Identifying who has long COVID in the USA: a machine learning approach using N3C data

Assessing the effect of selective serotonin reuptake inhibitors in the prevention of post-acute sequelae of COVID-19

Background

Post-acute sequelae of COVID-19 (PASC) produce significant morbidity, prompting evaluation of interventions that might lower risk. Selective serotonin reuptake inhibitors (SSRIs) potentially could modulate risk of PASC via their central, hypothesized immunomodulatory, and/or antiplatelet properties although clinical trial data are lacking.

Materials and Methods

This retrospective study was conducted leveraging real-world clinical data within the National COVID Cohort Collaborative (N3C) to evaluate whether SSRIs with agonist activity at the sigma-1 receptor (S1R) lower the risk of PASC, since agonism at this receptor may serve as a mechanism by which SSRIs attenuate an inflammatory response. Additionally, determine whether the potential benefit could be traced to S1R agonism. Presumed PASC was defined based on a computable PASC phenotype trained on the U09.9 ICD-10 diagnosis code.

Results

Of the 17,908 patients identified, 1521 were exposed at baseline to a S1R agonist SSRI, 1803 to a non-S1R agonist SSRI, and 14,584 to neither. Using inverse probability weighting and Poisson regression, relative risk (RR) of PASC was assessed.A 29% reduction in the RR of PASC (0.704 [95% CI, 0.58-0.85]; P = 4 ×10-4) was seen among patients who received an S1R agonist SSRI compared to SSRI unexposed patients and a 21% reduction in the RR of PASC was seen among those receiving an SSRI without S1R agonist activity (0.79 [95% CI, 0.67 - 0.93]; P = 0.005).Thus, SSRIs with and without reported agonist activity at the S1R were associated with a significant decrease in the risk of PASC.

The Prevalence of Post-Acute Sequelae of COVID-19 in Solid Organ Transplant Recipients: Evaluation of Risk in the National COVID Cohort Collaborative (N3C)

Post-acute sequelae after COVID-19 (PASC) is increasingly recognized, though data in solid organ transplant recipients (SOTR) are limited. Using the N3C, we performed 1:1 propensity score matching (PSM) of all adult SOTR and non-immunosuppressed/immunocompromised (ISC) patients with acute COVID (08-01-2021 to 01-13-2023), for a subsequent PASC diagnosis using ICD-10-CM codes. Multivariable logistic regression was used to examine the association of SOT status with PASC, but also other patient factors after stratifying by SOT status. Prior to PSM, there were 8,769 SOT and 1,576,769 non-ISC patients with acute COVID. After PSM, 8,756 SOTR and 8,756 non-ISC patients were included; 2.2% of SOTR (n=192) and 1.4% (n=122) of non-ISC patients developed PASC (p-value<0.001). In the overall matched cohort, SOT was independently associated with PASC (aOR 1.48, 95% CI 1.09-2.01). Amongst SOTR, COVID severity (aOR 11.6, 95% CI 3.93-30.0 for severe versus mild disease), older age (aOR 1.02, 95% CI 1.01-1.03 per year), and mycophenolate mofetil use (aOR 2.04, 95% CI 1.38-3.05) were each independently associated with PASC. In non-ISC patients, only depression (aOR 1.96, 95% CI 1.24-3.07) and COVID severity were. In conclusion, PASC occurs more commonly in SOTR than non-ISC patients, with differences in risk profiles based on SOT status.

Clinical coding of long COVID in primary care 2020-2023 in a cohort of 19 million adults: an OpenSAFELY analysis

Background

Long COVID is the patient-coined term for the persistent symptoms of COVID-19 illness for weeks, months or years following the acute infection. There is a large burden of long COVID globally from self-reported data, but the epidemiology, causes and treatments remain poorly understood. Primary care is used to help identify and treat patients with long COVID and therefore Electronic Health Records (EHRs) of past COVID-19 patients could be used to help fill these knowledge gaps. We aimed to describe the incidence and differences in demographic and clinical characteristics in recorded long COVID in primary care records in England.

Methods

With the approval of NHS England we used routine clinical data from over 19 million adults in England linked to SARS-COV-2 test result, hospitalisation and vaccination data to describe trends in the recording of 16 clinical codes related to long COVID between November 2020 and January 2023. Using OpenSAFELY, we calculated rates per 100,000 person-years and plotted how these changed over time. We compared crude and adjusted (for age, sex, 9 NHS regions of England, and the dominant variant circulating) rates of recorded long COVID in patient records between different key demographic and vaccination characteristics using negative binomial models.

Findings

We identified a total of 55,465 people recorded to have long COVID over the study period, which included 20,025 diagnoses codes and 35,440 codes for further assessment. The incidence of new long COVID records increased steadily over 2021, and declined over 2022. The overall rate per 100,000 person-years was 177.5 cases in women (95% CI: 175.5-179) and 100.5 in men (99.5-102). The majority of those with a long COVID record did not have a recorded positive SARS-COV-2 test 12 or more weeks before the long COVID record.

Interpretation

In this descriptive study, EHR recorded long COVID was very low between 2020 and 2023, and incident records of long COVID declined over 2022. Using EHR diagnostic or referral codes unfortunately has major limitations in identifying and ascertaining true cases and timing of long COVID.

Funding

This research was supported by the National Institute for Health and Care Research (NIHR) (OpenPROMPT: COV-LT2-0073).

Risk of Post-Acute Sequelae of SARS-CoV-2 Infection (PASC) Among Patients with Type 2 Diabetes Mellitus on Anti-Hyperglycemic Medications

Background

Observed activity of metformin in reducing the risk of severe COVID-19 suggests a potential use of the anti-hyperglycemic in the prevention of post-acute sequelae of SARS-CoV-2 infection (PASC). We assessed the 3-month and 6-month risk of PASC among patients with type 2 diabetes mellitus (T2DM) comparing metformin users to sulfonylureas (SU) or dipeptidyl peptidase-4 inhibitors (DPP4i) users.

Methods

We used de-identified patient level electronic health record data from the National Covid Cohort Collaborative (N3C) between October 2021 and April 2023. Participants were adults ≥ 18 years with T2DM who had at least one outpatient healthcare encounter in health institutions in the United States prior to COVID-19 diagnosis. The outcome of PASC was defined based on the presence of a diagnosis code for the illness or using a predicted probability based on a machine learning algorithm. We estimated the 3-month and 6-month risk of PASC and calculated crude and weighted risk ratios (RR), risk differences (RD), and differences in mean predicted probability.

Results

We identified 5596 (mean age: 61.1 years; SD: 12.6) and 1451 (mean age: 64.9 years; SD 12.5) eligible prevalent users of metformin and SU/DPP4i respectively. We did not find a significant difference in risk of PASC at 3 months (RR = 0.86 [0.56; 1.32], RD = -3.06 per 1000 [-12.14; 6.01]), or at 6 months (RR = 0.81 [0.55; 1.20], RD = -4.91 per 1000 [-14.75, 4.93]) comparing prevalent users of metformin to prevalent users of SU/ DPP4i. Similar observations were made for the outcome definition using the ML algorithm.

Conclusion

The observed estimates in our study are consistent with a reduced risk of PASC among prevalent users of metformin, however the uncertainty of our confidence intervals warrants cautious interpretations of the results. A standardized clinical definition of PASC is warranted for thorough evaluation of the effectiveness of therapies under assessment for the prevention of PASC.

EHR-based Case Identification of Pediatric Long COVID: A Report from the RECOVER EHR Cohort

Objective

Long COVID, marked by persistent, recurring, or new symptoms post-COVID-19 infection, impacts children's well-being yet lacks a unified clinical definition. This study evaluates the performance of an empirically derived Long COVID case identification algorithm, or computable phenotype, with manual chart review in a pediatric sample. This approach aims to facilitate large-scale research efforts to understand this condition better.

Methods

The algorithm, composed of diagnostic codes empirically associated with Long COVID, was applied to a cohort of pediatric patients with SARS-CoV-2 infection in the RECOVER PCORnet EHR database. The algorithm classified 31,781 patients with conclusive, probable, or possible Long COVID and 307,686 patients without evidence of Long COVID. A chart review was performed on a subset of patients (n=651) to determine the overlap between the two methods. Instances of discordance were reviewed to understand the reasons for differences.

Results

The sample comprised 651 pediatric patients (339 females, M age = 10.10 years) across 16 hospital systems. Results showed moderate overlap between phenotype and chart review Long COVID identification (accuracy = 0.62, PPV = 0.49, NPV = 0.75); however, there were also numerous cases of disagreement. No notable differences were found when the analyses were stratified by age at infection or era of infection. Further examination of the discordant cases revealed that the most common cause of disagreement was the clinician reviewers' tendency to attribute Long COVID-like symptoms to prior medical conditions. The performance of the phenotype improved when prior medical conditions were considered (accuracy = 0.71, PPV = 0.65, NPV = 0.74).

Conclusions

Although there was moderate overlap between the two methods, the discrepancies between the two sources are likely attributed to the lack of consensus on a Long COVID clinical definition. It is essential to consider the strengths and limitations of each method when developing Long COVID classification algorithms.

Identifying potential (re)hemorrhage among sporadic cerebral cavernous malformations using machine learning

The (re)hemorrhage in patients with sporadic cerebral cavernous malformations (CCM) was the primary aim for CCM management. However, accurately identifying the potential (re)hemorrhage among sporadic CCM patients in advance remains a challenge. This study aims to develop machine learning models to detect potential (re)hemorrhage in sporadic CCM patients. This study was based on a dataset of 731 sporadic CCM patients in open data platform Dryad. Sporadic CCM patients were followed up 5 years from January 2003 to December 2018. Support vector machine (SVM), stacked generalization, and extreme gradient boosting (XGBoost) were used to construct models. The performance of models was evaluated by area under receiver operating characteristic curves (AUROC), area under the precision-recall curve (PR-AUC) and other metrics. A total of 517 patients with sporadic CCM were included (330 female [63.8%], mean [SD] age at diagnosis, 42.1 [15.5] years). 76 (re)hemorrhage (14.7%) occurred during follow-up. Among 3 machine learning models, XGBoost model yielded the highest mean (SD) AUROC (0.87 [0.06]) in cross-validation. The top 4 features of XGBoost model were ranked with SHAP (SHapley Additive exPlanations). All-Elements XGBoost model achieved an AUROCs of 0.84 and PR-AUC of 0.49 in testing set, with a sensitivity of 0.86 and a specificity of 0.76. Importantly, 4-Elements XGBoost model developed using top 4 features got a AUROCs of 0.83 and PR-AUC of 0.40, a sensitivity of 0.79, and a specificity of 0.72 in testing set. Two machine learning-based models achieved accurate performance in identifying potential (re)hemorrhages within 5 years in sporadic CCM patients. These models may provide insights for clinical decision-making.

Characterization of Post-COVID-19 Definitions and Clinical Coding Practices: Longitudinal Study

BACKGROUND

Post-COVID-19 condition (colloquially known as "long COVID-19") characterized as postacute sequelae of SARS-CoV-2 has no universal clinical case definition. Recent efforts have focused on understanding long COVID-19 symptoms, and electronic health record (EHR) data provide a unique resource for understanding this condition. The introduction of the International Classification of Diseases, Tenth Revision (ICD-10) code U09.9 for "Post COVID-19 condition, unspecified" to identify patients with long COVID-19 has provided a method of evaluating this condition in EHRs; however, the accuracy of this code is unclear.

OBJECTIVE

This study aimed to characterize the utility and accuracy of the U09.9 code across 3 health care systems-the Veterans Health Administration, the Beth Israel Deaconess Medical Center, and the University of Pittsburgh Medical Center-against patients identified with long COVID-19 via a chart review by operationalizing the World Health Organization (WHO) and Centers for Disease Control and Prevention (CDC) definitions.

METHODS

Patients who were COVID-19 positive with either a U07.1 ICD-10 code or positive polymerase chain reaction test within these health care systems were identified for chart review. Among this cohort, we sampled patients based on two approaches: (1) with a U09.9 code and (2) without a U09.9 code but with a new onset long COVID-19-related ICD-10 code, which allows us to assess the sensitivity of the U09.9 code. To operationalize the long COVID-19 definition based on health agency guidelines, symptoms were grouped into a "core" cluster of 11 commonly reported symptoms among patients with long COVID-19 and an extended cluster that captured all other symptoms by disease domain. Patients having ≥2 symptoms persisting for ≥60 days that were new onset after their COVID-19 infection, with ≥1 symptom in the core cluster, were labeled as having long COVID-19 per chart review. The code's performance was compared across 3 health care systems and across different time periods of the pandemic.

RESULTS

Overall, 900 patient charts were reviewed across 3 health care systems. The prevalence of long COVID-19 among the cohort with the U09.9 ICD-10 code based on the operationalized WHO definition was between 23.2% and 62.4% across these health care systems. We also evaluated a less stringent version of the WHO definition and the CDC definition and observed an increase in the prevalence of long COVID-19 at all 3 health care systems.

CONCLUSIONS

This is one of the first studies to evaluate the U09.9 code against a clinical case definition for long COVID-19, as well as the first to apply this definition to EHR data using a chart review approach on a nationwide cohort across multiple health care systems. This chart review approach can be implemented at other EHR systems to further evaluate the utility and performance of the U09.9 code.

Prevalence and risk factors for long COVID among adults in Scotland using electronic health records: a national, retrospective, observational cohort study

Background

Long COVID is a debilitating multisystem condition. The objective of this study was to estimate the prevalence of long COVID in the adult population of Scotland, and to identify risk factors associated with its development.

Methods

In this national, retrospective, observational cohort study, we analysed electronic health records (EHRs) for all adults (≥18 years) registered with a general medical practice and resident in Scotland between March 1, 2020, and October 26, 2022 (98-99% of the population). We linked data from primary care, secondary care, laboratory testing and prescribing. Four outcome measures were used to identify long COVID: clinical codes, free text in primary care records, free text on sick notes, and a novel operational definition. The operational definition was developed using Poisson regression to identify clinical encounters indicative of long COVID from a sample of negative and positive COVID-19 cases matched on time-varying propensity to test positive for SARS-CoV-2. Possible risk factors for long COVID were identified by stratifying descriptive statistics by long COVID status.

Findings

Of 4,676,390 participants, 81,219 (1.7%) were identified as having long COVID. Clinical codes identified the fewest cases (n = 1,092, 0.02%), followed by free text (n = 8,368, 0.2%), sick notes (n = 14,469, 0.3%), and the operational definition (n = 64,193, 1.4%). There was limited overlap in cases identified by the measures; however, temporal trends and patient characteristics were consistent across measures. Compared with the general population, a higher proportion of people with long COVID were female (65.1% versus 50.4%), aged 38-67 (63.7% versus 48.9%), overweight or obese (45.7% versus 29.4%), had one or more comorbidities (52.7% versus 36.0%), were immunosuppressed (6.9% versus 3.2%), shielding (7.9% versus 3.4%), or hospitalised within 28 days of testing positive (8.8% versus 3.3%%), and had tested positive before Omicron became the dominant variant (44.9% versus 35.9%). The operational definition identified long COVID cases with combinations of clinical encounters (from four symptoms, six investigation types, and seven management strategies) recorded in EHRs within 4-26 weeks of a positive SARS-CoV-2 test. These combinations were significantly (p < 0.0001) more prevalent in positive COVID-19 patients than in matched negative controls. In a case-crossover analysis, 16.4% of those identified by the operational definition had similar healthcare patterns recorded before testing positive.

Interpretation

The prevalence of long COVID presenting in general practice was estimated to be 0.02-1.7%, depending on the measure used. Due to challenges in diagnosing long COVID and inconsistent recording of information in EHRs, the true prevalence of long COVID is likely to be higher. The operational definition provided a novel approach but relied on a restricted set of symptoms and may misclassify individuals with pre-existing health conditions. Further research is needed to refine and validate this approach.

Funding

Chief Scientist Office (Scotland), Medical Research Council, and BREATHE.

129Xe MRI Ventilation Textures and Longitudinal Quality-of-Life Improvements in Long-COVID

RATIONALE AND OBJECTIVES

It remains difficult to predict longitudinal outcomes in long-COVID, even with chest CT and functional MRI. 129Xe MRI reflects airway dysfunction, measured using ventilation defect percent (VDP) and in long-COVID patients, MRI VDP was abnormal, suggestive of airways disease. While MRI VDP and quality-of-life improved 15-month post-COVID infection, both remained abnormal. To better understand the relationship of airways disease and quality-of-life improvements in patients with long-COVID, we extracted 129Xe ventilation MRI textures and generated machine-learning models in an effort to predict improved quality-of-life, 15-month post-infection.

MATERIALS AND METHODS

Long-COVID patients provided written-informed consent to 3-month and 15-month post-infection visits. Pyradiomics was used to extract 129Xe ventilation MRI texture features, which were ranked using a Random-Forest classifier. Top-ranking features were used in classification models to dichotomize patients based on St. George's Respiratory Questionnaire (SGRQ) score improvement greater than the minimal-clinically-important-difference (MCID). Classification performance was evaluated using the area under the receiver-operator-characteristic-curve (AUC), sensitivity, and specificity.

RESULTS

120 texture features were extracted from 129Xe ventilation MRI in 44 long-COVID participants (54 ± 14 years), including 30 (52 ± 12 years) with ΔSGRQ≥MCID and 14 (58 ± 18 years) with ΔSGRQ

CONCLUSION

A machine learning model exclusively trained on 129Xe MRI ventilation textures explained improved SGRQ-scores 12 months later, and outperformed clinical models. Their unique spatial-intensity information helps build our understanding about long-COVID airway dysfunction.

Collapse

Key Words Collapse

MESH Headings Collapse

Grants Collapse

Affiliation(s)

Harkiran K Kooner Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada
Maksym Sharma Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada
Marrissa J McIntosh Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada
Inderdeep Dhaliwal Division of Respirology, Department of Medicine, Western University, London, Canada
J Michael Nicholson Division of Respirology, Department of Medicine, Western University, London, Canada
Miranda Kirby Department of Physics, Toronto Metropolitan University, Toronto, Canada
Sarah Svenningsen Division of Respirology, Department of Medicine, McMaster University and Firestone Institute for Respiratory Health, St. Joseph's Health Care, Hamilton, Canada
Grace Parraga Robarts Research Institute, Western University, London, Canada; Department of Medical Biophysics, Western University, London, Canada; Division of Respirology, Department of Medicine, Western University, London, Canada.

Collapse

Proposal and Definition of an Intelligent Clinical Decision Support System Applied to the Prediction of Dyspnea after 12 Months of an Acute Episode of COVID-19

Long COVID is a condition that affects a significant proportion of patients who have had COVID-19. It is characterised by the persistence of associated symptoms after the acute phase of the illness has subsided. Although several studies have investigated the risk factors associated with long COVID, identifying which patients will experience long-term symptoms remains a complex task. Among the various symptoms, dyspnea is one of the most prominent due to its close association with the respiratory nature of COVID-19 and its disabling consequences. This work proposes a new intelligent clinical decision support system to predict dyspnea 12 months after a severe episode of COVID-19 based on the SeguiCovid database from the Álvaro Cunqueiro Hospital in Vigo (Galicia, Spain). The database is initially processed using a CART-type decision tree to identify the variables with the highest predictive power. Based on these variables, a cascade of expert systems has been defined with Mamdani-type fuzzy-inference engines. The rules for each system were generated using the Wang-Mendel automatic rule generation algorithm. At the output of the cascade, a risk indicator is obtained, which allows for the categorisation of patients into two groups: those with dyspnea and those without dyspnea at 12 months. This simplifies follow-up and the performance of studies aimed at those patients at risk. The system has produced satisfactory results in initial tests, supported by an AUC of 0.75, demonstrating the potential and usefulness of this tool in clinical practice.

EFFECT OF PAXLOVID TREATMENT DURING ACUTE COVID-19 ON LONG COVID ONSET: AN EHR-BASED TARGET TRIAL EMULATION FROM THE N3C AND RECOVER CONSORTIA

Preventing and treating post-acute sequelae of SARS-CoV-2 infection (PASC), commonly known as Long COVID, has become a public health priority. In this study, we examined whether treatment with Paxlovid in the acute phase of COVID-19 helps prevent the onset of PASC. We used electronic health records from the National Covid Cohort Collaborative (N3C) to define a cohort of 426,352 patients who had COVID-19 since April 1, 2022, and were eligible for Paxlovid treatment due to risk for progression to severe COVID-19. We used the target trial emulation (TTE) framework to estimate the effect of Paxlovid treatment on PASC incidence. We estimated overall PASC incidence using a computable phenotype. We also measured the onset of novel cognitive, fatigue, and respiratory symptoms in the post-acute period. Paxlovid treatment did not have a significant effect on overall PASC incidence (relative risk [RR] = 0.98, 95% confidence interval [CI] 0.95-1.01). However, it had a protective effect on cognitive (RR = 0.90, 95% CI 0.84-0.96) and fatigue (RR = 0.95, 95% CI 0.91-0.98) symptom clusters, which suggests that the etiology of these symptoms may be more closely related to viral load than that of respiratory symptoms.

Long COVID: Long-Term Impact of SARS-CoV2

Four years post-pandemic, SARS-CoV-2 continues to affect many lives across the globe. An estimated 65 million people suffer from long COVID, a term used to encapsulate the post-acute sequelae of SARS-CoV-2 infections that affect multiple organ systems. Known symptoms include chronic fatigue syndrome, brain fog, cardiovascular issues, autoimmunity, dysautonomia, and clotting due to inflammation. Herein, we review long COVID symptoms, the proposed theories behind the pathology, diagnostics, treatments, and the clinical trials underway to explore treatments for viral persistence, autonomic and cognitive dysfunctions, sleep disturbances, fatigue, and exercise intolerance.

Unraveling Links between Chronic Inflammation and Long COVID: Workshop Report

As COVID-19 continues, an increasing number of patients develop long COVID symptoms varying in severity that last for weeks, months, or longer. Symptoms commonly include lingering loss of smell and taste, hearing loss, extreme fatigue, and "brain fog." Still, persistent cardiovascular and respiratory problems, muscle weakness, and neurologic issues have also been documented. A major problem is the lack of clear guidelines for diagnosing long COVID. Although some studies suggest that long COVID is due to prolonged inflammation after SARS-CoV-2 infection, the underlying mechanisms remain unclear. The broad range of COVID-19's bodily effects and responses after initial viral infection are also poorly understood. This workshop brought together multidisciplinary experts to showcase and discuss the latest research on long COVID and chronic inflammation that might be associated with the persistent sequelae following COVID-19 infection.

Computable Phenotypes for Post-acute sequelae of SARS-CoV-2: A National COVID Cohort Collaborative Analysis

Post-acute sequelae of SARS-CoV-2 (PASC) is an increasingly recognized yet incompletely understood public health concern. Several studies have examined various ways to phenotype PASC to better characterize this heterogeneous condition. However, many gaps in PASC phenotyping research exist, including a lack of the following: 1) standardized definitions for PASC based on symptomatology; 2) generalizable and reproducible phenotyping heuristics and meta-heuristics; and 3) phenotypes based on both COVID-19 severity and symptom duration. In this study, we defined computable phenotypes (or heuristics) and meta-heuristics for PASC phenotypes based on COVID-19 severity and symptom duration. We also developed a symptom profile for PASC based on a common data standard. We identified four phenotypes based on COVID-19 severity (mild vs. moderate/severe) and duration of PASC symptoms (subacute vs. chronic). The symptoms groups with the highest frequency among phenotypes were cardiovascular and neuropsychiatric with each phenotype characterized by a different set of symptoms.

A survey on the role of artificial intelligence in managing Long COVID

In the last years, several techniques of artificial intelligence have been applied to data from COVID-19. In addition to the symptoms related to COVID-19, many individuals with SARS-CoV-2 infection have described various long-lasting symptoms, now termed Long COVID. In this context, artificial intelligence techniques have been utilized to analyze data from Long COVID patients in order to assist doctors and alleviate the considerable strain on care and rehabilitation facilities. In this paper, we explore the impact of the machine learning methodologies that have been applied to analyze the many aspects of Long COVID syndrome, from clinical presentation through diagnosis. We also include the text mining techniques used to extract insights and trends from large amounts of text data related to Long COVID. Finally, we critically compare the various approaches and outline the work that has to be done to create a robust artificial intelligence approach for efficient diagnosis and treatment of Long COVID.

Modeling long COVID dynamics: Impact of underlying health conditions

We propose a new mathematical model to investigate the population dynamics of long COVID, with a focus on the impact of chronic health conditions. Our model connects long COVID with the transmission of COVID-19 so as to accurately predict the prevalence of long COVID from the progression of the infection in the host population. The model additionally incorporates the effects of COVID-19 vaccination. We implement the model with data from both the US and the UK to demonstrate the real-world applications of this modeling framework.

Improving long COVID-related text classification: a novel end-to-end domain-adaptive paraphrasing framework

The emergence of long COVID during the ongoing COVID-19 pandemic has presented considerable challenges for healthcare professionals and researchers. The task of identifying relevant literature is particularly daunting due to the rapidly evolving scientific landscape, inconsistent definitions, and a lack of standardized nomenclature. This paper proposes a novel solution to this challenge by employing machine learning techniques to classify long COVID literature. However, the scarcity of annotated data for machine learning poses a significant obstacle. To overcome this, we introduce a strategy called medical paraphrasing, which diversifies the training data while maintaining the original content. Additionally, we propose a Data-Reweighting-Based Multi-Level Optimization Framework for Domain Adaptive Paraphrasing, supported by a Meta-Weight-Network (MWN). This innovative approach incorporates feedback from the downstream text classification model to influence the training of the paraphrasing model. During the training process, the framework assigns higher weights to the training examples that contribute more effectively to the downstream task of long COVID text classification. Our findings demonstrate that this method substantially improves the accuracy and efficiency of long COVID literature classification, offering a valuable tool for physicians and researchers navigating this complex and ever-evolving field.

Biomedical Big Data Technologies, Applications, and Challenges for Precision Medicine: A Review

The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large-scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields-Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence-aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy-are discussed.

Chronic Lung Injury after COVID-19 Pneumonia: Clinical, Radiologic, and Histopathologic Perspectives

With the COVID-19 pandemic having lasted more than 3 years, concerns are growing about prolonged symptoms and respiratory complications in COVID-19 survivors, collectively termed post-COVID-19 condition (PCC). Up to 50% of patients have residual symptoms and physiologic impairment, particularly dyspnea and reduced diffusion capacity. Studies have also shown that 24%-54% of patients hospitalized during the 1st year of the pandemic exhibit radiologic abnormalities, such as ground-glass opacity, reticular opacity, bronchial dilatation, and air trapping, when imaged more than 1 year after infection. In patients with persistent respiratory symptoms but normal results at chest CT, dual-energy contrast-enhanced CT, xenon 129 MRI, and low-field-strength MRI were reported to show abnormal ventilation and/or perfusion, suggesting that some lung injury may not be detectable with standard CT. Histologic patterns in post-COVID-19 lung disease include fibrosis, organizing pneumonia, and vascular abnormality, indicating that different pathologic mechanisms may contribute to PCC. Therefore, a comprehensive imaging approach is necessary to evaluate and diagnose patients with persistent post-COVID-19 symptoms. This review will focus on the long-term findings of clinical and radiologic abnormalities and describe histopathologic perspectives. It also addresses advanced imaging techniques and deep learning approaches that can be applied to COVID-19 survivors. This field remains an active area of research, and further follow-up studies are warranted for a better understanding of the chronic stage of the disease and developing a multidisciplinary approach for patient management.

Genetic and Survey Data Improves Performance of Machine Learning Model for Long COVID

Over 200 million SARS-CoV-2 patients have or will develop persistent symptoms (long COVID). Given this pressing research priority, the National COVID Cohort Collaborative (N3C) developed a machine learning model using only electronic health record data to identify potential patients with long COVID. We hypothesized that additional data from health surveys, mobile devices, and genotypes could improve prediction ability. In a cohort of SARS-CoV-2 infected individuals (n=17,755) in the All of Us program, we applied and expanded upon the N3C long COVID prediction model, testing machine learning infrastructures, assessing model performance, and identifying factors that contributed most to the prediction models. For the survey/mobile device information and genetic data, extreme gradient boosting and a convolutional neural network delivered the best performance for predicting long COVID, respectively. Combined survey, genetic, and mobile data increased specificity and the Area Under Curve the Receiver Operating Characteristic score versus the original N3C model.

Using Multi-Modal Electronic Health Record Data for the Development and Validation of Risk Prediction Models for Long COVID Using the Super Learner Algorithm

BACKGROUND

Post-Acute Sequelae of COVID-19 (PASC) have emerged as a global public health and healthcare challenge. This study aimed to uncover predictive factors for PASC from multi-modal data to develop a predictive model for PASC diagnoses.

METHODS

We analyzed electronic health records from 92,301 COVID-19 patients, covering medical phenotypes, medications, and lab results. We used a Super Learner-based prediction approach to identify predictive factors. We integrated the model outputs into individual and composite risk scores and evaluated their predictive performance.

RESULTS

Our analysis identified several factors predictive of diagnoses of PASC, including being overweight/obese and the use of HMG CoA reductase inhibitors prior to COVID-19 infection, and respiratory system symptoms during COVID-19 infection. We developed a composite risk score with a moderate discriminatory ability for PASC (covariate-adjusted AUC (95% confidence interval): 0.66 (0.63, 0.69)) by combining the risk scores based on phenotype and medication records. The combined risk score could identify 10% of individuals with a 2.2-fold increased risk for PASC.

CONCLUSIONS

We identified several factors predictive of diagnoses of PASC and integrated the information into a composite risk score for PASC prediction, which could contribute to the identification of individuals at higher risk for PASC and inform preventive efforts.

Nationwide Genomic Surveillance and Response to COVID-19: The VA SeqFORCE and SeqCURE Consortiums

Background

The US Department of Veterans Affairs (VA) has dedicated significant resources toward countering the COVID-19 pandemic. Sequencing for Research Clinical and Epidemiology (SeqFORCE) and Sequencing Collaborations United for Research and Epidemiology (SeqCURE) were developed as clinical and research consortiums, respectively, focused on the genetic COVID-19 surveillance.

Observations

Through genetic sequencing, VA SeqFORCE and SeqCURE collaborations contributed to the COVID-19 pandemic response and scientific understanding. Future directions for each program include the assessment of the unique impact of COVID-19 on the veteran population, as well as the adaptation of these programs to future infectious disease threats. We foresee the use of these established platforms beyond infectious diseases.

Conclusions

VA SeqFORCE and SeqCURE were established as clinical and research programs dedicated to sequencing COVID-19 as part of ongoing clinical and surveillance efforts. In the future, we anticipate that having these programs embedded within the largest integrated health care system in the US will enable the study of pathogens and pandemics beyond COVID-19 and at an unprecedented scale. The investment in these programs will form an integral part of our nation's response to emerging infectious diseases, with future applications to precision medicine and beyond.

A Mechanistic Model for Long COVID Dynamics

Long COVID, a long-lasting disorder following an acute infection of COVID-19, represents a significant public health burden at present. In this paper, we propose a new mechanistic model based on differential equations to investigate the population dynamics of long COVID. By connecting long COVID with acute infection at the population level, our modeling framework emphasizes the interplay between COVID-19 transmission, vaccination, and long COVID dynamics. We conducted a detailed mathematical analysis of the model. We also validated the model using numerical simulation with real data from the US state of Tennessee and the UK.

The long-term health outcomes, pathophysiological mechanisms and multidisciplinary management of long COVID

There have been hundreds of millions of cases of coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). With the growing population of recovered patients, it is crucial to understand the long-term consequences of the disease and management strategies. Although COVID-19 was initially considered an acute respiratory illness, recent evidence suggests that manifestations including but not limited to those of the cardiovascular, respiratory, neuropsychiatric, gastrointestinal, reproductive, and musculoskeletal systems may persist long after the acute phase. These persistent manifestations, also referred to as long COVID, could impact all patients with COVID-19 across the full spectrum of illness severity. Herein, we comprehensively review the current literature on long COVID, highlighting its epidemiological understanding, the impact of vaccinations, organ-specific sequelae, pathophysiological mechanisms, and multidisciplinary management strategies. In addition, the impact of psychological and psychosomatic factors is also underscored. Despite these crucial findings on long COVID, the current diagnostic and therapeutic strategies based on previous experience and pilot studies remain inadequate, and well-designed clinical trials should be prioritized to validate existing hypotheses. Thus, we propose the primary challenges concerning biological knowledge gaps and efficient remedies as well as discuss the corresponding recommendations.

Risk factors associated with post-acute sequelae of SARS-CoV-2: an N3C and NIH RECOVER study

BACKGROUND

More than one-third of individuals experience post-acute sequelae of SARS-CoV-2 infection (PASC, which includes long-COVID). The objective is to identify risk factors associated with PASC/long-COVID diagnosis.

METHODS

This was a retrospective case-control study including 31 health systems in the United States from the National COVID Cohort Collaborative (N3C). 8,325 individuals with PASC (defined by the presence of the International Classification of Diseases, version 10 code U09.9 or a long-COVID clinic visit) matched to 41,625 controls within the same health system and COVID index date within ± 45 days of the corresponding case's earliest COVID index date. Measurements of risk factors included demographics, comorbidities, treatment and acute characteristics related to COVID-19. Multivariable logistic regression, random forest, and XGBoost were used to determine the associations between risk factors and PASC.

RESULTS

Among 8,325 individuals with PASC, the majority were > 50 years of age (56.6%), female (62.8%), and non-Hispanic White (68.6%). In logistic regression, middle-age categories (40 to 69 years; OR ranging from 2.32 to 2.58), female sex (OR 1.4, 95% CI 1.33-1.48), hospitalization associated with COVID-19 (OR 3.8, 95% CI 3.05-4.73), long (8-30 days, OR 1.69, 95% CI 1.31-2.17) or extended hospital stay (30 + days, OR 3.38, 95% CI 2.45-4.67), receipt of mechanical ventilation (OR 1.44, 95% CI 1.18-1.74), and several comorbidities including depression (OR 1.50, 95% CI 1.40-1.60), chronic lung disease (OR 1.63, 95% CI 1.53-1.74), and obesity (OR 1.23, 95% CI 1.16-1.3) were associated with increased likelihood of PASC diagnosis or care at a long-COVID clinic. Characteristics associated with a lower likelihood of PASC diagnosis or care at a long-COVID clinic included younger age (18 to 29 years), male sex, non-Hispanic Black race, and comorbidities such as substance abuse, cardiomyopathy, psychosis, and dementia. More doctors per capita in the county of residence was associated with an increased likelihood of PASC diagnosis or care at a long-COVID clinic. Our findings were consistent in sensitivity analyses using a variety of analytic techniques and approaches to select controls.

CONCLUSIONS

This national study identified important risk factors for PASC diagnosis such as middle age, severe COVID-19 disease, and specific comorbidities. Further clinical and epidemiological research is needed to better understand underlying mechanisms and the potential role of vaccines and therapeutics in altering PASC course.

Association between co-exposure to phenols, phthalates, and polycyclic aromatic hydrocarbons with the risk of frailty

The phenomenon of population aging has brought forth the challenge of frailty. Nevertheless, the contribution of environmental exposure to frailty remains ambiguous. Our objective was to investigate the association between phenols, phthalates (PAEs), and polycyclic aromatic hydrocarbons (PAHs) with frailty. We constructed a 48-item frailty index using data from the National Health and Nutrition Examination Survey (NHANES). The exposure levels of 20 organic contaminants were obtained from the survey circle between 2005 and 2016. The association between individual organic contaminants and the frailty index was assessed using negative binomial regression models. The combined effect of organic contaminants was examined using weighted quantile sum (WQS) regression. Dose-response patterns were modeled using generalized additive models (GAMs). Additionally, an interpretable machine learning approach was employed to develop a predictive model for the frailty index. A total of 1566 participants were included in the analysis. Positive associations were observed between exposure to MIB, P02, ECP, MBP, MHH, MOH, MZP, MC1, and P01 with the frailty index. WQS regression analysis revealed a significant increase in the frailty index with higher levels of the mixture of organic contaminants (aOR, 1.12; 95% CI, 1.05-1.20; p < 0.001), with MIB, ECP, COP, MBP, P02, and P01 identified as the major contributors. Dose-response relationships were observed between MIB, ECP, MBP, P02, and P01 exposure with an increased risk of frailty (both with p < 0.05). The developed predictive model based on organic contaminants exposure demonstrated high performance, with an R2 of 0.9634 and 0.9611 in the training and testing sets, respectively. Furthermore, the predictive model suggested potential synergistic effects in the MIB-MBP and P01-P02 pairs. Taken together, these findings suggest a significant association between exposure to phthalates and PAHs with an increased susceptibility to frailty.

Outpatient treatment of COVID-19 and incidence of post-COVID-19 condition over 10 months (COVID-OUT): a multicentre, randomised, quadruple-blind, parallel-group, phase 3 trial

BACKGROUND

Post-COVID-19 condition (also known as long COVID) is an emerging chronic illness potentially affecting millions of people. We aimed to evaluate whether outpatient COVID-19 treatment with metformin, ivermectin, or fluvoxamine soon after SARS-CoV-2 infection could reduce the risk of long COVID.

METHODS

We conducted a decentralised, randomised, quadruple-blind, parallel-group, phase 3 trial (COVID-OUT) at six sites in the USA. We included adults aged 30-85 years with overweight or obesity who had COVID-19 symptoms for fewer than 7 days and a documented SARS-CoV-2 positive PCR or antigen test within 3 days before enrolment. Participants were randomly assigned via 2 × 3 parallel factorial randomisation (1:1:1:1:1:1) to receive metformin plus ivermectin, metformin plus fluvoxamine, metformin plus placebo, ivermectin plus placebo, fluvoxamine plus placebo, or placebo plus placebo. Participants, investigators, care providers, and outcomes assessors were masked to study group assignment. The primary outcome was severe COVID-19 by day 14, and those data have been published previously. Because the trial was delivered remotely nationwide, the a priori primary sample was a modified intention-to-treat sample, meaning that participants who did not receive any dose of study treatment were excluded. Long COVID diagnosis by a medical provider was a prespecified, long-term secondary outcome. This trial is complete and is registered with ClinicalTrials.gov, NCT04510194.

FINDINGS

Between Dec 30, 2020, and Jan 28, 2022, 6602 people were assessed for eligibility and 1431 were enrolled and randomly assigned. Of 1323 participants who received a dose of study treatment and were included in the modified intention-to-treat population, 1126 consented for long-term follow-up and completed at least one survey after the assessment for long COVID at day 180 (564 received metformin and 562 received matched placebo; a subset of participants in the metformin vs placebo trial were also randomly assigned to receive ivermectin or fluvoxamine). 1074 (95%) of 1126 participants completed at least 9 months of follow-up. 632 (56·1%) of 1126 participants were female and 494 (43·9%) were male; 44 (7·0%) of 632 women were pregnant. The median age was 45 years (IQR 37-54) and median BMI was 29·8 kg/m2 (IQR 27·0-34·2). Overall, 93 (8·3%) of 1126 participants reported receipt of a long COVID diagnosis by day 300. The cumulative incidence of long COVID by day 300 was 6·3% (95% CI 4·2-8·2) in participants who received metformin and 10·4% (7·8-12·9) in those who received identical metformin placebo (hazard ratio [HR] 0·59, 95% CI 0·39-0·89; p=0·012). The metformin beneficial effect was consistent across prespecified subgroups. When metformin was started within 3 days of symptom onset, the HR was 0·37 (95% CI 0·15-0·95). There was no effect on cumulative incidence of long COVID with ivermectin (HR 0·99, 95% CI 0·59-1·64) or fluvoxamine (1·36, 0·78-2·34) compared with placebo.

INTERPRETATION

Outpatient treatment with metformin reduced long COVID incidence by about 41%, with an absolute reduction of 4·1%, compared with placebo. Metformin has clinical benefits when used as outpatient treatment for COVID-19 and is globally available, low-cost, and safe.

FUNDING

Parsemus Foundation; Rainwater Charitable Foundation; Fast Grants; UnitedHealth Group Foundation; National Institute of Diabetes, Digestive and Kidney Diseases; National Institutes of Health; and National Center for Advancing Translational Sciences.

Advancing the Management of Long COVID by Integrating into Health Informatics Domain: Current and Future Perspectives

The ongoing COVID-19 pandemic has profoundly affected millions of lives globally, with some individuals experiencing persistent symptoms even after recovering. Understanding and managing the long-term sequelae of COVID-19 is crucial for research, prevention, and control. To effectively monitor the health of those affected, maintaining up-to-date health records is essential, and digital health informatics apps for surveillance play a pivotal role. In this review, we overview the existing literature on identifying and characterizing long COVID manifestations through hierarchical classification based on Human Phenotype Ontology (HPO). We outline the aspects of the National COVID Cohort Collaborative (N3C) and Researching COVID to Enhance Recovery (RECOVER) initiative in artificial intelligence (AI) to identify long COVID. Through knowledge exploration, we present a concept map of clinical pathways for long COVID, which offers insights into the data required and explores innovative frameworks for health informatics apps for tackling the long-term effects of COVID-19. This study achieves two main objectives by comprehensively reviewing long COVID identification and characterization techniques, making it the first paper to explore incorporating long COVID as a variable risk factor within a digital health informatics application. By achieving these objectives, it provides valuable insights on long COVID's challenges and impact on public health.

Long Covid symptoms and diagnosis in primary care: A cohort study using structured and unstructured data in The Health Improvement Network primary care database

BACKGROUND

Long Covid is a widely recognised consequence of COVID-19 infection, but little is known about the burden of symptoms that patients present with in primary care, as these are typically recorded only in free text clinical notes.

AIMS

To compare symptoms in patients with and without a history of COVID-19, and investigate symptoms associated with a Long Covid diagnosis.

METHODS

We used primary care electronic health record data until the end of December 2020 from The Health Improvement Network (THIN), a Cegedim database. We included adults registered with participating practices in England, Scotland or Wales. We extracted information about 89 symptoms and 'Long Covid' diagnoses from free text using natural language processing. We calculated hazard ratios (adjusted for age, sex, baseline medical conditions and prior symptoms) for each symptom from 12 weeks after the COVID-19 diagnosis.

RESULTS

We compared 11,015 patients with confirmed COVID-19 and 18,098 unexposed controls. Only 20% of symptom records were coded, with 80% in free text. A wide range of symptoms were associated with COVID-19 at least 12 weeks post-infection, with strongest associations for fatigue (adjusted hazard ratio (aHR) 3.46, 95% confidence interval (CI) 2.87, 4.17), shortness of breath (aHR 2.89, 95% CI 2.48, 3.36), palpitations (aHR 2.59, 95% CI 1.86, 3.60), and phlegm (aHR 2.43, 95% CI 1.65, 3.59). However, a limited subset of symptoms were recorded within 7 days prior to a Long Covid diagnosis in more than 20% of cases: shortness of breath, chest pain, pain, fatigue, cough, and anxiety / depression.

CONCLUSIONS

Numerous symptoms are reported to primary care at least 12 weeks after COVID-19 infection, but only a subset are commonly associated with a GP diagnosis of Long Covid.

The importance of patient-partnered research in addressing long COVID: Takeaways for biomedical research study design from the RECOVER Initiative's Mechanistic Pathways taskforce

The NIH-funded RECOVER study is collecting clinical data on patients who experience a SARS-CoV-2 infection. As patient representatives of the RECOVER Initiative's Mechanistic Pathways task force, we offer our perspectives on patient motivations for partnering with researchers to obtain results from mechanistic studies. We emphasize the challenges of balancing urgency with scientific rigor. We recognize the importance of such partnerships in addressing post-acute sequelae of SARS-CoV-2 infection (PASC), which includes 'long COVID,' through contrasting objective and subjective narratives. Long COVID's prevalence served as a call to action for patients like us to become actively involved in efforts to understand our condition. Patient-centered and patient-partnered research informs the balance between urgency and robust mechanistic research. Results from collaborating on protocol design, diverse patient inclusion, and awareness of community concerns establish a new precedent in biomedical research study design. With a public health matter as pressing as the long-term complications that can emerge after SARS-CoV-2 infection, considerate and equitable stakeholder involvement is essential to guiding seminal research. Discussions in the RECOVER Mechanistic Pathways task force gave rise to this commentary as well as other review articles on the current scientific understanding of PASC mechanisms.

Risk of post-acute sequelae of SARS-CoV-2 infection associated with pre-coronavirus disease obstructive sleep apnea diagnoses: an electronic health record-based analysis from the RECOVER initiative

STUDY OBJECTIVES

Obstructive sleep apnea (OSA) has been associated with more severe acute coronavirus disease-2019 (COVID-19) outcomes. We assessed OSA as a potential risk factor for Post-Acute Sequelae of SARS-CoV-2 (PASC).

METHODS

We assessed the impact of preexisting OSA on the risk for probable PASC in adults and children using electronic health record data from multiple research networks. Three research networks within the REsearching COVID to Enhance Recovery initiative (PCORnet Adult, PCORnet Pediatric, and the National COVID Cohort Collaborative [N3C]) employed a harmonized analytic approach to examine the risk of probable PASC in COVID-19-positive patients with and without a diagnosis of OSA prior to pandemic onset. Unadjusted odds ratios (ORs) were calculated as well as ORs adjusted for age group, sex, race/ethnicity, hospitalization status, obesity, and preexisting comorbidities.

RESULTS

Across networks, the unadjusted OR for probable PASC associated with a preexisting OSA diagnosis in adults and children ranged from 1.41 to 3.93. Adjusted analyses found an attenuated association that remained significant among adults only. Multiple sensitivity analyses with expanded inclusion criteria and covariates yielded results consistent with the primary analysis.

CONCLUSIONS

Adults with preexisting OSA were found to have significantly elevated odds of probable PASC. This finding was consistent across data sources, approaches for identifying COVID-19-positive patients, and definitions of PASC. Patients with OSA may be at elevated risk for PASC after SARS-CoV-2 infection and should be monitored for post-acute sequelae.

Artificial intelligence in clinical medicine: catalyzing a sustainable global healthcare paradigm

As the demand for quality healthcare increases, healthcare systems worldwide are grappling with time constraints and excessive workloads, which can compromise the quality of patient care. Artificial intelligence (AI) has emerged as a powerful tool in clinical medicine, revolutionizing various aspects of patient care and medical research. The integration of AI in clinical medicine has not only improved diagnostic accuracy and treatment outcomes, but also contributed to more efficient healthcare delivery, reduced costs, and facilitated better patient experiences. This review article provides an extensive overview of AI applications in history taking, clinical examination, imaging, therapeutics, prognosis and research. Furthermore, it highlights the critical role AI has played in transforming healthcare in developing nations.

SARS-CoV-2 Reinfections and Long COVID in the Post-Omicron Phase of the Pandemic

We are reviewing the current state of knowledge on the virological and immunological correlates of long COVID, focusing on recent evidence for the possible association between the increasing number of SARS-CoV-2 reinfections and the parallel pandemic of long COVID. The severity of reinfections largely depends on the severity of the initial episode; in turn, this is determined both by a combination of genetic factors, particularly related to the innate immune response, and by the pathogenicity of the specific variant, especially its ability to infect and induce syncytia formation at the lower respiratory tract. The cumulative risk of long COVID as well as of various cardiac, pulmonary, or neurological complications increases proportionally to the number of SARS-CoV-2 infections, primarily in the elderly. Therefore, the number of long COVID cases is expected to remain high in the future. Reinfections apparently increase the likelihood of long COVID, but less so if they are mild or asymptomatic as in children and adolescents. Strategies to prevent SARS-CoV-2 reinfections are urgently needed, primarily among older adults who have a higher burden of comorbidities. Follow-up studies using an established case definition and precise diagnostic criteria of long COVID in people with or without reinfection may further elucidate the contribution of SARS-CoV-2 reinfections to the long COVID burden. Although accumulating evidence supports vaccination, both before and after the SARS-CoV-2 infection, as a preventive strategy to reduce the risk of long COVID, more robust comparative observational studies, including randomized trials, are needed to provide conclusive evidence of the effectiveness of vaccination in preventing or mitigating long COVID in all age groups. Thankfully, answers not only on the prevention, but also on treatment options and rates of recovery from long COVID are gradually starting to emerge.

A machine learning-based phenotype for long COVID in children: An EHR-based study from the RECOVER program

As clinical understanding of pediatric Post-Acute Sequelae of SARS CoV-2 (PASC) develops, and hence the clinical definition evolves, it is desirable to have a method to reliably identify patients who are likely to have post-acute sequelae of SARS CoV-2 (PASC) in health systems data. In this study, we developed and validated a machine learning algorithm to classify which patients have PASC (distinguishing between Multisystem Inflammatory Syndrome in Children (MIS-C) and non-MIS-C variants) from a cohort of patients with positive SARS- CoV-2 test results in pediatric health systems within the PEDSnet EHR network. Patient features included in the model were selected from conditions, procedures, performance of diagnostic testing, and medications using a tree-based scan statistic approach. We used an XGboost model, with hyperparameters selected through cross-validated grid search, and model performance was assessed using 5-fold cross-validation. Model predictions and feature importance were evaluated using Shapley Additive exPlanation (SHAP) values. The model provides a tool for identifying patients with PASC and an approach to characterizing PASC using diagnosis, medication, laboratory, and procedure features in health systems data. Using appropriate threshold settings, the model can be used to identify PASC patients in health systems data at higher precision for inclusion in studies or at higher recall in screening for clinical trials, especially in settings where PASC diagnosis codes are used less frequently or less reliably. Analysis of how specific features contribute to the classification process may assist in gaining a better understanding of features that are associated with PASC diagnoses.

Machine learning in predicting T-score in the Oxford classification system of IgA nephropathy

Background

Immunoglobulin A nephropathy (IgAN) is one of the leading causes of end-stage kidney disease (ESKD). Many studies have shown the significance of pathological manifestations in predicting the outcome of patients with IgAN, especially T-score of Oxford classification. Evaluating prognosis may be hampered in patients without renal biopsy.

Methods

A baseline dataset of 690 patients with IgAN and an independent follow-up dataset of 1,168 patients were used as training and testing sets to develop the pathology T-score prediction (T pre) model based on the stacking algorithm, respectively. The 5-year ESKD prediction models using clinical variables (base model), clinical variables and real pathological T-score (base model plus T bio), and clinical variables and T pre (base model plus T pre) were developed separately in 1,168 patients with regular follow-up to evaluate whether T pre could assist in predicting ESKD. In addition, an external validation set consisting of 355 patients was used to evaluate the performance of the 5-year ESKD prediction model using T pre.

Results

The features selected by AUCRF for the T pre model included age, systolic arterial pressure, diastolic arterial pressure, proteinuria, eGFR, serum IgA, and uric acid. The AUC of the T pre was 0.82 (95% CI: 0.80-0.85) in an independent testing set. For the 5-year ESKD prediction model, the AUC of the base model was 0.86 (95% CI: 0.75-0.97). When the T bio was added to the base model, there was an increase in AUC [from 0.86 (95% CI: 0.75-0.97) to 0.92 (95% CI: 0.85-0.98); P = 0.03]. There was no difference in AUC between the base model plus T pre and the base model plus T bio [0.90 (95% CI: 0.82-0.99) vs. 0.92 (95% CI: 0.85-0.98), P = 0.52]. The AUC of the 5-year ESKD prediction model using T pre was 0.93 (95% CI: 0.87-0.99) in the external validation set.

Conclusion

A pathology T-score prediction (T pre) model using routine clinical characteristics was constructed, which could predict the pathological severity and assist clinicians to predict the prognosis of IgAN patients lacking kidney pathology scores.

Commentary: Predicting adverse outcomes in pregnant patients positive for SARS-CoV-2 by a machine learning approach

SARS-CoV-2 infection poses a significant risk increase for adverse pregnancy outcomes both from maternal and fetal sides. A recent publication in BMC Pregnancy and Childbirth presented a machine learning algorithm to predict this risk. This commentary will discuss potential implications and applications of this study for future global health policies.

A retrospective cohort analysis leveraging augmented intelligence to characterize long COVID in the electronic health record: A precision medicine framework

Physical and psychological symptoms lasting months following an acute COVID-19 infection are now recognized as post-acute sequelae of COVID-19 (PASC). Accurate tools for identifying such patients could enhance screening capabilities for the recruitment for clinical trials, improve the reliability of disease estimates, and allow for more accurate downstream cohort analysis. In this retrospective cohort study, we analyzed the EHR of hospitalized COVID-19 patients across three healthcare systems to develop a pipeline for better identifying patients with persistent PASC symptoms (dyspnea, fatigue, or joint pain) after their SARS-CoV-2 infection. We implemented distributed representation learning powered by the Machine Learning for modeling Health Outcomes (MLHO) to identify novel EHR features that could suggest PASC symptoms outside of typical diagnosis codes. MLHO applies an entropy-based feature selection and boosting algorithms for representation mining. These improved definitions were then used for estimating PASC among hospitalized patients. 30,422 hospitalized patients were diagnosed with COVID-19 across three healthcare systems between March 13, 2020 and February 28, 2021. The mean age of the population was 62.3 years (SD, 21.0 years) and 15,124 (49.7%) were female. We implemented the distributed representation learning technique to augment PASC definitions. These definitions were found to have positive predictive values of 0.73, 0.74, and 0.91 for dyspnea, fatigue, and joint pain, respectively. We estimated that 25 percent (CI 95%: 6-48), 11 percent (CI 95%: 6-15), and 13 percent (CI 95%: 8-17) of hospitalized COVID-19 patients will have dyspnea, fatigue, and joint pain, respectively, 3 months or longer after a COVID-19 diagnosis. We present a validated framework for screening and identifying patients with PASC in the EHR and then use the tool to estimate its prevalence among hospitalized COVID-19 patients.

Using multiple indicators to predict the risk of surgical site infection after ORIF of tibia fractures: a machine learning based study

Objective

Surgical site infection (SSI) are a serious complication that can occur after open reduction and internal fixation (ORIF) of tibial fractures, leading to severe consequences. This study aimed to develop a machine learning (ML)-based predictive model to screen high-risk patients of SSI following ORIF of tibial fractures, thereby aiding in personalized prevention and treatment.

Methods

Patients who underwent ORIF of tibial fractures between January 2018 and October 2022 at the Department of Emergency Trauma Surgery at Ganzhou People's Hospital were retrospectively included. The demographic characteristics, surgery-related variables and laboratory indicators of patients were collected in the inpatient electronic medical records. Ten different machine learning algorithms were employed to develop the prediction model, and the performance of the models was evaluated to select the best predictive model. Ten-fold cross validation for the training set and ROC curves for the test set were used to evaluate model performance. The decision curve and calibration curve analysis were used to verify the clinical value of the model, and the relative importance of features in the model was analyzed.

Results

A total of 351 patients who underwent ORIF of tibia fractures were included in this study, among whom 51 (14.53%) had SSI and 300 (85.47%) did not. Of the patients with SSI, 15 cases were of deep infection, and 36 cases were of superficial infection. Given the initial parameters, the ET, LR and RF are the top three algorithms with excellent performance. Ten-fold cross-validation on the training set and ROC curves on the test set revealed that the ET model had the best performance, with AUC values of 0.853 and 0.866, respectively. The decision curve analysis and calibration curves also showed that the ET model had the best clinical utility. Finally, the performance of the ET model was further tested, and the relative importance of features in the model was analyzed.

Conclusion

In this study, we constructed a multivariate prediction model for SSI after ORIF of tibial fracture through ML, and the strength of this study was the use of multiple indicators to establish an infection prediction model, which can better reflect the real situation of patients, and the model show great clinical prediction performance.

Bottom-up and top-down paradigms of artificial intelligence research approaches to healthcare data science using growing real-world big data

OBJECTIVES

As the real-world electronic health record (EHR) data continue to grow exponentially, novel methodologies involving artificial intelligence (AI) are becoming increasingly applied to enable efficient data-driven learning and, ultimately, to advance healthcare. Our objective is to provide readers with an understanding of evolving computational methods and help in deciding on methods to pursue.

TARGET AUDIENCE

The sheer diversity of existing methods presents a challenge for health scientists who are beginning to apply computational methods to their research. Therefore, this tutorial is aimed at scientists working with EHR data who are early entrants into the field of applying AI methodologies.

SCOPE

This manuscript describes the diverse and growing AI research approaches in healthcare data science and categorizes them into 2 distinct paradigms, the bottom-up and top-down paradigms to provide health scientists venturing into artificial intelligent research with an understanding of the evolving computational methods and help in deciding on methods to pursue through the lens of real-world healthcare data.

De-black-boxing health AI: demonstrating reproducible machine learning computable phenotypes using the N3C-RECOVER Long COVID model in the All of Us data repository

Machine learning (ML)-driven computable phenotypes are among the most challenging to share and reproduce. Despite this difficulty, the urgent public health considerations around Long COVID make it especially important to ensure the rigor and reproducibility of Long COVID phenotyping algorithms such that they can be made available to a broad audience of researchers. As part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, researchers with the National COVID Cohort Collaborative (N3C) devised and trained an ML-based phenotype to identify patients highly probable to have Long COVID. Supported by RECOVER, N3C and NIH's All of Us study partnered to reproduce the output of N3C's trained model in the All of Us data enclave, demonstrating model extensibility in multiple environments. This case study in ML-based phenotype reuse illustrates how open-source software best practices and cross-site collaboration can de-black-box phenotyping algorithms, prevent unnecessary rework, and promote open science in informatics.

Plasma proteome of Long-COVID patients indicates HIF-mediated vasculo-proliferative disease with impact on brain and heart function

AIMS

Long-COVID occurs after SARS-CoV-2 infection and results in diverse, prolonged symptoms. The present study aimed to unveil potential mechanisms, and to inform prognosis and treatment.

METHODS

Plasma proteome from Long-COVID outpatients was analyzed in comparison to matched acutely ill COVID-19 (mild and severe) inpatients and healthy control subjects. The expression of 3072 protein biomarkers was determined with proximity extension assays and then deconvoluted with multiple bioinformatics tools into both cell types and signaling mechanisms, as well as organ specificity.

RESULTS

Compared to age- and sex-matched acutely ill COVID-19 inpatients and healthy control subjects, Long-COVID outpatients showed natural killer cell redistribution with a dominant resting phenotype, as opposed to active, and neutrophils that formed extracellular traps. This potential resetting of cell phenotypes was reflected in prospective vascular events mediated by both angiopoietin-1 (ANGPT1) and vascular-endothelial growth factor-A (VEGFA). Several markers (ANGPT1, VEGFA, CCR7, CD56, citrullinated histone 3, elastase) were validated by serological methods in additional patient cohorts. Signaling of transforming growth factor-β1 with probable connections to elevated EP/p300 suggested vascular inflammation and tumor necrosis factor-α driven pathways. In addition, a vascular proliferative state associated with hypoxia inducible factor 1 pathway suggested progression from acute COVID-19 to Long-COVID. The vasculo-proliferative process predicted in Long-COVID might contribute to changes in the organ-specific proteome reflective of neurologic and cardiometabolic dysfunction.

CONCLUSIONS

Taken together, our findings point to a vasculo-proliferative process in Long-COVID that is likely initiated either prior hypoxia (localized or systemic) and/or stimulatory factors (i.e., cytokines, chemokines, growth factors, angiotensin, etc). Analyses of the plasma proteome, used as a surrogate for cellular signaling, unveiled potential organ-specific prognostic biomarkers and therapeutic targets.

Long COVID risk and pre-COVID vaccination in an EHR-based cohort study from the RECOVER program

Long COVID, or complications arising from COVID-19 weeks after infection, has become a central concern for public health experts. The United States National Institutes of Health founded the RECOVER initiative to better understand long COVID. We used electronic health records available through the National COVID Cohort Collaborative to characterize the association between SARS-CoV-2 vaccination and long COVID diagnosis. Among patients with a COVID-19 infection between August 1, 2021 and January 31, 2022, we defined two cohorts using distinct definitions of long COVID-a clinical diagnosis (n = 47,404) or a previously described computational phenotype (n = 198,514)-to compare unvaccinated individuals to those with a complete vaccine series prior to infection. Evidence of long COVID was monitored through June or July of 2022, depending on patients' data availability. We found that vaccination was consistently associated with lower odds and rates of long COVID clinical diagnosis and high-confidence computationally derived diagnosis after adjusting for sex, demographics, and medical history.

Predictive Attributes for Developing Long COVID-A Study Using Machine Learning and Real-World Data from Primary Care Physicians in Germany

(1) In the present study, we used data comprising patient medical histories from a panel of primary care practices in Germany to predict post-COVID-19 conditions in patients after COVID-19 diagnosis and to evaluate the relevant factors associated with these conditions using machine learning methods. (2) Methods: Data retrieved from the IQVIA^TM Disease Analyzer database were used. Patients with at least one COVID-19 diagnosis between January 2020 and July 2022 were selected for inclusion in the study. Age, sex, and the complete history of diagnoses and prescription data before COVID-19 infection at the respective primary care practice were extracted for each patient. A gradient boosting classifier (LGBM) was deployed. The prepared design matrix was randomly divided into train (80%) and test data (20%). After optimizing the hyperparameters of the LGBM classifier by maximizing the F2 score, model performance was evaluated using several test metrics. We calculated SHAP values to evaluate the importance of the individual features, but more importantly, to evaluate the direction of influence of each feature in our dataset, i.e., whether it is positively or negatively associated with a diagnosis of long COVID. (3) Results: In both the train and test data sets, the model showed a high recall (sensitivity) of 81% and 72% and a high specificity of 80% and 80%; this was offset, however, by a moderate precision of 8% and 7% and an F2-score of 0.28 and 0.25. The most common predictive features identified using SHAP included COVID-19 variant, physician practice, age, distinct number of diagnoses and therapies, sick days ratio, sex, vaccination rate, somatoform disorders, migraine, back pain, asthma, malaise and fatigue, as well as cough preparations. (4) Conclusions: The present exploratory study describes an initial investigation of the prediction of potential features increasing the risk of developing long COVID after COVID-19 infection by using the patient history from electronic medical records before COVID-19 infection in primary care practices in Germany using machine learning. Notably, we identified several predictive features for the development of long COVID in patient demographics and their medical histories.

Identification and diagnosis of long COVID-19: A scoping review

Long COVID-19 (LC-19) is a condition that has affected a high percentage of the population that recovered from the initial disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). LC-19 diagnosis is currently poorly defined because of its variable, multisystem, episodic symptoms, and lack of uniformity in the critical time points associated with the disease. Considering the number of cases, workers' compromised efficiency or inability to return to their duties can affect organizations and impact economies. LC-19 represents a significant burden on multiple levels and effectively reduces quality of life. These factors necessitate the establishment of firm parameters of diagnoses to provide a foundation for ongoing and future studies of clinical characteristics, epidemiology, risk factors, and therapy. In this scoping review, we conducted a literature search across multiple publication sites to identify papers of interest regarding the diagnosis of LC-19. We identified 225 records of interest and categorized them into seven categories. Based on our findings, there are only 11 original papers that outline the diagnostic process in detail with little overlap. This scoping review highlights the lack of consensus regarding the definition and, thereby, the LC-19 diagnosis processes. Due to no clear directive and considering the many unknowns surrounding the natural history of the disease and further recovery/sequelae from COVID-19, continued discussion and agreement on a definition/diagnosis will help future research and management of these patients.

Long COVID: a review and proposed visualization of the complexity of long COVID

Post-Acute Sequelae of Severe Acute Respiratory Syndrome Coronavirus - 2 (SARS-CoV-2) infection, or Long COVID, is a prevailing second pandemic with nearly 100 million affected individuals globally and counting. We propose a visual description of the complexity of Long COVID and its pathogenesis that can be used by researchers, clinicians, and public health officials to guide the global effort toward an improved understanding of Long COVID and the eventual mechanism-based provision of care to afflicted patients. The proposed visualization or framework for Long COVID should be an evidence-based, dynamic, modular, and systems-level approach to the condition. Furthermore, with further research such a framework could establish the strength of the relationships between pre-existing conditions (or risk factors), biological mechanisms, and resulting clinical phenotypes and outcomes of Long COVID. Notwithstanding the significant contribution that disparities in access to care and social determinants of health have on outcomes and disease course of long COVID, our model focuses primarily on biological mechanisms. Accordingly, the proposed visualization sets out to guide scientific, clinical, and public health efforts to better understand and abrogate the health burden imposed by long COVID.

The role of machine learning in health policies during the COVID-19 pandemic and in long COVID management

The ongoing COVID-19 pandemic is arguably one of the most challenging health crises in modern times. The development of effective strategies to control the spread of SARS-CoV-2 were major goals for governments and policy makers. Mathematical modeling and machine learning emerged as potent tools to guide and optimize the different control measures. This review briefly summarizes the SARS-CoV-2 pandemic evolution during the first 3 years. It details the main public health challenges focusing on the contribution of mathematical modeling to design and guide government action plans and spread mitigation interventions of SARS-CoV-2. Next describes the application of machine learning methods in a series of study cases, including COVID-19 clinical diagnosis, the analysis of epidemiological variables, and drug discovery by protein engineering techniques. Lastly, it explores the use of machine learning tools for investigating long COVID, by identifying patterns and relationships of symptoms, predicting risk indicators, and enabling early evaluation of COVID-19 sequelae.

Prevalence and characteristics of long COVID in elderly patients: An observational cohort study of over 2 million adults in the US

BACKGROUND

Incidence of long COVID in the elderly is difficult to estimate and can be underreported. While long COVID is sometimes considered a novel disease, many viral or bacterial infections have been known to cause prolonged illnesses. We postulate that some influenza patients might develop residual symptoms that would satisfy the diagnostic criteria for long COVID, a condition we call "long Flu." In this study, we estimate the incidence of long COVID and long Flu among Medicare patients using the World Health Organization (WHO) consensus definition. We compare the incidence, symptomatology, and healthcare utilization between long COVID and long Flu patients.

METHODS AND FINDINGS

This is a cohort study of Medicare (the US federal health insurance program) beneficiaries over 65. ICD-10-CM codes were used to capture COVID-19, influenza, and residual symptoms. Long COVID was identified by (a) the designated long COVID code B94.8 (code-based definition), or (b) any of 11 symptoms identified in the WHO definition (symptom-based definition), from 1 to 3 months post-infection. A symptom would be excluded if it occurred in the year prior to infection. Long Flu was identified in influenza patients from the combined 2018 and 2019 Flu seasons by the same symptom-based definition for long COVID. Long COVID and long Flu were compared in 4 outcome measures: (a) hospitalization (any cause); (b) hospitalization (for long COVID symptom); (c) emergency department (ED) visit (for long COVID symptom); and (d) number of outpatient encounters (for long COVID symptom), adjusted for age, sex, race, region, Medicare-Medicaid dual eligibility status, prior-year hospitalization, and chronic comorbidities. Among 2,071,532 COVID-19 patients diagnosed between April 2020 and June 2021, symptom-based definition identified long COVID in 16.6% (246,154/1,479,183) and 29.2% (61,631/210,765) of outpatients and inpatients, respectively. The designated code gave much lower estimates (outpatients 0.49% (7,213/1,479,183), inpatients 2.6% (5,521/210,765)). Among 933,877 influenza patients, 17.0% (138,951/817,336) of outpatients and 24.6% (18,824/76,390) of inpatients fit the long Flu definition. Long COVID patients had higher incidence of dyspnea, fatigue, palpitations, loss of taste/smell, and neurocognitive symptoms compared to long Flu. Long COVID outpatients were more likely to have any-cause hospitalization (31.9% (74,854/234,688) versus 26.8% (33,140/123,736), odds ratio 1.06 (95% CI 1.05 to 1.08, p < 0.001)), and more outpatient visits than long Flu outpatients (mean 2.9(SD 3.4) versus 2.5(SD 2.7) visits, incidence rate ratio 1.09 (95% CI 1.08 to 1.10, p < 0.001)). There were less ED visits in long COVID patients, probably because of reduction in ED usage during the pandemic. The main limitation of our study is that the diagnosis of long COVID in is not independently verified.

CONCLUSIONS

Relying on specific long COVID diagnostic codes results in significant underreporting. We observed that about 30% of hospitalized COVID-19 patients developed long COVID. In a similar proportion of patients, long COVID-like symptoms (long Flu) can be observed after influenza, but there are notable differences in symptomatology between long COVID and long Flu. The impact of long COVID on healthcare utilization is higher than long Flu.

Cluster analysis of COVID-19 recovery center patients at a clinic in Boston, MA 2021-2022: impact on strategies for access and personalized care

BACKGROUND

There are known disparities in COVID-19 resource utilization that may persist during the recovery period for some patients. We sought to define subpopulations of patients seeking COVID-19 recovery care in terms of symptom reporting and care utilization to better personalize their care and to identify ways to improve access to subspecialty care.

METHODS

Prospective study of adult patients with prior COVID-19 infection seen in an ambulatory COVID-19 recovery center (CRC) in Boston, Massachusetts from April 2021 to April 2022. Hierarchical clustering with complete linkage to differentiate subpopulations was done with four sociodemographic variables: sex, race, language, and insurance status. Outcomes included ICU admission, utilization of supplementary care, self-report of symptoms.

RESULTS

We included 1285 COVID-19 patients referred to the CRC with a mean age of 47 years, of whom 71% were female and 78% White. We identified 3 unique clusters of patients. Cluster 1 and 3 patients were more likely to have had intensive care unit (ICU) admissions; Cluster 2 were more likely to be White with commercial insurance and a low percentage of ICU admission; Cluster 3 were more likely to be Black/African American or Latino/a and have commercial insurance. Compared to Cluster 2, Cluster 1 patients were more likely to report symptoms (ORs ranging 2.4-3.75) but less likely to use support groups, psychoeducation, or care coordination (all p < 0.05). Cluster 3 patients reported greater symptoms with similar levels of community resource utilization.

CONCLUSIONS

Within a COVID-19 recovery center, there are distinct groups of patients with different clinical and socio-demographic profiles, which translates to differential resource utilization. These insights from different subpopulations of patients can inform targeted strategies which are tailored to specific patient needs.