scholarly journals Knowledge translation of prediction rules: methods to help health professionals understand their trade-offs

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
K. Hemming ◽  
M. Taljaard
Keyword(s):  
Knowledge Translation ◽  
Health Professionals ◽  
Natural Frequencies ◽  
Prediction Models ◽  
Prediction Rule ◽  
Performance Measure ◽  
Essential Information ◽  
Prediction Rules ◽  
Cut Points ◽  
Trade Offs

AbstractClinical prediction models are developed with the ultimate aim of improving patient outcomes, and are often turned into prediction rules (e.g. classifying people as low/high risk using cut-points of predicted risk) at some point during the development stage. Prediction rules often have reasonable ability to either rule-in or rule-out disease (or another event), but rarely both. When a prediction model is intended to be used as a prediction rule, conveying its performance using the C-statistic, the most commonly reported model performance measure, does not provide information on the magnitude of the trade-offs. Yet, it is important that these trade-offs are clear, for example, to health professionals who might implement the prediction rule. This can be viewed as a form of knowledge translation. When communicating information on trade-offs to patients and the public there is a large body of evidence that indicates natural frequencies are most easily understood, and one particularly well-received way of depicting the natural frequency information is to use population diagrams. There is also evidence that health professionals benefit from information presented in this way.Here we illustrate how the implications of the trade-offs associated with prediction rules can be more readily appreciated when using natural frequencies. We recommend that the reporting of the performance of prediction rules should (1) present information using natural frequencies across a range of cut-points to inform the choice of plausible cut-points and (2) when the prediction rule is recommended for clinical use at a particular cut-point the implications of the trade-offs are communicated using population diagrams. Using two existing prediction rules, we illustrate how these methods offer a means of effectively and transparently communicating essential information about trade-offs associated with prediction rules.

scholarly journals A new approach to categorising continuous variables in prediction models: Proposal and validation

2015 ◽  
Vol 26 (6) ◽  
pp. 2586-2602 ◽  
Author(s):  
Irantzu Barrio ◽  
Inmaculada Arostegui ◽  
María-Xosé Rodríguez-Álvarez ◽  
José-María Quintana
Keyword(s):  
Prediction Models ◽  
Characteristic Curve ◽  
Prediction Rule ◽  
Real Data ◽  
Clinical Variable ◽  
Chronic Obstructive ◽  
Continuous Variables ◽  
Discriminative Ability ◽  
Data Set ◽  
Statistical Point

When developing prediction models for application in clinical practice, health practitioners usually categorise clinical variables that are continuous in nature. Although categorisation is not regarded as advisable from a statistical point of view, due to loss of information and power, it is a common practice in medical research. Consequently, providing researchers with a useful and valid categorisation method could be a relevant issue when developing prediction models. Without recommending categorisation of continuous predictors, our aim is to propose a valid way to do it whenever it is considered necessary by clinical researchers. This paper focuses on categorising a continuous predictor within a logistic regression model, in such a way that the best discriminative ability is obtained in terms of the highest area under the receiver operating characteristic curve (AUC). The proposed methodology is validated when the optimal cut points’ location is known in theory or in practice. In addition, the proposed method is applied to a real data-set of patients with an exacerbation of chronic obstructive pulmonary disease, in the context of the IRYSS-COPD study where a clinical prediction rule for severe evolution was being developed. The clinical variable PCO2 was categorised in a univariable and a multivariable setting.

scholarly journals Consuming sustainable seafood: guidelines, recommendations and realities

2018 ◽  
Vol 21 (8) ◽  
pp. 1503-1514 ◽  
Author(s):  
Anna K Farmery ◽  
Gabrielle O’Kane ◽  
Alexandra McManus ◽  
Bridget S Green
Keyword(s):  
Health Professionals ◽  
Quantitative Data ◽  
Information Needs ◽  
Cost Effective ◽  
Seafood Consumption ◽  
Dietary Recommendations ◽  
Online Questionnaire ◽  
Trade Offs ◽  
Seafood Industry ◽  
Consumption Advice

AbstractObjectiveEncouraging people to eat more seafood can offer a direct, cost-effective way of improving overall health outcomes. However, dietary recommendations to increase seafood consumption have been criticised following concern over the capacity of the seafood industry to meet increased demand, while maintaining sustainable fish stocks. The current research sought to investigate Australian accredited practising dietitians’ (APD) and public health nutritionists’ (PHN) views on seafood sustainability and their dietary recommendations, to identify ways to better align nutrition and sustainability goals.DesignA self-administered online questionnaire exploring seafood consumption advice, perceptions of seafood sustainability and information sources of APD and PHN. Qualitative and quantitative data were collected via open and closed questions. Quantitative data were analysed with χ2 tests and reported using descriptive statistics. Content analysis was used for qualitative data.SettingAustralia.SubjectsAPD and PHN were targeted to participate; the sample includes respondents from urban and regional areas throughout Australia.ResultsResults indicate confusion around the concept of seafood sustainability and where to obtain information, which may limit health professionals’ ability to recommend the best types of seafood to maximise health and sustainability outcomes. Respondents demonstrated limited understanding of seafood sustainability, with 7·5 % (n 6/80) satisfied with their level of understanding.ConclusionsNutrition and sustainability goals can be better aligned by increasing awareness on seafood that is healthy and sustainable. For health professionals to confidently make recommendations, or identify trade-offs, more evidence-based information needs to be made accessible through forums such as dietetic organisations, industry groups and nutrition programmes.

scholarly journals Predictive modelling using pathway scores: robustness and significance of pathway collections

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Marcelo P. Segura-Lepe ◽  
Hector C. Keun ◽  
Timothy M. D. Ebbels
Keyword(s):  
Gene Expression ◽  
Prediction Models ◽  
Disease Status ◽  
Predictive Modelling ◽  
Data Set ◽  
Prediction Rules ◽  
Similar Accuracy ◽  
Robust To Noise ◽  
Pathway Databases ◽  
Gene Expression Levels

Abstract Background Transcriptomic data is often used to build statistical models which are predictive of a given phenotype, such as disease status. Genes work together in pathways and it is widely thought that pathway representations will be more robust to noise in the gene expression levels. We aimed to test this hypothesis by constructing models based on either genes alone, or based on sample specific scores for each pathway, thus transforming the data to a ‘pathway space’. We progressively degraded the raw data by addition of noise and examined the ability of the models to maintain predictivity. Results Models in the pathway space indeed had higher predictive robustness than models in the gene space. This result was independent of the workflow, parameters, classifier and data set used. Surprisingly, randomised pathway mappings produced models of similar accuracy and robustness to true mappings, suggesting that the success of pathway space models is not conferred by the specific definitions of the pathway. Instead, predictive models built on the true pathway mappings led to prediction rules with fewer influential pathways than those built on randomised pathways. The extent of this effect was used to differentiate pathway collections coming from a variety of widely used pathway databases. Conclusions Prediction models based on pathway scores are more robust to degradation of gene expression information than the equivalent models based on ungrouped genes. While models based on true pathway scores are not more robust or accurate than those based on randomised pathways, true pathways produced simpler prediction rules, emphasizing a smaller number of pathways.

scholarly journals Systematic scoping review protocol for clinical prediction rules (CPRs) in the management of patients with spinal cord injuries

BMJ Open ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. e025076 ◽  
Author(s):  
Blake Boggenpoel ◽  
Vuyolwethu Madasa ◽  
Tarryn Jeftha ◽  
Conran Joseph
Keyword(s):  
Spinal Cord ◽  
Scoping Review ◽  
Impact Analysis ◽  
Spinal Cord Injuries ◽  
Prediction Models ◽  
Grey Literature ◽  
Clinical Prediction ◽  
Clinical Prediction Rules ◽  
Prediction Rules ◽  
Review Protocol

IntroductionThe upsurge in the use of clinical prediction models in general medical practice is a result of evidence-based practice. However, the total number of clinical prediction rules (CPRs) currently being used or undergoing impact analysis in the management of patients who have sustained spinal cord injuries (SCIs) is unknown. This scoping review protocol will describe the current CPRs being used and highlight their possible strengths and weaknesses in SCI management.Methods and analysisArksey and O’Malley’s scoping review framework will be used. The following databases will be searched to identify relevant literature relating to the use of CPRs in the management of patients who have sustained an SCI: PubMed, Cumulative Index of Nursing and Allied Health Literature (CINAHL), ScienceDirect, EBSCOhost, Medline, OvidMedline and Google Scholar. Grey literature as well as reference lists of included studies will be searched. All studies relating to the use of CPRs in the management of patients with SCIs will be included. Literature searches and data extraction will be performed independently by two groups of reviewers.Ethics and disseminationEthical clearance is not required for this scoping review study since only secondary data sources will be used. The findings of this review will be disseminated by means of peer-reviewed publication and conference proceedings. The final paper will be submitted for publication. Results of this review will also be presented at relevant conferences and disseminated to important stakeholders such as practicing physicians within specialised spinal care facilities within South Africa.

Modeling of Recast Layer in Micro-Electrical Discharge Machining

2010 ◽  
Vol 132 (3) ◽  
Author(s):  
P. C. Tan ◽  
S. H. Yeo
Keyword(s):  
Numerical Model ◽  
Electrical Discharge ◽  
Prediction Models ◽  
Electrical Discharge Machining ◽  
Performance Measure ◽  
Recast Layer ◽  
Micro Edm ◽  
Machined Surface ◽  
Functional Layer ◽  
Pulse On Time

The thickness of recast layers produced during electrical discharge machining (EDM) is an important process performance measure as it may indicate an extent of crack propagation in a machined surface or thickness of a functional layer alloyed onto a machined surface. Thus, the availability of the recast layer thickness prediction models is needed to allow better control of machining outcomes, which becomes more vital for micro-EDM due to the microscale of machined features. The proposed numerical model, based on a multiple discharge approach for recast layer prediction, is developed to fill an existing gap in micro-EDM. The multiple discharge approach accounts for the overlapping nature by which craters are generated on the machined surface and considers the recast layer to be a combination of individual recast regions from individual craters. The numerical analysis, based on finite element methods, is used to determine the melting isotherms due to heat inputs on overlapping crater profiles. Then, a hemispherical-capped crater profile is estimated by applying a recast plasma flushing efficiency to the amount of molten material bounded by the melting isotherm. Finally, the recast region is defined to be bounded by the melting isotherm and crater profile. The model, developed for a peak discharge current of 1.45 A and pulse on time between 166 ns and 606 ns, predicted recast layer thicknesses of between 1.0 μm and 1.82 μm. It is then validated at pulse on time settings of 244 ns and 458 ns, which generated average recast layer thicknesses of 1.18 μm and 1.56 μm, respectively. Thus, the numerical model developed using the multiple discharge approach is suitable for estimation of recast layer thicknesses in micro-EDM.

Analytical Dynamic Performance Modeling for Individual C-block Actuators

1999 ◽  
Vol 121 (2) ◽  
pp. 221-230 ◽  
Author(s):  
A. J. Moskalik ◽  
D. Brei
Keyword(s):  
Analytical Model ◽  
Performance Modeling ◽  
Natural Frequencies ◽  
Block Design ◽  
Dynamic Performance ◽  
Design Parameters ◽  
Good Match ◽  
Amplitude Response ◽  
Trade Offs ◽  
Analytical Dynamic

C-blocks are mid-range piezoelectric actuators that show promise for use in dynamic applications, such as noise and vibration control. This paper presents an analytical model of an individual C-block actuator, including the identification of the natural frequencies and the description of the amplitude response across the frequency spectrum. In addition, an experimental study with three case studies is presented investigating the accuracy of the model and the sensitivity of the overall dynamic performance to C-block design parameters. The experimental results showed a good match to the analytical model and outlined the trade-offs between displacement amplitude and bandwidth.

The Use of a Clinical Prediction Model and D-Dimer (DD) Testing in the Diagnosis of Deep Vein Thrombosis (DVT): A Systematic Review.

Blood ◽  
2004 ◽  
Vol 104 (11) ◽  
pp. 1052-1052
Author(s):  
Carolyn J. Owen ◽  
Steve Doucette ◽  
Philip S. Wells
Keyword(s):  
High Risk ◽  
High Probability ◽  
Prediction Rule ◽  
Clinical Prediction Rule ◽  
Clinical Prediction ◽  
Clinical Prediction Model ◽  
Prediction Rules ◽  
Clinical Probability ◽  
Probability Estimates ◽  
Low Probability

Abstract Background: The diagnosis of DVT can be made by determining pretest probability of disease and using this information in combination with DD testing and ultrasound imaging. A number of studies have evaluated the use of clinical probability but this literature has not been summarized. Purpose: To systematically review trials that evaluated DVT prevalence using clinical prediction rules either with or without DD for the diagnosis of DVT. Data Sources: English and French language studies were identified from a MEDLINE search from 1990 to March 2004 and were supplemented by a review of all relevant bibliographies. Study Selection: Prospective management studies of symptomatic outpatients with suspected DVT in which patients were followed for a minimum of 3 months were selected. Clinical prediction rules had to be employed prior to DD and diagnostic tests. Studies were excluded if patients with a history of prior DVT were enrolled or if insufficient information was presented to calculate the prevalence of DVT for each of the 3 clinical probability estimates (low, moderate and high risk). Data Extraction: Two reviewers assessed each study for inclusion/exclusion criteria and collected data on prevalence and on sensitivity, specificity and likelihood ratios of DD in each of the 3 clinical probability estimates (low, moderate and high risk). Data Synthesis: 14 management studies involving a clinical prediction model in the diagnosis of DVT in over 8000 patients were included, of which 11 utilized DD in the diagnostic algorithm. All studies employed the same clinical prediction rule. The inverse variance weighted average prevalence of DVT in the low, moderate and high probability subgroups were 4.9% (95% CI= 4.2% to 5.7%), 17.4% (95% CI= 16.2% to 18.8%), and 53.6% (95% CI= 51.1% to 56.2%), respectively. The overall weighted prevalence was 18.3% (95% CI= 17.4% to 19.2%). The sensitivity of DD for the diagnosis of DVT in the low, moderate and high probability subgroups were 90.4% (95% CI= 84.7% to 94.2%), 92.0 % (95% CI= 89.1% to 94.2%), 93.6% (95% CI= 91.2% to 94.3%); and the specificities were 69.9% (95% CI= 68.0% to 71.8%), 52.4% (95% CI= 49.8% to 55.0%), and 43.2% (95% CI= 38.8% to 47.6%), respectively. The Mantel-Haenszel pooled estimates for diagnostic odds ratios (DOR) were 17.4 (95%CI=10.4–29.1), 10.2 (95% CI=7.1–14.6), and 10.1 (95% CI=6.9–14.9) in low, moderate and high groups respectively. Conclusion: Accurate estimates of the prevalence of DVT can be achieved using the same clinical prediction rule. Using this rule, it is unlikely that low probability patients have a DVT probability of more than 5%. Specificity of the DD seems to have clinically relevant differences depending on pretest probability but the DORs (which incorporate sensitivity and specificity) are similar. The data suggest that DVT can be excluded if patients are low probability even when DDs of lower sensitivity are employed and that DD testing has lower utility in high probability patients since false positives are common.

ADJUSTED GEOMETRIC-MEAN: A NOVEL PERFORMANCE MEASURE FOR IMBALANCED BIOINFORMATICS DATASETS LEARNING

2012 ◽  
Vol 10 (04) ◽  
pp. 1250003 ◽  
Author(s):  
RUKSHAN BATUWITA ◽  
VASILE PALADE
Keyword(s):  
Prediction Models ◽  
Geometric Mean ◽  
Recognition Rate ◽  
Class Imbalance ◽  
Performance Measure ◽  
Learning Methods ◽  
Splice Site Prediction ◽  
Promoter Recognition ◽  
Imbalance Learning ◽  
Class Imbalance Learning

One common and challenging problem faced by many bioinformatics applications, such as promoter recognition, splice site prediction, RNA gene prediction, drug discovery and protein classification, is the imbalance of the available datasets. In most of these applications, the positive data examples are largely outnumbered by the negative data examples, which often leads to the development of sub-optimal prediction models having high negative recognition rate (Specificity = SP) and low positive recognition rate (Sensitivity = SE). When class imbalance learning methods are applied, usually, the SE is increased at the expense of reducing some amount of the SP. In this paper, we point out that in these data-imbalanced bioinformatics applications, the goal of applying class imbalance learning methods would be to increase the SE as high as possible by keeping the reduction of SP as low as possible. We explain that the existing performance measures used in class imbalance learning can still produce sub-optimal models with respect to this classification goal. In order to overcome these problems, we introduce a new performance measure called Adjusted Geometric-mean (AGm). The experimental results obtained on ten real-world imbalanced bioinformatics datasets demonstrates that the AGm metric can achieve a lower rate of reduction of SP than the existing performance metrics, when increasing the SE through class imbalance learning methods. This characteristic of AGm metric makes it more suitable for achieving the proposed classification goal in imbalanced bioinformatics datasets learning.

scholarly journals Balancing Trade-Offs in the Detection of Schools at Risk

2020 ◽  
Author(s):  
Alexander Olof Savi ◽  
Ilja Cornelisz ◽  
Matthias J. Sjerps ◽  
Steffen L. Greup ◽  
Chris M. Bres ◽  
...  
Keyword(s):  
Primary Schools ◽  
Prediction Models ◽  
Regulatory Compliance ◽  
Inspection Method ◽  
School Inspections ◽  
Trade Offs ◽  
Daunting Task ◽  
Causal Impact ◽  
School Failures ◽  
The One

The quality assurance and evaluation of schools requires early risk-detection; a daunting task since school failures are typically rare and their origins complex. In the Netherlands, the Inspectorate of Education monitors the regulatory compliance of roughly 6000 primary schools, with limited resources and capacity, and a desire for proportionality. In order to aid their risk-based inspection method, we evaluate various case-based prediction models, and propose a principled exploit-explore procedure for organizing school inspections. This approach has the potential to balance the benefits of prioritizing inspections of presumed high-risk schools on the one hand, with the benefits of verifying predicted risks and causal impact evaluations of school inspections on the other.

scholarly journals Threshold benchmarking for feature ranking techniques

2021 ◽  
Vol 10 (2) ◽  
pp. 1063-1070
Author(s):  
Ruchika Malhotra ◽  
Anjali Sharma
Keyword(s):  
Prediction Models ◽  
Area Under The Curve ◽  
Threshold Value ◽  
Performance Measure ◽  
Machine Learning Techniques ◽  
Feature Ranking ◽  
Ranking Algorithms ◽  
Learning Techniques ◽  
Defect Prediction Models ◽  
Necessary And Sufficient

In prediction modeling, the choice of features chosen from the original feature set is crucial for accuracy and model interpretability. Feature ranking techniques rank the features by its importance but there is no consensus on the number of features to be cut-off. Thus, it becomes important to identify a threshold value or range, so as to remove the redundant features. In this work, an empirical study is conducted for identification of the threshold benchmark for feature ranking algorithms. Experiments are conducted on Apache Click dataset with six popularly used ranker techniques and six machine learning techniques, to deduce a relationship between the total number of input features (N) to the threshold range. The area under the curve analysis shows that ≃ 33-50% of the features are necessary and sufficient to yield a reasonable performance measure, with a variance of 2%, in defect prediction models. Further, we also find that the log2(N) as the ranker threshold value represents the lower limit of the range.

Sign in / Sign up

Export Citation Format

Share Document