Estimating average human performance has been performed inconsistently in research in diagnostic medicine. This has been particularly apparent in the field of medical artificial intelligence, where humans are often compared against AI models in multi
-reader multi-case studies, and commonly reported metrics such as the pooled or average human sensitivity and specificity will systematically underestimate the performance of human experts. We present the use of summary receiver operating characteristic curve analysis, a technique commonly used in the meta-analysis of diagnostic test accuracy studies, as a sensible and methodologically robust alternative. We describe the motivation for using these methods and present results where we apply these meta-analytic techniques to a handful of prominent medical AI studies.
Machine learning models for medical image analysis often suffer from poor performance on important subsets of a population that are not identified during training or testing. For example, overall performance of a cancer detection model may be high, b
ut the model still consistently misses a rare but aggressive cancer subtype. We refer to this problem as hidden stratification, and observe that it results from incompletely describing the meaningful variation in a dataset. While hidden stratification can substantially reduce the clinical efficacy of machine learning models, its effects remain difficult to measure. In this work, we assess the utility of several possible techniques for measuring and describing hidden stratification effects, and characterize these effects on multiple medical imaging datasets. We find evidence that hidden stratification can occur in unidentified imaging subsets with low prevalence, low label quality, subtle distinguishing features, or spurious correlates, and that it can result in relative performance differences of over 20% on clinically important subsets. Finally, we explore the clinical implications of our findings, and suggest that evaluation of hidden stratification should be a critical component of any machine learning deployment in medical imaging.
Rationale and Objectives: Medical artificial intelligence systems are dependent on well characterised large scale datasets. Recently released public datasets have been of great interest to the field, but pose specific challenges due to the disconnect
they cause between data generation and data usage, potentially limiting the utility of these datasets. Materials and Methods: We visually explore two large public datasets, to determine how accurate the provided labels are and whether other subtle problems exist. The ChestXray14 dataset contains 112,120 frontal chest films, and the MURA dataset contains 40,561 upper limb radiographs. A subset of around 700 images from both datasets was reviewed by a board-certified radiologist, and the quality of the original labels was determined. Results: The ChestXray14 labels did not accurately reflect the visual content of the images, with positive predictive values mostly between 10% and 30% lower than the values presented in the original documentation. There were other significant problems, with examples of hidden stratification and label disambiguation failure. The MURA labels were more accurate, but the original normal/abnormal labels were inaccurate for the subset of cases with degenerative joint disease, with a sensitivity of 60% and a specificity of 82%. Conclusion: Visual inspection of images is a necessary component of understanding large image datasets. We recommend that teams producing public datasets should perform this important quality control procedure and include a thorough description of their findings, along with an explanation of the data generating procedures and labelling rules, in the documentation for their datasets.
Current approaches to explaining the decisions of deep learning systems for medical tasks have focused on visualising the elements that have contributed to each decision. We argue that such approaches are not enough to open the black box of medical d
ecision making systems because they are missing a key component that has been used as a standard communication tool between doctors for centuries: language. We propose a model-agnostic interpretability method that involves training a simple recurrent neural network model to produce descriptive sentences to clarify the decision of deep learning classifiers. We test our method on the task of detecting hip fractures from frontal pelvic x-rays. This process requires minimal additional labelling despite producing text containing elements that the original deep learning classification model was not specifically trained to detect. The experimental results show that: 1) the sentences produced by our method consistently contain the desired information, 2) the generated sentences are preferred by doctors compared to current tools that create saliency maps, and 3) the combination of visualisations and generated text is better than either alone.
We developed an automated deep learning system to detect hip fractures from frontal pelvic x-rays, an important and common radiological task. Our system was trained on a decade of clinical x-rays (~53,000 studies) and can be applied to clinical data,
automatically excluding inappropriate and technically unsatisfactory studies. We demonstrate diagnostic performance equivalent to a human radiologist and an area under the ROC curve of 0.994. Translated to clinical practice, such a system has the potential to increase the efficiency of diagnosis, reduce the need for expensive additional testing, expand access to expert level medical image interpretation, and improve overall patient outcomes.
We propose new methods for the prediction of 5-year mortality in elderly individuals using chest computed tomography (CT). The methods consist of a classifier that performs this prediction using a set of features extracted from the CT image and segme
ntation maps of multiple anatomic structures. We explore two approaches: 1) a unified framework based on deep learning, where features and classifier are automatically learned in a single optimisation process; and 2) a multi-stage framework based on the design and selection/extraction of hand-crafted radiomics features, followed by the classifier learning process. Experimental results, based on a dataset of 48 annotated chest CTs, show that the deep learning model produces a mean 5-year mortality prediction accuracy of 68.5%, while radiomics produces a mean accuracy that varies between 56% to 66% (depending on the feature selection/extraction method and classifier). The successful development of the proposed models has the potential to make a profound impact in preventive and personalised healthcare.
