The rapidly expanding field of big data analytics has started to play a pivotal role in the evolution of healthcare practices and research. It has provided tools to accumulate, manage, analyze, and assimilate large volumes of disparate, structured, and unstructured data produced by current healthcare systems. Big data analytics has been recently applied towards aiding the process of care delivery and disease exploration. However, the adoption rate and research development in this space is still hindered by some fundamental problems inherent within the big data paradigm. In this paper, we discuss some of these major challenges with a focus on three upcoming and promising areas of medical research: image, signal, and genomics based analytics. Recent research which targets utilization of large volumes of medical data while combining multimodal data from disparate sources is discussed. Potential areas of research within this field which have the ability to provide meaningful impact on healthcare delivery are also examined.

Background: Automated segmentation of coronary arteries is a crucial step for computer-aided coronary artery disease (CAD) diagnosis and treatment planning. Correct delineation of the coronary artery is challenging in X-ray coronary angiography (XCA) due to the low signal-to-noise ratio and confounding background structures.Methods: A novel ensemble framework for coronary artery segmentation in XCA images is proposed, which utilizes deep learning and filter-based features to construct models using the gradient boosting decision tree (GBDT) and deep forest classifiers. The proposed method was trained and tested on 130 XCA images. For each pixel of interest in the XCA images, a 37-dimensional feature vector was constructed based on (1) the statistics of multi-scale filtering responses in the morphological, spatial, and frequency domains; and (2) the feature maps obtained from trained deep neural networks. The performance of these models was compared with those of common deep neural networks on metrics including precision, sensitivity, specificity, F1 score, AUROC (the area under the receiver operating characteristic curve), and IoU (intersection over union).Results: With hybrid under-sampling methods, the best performing GBDT model achieved a mean F1 score of 0.874, AUROC of 0.947, sensitivity of 0.902, and specificity of 0.992; while the best performing deep forest model obtained a mean F1 score of 0.867, AUROC of 0.95, sensitivity of 0.867, and specificity of 0.993. Compared with the evaluated deep neural networks, both models had better or comparable performance for all evaluated metrics with lower standard deviations over the test images.Conclusions: The proposed feature-based ensemble method outperformed common deep convolutional neural networks in most performance metrics while yielding more consistent results. Such a method can be used to facilitate the assessment of stenosis and improve the quality of care in patients with CAD.

When training a machine learning algorithm for a supervised-learning task in some clinical applications, uncertainty in the correct labels of some patients may adversely affect the performance of the algorithm. For example, even clinical experts may have less confidence when assigning a medical diagnosis to some patients because of ambiguity in the patient's case or imperfect reliability of the diagnostic criteria. As a result, some cases used in algorithm training may be mislabeled, adversely affecting the algorithm's performance. However, experts may also be able to quantify their diagnostic uncertainty in these cases. We present a robust method implemented with support vector machines (SVM) to account for such clinical diagnostic uncertainty when training an algorithm to detect patients who develop the acute respiratory distress syndrome (ARDS). ARDS is a syndrome of the critically ill that is diagnosed using clinical criteria known to be imperfect. We represent uncertainty in the diagnosis of ARDS as a graded weight of confidence associated with each training label. We also performed a novel time-series sampling method to address the problem of intercorrelation among the longitudinal clinical data from each patient used in model training to limit overfitting. Preliminary results show that we can achieve meaningful improvement in the performance of algorithm to detect patients with ARDS on a hold-out sample, when we compare our method that accounts for the uncertainty of training labels with a conventional SVM algorithm.

Endoscopic assessment of ulcerative colitis (UC) typically reports only maximum severity observed. Computer vision methods may better quantify mucosal injury detail that varies between patients. Endoscopic video from the UNIFI clinical trial comparing ustekinumab and placebo for UC were processed in a computer vision analysis that spatially mapped Mayo endoscopic scores (MES) to generate the cumulative disease score (CDS). CDS was compared to the Mayo score for differentiating ustekinumab vs. placebo treatment response and agreement with symptomatic remission at week 44. Statistical power, effect and estimated sample sizes for detecting endoscopic differences between treatments were calculated using both CDS and MES measures. Endoscopic video from a separate phase 2 clinical trial replication cohort was performed for validation of CDS performance. Among 748 induction and 348 maintenance subjects, CDS was lower in ustekinumab vs. placebo users at week 8 (141.9 vs. 184.3, P<.0001) and week 44 (78.2 vs. 151.5, P<.0001). CDS was correlated with the MES (P<.0001) and all clinical components of the partial Mayo score (P<.0001). Stratification by pre-treatment CDS revealed ustekinumab was more effective than placebo (P<.0001) with increasing effect in severe vs. mild disease (-85.0 vs. -55.4, P<.0001). Compared to the MES, CDS was more sensitive to change, needing 50% less subjects to demonstrate endoscopic differences between ustekinumab and placebo (g=0.743 vs. 0.460). CDS performance in the JAK-UC replication cohort was similar to UNIFI. As an automated and quantitative measure of global endoscopic disease severity, the CDS offers artificial intelligence enhancement of traditional MES capability to better evaluate UC in clinical trials and potentially practice.

Accurate analysis of CT brain scans is vital for diagnosis and treatment of Traumatic Brain Injuries (TBI). Automatic processing of these CT brain scans could speed up the decision making process, lower the cost of healthcare, and reduce the chance of human error. In this paper, we focus on automatic processing of CT brain images to segment and identify the ventricular systems. The segmentation of ventricles provides quantitative measures on the changes of ventricles in the brain that form vital diagnosis information.

Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Automated brain hematoma segmentation and outcome prediction for patients with TBI can effectively facilitate patient management. In this study, we propose a novel Multi-view convolutional neural network with a mixed loss to segment total acute hematoma on head CT scans collected within 24 h after the injury. Based on the automated segmentation, the volumetric distribution and shape characteristics of the hematoma were extracted and combined with other clinical observations to predict 6-month mortality. The proposed hematoma segmentation network achieved an average Dice coefficient of 0.697 and an intraclass correlation coefficient of 0.966 between the volumes estimated from the predicted hematoma segmentation and volumes of the annotated hematoma segmentation on the test set. Compared with other published methods, the proposed method has the most accurate segmentation performance and volume estimation. For 6-month mortality prediction, the model achieved an average area under the precision-recall curve (AUCPR) of 0.559 and area under the receiver operating characteristic curve (AUC) of 0.853 using 10-fold cross-validation on a dataset consisting of 828 patients. The average AUCPR and AUC of the proposed model are respectively more than 10% and 5% higher than those of the widely used IMPACT model.