Predictive models of long COVID.

BACKGROUND: The cause and symptoms of long COVID are poorly understood. It is challenging to predict whether a given COVID-19 patient will develop long COVID in the future. METHODS: We used electronic health record (EHR) data from the National COVID Cohort Collaborative to predict the incidence of long COVID. We trained two machine learning (ML) models - logistic regression (LR) and random forest (RF). Features used to train predictors included symptoms and drugs ordered during acute infection, measures of COVID-19 treatment, pre-COVID comorbidities, and demographic information. We assigned the 'long COVID' label to patients diagnosed with the U09.9 ICD10-CM code. The cohorts included patients with (a) EHRs reported from data partners using U09.9 ICD10-CM code and (b) at least one EHR in each feature category. We analysed three cohorts: all patients (n = 2,190,579; diagnosed with long COVID = 17,036), inpatients (149,319; 3,295), and outpatients (2,041,260; 13,741). FINDINGS: LR and RF models yielded median AUROC of 0.76 and 0.75, respectively. Ablation study revealed that drugs had the highest influence on the prediction task. The SHAP method identified age, gender, cough, fatigue, albuterol, obesity, diabetes, and chronic lung disease as explanatory features. Models trained on data from one N3C partner and tested on data from the other partners had average AUROC of 0.75. INTERPRETATION: ML-based classification using EHR information from the acute infection period is effective in predicting long COVID. SHAP methods identified important features for prediction. Cross-site analysis demonstrated the generalizability of the proposed methodology. FUNDING: NCATS U24 TR002306, NCATS UL1 TR003015, Axle Informatics Subcontract: NCATS-P00438-B, NIH/NIDDK/OD, PSR2015-1720GVALE_01, G43C22001320007, and Director, Office of Science, Office of Basic Energy Sciences of the U.S. Department of Energy Contract No. DE-AC02-05CH11231.

Consistent connectome landscape mining for cross-site brain disease identification using functional MRI.

Many human brain disorders are associated with characteristic alterations in functional connectivity of the brain. A lot of efforts have been devoted to mining disease-related biomarkers for identifying patients with brain disorders from normal controls. However, previous studies show largely inconsistent findings due to variability across numerous study-specific factors such as heterogeneity across different preprocessing pipelines or the use of multi-site data. Also, existing methods usually employ human-engineered features (e.g., graph-theoretical measures) that may be less discriminate for disease identification. To this end, we propose a novel Connectome Landscape Modeling (CLM) method that can mine cross-site consistent connectome landscape and extract data-driven representation of functional connectivity networks for brain disorder identification. Specifically, with functional connectivity networks as input, the proposed CLM model aims to learn a weight matrix for joint cross-site consistent connectome landscape learning, network feature extraction, and disease identification. We impose the row-column overlap norm penalty on the network-based predictor to capture consistent connectome landscape across multiple sites. To capture site-specific patterns, we introduce an ℓ1-norm penalty in CLM. We develop an efficient algorithm based on the Alternating Direction Method of Multipliers (ADMM) to solve the proposed objective function. Experimental results on three real-world fMRI datasets demonstrate the potential use of our CLM in cross-site brain disorder analysis.

Barriers and facilitators to implementation of the Accountable Health Communities (AHC) Model: Findings from a between-site qualitative assessment of implementation strategies.

Introduction: A multitude of HRSN interventions are undergoing testing in the U.S., with the CMS Accountable Health Communities (AHC) Model as the largest. HRSN interventions typically include screening for social needs, referral to community resources, and patient navigation to ensure needs are met. There is currently a paucity of evidence on implementation of HRSN interventions. The Consolidated Framework for Implementation Research (CFIR) is a determinant framework widely used to plan and assess implementation. To the authors knowledge, there are no published studies assessing CFIR constructs for HRSN intervention implementation in the U.S. In the Assessment step of the Strengthening Peer AHC Navigation (SPAN) model, a between-site qualitative assessment methodology was used to examine implementation within and between AHC bridge organizations (BOs) within six ERIC implementation strategies identified by the authors based on AHC Model requirements. Objective: Our aim was to identify and present between-site barriers and facilitators to AHC Model implementation strategies. Design: A multi-site qualitative analysis methodology was used. CFIR determinants were linked to six Expert Recommendations for Implementing Change (ERIC) strategies: staff training, identify and prepare champions, facilitation, community resource engagement (alignment through advisory boards and working groups), data systems, and quality monitoring and assurance. Interviews were analyzed using thematic content analysis in NVivo 12 (QSR International). Setting: Five health-related bridge organizations participating in the AHC Model. Results: Fifty-eight interviews were completed with 34 staff and 24 patients or patient proxies. Facilitators were identified across five of the six ERIC strategies. Barriers were identified across all six. While organizations found the AHC Model compatible and facilitators to implementation included previous experience, meeting patient needs and resources, and leadership engagement and support, a number of barriers presented challenges to implementation. Issues with adequate staff training, staff skills to resolve HRSN, including patient communication and boundary spanning, setting staff goals, beneficiary caseloads and measurement of progress, data infrastructure (including EHR), available resources to implement and differences in perceptions between clinical delivery site (CDS), and CSP of how to measure and resolve HRSN. Conclusions and relevance: The conduct of a pre-implementation readiness assessment benefited from identifying CFIR determinants linked to various ERIC implementation strategies.