Artificial intelligence in the management and treatment of burns: A systematic review and meta-analyses.

INTRODUCTION AND AIM: Artificial Intelligence (AI) is already being successfully employed to aid the interpretation of multiple facets of burns care. In the light of the growing influence of AI, this systematic review and diagnostic test accuracy meta-analyses aim to appraise and summarise the current direction of research in this field. METHOD: A systematic literature review was conducted of relevant studies published between 1990 and 2021, yielding 35 studies. Twelve studies were suitable for a Diagnostic Test Meta-Analyses. RESULTS: The studies generally focussed on burn depth (Accuracy 68.9%-95.4%, Sensitivity 90.8% and Specificity 84.4%), burn segmentation (Accuracy 76.0%-99.4%, Sensitivity 97.9% and specificity 97.6%) and burn related mortality (Accuracy >90%-97.5% Sensitivity 92.9% and specificity 93.4%). Neural networks were the most common machine learning (ML) algorithm utilised in 69% of the studies. The QUADAS-2 tool identified significant heterogeneity between studies. DISCUSSION: The potential application of AI in the management of burns patients is promising, especially given its propitious results across a spectrum of dimensions, including burn depth, size, mortality, related sepsis and acute kidney injuries. The accuracy of the results analysed within this study is comparable to current practices in burns care. CONCLUSION: The application of AI in the treatment and management of burns patients, as a series of point of care diagnostic adjuncts, is promising. Whilst AI is a potentially valuable tool, a full evaluation of its current utility and potential is limited by significant variations in research methodology and reporting.

Time extrapolation in regulatory risk assessment: The impact of study differences on the extrapolation factors.

In human risk assessment, time extrapolation factors (EFs) account for differences in exposure duration of experimental studies. We calculated EFs based on N(L)OEL (no (lowest) observed effect level) ratios, dividing shorter-term by longer-term values. The 'oral' datasets comprised 302 EFs (subacute-subchronic) and 1059 EFs (subchronic-chronic). The 'inhalation' datasets contained 67 EFs (subacute-subchronic) and 226 EFs (subchronic-chronic). The experimental EF distribution oral:subchronic-chronic showed that study parameters like deviation in dose selection and spacing influence mainly the data variance. Exclusion of these influences led to a dataset representing more realistically the difference of N(L)OELs with prolonged treatment. This dataset showed a GM of 1.5, indicating that the impact of a longer treatment period on the study N(L)OEL is on average not high. A factor of 1.5 seemed to be also sufficiently conservative for subacute-subchronic and subchronic-chronic extrapolation (inhalation or oral exposure). EFs for groups of similar compounds did not differ, but for compounds with low and high NOEL values. Relatively toxic compounds (GM 1) might thus not require time extrapolation. Within and between chemical variance was analysed in the dataset oral:subchronic-chronic (GSD 4.8). The variance between chemicals should be considered within extrapolation by selecting an appropriate percentile for which a chemical variance factor is suggested. In risk assessment, often a combination of EFs is required. Our analysis indicates that such a combination will result in an accumulation of non-toxicological variance and therefore unrealistically high EFs. Further evaluations are needed to identify appropriate chemical variance factors for these situations.

Functional bioinformatics for Arabidopsis thaliana.

MOTIVATION: The genome of Arabidopsis thaliana, which has the best understood plant genome, still has approximately one-third of its genes with no functional annotation at all from either MIPS or TAIR. We have applied our Data Mining Prediction (DMP) method to the problem of predicting the functional classes of these protein sequences. This method is based on using a hybrid machine-learning/data-mining method to identify patterns in the bioinformatic data about sequences that are predictive of function. We use data about sequence, predicted secondary structure, predicted structural domain, InterPro patterns, sequence similarity profile and expressions data. RESULTS: We predicted the functional class of a high percentage of the Arabidopsis genes with currently unknown function. These predictions are interpretable and have good test accuracies. We describe in detail seven of the rules produced.

The utility of different representations of protein sequence for predicting functional class.

MOTIVATION: Data Mining Prediction (DMP) is a novel approach to predicting protein functional class from sequence. DMP works even in the absence of a homologous protein of known function. We investigate the utility of different ways of representing protein sequence in DMP (residue frequencies, phylogeny, predicted structure) using the Escherichia coli genome as a model. RESULTS: Using the different representations DMP learnt prediction rules that were more accurate than default at every level of function using every type of representation. The most effective way to represent sequence was using phylogeny (75% accuracy and 13% coverage of unassigned ORFs at the most general level of function: 69% accuracy and 7% coverage at the most detailed). We tested different methods for combining predictions from the different types of representation. These improved both the accuracy and coverage of predictions, e.g. 40% of all unassigned ORFs could be predicted at an estimated accuracy of 60% and 5% of unassigned ORFs could be predicted at an estimated accuracy of 86%.

Accurate prediction of protein functional class from sequence in the Mycobacterium tuberculosis and Escherichia coli genomes using data mining.

The analysis of genomics data needs to become as automated as its generation. Here we present a novel data-mining approach to predicting protein functional class from sequence. This method is based on a combination of inductive logic programming clustering and rule learning. We demonstrate the effectiveness of this approach on the M. tuberculosis and E. coli genomes, and identify biologically interpretable rules which predict protein functional class from information only available from the sequence. These rules predict 65% of the ORFs with no assigned function in M. tuberculosis and 24% of those in E. coli, with an estimated accuracy of 60-80% (depending on the level of functional assignment). The rules are founded on a combination of detection of remote homology, convergent evolution and horizontal gene transfer. We identify rules that predict protein functional class even in the absence of detectable sequence or structural homology. These rules give insight into the evolutionary history of M. tuberculosis and E. coli.