a probabilistic modeling algorithm that allows clustering of data and statistical inference. There has been a recent upsurge in the application of latent class analysis in the fields of critical care, respiratory medicine, and beyond. In this review, we present a brief overview of the principles behind latent class analysis. Furthermore, in a stepwise manner, we outline the key processes necessary to perform latent class analysis including some of the challenges and pitfalls faced at each of these steps. The review provides a one-stop shop for investigators seeking to apply latent class analysis to their data.
| S-EPMC7746621 | biostudies-literature
Project description:BackgroundAtopic dermatitis (AD) is a heterogeneous disease with a multifactorial aetiology and complex pathophysiology. This heterogeneity translates into different trajectories of disease progression with respect to severity, persistence and risk of development of atopic comorbidities. Determining which possible disease trajectories or comorbidities any individual child might develop is challenging in clinical practice. Tools that help identify paediatric patients at higher risk of disease progression would greatly aid clinicians.MethodsWe reviewed recent cohort studies to synthesize and simplify the epidemiological data to try to identify shared clinically relevant characteristics that may help physicians estimate the risk of disease progression in paediatric patients with AD.ResultsDespite the variability in data collection and methods of analysis and their limitations, there are common patterns of early-childhood AD that may aid in the estimation of risk for disease progression. Factors associated with risk of AD progression include younger age of onset, family history of atopy, greater AD severity, filaggrin mutations, urban environment and polysensitization and/or allergic multimorbidity. Based on these factors, we provide a practitioner's guide for identifying, counselling and/or referring infants and children with AD at potentially higher risk of developing persistent AD and atopic comorbidities. We also present clinical scenarios to illustrate how these data relate to real-life situations.ConclusionsUseful insights are provided for physicians and patients to inform them better about the risk of AD progression and to help guide care pathways for the paediatric population with AD. What's already known about this topic? The complex pathophysiology of atopic dermatitis (AD) translates into a heterogeneous clinical presentation and trajectories of disease progression. Although the consensus is that most paediatric patients with AD will eventually 'outgrow' the disease or follow the longitudinal trajectory known as the 'atopic march', a significant proportion will develop persistent AD and/or other atopic conditions. No known factors conclusively predict the risk of progression or development of comorbidities. What does this study add? Recent analyses of data from large cohorts of paediatric patients with AD have suggested the existence of potentially discrete clusters of patients who present with relatively common AD phenotypes. These studies have shed some light onto the factors associated with risk of progression, which we review in this article. A practitioner's guide with clinical scenarios is provided to help identify patients at high risk of progression to determine whether a patient should be monitored and/or would require specialist referral.
| S-EPMC6899789 | biostudies-literature