Automating Clinical Trial Matches Via Natural Language Processing of Synthetic Electronic Health Records and Clinical Trial Eligibility Criteria.

Clinical trials are critical to many medical advances; however, recruiting patients remains a persistent obstacle. Automated clinical trial matching could expedite recruitment across all trial phases. We detail our initial efforts towards automating the matching process by linking realistic synthetic electronic health records to clinical trial eligibility criteria using natural language processing methods. We also demonstrate how the Sørensen-Dice Index can be adapted to quantify match quality between a patient and a clinical trial.

Transfer Learning for Mortality Prediction in Non-Small Cell Lung Cancer with Low-Resolution Histopathology Slide Snapshots.

High-resolution whole slide image scans of histopathology slides have been widely used in recent years for prediction in cancer. However, in some cases, clinical informatics practitioners may only have access to low-resolution snapshots of histopathology slides, not high-resolution scans. We evaluated strategies for training neural network prognostic models in non-small cell lung cancer (NSCLC) based on low-resolution snapshots, using data from the Veterans Affairs Precision Oncology Data Repository. We compared strategies without transfer learning, with transfer learning from general domain images, and with transfer learning from publicly available high-resolution histopathology scans. We found transfer learning from high-resolution scans achieved significantly better performance than other strategies. Our contribution provides a foundation for future development of prognostic models in NSCLC that incorporate data from low-resolution pathology slide snapshots alongside known clinical predictors.

Deep learning classification of COVID-19 in chest radiographs: performance and influence of supplemental training.

Purpose: Accurate classification of COVID-19 in chest radiographs is invaluable to hard-hit pandemic hot spots. Transfer learning techniques for images using well-known convolutional neural networks show promise in addressing this problem. These methods can significantly benefit from supplemental training on similar conditions, considering that there currently exists no widely available chest x-ray dataset on COVID-19. We evaluate whether targeted pretraining for similar tasks in radiography labeling improves classification performance in a sample radiograph dataset containing COVID-19 cases. Approach: We train a DenseNet121 to classify chest radiographs through six training schemes. Each training scheme is designed to incorporate cases from established datasets for general findings in chest radiography (CXR) and pneumonia, with a control scheme with no pretraining. The resulting six permutations are then trained and evaluated on a dataset of 1060 radiographs collected from 475 patients after March 2020, containing 801 images of laboratory-confirmed COVID-19 cases. Results: Sequential training phases yielded substantial improvement in classification accuracy compared to a baseline of standard transfer learning with ImageNet parameters. The test set area under the receiver operating characteristic curve for COVID-19 classification improved from 0.757 in the control to 0.857 for the optimal training scheme in the available images. Conclusions: We achieve COVID-19 classification accuracies comparable to previous benchmarks of pneumonia classification. Deliberate sequential training, rather than pooling datasets, is critical in training effective COVID-19 classifiers within the limitations of early datasets. These findings bring clinical-grade classification through CXR within reach for more regions impacted by COVID-19.

A comparison of COVID-19 and imaging radiation risk in clinical patient populations.

The outbreak of coronavirus SARS-COV2 affected more than 180 countries necessitating fast and accurate diagnostic tools. Reverse transcriptase polymerase chain reaction (RT-PCR) has been identified as a gold standard test with Chest CT and Chest Radiography showing promising results as well. However, radiological solutions have not been used extensively for the diagnosis of COVID-19 disease, partly due to radiation risk. This study aimed to provide quantitative comparison of imaging radiation risk versus COVID risk. The analysis was performed in terms of mortality rate per age group. COVID-19 mortality was extracted from epidemiological data across 299, 004 patients published by ISS-Integrated surveillance of COVID-19 in Italy. For radiological risk, the study considered 659 Chest CT performed in adult patients. Organ doses were estimated using a Monte Carlo method and then used to calculate Risk Index that was converted into an upper bound for related mortality rate following NCI-SEER data. COVID-19 mortality showed a rapid rise for ages >30 years old (min: 0.30%; max: 30.20%), whereas only four deaths were reported in the analysed patient cohort for ages <20 years old. The rates decreased for radiation risk across age groups. The median mortality rate across all ages for Chest-CT and Chest-Radiography were 0.007% (min: 0.005%; max: 0.011%) and 0.0003% (min: 0.0002%; max: 0.0004%), respectively. COVID-19, Chest Radiography, and Chest CT mortality rates showed different magnitudes and trends across age groups. In higher ages, the risk of COVID-19 far outweighs that of radiological exams. Based on risk comparison alone, Chest Radiography and CT for COVID-19 care is justified for patients older than 20 and 30 years old, respectively. Notwithstanding other aspects of diagnosis, the present results capture a component of risk consideration associated with the use of imaging for COVID. Once integrated with other diagnostic factors, they may help inform better management of the pandemic.

Robust Prediction Of Treatment Times In Concurrent Patient Care.

Outpatient centers comprised of many concurrent clinics increasingly see higher patient volumes. In these centers, decisions to improve clinic flow must account for the high degree of interdependence when critical personnel or equipment is shared between clinics. Discrete event simulation models have provided clinical decision support, but rarely address high-volume clinics with shared resources. While highly complex models are now capable of representing clinics in detail, validation techniques often do not evaluate model predictive performance when presented with new data. Cross-validation provides a means to evaluate the robustness of model treatment time predictions when ongoing data collection in clinics is impractical. Ensuring robust predictions assures validity in the use of models to optimize clinic performance. We apply cross-validation in evaluating a model of glaucoma clinic service at Duke Eye Center. In-person observation is used to verify the accuracy of operations data collected through electronic health records (EHR). From the EHR data, we formulate a stochastic reward net model, employing phase-type distributions to represent treatment durations, and solved through discrete event simulation. The model is formulated in two configurations to represent (1) concurrent demand on clinic staff, or (2) independently functioning clinics. Evaluating these two alternatives in cross-validation studies, we find model prediction accuracy improves when interdependence is explicitly modeled in the examined setting.