Search

Some methods for analysing mineral prospectivity, especially the weights of evidence technique, require the predictor variables to be binary values. When the original evidence data are numerical values, such as geochemical indices, they can be converted to binary values by thresholding. When the evidence layer is a spatial feature such as a geological fault system, it can be converted to a binary predictor by buffering at a suitable cut-off distance. This paper reviews methods for selecting the best threshold or cut-off value and compares their performance. The review covers techniques which are well known in prospectivity analysis as well as unfamiliar techniques borrowed from other literature. Methods include maximisation of the estimated contrast, Studentised contrast, χ 2 test statistic, Youden criterion, statistical likelihood, Akman–Raftery criterion, and curvature of the capture–efficiency curve. We identify connections between the different methods, and we highlight a common technical error in their application. Simulation experiments indicate that the Youden criterion has the best performance for selection of the threshold or cut-off value, assuming that a simple binary threshold relationship truly holds. If the relationship between predictor and prospectivity is more complicated, then the likelihood method is the most easily adaptable. The weights-of-evidence contrast performs poorly overall. These conclusions are supported by our analysis of data from the Murchison goldfields, Western Australia. We also propose a bootstrap method for calculating standard errors and confidence intervals for the location of the threshold. [ABSTRACT FROM AUTHOR]

Quantification of stillbirth risk has potential to support clinical decision-making. Studies that have attempted to quantify stillbirth risk have been hampered by small event rates, a limited range of predictors that typically exclude obstetric history, lack of validation, and restriction to a single classifier (logistic regression). Consequently, predictive performance remains low, and risk quantification has not been adopted into antenatal practice. The study population consisted of all births to women in Western Australia from 1980 to 2015, excluding terminations. After all exclusions there were 947,025 livebirths and 5,788 stillbirths. Predictive models for stillbirth were developed using multiple machine learning classifiers: regularised logistic regression, decision trees based on classification and regression trees, random forest, extreme gradient boosting (XGBoost), and a multilayer perceptron neural network. We applied 10-fold cross-validation using independent data not used to develop the models. Predictors included maternal socio-demographic characteristics, chronic medical conditions, obstetric complications and family history in both the current and previous pregnancy. In this cohort, 66% of stillbirths were observed for multiparous women. The best performing classifier (XGBoost) predicted 45% (95% CI: 43%, 46%) of stillbirths for all women and 45% (95% CI: 43%, 47%) of stillbirths after the inclusion of previous pregnancy history. Almost half of stillbirths could be potentially identified antenatally based on a combination of current pregnancy complications, congenital anomalies, maternal characteristics, and medical history. Greatest sensitivity is achieved with addition of current pregnancy complications. Ensemble classifiers offered marginal improvement for prediction compared to logistic regression. [ABSTRACT FROM AUTHOR]