While deep learning methods are increasingly being applied to tasks such as computer-aided diagnosis, these models are difficult to interpret, do not incorporate prior domain knowledge, and are often considered as a "black-box." The lack of model interpretability hinders them from being fully understood by target users such as radiologists. In this paper, we present a novel interpretable deep hierarchical semantic convolutional neural network (HSCNN) to predict whether a given pulmonary nodule observed on a computed tomography (CT) scan is malignant. Our network provides two levels of output: 1) low-level radiologist semantic features; and 2) a high-level malignancy prediction score. The low-level semantic outputs quantify the diagnostic features used by radiologists and serve to explain how the model interprets the images in an expert-driven manner. The information from these low-level tasks, along with the representations learned by the convolutional layers, are then combined and used to infer the high-level task of predicting nodule malignancy. This unified architecture is trained by optimizing a global loss function including both low-and high-level tasks, thereby learning all the parameters within a joint framework. Our experimental results using the Lung Image Database Consortium (LIDC) show that the proposed method not only produces interpretable lung cancer predictions but also achieves significantly better results compared to common 3D CNN approaches.

An increasing amount of data is now accrued in medical information systems; however, the organization of this data is still primarily driven by data source, and does not support the cognitive processes of physicians. As such, new methods to visualize patient medical records are becoming imperative in order to assist physicians with clinical tasks and medical decision-making. The TimeLine system is a problem-centric temporal visualization for medical data: information contained with medical records is reorganized around medical disease entities and conditions. Automatic construction of the TimeLine display from existing clinical repositories occurs in three steps: 1) data access, which uses an eXtensible Markup Language (XML) data representation to handle distributed, heterogeneous medical databases; 2) data mapping and reorganization, reformulating data into hierarchical, problemcentric views; and 3) data visualization, which renders the display to a target presentation platform. Leveraging past work, we describe the latter two components of the TimeLine system in this paper, and the issues surrounding the creation of medical problems lists and temporal visualization of medical data. A driving factor in the development of TimeLine was creating a foundation upon which new data types and the visualization metaphors could be readily incorporated.

Asthma is the most prevalent chronic disease among pediatrics, as it is the leading cause of student absenteeism and hospitalization for those under the age of 15. To address the significant need to manage this disease in children, the authors present a mobile health (mHealth) system that determines the risk of an asthma attack through physiological and environmental wireless sensors and representational state transfer application program interfaces (RESTful APIs). The data is sent from wireless sensors to a smartwatch application (app) via a Health Insurance Portability and Accountability Act (HIPAA) compliant cryptography framework, which then sends data to a cloud for real-time analytics. The asthma risk is then sent to the smartwatch and provided to the user via simple graphics for easy interpretation by children. After testing the safety and feasibility of the system in an adult with moderate asthma prior to testing in children, it was found that the analytics model is able to determine the overall asthma risk (high, medium, or low risk) with an accuracy of 80.10±14.13%. Furthermore, the features most important for assessing the risk of an asthma attack were multifaceted, highlighting the importance of continuously monitoring different wireless sensors and RESTful APIs. Future testing this asthma attack risk prediction system in pediatric asthma individuals may lead to an effective self-management asthma program.

No abstract

Provisional records from the US Centers for Disease Control and Prevention (CDC) through July 2020 indicate that overdose deaths spiked during the early months of the COVID-19 pandemic, yet more recent trends are not available, and the data are not disaggregated by month of occurrence, race/ethnicity, or other social categories. In contrast, data from emergency medical services (EMS) provide a source of information nearly in real time that may be useful for rapid and more granular surveillance of overdose mortality.OBJECTIVE To describe racial/ethnic, social, and geographic trends in EMS-observed overdoseassociated cardiac arrests during the COVID-19 pandemic through December 2020 and assess the concordance with CDC-reported provisional total overdose mortality through May 2020.DESIGN, SETTING, AND PARTICIPANTS This cohort study included more than 11 000 EMS agencies in 49 US states that participate in the National EMS Information System and 83.7 million EMS activations in which patient contact was made.EXPOSURES Year and month of occurrence of overdose-associated cardiac arrest; patient race/ethnicity; census region and division; county-level urbanicity; and zip code-level racial/ethnic composition, poverty, and educational attainment. MAIN OUTCOMES AND MEASURESOverdose-associated cardiac arrests per 100 000 EMS activations with patient contact in 2020 were compared with a baseline of values from 2018 and 2019. Aggregate numbers of overdose-associated cardiac arrests and percentage increases were compared with provisional total mortality in CDC records from rolling 12-month windows with end months spanning January 2018 through July 2020.RESULTS Among 33.4 million EMS activations in 2020, 16.8 million (50.2%) involved female patients and 16.3 million (48.8%) involved non-Hispanic White individuals. Overdoseassociated cardiac arrests were elevated by 42.1% nationally in 2020 (42.3 per 100 000 EMS activations at baseline vs 60.1 per 100 000 EMS activations in 2020). The highest percentage increases were seen among Latinx individuals (49.7%; 38.8 per 100 000 activations at baseline vs 58.1 per 100 000 activations in 2020) and Black or African American individuals (50.3%; 21.5 per 100 000 activations at baseline vs 32.3 per 100 000 activations in 2020), people living in more impoverished neighborhoods (46.4%; 42.0 per 100 000 activations at baseline vs 61.5 per 100 000 activations in 2020), and the Pacific states (63.8%; 33.1 per 100 000 activations at baseline vs 54.2 per 100 000 activations in 2020), despite lower rates at baseline for these groups. The EMS records were available 6 to 12 months ahead of CDC mortality figures and showed a high concordance (r = 0.98) for months in which both data sets were available. If the historical association between EMS-observed and total overdose mortality holds true, an expected total of approximately 90 632 (95% CI, 85 737-95 525) overdose deaths may eventually be reported by the CDC for 2020. CONCLUSIONS AND RELEVANCEIn this cohort study, records from EMS agencies provided a...