Machine learning to understand risks for severe COVID-19 outcomes: a retrospective cohort study of immune-mediated inflammatory diseases, immunomodulatory medications, and comorbidities in a large US health-care system

BACKGROUND

In the context of immune-mediated inflammatory diseases (IMIDs), COVID-19 outcomes are incompletely understood and vary considerably depending on the patient population studied. We aimed to analyse severe COVID-19 outcomes and to investigate the effects of the pandemic time period and the risks associated with individual IMIDs, classes of immunomodulatory medications (IMMs), chronic comorbidities, and COVID-19 vaccination status.

METHODS

In this retrospective cohort study, clinical data were derived from the electronic health records of an integrated health-care system serving patients in 51 hospitals and 1085 clinics across seven US states (Providence St Joseph Health). Data were observed for patients (no age restriction) with one or more IMID and for unmatched controls without IMIDs. COVID-19 was identified with a positive nucleic acid amplification test result for SARS-CoV-2. Two timeframes were analysed: March 1, 2020-Dec 25, 2021 (pre-omicron period), and Dec 26, 2021-Aug 30, 2022 (omicron-predominant period). Primary outcomes were hospitalisation, mechanical ventilation, and mortality in patients with COVID-19. Factors, including IMID diagnoses, comorbidities, long-term use of IMMs, and COVID-19 vaccination status, were analysed with multivariable logistic regression (LR) and extreme gradient boosting (XGB).

FINDINGS

Of 2 167 656 patients tested for SARS-CoV-2, 290 855 (13·4%) had confirmed COVID-19: 15 397 (5·3%) patients with IMIDs and 275 458 (94·7%) without IMIDs. In the pre-omicron period, 169 993 (11·2%) of 1 517 295 people who were tested for COVID-19 tested positive, of whom 23 330 (13·7%) were hospitalised, 1072 (0·6%) received mechanical ventilation, and 5294 (3·1%) died. Compared with controls, patients with IMIDs and COVID-19 had higher rates of hospitalisation (1176 [14·6%] vs 22 154 [13·7%]; p=0·024) and mortality (314 [3·9%] vs 4980 [3·1%]; p<0·0001). In the omicron-predominant period, 120 862 (18·6%) of 650 361 patients tested positive for COVID-19, of whom 14 504 (12·0%) were hospitalised, 567 (0·5%) received mechanical ventilation, and 2001 (1·7%) died. Compared with controls, patients with IMIDs and COVID-19 (7327 [17·3%] of 42 249) had higher rates of hospitalisation (13 422 [11·8%] vs 1082 [14·8%]; p<0·0001) and mortality (1814 [1·6%] vs 187 [2·6%]; p<0·0001). Age was a risk factor for worse outcomes (adjusted odds ratio [OR] from 2·1 [95% CI 2·0-2·1]; p<0·0001 to 3·0 [2·9-3·0]; p<0·0001), whereas COVID-19 vaccination (from 0·082 [0·080-0·085]; p<0·0001 to 0·52 [0·50-0·53]; p<0·0001) and booster vaccination (from 2·1 [2·0-2·2]; p<0·0001 to 3·0 [2·9-3·0]; p<0·0001) status were associated with better outcomes. Seven chronic comorbidities were significant risk factors during both time periods for all three outcomes: atrial fibrillation, coronary artery disease, heart failure, chronic kidney disease, chronic obstructive pulmonary disease, chronic liver disease, and cancer. Two IMIDs, asthma (adjusted OR from 0·33 [0·32-0·34]; p<0·0001 to 0·49 [0·48-0·51]; p<0·0001) and psoriasis (from 0·52 [0·48-0·56] to 0·80 [0·74-0·87]; p<0·0001), were associated with a reduced risk of severe outcomes. IMID diagnoses did not appear to be significant risk factors themselves, but results were limited by small sample size, and vasculitis had high feature importance in LR. IMMs did not appear to be significant, but less frequently used IMMs were limited by sample size. XGB outperformed LR, with the area under the receiver operating characteristic curve for models across different time periods and outcomes ranging from 0·77 to 0·92.

INTERPRETATION

Our results suggest that age, chronic comorbidities, and not being fully vaccinated might be greater risk factors for severe COVID-19 outcomes in patients with IMIDs than the use of IMMs or the IMIDs themselves. Overall, there is a need to take age and comorbidities into consideration when developing COVID-19 guidelines for patients with IMIDs. Further research is needed for specific IMIDs (including IMID severity at the time of SARS-CoV-2 infection) and IMMs (considering dosage and timing before a patient's first COVID-19 infection).

FUNDING

Pfizer, Novartis, Janssen, and the National Institutes of Health.

An approach for collaborative development of a federated biomedical knowledge graph-based question-answering system: Question-of-the-Month challenges

Knowledge graphs have become a common approach for knowledge representation. Yet, the application of graph methodology is elusive due to the sheer number and complexity of knowledge sources. In addition, semantic incompatibilities hinder efforts to harmonize and integrate across these diverse sources. As part of The Biomedical Translator Consortium, we have developed a knowledge graph-based question-answering system designed to augment human reasoning and accelerate translational scientific discovery: the Translator system. We have applied the Translator system to answer biomedical questions in the context of a broad array of diseases and syndromes, including Fanconi anemia, primary ciliary dyskinesia, multiple sclerosis, and others. A variety of collaborative approaches have been used to research and develop the Translator system. One recent approach involved the establishment of a monthly "Question-of-the-Month (QotM) Challenge" series. Herein, we describe the structure of the QotM Challenge; the six challenges that have been conducted to date on drug-induced liver injury, cannabidiol toxicity, coronavirus infection, diabetes, psoriatic arthritis, and ATP1A3-related phenotypes; the scientific insights that have been gleaned during the challenges; and the technical issues that were identified over the course of the challenges and that can now be addressed to foster further development of the prototype Translator system. We close with a discussion on Large Language Models such as ChatGPT and highlight differences between those models and the Translator system.

Risk factors for severe COVID-19 outcomes: a study of immune-mediated inflammatory diseases, immunomodulatory medications, and comorbidities in a large US healthcare system

Background

COVID-19 outcomes, in the context of immune-mediated inflammatory diseases (IMIDs), are incompletely understood. Reported outcomes vary considerably depending on the patient population studied. It is essential to analyse data for a large population, while considering the effects of the pandemic time period, comorbidities, long term use of immunomodulatory medications (IMMs), and vaccination status.

Methods

In this retrospective case-control study, patients of all ages with IMIDs were identified from a large U.S. healthcare system. COVID-19 infections were identified based on SARS-CoV-2 NAAT test results. Controls without IMIDs were selected from the same database. Severe outcomes were hospitalisation, mechanical ventilation (MV), and death. We analysed data from 1 March 2020 to 30 August 2022, looking separately at both pre-Omicron and Omicron predominant periods. Factors including IMID diagnoses, comorbidities, long term use of IMMs, and vaccination and booster status were analysed using multivariable logistic regression (LR) and extreme gradient boosting (XGB).

Findings

Out of 2 167 656 patients tested for SARS-CoV-2, there were 290 855 with confirmed COVID-19 infection: 15 397 patients with IMIDs and 275 458 controls (patients without IMIDs). Age and most chronic comorbidities were risk factors for worse outcomes, whereas vaccination and boosters were protective. Patients with IMIDs had higher rates of hospitalisation and mortality compared with controls. However, in multivariable analyses, few IMIDs were rarely risk factors for worse outcomes. Further, asthma, psoriasis and spondyloarthritis were associated with reduced risk. Most IMMs had no significant association, but less frequently used IMM drugs were limited by sample size. XGB outperformed LR, with the AUROCs for models across different time periods and outcomes ranging from 0·77 to 0·92.

Interpretation

For patients with IMIDs, as for controls, age and comorbidities were risk factors for worse COVID-19 outcomes, whereas vaccinations were protective. Most IMIDs and immunomodulatory therapies were not associated with more severe outcomes. Interestingly, asthma, psoriasis and spondyloarthritis were associated with less severe COVID-19 outcomes than those expected for the population overall. These results can help inform clinical, policy and research decisions.

Funding

Pfizer, Novartis, Janssen, NIH.

Biolink Model: A universal schema for knowledge graphs in clinical, biomedical, and translational science

Within clinical, biomedical, and translational science, an increasing number of projects are adopting graphs for knowledge representation. Graph‐based data models elucidate the interconnectedness among core biomedical concepts, enable data structures to be easily updated, and support intuitive queries, visualizations, and inference algorithms. However, knowledge discovery across these “knowledge graphs” (KGs) has remained difficult. Data set heterogeneity and complexity; the proliferation of ad hoc data formats; poor compliance with guidelines on findability, accessibility, interoperability, and reusability; and, in particular, the lack of a universally accepted, open‐access model for standardization across biomedical KGs has left the task of reconciling data sources to downstream consumers. Biolink Model is an open‐source data model that can be used to formalize the relationships between data structures in translational science. It incorporates object‐oriented classification and graph‐oriented features. The core of the model is a set of hierarchical, interconnected classes (or categories) and relationships between them (or predicates) representing biomedical entities such as gene, disease, chemical, anatomic structure, and phenotype. The model provides class and edge attributes and associations that guide how entities should relate to one another. Here, we highlight the need for a standardized data model for KGs, describe Biolink Model, and compare it with other models. We demonstrate the utility of Biolink Model in various initiatives, including the Biomedical Data Translator Consortium and the Monarch Initiative, and show how it has supported easier integration and interoperability of biomedical KGs, bringing together knowledge from multiple sources and helping to realize the goals of translational science.