Assessing the Performance of Machine Learning Methods Trained on Public Health Observational Data: A Case Study From COVID-19.

From early in the coronavirus disease 2019 (COVID-19) pandemic, there was interest in using machine learning methods to predict COVID-19 infection status based on vocal audio signals, for example, cough recordings. However, early studies had limitations in terms of data collection and of how the performances of the proposed predictive models were assessed. This article describes how these limitations have been overcome in a study carried out by the Turing-RSS Health Data Laboratory and the UK Health Security Agency.

A large-scale and PCR-referenced vocal audio dataset for COVID-19.

The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory symptoms using vocal audio. The UK Health Security Agency recruited voluntary participants through the national Test and Trace programme and the REACT-1 survey in England from March 2021 to March 2022, during dominant transmission of the Alpha and Delta SARS-CoV-2 variants and some Omicron variant sublineages. Audio recordings of volitional coughs, exhalations, and speech were collected in the 'Speak up and help beat coronavirus' digital survey alongside demographic, symptom and self-reported respiratory condition data.

Bradyphrenia and Tachyphrenia in Idiopathic Parkinsonism Appear, in Part, Iatrogenic: An Observational Study with Systematic Review Background.

We question whether bradyphrenia, slowing of cognitive processing not explained by depression or a global cognitive assessment, is a nosological entity in idiopathic parkinsonism (IP). The time taken to break contact of an index finger with a touch-sensitive plate was measured, with and without a warning in the alerting signal as to which side the imperative would indicate, in 77 people diagnosed with IP and in 124 people without an IP diagnosis. The ability to utilise a warning, measured by the difference between log-transformed reaction times (unwarned minus warned), was termed 'cognitive efficiency'.

Group screening for rare events based on incomplete block designs.

Fields such as, diagnostic testing, biotherapeutics, drug development, and toxicology among others, center on the premise of searching through many specimens for a rare event. Scientists in the business of "searching for a needle in a haystack" may greatly benefit from the use of group screening design strategies. Group screening, where specimens are composited into pools with each pool being tested for the presence of the event, can be much more cost-efficient than testing each individual specimen.

Optimum designs for non-linear mixed effects models in the presence of covariates.

In this article, we present a new method for optimizing designs of experiments for non-linear mixed effects models, where a categorical factor with covariate information is a design variable combined with another design factor. The work is motivated by the need to efficiently design preclinical experiments in enzyme kinetics for a set of Human Liver Microsomes. However, the results are general and can be applied to other experimental situations where the variation in the response due to a categorical factor can be partially accounted for by a covariate.

Transform-both-sides nonlinear models for in vitro pharmacokinetic experiments.

Transform-both-sides nonlinear models have proved useful in many experimental applications including those in pharmaceutical sciences and biochemistry. The maximum likelihood method is commonly used to fit transform-both-sides nonlinear models, where the regression and transformation parameters are estimated simultaneously. In this paper, an analysis of variance-based method is described in detail for estimating transform-both-sides nonlinear models from randomized experiments.

Response surface designs for experiments in bioprocessing.

Many processes in the biological industries are studied using response surface methodology. The use of biological materials, however, means that run-to-run variation is typically much greater than that in many experiments in mechanical or chemical engineering and so the designs used require greater replication. The data analysis which is performed may involve some variable selection, as well as fitting polynomial response surface models.

Design of microarray experiments for genetical genomics studies.

Microarray experiments have been used recently in genetical genomics studies, as an additional tool to understand the genetic mechanisms governing variation in complex traits, such as for estimating heritabilities of mRNA transcript abundances, for mapping expression quantitative trait loci, and for inferring regulatory networks controlling gene expression. Several articles on the design of microarray experiments discuss situations in which treatment effects are assumed fixed and without any structure. In the case of two-color microarray platforms, several authors have studied reference and circular designs.

Novel experimental design for steady-state processes: a systematic Bayesian approach for enzymes, drug transport, receptor binding, continuous culture and cell transport kinetics.

We demonstrate that a Bayesian approach (the use of prior knowledge) to the design of steady-state experiments can produce major gains quantifiable in terms of information, productivity and accuracy of each experiment. Developing the use of Bayesian utility functions, we have used a systematic method to identify the optimum experimental designs for a number of kinetic model data sets. This has enabled the identification of trends between kinetic model types, sets of design rules and the key conclusion that such designs should be based on some prior knowledge of the kinetic model.

Efficient and cost-effective experimental determination of kinetic constants and data: the success of a Bayesian systematic approach to drug transport, receptor binding, continuous culture and cell transport kinetics.

Details about the parameters of kinetic systems are crucial for progress in both medical and industrial research, including drug development, clinical diagnosis and biotechnology applications. Such details must be collected by a series of kinetic experiments and investigations. The correct design of the experiment is essential to collecting data suitable for analysis, modelling and deriving the correct information.

Planning incomplete block experiments when treatments are genetically related.

Selection trials in plant and animal breeding, in incomplete blocks, are described by linear models with random effect parameters associated with treatments with known genetic covariance structure. It is now well known that the information on relatives can improve the analysis and many extensions of this model have been proposed, but no studies have been done on the consequences of this genetical relatedness among treatments for the optimality of block designs. Using a suitable optimality criterion, we show that the knowledge on relatedness may imply that the optimal design is not in the class of designs which are optimal for unrelated treatments.

Efficient and accurate experimental design for enzyme kinetics: Bayesian studies reveal a systematic approach.

In areas such as drug development, clinical diagnosis and biotechnology research, acquiring details about the kinetic parameters of enzymes is crucial. The correct design of an experiment is critical to collecting data suitable for analysis, modelling and deriving the correct information. As classical design methods are not targeted to the more complex kinetics being frequently studied, attention is needed to estimate parameters of such models with low variance.

Effective experimental design: enzyme kinetics in the bioinformatics era.

Acquiring details about the kinetic parameters of enzymes is crucial to both drug development and clinical diagnosis. The correct design of an experiment is crucial to collecting data suitable for analysis, modelling and deriving the correct information. As classical design methods are not targeted to the more complex kinetics now frequently studied, further work is required to estimate parameters of such models with low variance.