No abstract

Since late 2019, the novel coronavirus SARS-CoV-2 has introduced a wide array of health challenges globally. In addition to a complex acute presentation that can affect multiple organ systems, increasing evidence points to long-term sequelae being common and impactful. As the worldwide scientific community forges ahead with efforts to characterize a wide range of outcomes associated with SARS-CoV-2 infection, the proliferation of available data has made it clear that formal definitions are needed in order to design robust and consistent studies of Long COVID that consistently capture variation in long-term outcomes. In the present study, we investigate the definitions used in the literature published to date and compare them against data available from electronic health records and patient-reported information collected via surveys. Long COVID holds the potential to produce a second public health crisis on the heels of the pandemic. Proactive efforts to identify the characteristics of this heterogeneous condition are imperative for a rigorous scientific effort to investigate and mitigate this threat.

Automatic summarization evaluation is critical to the development of summarization systems. While ROUGE has been shown to correlate well with human evaluation for content match in text summarization, there are many characteristics in multiparty meeting domain, which may pose potential problems to ROUGE. In this paper, we carefully examine how well the ROUGE scores correlate with human evaluation for extractive meeting summarization. Our experiments show that generally the correlation is rather low, but a significantly better correlation can be obtained by accounting for several unique meeting characteristics, such as disfluencies and speaker information, especially when evaluating system-generated summaries.

PURPOSE Variation in risk of adverse clinical outcomes in patients with cancer and COVID-19 has been reported from relatively small cohorts. The NCATS’ National COVID Cohort Collaborative (N3C) is a centralized data resource representing the largest multicenter cohort of COVID-19 cases and controls nationwide. We aimed to construct and characterize the cancer cohort within N3C and identify risk factors for all-cause mortality from COVID-19. METHODS We used 4,382,085 patients from 50 US medical centers to construct a cohort of patients with cancer. We restricted analyses to adults ≥ 18 years old with a COVID-19–positive or COVID-19–negative diagnosis between January 1, 2020, and March 25, 2021. We followed N3C selection of an index encounter per patient for analyses. All analyses were performed in the N3C Data Enclave Palantir platform. RESULTS A total of 398,579 adult patients with cancer were identified from the N3C cohort; 63,413 (15.9%) were COVID-19–positive. Most common represented cancers were skin (13.8%), breast (13.7%), prostate (10.6%), hematologic (10.5%), and GI cancers (10%). COVID-19 positivity was significantly associated with increased risk of all-cause mortality (hazard ratio, 1.20; 95% CI, 1.15 to 1.24). Among COVID-19–positive patients, age ≥ 65 years, male gender, Southern or Western US residence, an adjusted Charlson Comorbidity Index score ≥ 4, hematologic malignancy, multitumor sites, and recent cytotoxic therapy were associated with increased risk of all-cause mortality. Patients who received recent immunotherapies or targeted therapies did not have higher risk of overall mortality. CONCLUSION Using N3C, we assembled the largest nationally representative cohort of patients with cancer and COVID-19 to date. We identified demographic and clinical factors associated with increased all-cause mortality in patients with cancer. Full characterization of the cohort will provide further insights into the effects of COVID-19 on cancer outcomes and the ability to continue specific cancer treatments.

Objective Clinical questions are often long and complex and take many forms. We have built a clinical question answering system named AskHERMES to perform robust semantic analysis on complex clinical questions and output question-focused extractive summaries as answers. Design This paper describes the system architecture and a preliminary evaluation of AskHERMES, which implements innovative approaches in question analysis, summarization, and answer presentation. Five types of resources were indexed in this system: MEDLINE abstracts, PubMed Central full-text articles, eMedicine documents, clinical guidelines and Wikipedia articles. Measurement We compared the AskHERMES system with Google (Google and Google Scholar) and UpToDate and asked physicians to score the three systems by ease of use, quality of answer, time spent, and overall performance. Results AskHERMES allows physicians to enter a question in a natural way with minimal query formulation and allows physicians to efficiently navigate among all the answer sentences to quickly meet their information needs. In contrast, physicians need to formulate queries to search for information in Google and UpToDate. The development of the AskHERMES system is still at an early stage, and the knowledge resource is limited compared with Google or UpToDate. Nevertheless, the evaluation results show that AskHERMES’ performance is comparable to the other systems. In particular, when answering complex clinical questions, it demonstrates the potential to outperform both Google and UpToDate systems. Conclusions AskHERMES, available at http://www.AskHERMES.org, has the potential to help physicians practice evidence-based medicine and improve the quality of patient care.