Uncovering Clinical Risk Factors and Predicting Severe COVID-19 Cases Using UK Biobank Data: Machine Learning Approach

Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients

Sepsis is characterized by a dysfunctional host response to infection culminating in life-threatening organ failure that requires complex patient management and rapid intervention. Timely diagnosis of the underlying cause of sepsis is crucial, and identifying those at risk of complications and death is imperative for triaging treatment and resource allocation. Here, we explored the potential of explainable machine learning models to predict mortality and causative pathogen in sepsis patients. By using a modelling pipeline employing multiple feature selection algorithms, we demonstrate the feasibility of identifying integrative patterns from clinical parameters, plasma biomarkers, and extensive phenotyping of blood immune cells. While no single variable had sufficient predictive power, models that combined five and more features showed a macro area under the curve (AUC) of 0.85 to predict 90-day mortality after sepsis diagnosis, and a macro AUC of 0.86 to discriminate between Gram-positive and Gram-negative bacterial infections. Parameters associated with the cellular immune response contributed the most to models predictive of 90-day mortality, most notably, the proportion of T cells among PBMCs, together with expression of CXCR3 by CD4+ T cells and CD25 by mucosal-associated invariant T (MAIT) cells. Frequencies of Vδ2+ γδ T cells had the most profound impact on the prediction of Gram-negative infections, alongside other T-cell-related variables and total neutrophil count. Overall, our findings highlight the added value of measuring the proportion and activation patterns of conventional and unconventional T cells in the blood of sepsis patients in combination with other immunological, biochemical, and clinical parameters.

Sex hormones and the total testosterone:estradiol ratio as predictors of severe acute respiratory syndrome coronavirus 2 infection in hospitalized men

BACKGROUND

The predictive ability of the early determination of sex steroids and the total testosterone:estradiol ratio for the risk of severe coronavirus disease 2019 or the potential existence of a biological gradient in this relationship has not been evaluated.

OBJECTIVES

To assess the relationship of sex steroid levels and the total testosterone:estradiol ratio with the risk of severe acute respiratory syndrome coronavirus 2 infection in men, defined as the need for intensive care unit admission or death, and the predictive ability of each biomarker.

MATERIALS AND METHODS

This was a prospective observational study. We included all consecutive adult men with severe acute respiratory syndrome coronavirus 2 infections in a single center admitted to a general hospital ward or to the intensive care unit. Sex steroids were evaluated at the centralized laboratory of our hospital.

RESULTS

We recruited 98 patients, 54 (55.1%) of whom developed severe coronavirus disease in 2019. Compared to patients with nonsevere coronavirus disease 2019, patients with severe coronavirus disease 2019 had significantly lower serum levels of total testosterone (111 ± 89 vs. 191 ± 143 ng/dL; p < 0.001), dehydroepiandrosterone (1.69 ± 1.26 vs. 2.96 ± 2.64 ng/mL; p < 0.001), and dehydroepiandrosterone sulfate (91.72 ± 76.20 vs. 134.28 ± 98.261 μg/dL; p = 0.009), significantly higher levels of estradiol (64.61 ± 59.35 vs. 33.78 ± 13.78 pg/mL; p = 0.001), and significantly lower total testosterone:estradiol ratio (0.28 ± 0.31 vs. 0.70 ± 0.75; p < 0.001). The lower the serum level of androgen and the lower the total testosterone:estradiol ratio values, the higher the likelihood of developing severe coronavirus disease 2019, with the linear trend in the adjusted analyses being statistically significant for all parameters except for androstenedione (p = 0.064). In the receiver operating characteristic analysis, better predictive performance was shown by the total testosterone:estradiol ratio, with an area under the curve of 0.77 (95% confidence interval 0.68-0.87; p < 0.001).

DISCUSSION AND CONCLUSION

Our results suggest that men with severe acute respiratory syndrome coronavirus 2 infection, decreased androgen levels and increased estradiol levels have a higher likelihood of developing an unfavorable outcome. The total testosterone:estradiol ratio showed the best predictive ability.

Predicting post-liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning

Liver transplantation (LT) is a treatment for acute-on-chronic liver failure (ACLF), but high post-LT mortality has been reported. Existing post-LT models in ACLF have been limited. We developed an Expert-Augmented Machine Learning (EAML) model to predict post-LT outcomes. We identified ACLF patients who underwent LT in the University of California Health Data Warehouse. We applied the RuleFit machine learning (ML) algorithm to extract rules from decision trees and create intermediate models. We asked human experts to rate the rules generated by RuleFit and incorporated these ratings to generate final EAML models. We identified 1384 ACLF patients. For death at 1 year, areas under the receiver-operating characteristic curve were 0.707 (confidence interval [CI] 0.625-0.793) for EAML and 0.719 (CI 0.640-0.800) for RuleFit. For death at 90 days, areas under the receiver-operating characteristic curve were 0.678 (CI 0.581-0.776) for EAML and 0.707 (CI 0.615-0.800) for RuleFit. In pairwise comparisons, both EAML and RuleFit models outperformed cross-sectional models. Significant discrepancies between experts and ML occurred in rankings of biomarkers used in clinical practice. EAML may serve as a method for ML-guided hypothesis generation in further ACLF research.

The NEAT Equating Via Chaining Random Forests in the Context of Small Sample Sizes: A Machine-Learning Method

The part of responses that is absent in the nonequivalent groups with anchor test (NEAT) design can be managed to a planned missing scenario. In the context of small sample sizes, we present a machine learning (ML)-based imputation technique called chaining random forests (CRF) to perform equating tasks within the NEAT design. Specifically, seven CRF-based imputation equating methods are proposed based on different data augmentation methods. The equating performance of the proposed methods is examined through a simulation study. Five factors are considered: (a) test length (20, 30, 40, 50), (b) sample size per test form (50 versus 100), (c) ratio of common/anchor items (0.2 versus 0.3), and (d) equivalent versus nonequivalent groups taking the two forms (no mean difference versus a mean difference of 0.5), and (e) three different types of anchors (random, easy, and hard), resulting in 96 conditions. In addition, five traditional equating methods, (1) Tucker method; (2) Levine observed score method; (3) equipercentile equating method; (4) circle-arc method; and (5) concurrent calibration based on Rasch model, were also considered, plus seven CRF-based imputation equating methods for a total of 12 methods in this study. The findings suggest that benefiting from the advantages of ML techniques, CRF-based methods that incorporate the equating result of the Tucker method, such as IMP_total_Tucker, IMP_pair_Tucker, and IMP_Tucker_cirlce methods, can yield more robust and trustable estimates for the "missingness" in an equating task and therefore result in more accurate equated scores than other counterparts in short-length tests with small samples.

Association of COVID-19 with short- and long-term risk of cardiovascular disease and mortality: a prospective cohort in UK Biobank

AIMS

This study aims to evaluate the short- and long-term associations between COVID-19 and development of cardiovascular disease (CVD) outcomes and mortality in the general population.

METHODS AND RESULTS

A prospective cohort of patients with COVID-19 infection between 16 March 2020 and 30 November 2020 was identified from UK Biobank, and followed for up to 18 months, until 31 August 2021. Based on age (within 5 years) and sex, each case was randomly matched with up to 10 participants without COVID-19 infection from two cohorts-a contemporary cohort between 16 March 2020 and 30 November 2020 and a historical cohort between 16 March 2018 and 30 November 2018. The characteristics between groups were further adjusted with propensity score-based marginal mean weighting through stratification. To determine the association of COVID-19 with CVD and mortality within 21 days of diagnosis (acute phase) and after this period (post-acute phase), Cox regression was employed. In the acute phase, patients with COVID-19 (n = 7584) were associated with a significantly higher short-term risk of CVD {hazard ratio (HR): 4.3 [95% confidence interval (CI): 2.6- 6.9]; HR: 5.0 (95% CI: 3.0-8.1)} and all-cause mortality [HR: 81.1 (95% CI: 58.5-112.4); HR: 67.5 (95% CI: 49.9-91.1)] than the contemporary (n = 75 790) and historical controls (n = 75 774), respectively. Regarding the post-acute phase, patients with COVID-19 (n = 7139) persisted with a significantly higher risk of CVD in the long-term [HR: 1.4 (95% CI: 1.2-1.8); HR: 1.3 (95% CI: 1.1- 1.6)] and all-cause mortality [HR: 5.0 (95% CI: 4.3-5.8); HR: 4.5 (95% CI: 3.9-5.2) compared to the contemporary (n = 71 296) and historical controls (n = 71 314), respectively.

CONCLUSIONS

COVID-19 infection, including long-COVID, is associated with increased short- and long-term risks of CVD and mortality. Ongoing monitoring of signs and symptoms of developing these cardiovascular complications post diagnosis and up till at least a year post recovery may benefit infected patients, especially those with severe disease.

Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19

Background

Most existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission.

Methods

We conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance.

Results

A total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722-0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set.

Conclusion

An easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation.

An Integrative Explainable Artificial Intelligence Approach to Analyze Fine-Scale Land-Cover and Land-Use Factors Associated with Spatial Distributions of Place of Residence of Reported Dengue Cases

Dengue fever is a prevalent mosquito-borne disease that burdens communities in subtropical and tropical regions. Dengue transmission is ecologically complex; several environmental conditions are critical for the spatial and temporal distribution of dengue. Interannual variability and spatial distribution of dengue transmission are well-studied; however, the effects of land cover and use are yet to be investigated. Therefore, we applied an explainable artificial intelligence (AI) approach to integrate the EXtreme Gradient Boosting and Shapley Additive Explanation (SHAP) methods to evaluate spatial patterns of the residences of reported dengue cases based on various fine-scale land-cover land-use types, Shannon's diversity index, and household density in Kaohsiung City, Taiwan, between 2014 and 2015. We found that the proportions of general roads and residential areas play essential roles in dengue case residences with nonlinear patterns. Agriculture-related features were negatively associated with dengue incidence. Additionally, Shannon's diversity index showed a U-shaped relationship with dengue infection, and SHAP dependence plots showed different relationships between various land-use types and dengue incidence. Finally, landscape-based prediction maps were generated from the best-fit model and highlighted high-risk zones within the metropolitan region. The explainable AI approach delineated precise associations between spatial patterns of the residences of dengue cases and diverse land-use characteristics. This information is beneficial for resource allocation and control strategy modification.

Prognostic models in COVID-19 infection that predict severity: a systematic review

Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.

The effect of ACE2 receptor, IFN-γ, and TNF-α polymorphisms on the severity and prognosis of the disease in SARS-CoV-2 infection

To investigate the effect of genetic variations in the angiotensin converting enzyme (ACE), interferon (IFNG) and tumor necrosis factor (TNF-α) genes on the severity of coronavirus disease (COVID-19). Between September and December 2021, 33 patients with COVID-19 were included in this prospective study. The patients were classified and compared according to disease severity: mild&moderate (n = 26) vs severe&critical (n = 7). These groups were evaluated to assess possible relationships with ACE, TNF-α and IFNG gene variations using univariate and multivariable analyses. The median age of the mild&moderate group was 45.5 (22-73), and that of the severe&critical group was 58 (49-80) years (p = 0.014). Seventeen (65.4%) of the mild&moderate patients and 3 (42.9%) of severe&critical patients were female (p = 0.393). According to results of univariate analysis, the percentage of patients with the c.418-70C>G variant of the ACE gene was significantly higher in the mild&moderate group (p = 0.027). The ACE gene polymorphisms, c.2312C>T, c.3490G>A, c.3801C>T, and c.731A>G, were each only seen in separate patients with critical disease. The following variants were observed more frequently in the mild&moderate group: c.582C>T, c.3836G>A, c.511+66A>G, c.1488-58T>C, c.3281+25C>T, c.1710-90G>C, c.2193A> G, c.3387T>C for ACE; c.115-3delT for IFNG; and c.27C>T for TNF. It can be expected that patients carrying the ACE gene c.418-70C>G variant may present with a mild clinical manifestation of COVID-19. Several genetic polymorphisms may be associated with pathophysiology, as they appear to help predict COVID-19 severity and enable early identification of the patients requiring aggressive treatment.

The Complex Interplay between Serum Testosterone and the Clinical Course of Coronavirus Disease 19 Pandemic: A Systematic Review of Clinical and Preclinical Evidence

Since the beginning of the coronavirus disease 19 (COVID-19) pandemic, efforts in defining risk factors and associations between the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), clinical, and molecular features have initiated. After three years of pandemic, it became evident that men have higher risk of adverse outcomes. Such evidence provided the impetus for defining the biological fundaments of such a gender disparity. Our objective was to analyze the most recent literature with the aim of defining the relationship between COVID-19 and fertility, in particular, we assessed the interplay between SARS-CoV-2 and testosterone in a systematic review of literature from December 2019 (first evidence of a novel coronavirus in the Hubei province) until March 2022. As a fundamental basis for understanding, articles pertaining preclinical aspects explaining the gender disparity (n=9) were included. The main review categories analyzed the risk of being infected with SARS-CoV-2 according to testosterone levels (n=5), the impact of serum testosterone on outcomes of COVID-19 (n=23), and the impact SARS-CoV-2 on testosterone levels after infection (n=19). Preclinical studies mainly evaluated the relation between angiotensin-converting enzyme 2 (ACE2) and its androgen-mediated regulation, articles exploring the risk of COVID-19 according to testosterone levels were few. Although most publications evaluating the effect of COVID-19 on fertility found low testosterone levels after the infection, follow-up was short, with some also suggesting no alterations during recovery. More conclusive findings were observed in men with low testosterone levels, that were generally at higher risk of experiencing worse outcomes (i.e., admission to intensive care units, longer hospitalization, and death). Interestingly, an inverse relationship was observed in women, where higher levels of testosterone were associated to worse outcomes. Our finding may provide meaningful insights to better patient counselling and individualization of care pathways in men with testosterone levels suggesting hypogonadism.

Importance of sex and gender factors for COVID-19 infection and hospitalisation: a sex-stratified analysis using machine learning in UK Biobank data

OBJECTIVE

To examine sex and gender roles in COVID-19 test positivity and hospitalisation in sex-stratified predictive models using machine learning.

DESIGN

Cross-sectional study.

SETTING

UK Biobank prospective cohort.

PARTICIPANTS

Participants tested between 16 March 2020 and 18 May 2020 were analysed.

MAIN OUTCOME MEASURES

The endpoints of the study were COVID-19 test positivity and hospitalisation. Forty-two individuals' demographics, psychosocial factors and comorbidities were used as likely determinants of outcomes. Gradient boosting machine was used for building prediction models.

RESULTS

Of 4510 individuals tested (51.2% female, mean age=68.5±8.9 years), 29.4% tested positive. Males were more likely to be positive than females (31.6% vs 27.3%, p=0.001). In females, living in more deprived areas, lower income, increased low-density lipoprotein (LDL) to high-density lipoprotein (HDL) ratio, working night shifts and living with a greater number of family members were associated with a higher likelihood of COVID-19 positive test. While in males, greater body mass index and LDL to HDL ratio were the factors associated with a positive test. Older age and adverse cardiometabolic characteristics were the most prominent variables associated with hospitalisation of test-positive patients in both overall and sex-stratified models.

CONCLUSION

High-risk jobs, crowded living arrangements and living in deprived areas were associated with increased COVID-19 infection in females, while high-risk cardiometabolic characteristics were more influential in males. Gender-related factors have a greater impact on females; hence, they should be considered in identifying priority groups for COVID-19 infection vaccination campaigns.

Diabetes Does Not Increase the Risk of Hospitalization Due to COVID-19 in Patients Aged 50 Years or Older in Primary Care—APHOSDIAB—COVID-19 Multicenter Study

The purpose of this study was to identify clinical, analytical, and sociodemographic variables associated with the need for hospital admission in people over 50 years infected with SARS-CoV-2 and to assess whether diabetes mellitus conditions the risk of hospitalization. A multicenter case-control study analyzing electronic medical records in patients with COVID-19 from 1 March 2020 to 30 April 2021 was conducted. We included 790 patients: 295 cases admitted to the hospital and 495 controls. Under half (n = 386, 48.8%) were women, and 8.5% were active smokers. The main comorbidities were hypertension (50.5%), dyslipidemia, obesity, and diabetes (37.5%). Multivariable logistic regression showed that hospital admission was associated with age above 65 years (OR from 2.45 to 3.89, ascending with age group); male sex (OR 2.15, 95% CI 1.47–3.15), fever (OR 4.31, 95% CI 2.87–6.47), cough (OR 1.89, 95% CI 1.28–2.80), asthenia/malaise (OR 2.04, 95% CI 1.38–3.03), dyspnea (4.69, 95% CI 3.00–7.33), confusion (OR 8.87, 95% CI 1.68–46.78), and a history of hypertension (OR 1.61, 95% CI 1.08–2.41) or immunosuppression (OR 4.97, 95% CI 1.45–17.09). Diabetes was not associated with increased risk of hospital admission (OR 1.18, 95% CI 0.80–1.72; p = 0.38). Diabetes did not increase the risk of hospital admission in people over 50 years old, but advanced age, male sex, fever, cough, asthenia, dyspnea/confusion, and hypertension or immunosuppression did.