Observational studies have shown that fetoscopic endoluminal tracheal occlusion (FETO) has been associated with increased survival among infants with severe pulmonary hypoplasia due to isolated ...congenital diaphragmatic hernia on the left side, but data from randomized trials are lacking.
In this open-label trial conducted at centers with experience in FETO and other types of prenatal surgery, we randomly assigned, in a 1:1 ratio, women carrying singleton fetuses with severe isolated congenital diaphragmatic hernia on the left side to FETO at 27 to 29 weeks of gestation or expectant care. Both treatments were followed by standardized postnatal care. The primary outcome was infant survival to discharge from the neonatal intensive care unit. We used a group-sequential design with five prespecified interim analyses for superiority, with a maximum sample size of 116 women.
The trial was stopped early for efficacy after the third interim analysis. In an intention-to-treat analysis that included 80 women, 40% of infants (16 of 40) in the FETO group survived to discharge, as compared with 15% (6 of 40) in the expectant care group (relative risk, 2.67; 95% confidence interval CI, 1.22 to 6.11; two-sided P = 0.009). Survival to 6 months of age was identical to the survival to discharge (relative risk, 2.67; 95% CI, 1.22 to 6.11). The incidence of preterm, prelabor rupture of membranes was higher among women in the FETO group than among those in the expectant care group (47% vs. 11%; relative risk, 4.51; 95% CI, 1.83 to 11.9), as was the incidence of preterm birth (75% vs. 29%; relative risk, 2.59; 95% CI, 1.59 to 4.52). One neonatal death occurred after emergency delivery for placental laceration from fetoscopic balloon removal, and one neonatal death occurred because of failed balloon removal. In an analysis that included 11 additional participants with data that were available after the trial was stopped, survival to discharge was 36% among infants in the FETO group and 14% among those in the expectant care group (relative risk, 2.65; 95% CI, 1.21 to 6.09).
In fetuses with isolated severe congenital diaphragmatic hernia on the left side, FETO performed at 27 to 29 weeks of gestation resulted in a significant benefit over expectant care with respect to survival to discharge, and this benefit was sustained to 6 months of age. FETO increased the risks of preterm, prelabor rupture of membranes and preterm birth. (Funded by the European Commission and others; TOTAL ClinicalTrials.gov number, NCT01240057.).
Methods to correct class imbalance (imbalance between the frequency of outcome events and nonevents) are receiving increasing interest for developing prediction models. We examined the effect of ...imbalance correction on the performance of logistic regression models.
Prediction models were developed using standard and penalized (ridge) logistic regression under 4 methods to address class imbalance: no correction, random undersampling, random oversampling, and SMOTE. Model performance was evaluated in terms of discrimination, calibration, and classification. Using Monte Carlo simulations, we studied the impact of training set size, number of predictors, and the outcome event fraction. A case study on prediction modeling for ovarian cancer diagnosis is presented.
The use of random undersampling, random oversampling, or SMOTE yielded poorly calibrated models: the probability to belong to the minority class was strongly overestimated. These methods did not result in higher areas under the ROC curve when compared with models developed without correction for class imbalance. Although imbalance correction improved the balance between sensitivity and specificity, similar results were obtained by shifting the probability threshold instead.
Imbalance correction led to models with strong miscalibration without better ability to distinguish between patients with and without the outcome event. The inaccurate probability estimates reduce the clinical utility of the model, because decisions about treatment are ill-informed.
Outcome imbalance is not a problem in itself, imbalance correction may even worsen model performance.
The objective of this study was to compare performance of logistic regression (LR) with machine learning (ML) for clinical prediction modeling in the literature.
We conducted a Medline literature ...search (1/2016 to 8/2017) and extracted comparisons between LR and ML models for binary outcomes.
We included 71 of 927 studies. The median sample size was 1,250 (range 72–3,994,872), with 19 predictors considered (range 5–563) and eight events per predictor (range 0.3–6,697). The most common ML methods were classification trees, random forests, artificial neural networks, and support vector machines. In 48 (68%) studies, we observed potential bias in the validation procedures. Sixty-four (90%) studies used the area under the receiver operating characteristic curve (AUC) to assess discrimination. Calibration was not addressed in 56 (79%) studies. We identified 282 comparisons between an LR and ML model (AUC range, 0.52–0.99). For 145 comparisons at low risk of bias, the difference in logit(AUC) between LR and ML was 0.00 (95% confidence interval, −0.18 to 0.18). For 137 comparisons at high risk of bias, logit(AUC) was 0.34 (0.20–0.47) higher for ML.
We found no evidence of superior performance of ML over LR. Improvements in methodology and reporting are needed for studies that compare modeling algorithms.
Multinomial Logistic Regression (MLR) has been advocated for developing clinical prediction models that distinguish between three or more unordered outcomes. We present a full‐factorial simulation ...study to examine the predictive performance of MLR models in relation to the relative size of outcome categories, number of predictors and the number of events per variable. It is shown that MLR estimated by Maximum Likelihood yields overfitted prediction models in small to medium sized data. In most cases, the calibration and overall predictive performance of the multinomial prediction model is improved by using penalized MLR. Our simulation study also highlights the importance of events per variable in the multinomial context as well as the total sample size. As expected, our study demonstrates the need for optimism correction of the predictive performance measures when developing the multinomial logistic prediction model. We recommend the use of penalized MLR when prediction models are developed in small data sets or in medium sized data sets with a small total sample size (ie, when the sizes of the outcome categories are balanced). Finally, we present a case study in which we illustrate the development and validation of penalized and unpenalized multinomial prediction models for predicting malignancy of ovarian cancer.
The role of P‐values for null hypothesis testing is under debate. We aim to explore the impact of the significance threshold on estimates for the strengths of associations (“effects”) and the ...implications for different types of epidemiological research. We consider situations with normal distribution of a true effect, while varying the effect size. We confirm the occurrence of “testimation bias”: estimating effect size only if the test was statistically significant leads to exaggerated results. The absolute bias is largest for true effects around 0.7 times the size of the standard error: +220% bias if effects are selected after testing with P < .05, and +335% if tested with P < .005. Less bias was found for testing with P < .20 (+130%) and larger true effect sizes. We conclude that a lower P‐value threshold for declaring statistical significance implies more exaggeration in an estimated effect. This implies that if a low threshold is used, effect size estimation should not be attempted, for example in the context of selecting promising discoveries that need further validation. Confirmatory studies, such as randomized controlled trials, might stick to the 0.05 threshold if adequately powered, while prediction modelling studies should use an even higher threshold, such as 0.2, to avoid strongly biased effect estimates.
When developing risk prediction models on datasets with limited sample size, shrinkage methods are recommended. Earlier studies showed that shrinkage results in better predictive performance on ...average. This simulation study aimed to investigate the variability of regression shrinkage on predictive performance for a binary outcome. We compared standard maximum likelihood with the following shrinkage methods: uniform shrinkage (likelihood-based and bootstrap-based), penalized maximum likelihood (ridge) methods, LASSO logistic regression, adaptive LASSO, and Firth’s correction. In the simulation study, we varied the number of predictors and their strength, the correlation between predictors, the event rate of the outcome, and the events per variable. In terms of results, we focused on the calibration slope. The slope indicates whether risk predictions are too extreme (slope < 1) or not extreme enough (slope > 1). The results can be summarized into three main findings. First, shrinkage improved calibration slopes on average. Second, the between-sample variability of calibration slopes was often increased relative to maximum likelihood. In contrast to other shrinkage approaches, Firth’s correction had a small shrinkage effect but showed low variability. Third, the correlation between the estimated shrinkage and the optimal shrinkage to remove overfitting was typically negative, with Firth’s correction as the exception. We conclude that, despite improved performance on average, shrinkage often worked poorly in individual datasets, in particular when it was most needed. The results imply that shrinkage methods do not solve problems associated with small sample size or low number of events per variable.
Many decisions in medicine involve trade-offs, such as between diagnosing patients with disease versus unnecessary additional testing for those who are healthy. Net benefit is an increasingly ...reported decision analytic measure that puts benefits and harms on the same scale. This is achieved by specifying an exchange rate, a clinical judgment of the relative value of benefits (such as detecting a cancer) and harms (such as unnecessary biopsy) associated with models, markers, and tests. The exchange rate can be derived by asking simple questions, such as the maximum number of patients a doctor would recommend for biopsy to find one cancer. As the answers to these sorts of questions are subjective, it is possible to plot net benefit for a range of reasonable exchange rates in a “decision curve.” For clinical prediction models, the exchange rate is related to the probability threshold to determine whether a patient is classified as being positive or negative for a disease. Net benefit is useful for determining whether basing clinical decisions on a model, marker, or test would do more good than harm. This is in contrast to traditional measures such as sensitivity, specificity, or area under the curve, which are statistical abstractions not directly informative about clinical value. Recent years have seen an increase in practical applications of net benefit analysis to research data. This is a welcome development, since decision analytic techniques are of particular value when the purpose of a model, marker, or test is to help doctors make better clinical decisions.
In 2019 we published a pair of articles in Statistics in Medicine that describe how to calculate the minimum sample size for developing a multivariable prediction model with a continuous outcome, or ...with a binary or time‐to‐event outcome. As for any sample size calculation, the approach requires the user to specify anticipated values for key parameters. In particular, for a prediction model with a binary outcome, the outcome proportion and a conservative estimate for the overall fit of the developed model as measured by the Cox‐Snell R2 (proportion of variance explained) must be specified. This proposal raises the question of how to identify a plausible value for R2 in advance of model development. Our articles suggest researchers should identify R2 from closely related models already published in their field. In this letter, we present details on how to derive R2 using the reported C statistic (AUROC) for such existing prediction models with a binary outcome. The C statistic is commonly reported, and so our approach allows researchers to obtain R2 for subsequent sample size calculations for new models. Stata and R code is provided, and a small simulation study.