Abstract
Statistical analyses form a fundamental part of causal inference in the experimental sciences. The statistical paradigm most commonly taught to science students around the world is that of ...frequentism, with a particular emphasis on the null hypothesis significance testing borne by the work of Neyman and Pearson in the early 20th century. This paradigm is often lauded as being the most objective of methods and remains commonplace in scientific journals. Despite its widespread use—and, indeed, requirement for publication in some journals—this paradigm has received substantial criticism in recent decades, and its impact on scientific publishing has been subjected to deeper scrutiny in response to the replication crisis in the psychological and medical sciences. It has been posited that the increasing use of the Bayesian statistical paradigm, made more accessible through technological advances in the last few decades, may have an important role to play in rendering research and statistical inference more robust, transparent, and reproducible. These methods can have a steep learning curve, and thus this paper seeks to introduce those working within clinical laboratories to the Bayesian paradigm of statistical analysis and provides worked examples of the Bayesian analysis of data commonly encountered in laboratory medicine using freely available, open source tools.
According to international standards, clinical laboratories are required to verify the performance of assays prior to their implementation in routine practice. This typically involves the assessment ...of the assay's imprecision and trueness vs. appropriate targets. The analysis of these data is typically performed using frequentist statistical methods and often requires the use of closed source, proprietary software. The motivation for this paper was therefore to develop an open-source, freely available software capable of performing Bayesian analysis of verification data.
The veRification application presented here was developed with the freely available R statistical computing environment, using the Shiny application framework. The codebase is fully open-source and is available as an R package on GitHub.
The developed application allows the user to analyze imprecision, trueness against external quality assurance, trueness against reference material, method comparison, and diagnostic performance data within a fully Bayesian framework (with frequentist methods also being available for some analyses).
Bayesian methods can have a steep learning curve and thus the work presented here aims to make Bayesian analyses of clinical laboratory data more accessible. Moreover, the development of the application and seeks to encourage the dissemination of open-source software within the community and provides a framework through which Shiny applications can be developed, shared, and iterated upon.
Urine steroid profiles are used in clinical practice for the diagnosis and monitoring of disorders of steroidogenesis and adrenal pathologies. Machine learning (ML) algorithms are powerful ...computational tools used extensively for the recognition of patterns in large data sets. Here, we investigated the utility of various ML algorithms for the automated biochemical interpretation of urine steroid profiles to support current clinical practices.
Data from 4619 urine steroid profiles processed between June 2012 and October 2016 were retrospectively collected. Of these, 1314 profiles were used to train and test various ML classifiers' abilities to differentiate between "No significant abnormality" and "?Abnormal" profiles. Further classifiers were trained and tested for their ability to predict the specific biochemical interpretation of the profiles.
The best performing binary classifier could predict the interpretation of No significant abnormality and ?Abnormal profiles with a mean area under the ROC curve of 0.955 (95% CI, 0.949-0.961). In addition, the best performing multiclass classifier could predict the individual abnormal profile interpretation with a mean balanced accuracy of 0.873 (0.865-0.880).
Here we have described the application of ML algorithms to the automated interpretation of urine steroid profiles. This provides a proof-of-concept application of ML algorithms to complex clinical laboratory data that has the potential to improve laboratory efficiency in a setting of limited staff resources.
Mass spectrometry is widely used to probe the proteome and its modifications in an untargeted manner, with unrivalled coverage. Applied to phosphoproteomics, it has tremendous potential to ...interrogate phospho-signalling and its therapeutic implications. However, this task is complicated by issues of undersampling of the phosphoproteome and challenges stemming from its high-content but low-sample-throughput nature. Hence, methods using such data to reconstruct signalling networks have been limited to restricted data sets and insights (for example, groups of kinases likely to be active in a sample). We propose a new method to handle high-content discovery phosphoproteomics data on perturbation by putting it in the context of kinase/phosphatase-substrate knowledge, from which we derive and train logic models. We show, on a data set obtained through perturbations of cancer cells with small-molecule inhibitors, that this method can study the targets and effects of kinase inhibitors, and reconcile insights obtained from multiple data sets, a common issue with these data.
The downregulation of Pleckstrin Homology-Like Domain family A member 1 (PHLDA1) expression mediates resistance to targeted therapies in receptor tyrosine kinase-driven cancers. The restoration and ...maintenance of PHLDA1 levels in cancer cells thus constitutes a potential strategy to circumvent resistance to inhibitors of receptor tyrosine kinases. Through a pharmacological approach, we identify the inhibition of MAPK signalling as a crucial step in
downregulation. Further ChIP-qPCR analysis revealed that MEK1/2 inhibition produces significant epigenetic changes at the
locus, specifically a decrease in the activatory marks H3Kme3 and H3K27ac. In line with this, we show that treatment with the clinically relevant class I histone deacetylase (HDAC) inhibitor 4SC-202 restores PHLDA1 expression in lapatinib-resistant human epidermal growth factor receptor-2 (HER2)
breast cancer cells. Critically, we show that when given in combination, 4SC-202 and lapatinib exert synergistic effects on 2D cell proliferation and colony formation capacity. We therefore propose that co-treatment with 4SC-202 may prolong the clinical efficacy of lapatinib in HER2
breast cancer patients.
The purpose of this study was to establish whether an artificially intelligent (AI) system can be developed to automate stress echocardiography analysis and support clinician interpretation.
Coronary ...artery disease is the leading global cause of mortality and morbidity and stress echocardiography remains one of the most commonly used diagnostic imaging tests.
An automated image processing pipeline was developed to extract novel geometric and kinematic features from stress echocardiograms collected as part of a large, United Kingdom-based prospective, multicenter, multivendor study. An ensemble machine learning classifier was trained, using the extracted features, to identify patients with severe coronary artery disease on invasive coronary angiography. The model was tested in an independent U.S. study. How availability of an AI classification might impact clinical interpretation of stress echocardiograms was evaluated in a randomized crossover reader study.
Acceptable classification accuracy for identification of patients with severe coronary artery disease in the training data set was achieved on cross-fold validation based on 31 unique geometric and kinematic features, with a specificity of 92.7% and a sensitivity of 84.4%. This accuracy was maintained in the independent validation data set. The use of the AI classification tool by clinicians increased inter-reader agreement and confidence as well as sensitivity for detection of disease by 10% to achieve an area under the receiver-operating characteristic curve of 0.93.
Automated analysis of stress echocardiograms is possible using AI and provision of automated classifications to clinicians when reading stress echocardiograms could improve accuracy, inter-reader agreement, and reader confidence.
Display omitted
Abstract
BACKGROUND
Plasma amino acid (PAA) profiles are used in routine clinical practice for the diagnosis and monitoring of inherited disorders of amino acid metabolism, organic acidemias, and ...urea cycle defects. Interpretation of PAA profiles is complex and requires substantial training and expertise to perform. Given previous demonstrations of the ability of machine learning (ML) algorithms to interpret complex clinical biochemistry data, we sought to determine if ML-derived classifiers could interpret PAA profiles with high predictive performance.
METHODS
We collected PAA profiling data routinely performed within a clinical biochemistry laboratory (2084 profiles) and developed decision support classifiers with several ML algorithms. We tested the generalization performance of each classifier using a nested cross-validation (CV) procedure and examined the effect of various subsampling, feature selection, and ensemble learning strategies.
RESULTS
The classifiers demonstrated excellent predictive performance, with the 3 ML algorithms tested producing comparable results. The best-performing ensemble binary classifier achieved a mean precision-recall (PR) AUC of 0.957 (95% CI 0.952, 0.962) and the best-performing ensemble multiclass classifier achieved a mean F4 score of 0.788 (0.773, 0.803).
CONCLUSIONS
This work builds upon previous demonstrations of the utility of ML-derived decision support tools in clinical biochemistry laboratories. Our findings suggest that, pending additional validation studies, such tools could potentially be used in routine clinical practice to streamline and aid the interpretation of PAA profiles. This would be particularly useful in laboratories with limited resources and large workloads. We provide the necessary code for other laboratories to develop their own decision support tools.
Cell survival is regulated by a signaling network driven by the activity of protein kinases; however, determining the contribution that each kinase in the network makes to such regulation remains ...challenging. Here, we report a computational approach that uses mass spectrometry-based phosphoproteomics data to rank protein kinases based on their contribution to cell regulation. We found that the scores returned by this algorithm, which we have termed kinase activity ranking using phosphoproteomics data (KARP), were a quantitative measure of the contribution that individual kinases make to the signaling output. Application of KARP to the analysis of eight hematological cell lines revealed that cyclin-dependent kinase (CDK) 1/2, casein kinase (CK) 2, extracellular signal-related kinase (ERK), and p21-activated kinase (PAK) were the most frequently highly ranked kinases in these cell models. The patterns of kinase activation were cell-line specific yet showed a significant association with cell viability as a function of kinase inhibitor treatment. Thus, our study exemplifies KARP as an untargeted approach to empirically and systematically identify regulatory kinases within signaling networks.
Development of resistance causes failure of drugs targeting receptor tyrosine kinase (RTK) networks and represents a critical challenge for precision medicine. Here, we show that PHLDA1 ...downregulation is critical to acquisition and maintenance of drug resistance in RTK-driven cancer. Using fibroblast growth factor receptor (FGFR) inhibition in endometrial cancer cells, we identify an Akt-driven compensatory mechanism underpinned by downregulation of PHLDA1. We demonstrate broad clinical relevance of our findings, showing that PHLDA1 downregulation also occurs in response to RTK-targeted therapy in breast and renal cancer patients, as well as following trastuzumab treatment in HER2+ breast cancer cells. Crucially, knockdown of PHLDA1 alone was sufficient to confer de novo resistance to RTK inhibitors and induction of PHLDA1 expression re-sensitized drug-resistant cancer cells to targeted therapies, identifying PHLDA1 as a biomarker for drug response and highlighting the potential of PHLDA1 reactivation as a means of circumventing drug resistance.
Display omitted
•The Akt pathway plays a critical role in resistance to tyrosine kinase inhibition•PHLDA1 is key to regulating Akt activity during the development of drug resistance•Knockdown of PHLDA1 alone confers de novo resistance to kinase inhibitors•PHLDA1 rescue resensitizes drug-resistant cancer cells
Fearon et al. use unbiased transcriptomic and phosphoproteomic analysis to identify PHLDA1 as a mediator of acquired resistance to kinase-targeted therapies in cancer. Using a range of cell models and clinical data, they uncover a mechanism underpinning the re-wiring of Akt signaling in cancer drug resistance.