Huang, Ming

Patient portals have been widely used by patients to enable timely communications with their providers via secure messaging for various issues including transportation barriers. The large volume of portal messages offers an invaluable opportunity for studying transportation barriers reported by patients. In this work, we explored the feasibility of cutting-edge deep learning techniques for identifying transportation issues mentioned in patient portal messages with deep semantic embeddings. The successful creation of annotated corpus and identification of 7 transportation issues showed the feasibility of this strategy. The developed annotated corpus could aid in developing an artificial intelligence tool to automatically identify transportation issues from millions of patient portal messages. The identified specific transportation issues and the analysis of patient demographics could shed light on how to reduce transportation gaps for patients.

1512 Background: In response to the COVID-19 pandemic, many cancer practices adopted telehealth, including telephone and video appointments. Following a period of initial expansion that began in March 2020, sustained telehealth integration has emerged across the Mayo Clinic Cancer Practice (MCCP) in 2021. The primary objective of this study was to identify factors associated with utilization of telehealth appointments. Methods: A cross-sectional, multi-site, retrospective analysis was conducted across MCCP – a multisite, multiregional cancer practice with tertiary referral campuses in Minnesota, Florida, and Arizona, as well as rural, community-based hospitals and clinics throughout the Upper Midwest. Multivariable models were used to examine the association of patient- and provider-level variables with telehealth utilization. Results: Outpatient appointments conducted in July – August 2019 (n = 32,932) were compared with those from 2020 (n = 33,662) and 2021 (n = 35,486). The rate of telehealth appointment utilization increased from <0.01% in 2019 to 11.0% in 2020 and 14.0% in 2021. The strongest provider-level predictor of telehealth utilization was female physician provider type (OR 1.06, 95% CI 1.01 to 1.11; P = 0.0297), a trend consistently observed across career stages, practice locations and settings in 2020 and 2021. Additionally, while the rate of telehealth utilization was not significantly different at referral and community-based campuses in 2020, providers at referral campuses were significantly more likely to utilize telehealth than community-based campuses in 2021 (OR 1.1, 95% CI 1.01 to 1.12; P = 0.0289). Regarding patient-level factors, rural residence (defined by Rural-Urban Commuting Area codes), which accounted for 44.2% of the patient population, was significantly associated with lower telehealth utilization as compared to patients with urban residences, particularly for video appointments (OR 1.04, 95% CI 1.02 to 1.07; P < 0.0001). Notably, the disparity in telehealth utilization between rural and urban populations was found to be less pronounced in 2021 as compared to 2020. Conclusions: Multivariable analysis across a multi-site, multi-regional cancer practice identified several factors associated with increased telehealth utilization. These included female physician provider type, referral-based campuses, and patients residing in urban settings. A detailed understanding of the factors that influence telehealth utilization – a method of care delivery which represents a “new normal” across many cancer practices – will be essential to enable continued equitable access to high-quality, high-impact, patient-centered cancer care.

Abstract Internal validation is the most popular evaluation strategy used for drug–target predictive models. The simple random shuffling in the cross-validation, however, is not always ideal to handle large, diverse and copious datasets as it could potentially introduce bias. Hence, these predictive models cannot be comprehensively evaluated to provide insight into their general performance on a variety of use-cases (e.g. permutations of different levels of connectiveness and categories in drug and target space, as well as validations based on different data sources). In this work, we introduce a benchmark, BETA, that aims to address this gap by (i) providing an extensive multipartite network consisting of 0.97 million biomedical concepts and 8.5 million associations, in addition to 62 million drug–drug and protein–protein similarities and (ii) presenting evaluation strategies that reflect seven cases (i.e. general, screening with different connectivity, target and drug screening based on categories, searching for specific drugs and targets and drug repurposing for specific diseases), a total of seven Tests (consisting of 344 Tasks in total) across multiple sampling and validation strategies. Six state-of-the-art methods covering two broad input data types (chemical structure- and gene sequence-based and network-based) were tested across all the developed Tasks. The best-worst performing cases have been analyzed to demonstrate the ability of the proposed benchmark to identify limitations of the tested methods for running over the benchmark tasks. The results highlight BETA as a benchmark in the selection of computational strategies for drug repurposing and target discovery.

AbstractPurposeRural populations are disproportionately affected by the COVID‐19 pandemic. We characterized urban‐rural disparities in patient portal messaging utilization for COVID‐19, and, of those who used the portal during its early stage in the Midwest.MethodsWe collected over 1 million portal messages generated by midwestern Mayo Clinic patients from February to August 2020. We analyzed patient‐generated messages (PGMs) on COVID‐19 by urban‐rural locality and incorporated patients’ sociodemographic factors into the analysis.FindingsThe urban‐rural ratio of portal users, message senders, and COVID‐19 message senders was 1.18, 1.31, and 1.79, indicating greater use among urban patients. The urban‐rural ratio (1.69) of PGMs on COVID‐19 was higher than that (1.43) of general PGMs. The urban‐rural ratios of messaging were 1.72‐1.85 for COVID‐19‐related care and 1.43‐1.66 for other health care issues on COVID‐19. Compared with urban patients, rural patients sent fewer messages for COVID‐19 diagnosis and treatment but more messages for other reasons related to COVID‐19‐related health care (eg, isolation and anxiety). The frequent senders of COVID‐19‐related messages among rural patients were 40+ years old, women, married, and White.ConclusionsIn this Midwest health system, rural patients were less likely to use patient online services during a pandemic and their reasons for its use differ from urban patients. Results suggest opportunities for increasing equity in rural patient engagement in patient portals (in particular, minority populations) for COVID‐19. Public health intervention strategies could target reasons why rural patients might seek health care in a pandemic, such as social isolation and anxiety.

Background . Patients increasingly use asynchronous communication platforms to converse with care teams. Natural language processing (NLP) to classify content and automate triage of these messages has great potential to enhance clinical efficiency. We characterize the contents of a corpus of portal messages generated by patients using NLP methods. We aim to demonstrate descriptive analyses of patient text that can contribute to the development of future sophisticated NLP applications. Methods . We collected approximately 3,000 portal messages from the cardiology, dermatology, and gastroenterology departments at Mayo Clinic. After labeling these messages as either Active Symptom, Logistical, Prescription, or Update, we used NER (named entity recognition) to identify medical concepts based on the UMLS library. We hierarchically analyzed the distribution of these messages in terms of departments, message types, medical concepts, and keywords therewithin. Results . Active Symptom and Logistical content types comprised approximately 67% of the message cohort. The “Findings” medical concept had the largest number of keywords across all groupings of content types and departments. “Anatomical Sites” and “Disorders” keywords were more prevalent in Active Symptom messages, while “Drugs” keywords were most prevalent in Prescription messages. Logistical messages tended to have the lower proportions of “Anatomical Sites,”, “Disorders,”, “Drugs,”, and “Findings” keywords when compared to other message content types. Conclusions . This descriptive corpus analysis sheds light on the content and foci of portal messages. The insight into the content and differences among message themes can inform the development of more robust NLP models.

Abstract Defining patient-to-patient similarity is essential for the development of precision medicine in clinical care and research. Conceptually, the identification of similar patient cohorts appears straightforward; however, universally accepted definitions remain elusive. Simultaneously, an explosion of vendors and published algorithms have emerged and all provide varied levels of functionality in identifying patient similarity categories. To provide clarity and a common framework for patient similarity, a workshop at the American Medical Informatics Association 2019 Annual Meeting was convened. This workshop included invited discussants from academics, the biotechnology industry, the FDA, and private practice oncology groups. Drawing from a broad range of backgrounds, workshop participants were able to coalesce around 4 major patient similarity classes: (1) feature, (2) outcome, (3) exposure, and (4) mixed-class. This perspective expands into these 4 subtypes more critically and offers the medical informatics community a means of communicating their work on this important topic.

Abstract To enable modularization for network-based prediction, we conducted a review of known methods conducting the various subtasks corresponding to the creation of a drug–target prediction framework and associated benchmarking to determine the highest-performing approaches. Accordingly, our contributions are as follows: (i) from a network perspective, we benchmarked the association-mining performance of 32 distinct subnetwork permutations, arranging based on a comprehensive heterogeneous biomedical network derived from 12 repositories; (ii) from a methodological perspective, we identified the best prediction strategy based on a review of combinations of the components with off-the-shelf classification, inference methods and graph embedding methods. Our benchmarking strategy consisted of two series of experiments, totaling six distinct tasks from the two perspectives, to determine the best prediction. We demonstrated that the proposed method outperformed the existing network-based methods as well as how combinatorial networks and methodologies can influence the prediction. In addition, we conducted disease-specific prediction tasks for 20 distinct diseases and showed the reliability of the strategy in predicting 75 novel drug–target associations as shown by a validation utilizing DrugBank 5.1.0. In particular, we revealed a connection of the network topology with the biological explanations for predicting the diseases, ‘Asthma’ ‘Hypertension’, and ‘Dementia’. The results of our benchmarking produced knowledge on a network-based prediction framework with the modularization of the feature selection and association prediction, which can be easily adapted and extended to other feature sources or machine learning algorithms as well as a performed baseline to comprehensively evaluate the utility of incorporating varying data sources.