Systematic review of how racialized health inequities are addressed in Epidemiologic Reviews articles (1979-2021): a critical conceptual and empirical content analysis and recommendations for best practices.

Critical analysis of the determinants of current and changing racialized health inequities, including the central role of racism, is an urgent priority for epidemiology, for both original research studies and epidemiologic review articles. Motivating our systematic overview review of Epidemiologic Reviews articles is the critical role of epidemiologic reviews in shaping discourse, research priorities, and policy relevant to the social patterning of population health. Our approach was first to document the number of articles published in Epidemiologic Reviews (1979-2021; n = 685) that either: (1) focused the review on racism and health, racial discrimination and health, or racialized health inequities (n = 27; 4%); (2) mentioned racialized groups but did not focus on racism or racialized health inequities (n = 399; 59%); or (3) included no mention of racialized groups or racialized health inequities (n = 250; 37%). We then conducted a critical content analysis of the 27 review articles that focused on racialized health inequities and assessed key characteristics, including (1) concepts, terms, and metrics used regarding racism and racialized groups (notably only 26% addressed the use or nonuse of measures explicitly linked to racism; 15% provided explicit definitions of racialized groups); (2) theories of disease distribution guiding (explicitly or implicitly) the review's approach; (3) interpretation of findings; and (4) recommendations offered. Guided by our results, we offer recommendations for best practices for epidemiologic review articles for addressing how epidemiologic research does or does not address ubiquitous racialized health inequities.

Dairy Food Intake Is Not Associated With Frailty in Adults From the Framingham Heart Study.

BACKGROUND: Nutrients, including protein, calcium, and fat may be associated with risk of frailty, yet specific contributions from whole dairy foods rich in these nutrients remain understudied. OBJECTIVE: To determine associations between dairy intake (milk, yogurt, cheese, total (milk + yogurt + cheese), low-fat and high-fat dairy, and servings per week) and frailty onset and frailty phenotype components. DESIGN: Prospective cohort study. All dairy intake exposures (servings per week) were assessed via a food frequency questionnaire. PARTICIPANTS AND SETTING: Participants (aged 33 to 86 years) from the Framingham Offspring Study who were not frail at baseline (1998-2001) completed a food frequency questionnaire and had 1 or 2 follow-up frailty assessments (2005-2008 and 2011-2014) were included. MAIN OUTCOME MEASURES: Frailty was defined as the presence of ≥3 Fried frailty phenotype components: unintentional weight-loss, exhaustion, slowness (gait speed), weakness (grip strength), and low physical activity. Individuals with zero to two components were considered nonfrail. STATISTICAL ANALYSES PERFORMED: Repeated measures logistic regression estimated odds ratios and 95% CIs for frailty onset. Logistic (exhaustion and weight loss) and linear regression (gait speed, grip strength, and physical activity) estimated the association between baseline dairy intake and each frailty component at follow-up, adjusting for baseline values for age, sex, energy intake (residual analysis), current smoking, and multivitamin use. Models were further adjusted for health status in a secondary analysis. RESULTS: Mean baseline age ± SD was 61 ± 9 years (range = 33 to 87 years), and 54% were women. Of 2,550 nonfrail individuals at baseline, 8.8% (2005-2008) and 13.5% (2011-2014) became frail. Higher yogurt intake was associated with decreased odds of frailty (odds ratio 0.96, 95% CI 0.93 to 0.99; P = 0.02). Each additional serving of yogurt (ß ± SE) .004 ± .001; P < 0.01) and low-fat dairy (ß ± SE) .001 ± .0006; P = 0.04) was associated with significantly faster follow-up gait speed. Dietary intakes of high-fat dairy were associated with increased odds of frailty (odds ratio 1.02, 95% CI 1.00 to 1.04; P = 0.05), but the P value was of borderline significance. No associations were observed for other dairy foods. After adjusting for health status, the associations of high-fat dairy and yogurt with frailty became nonsignificant, although the magnitudes of the associations did not change. The association between yogurt and gait speed decreased in magnitude after adjusting for health status (ß ± SE) .002 ± .001; P = 0.01). CONCLUSIONS: Dietary intakes of yogurt were modestly associated with reduced frailty onset and dietary intakes of high-fat dairy had a borderline association with increased odds of frailty, but other dairy food intakes showed no association in this study of healthy adults. Some dairy food intakes were modestly associated with follow-up gait speed. However, effect sizes were small, and the clinical importance of these associations remains undetermined.

Foot pain and inflammatory markers: a cross sectional study in older adults.

BACKGROUND: Foot disorders may limit independence and reduce quality of life for older adults. Obesity is a risk factor for foot conditions; both mechanical load and metabolic effects may contribute to these conditions. This study determined cross-sectional associations between inflammatory markers and foot disorders. METHODS: Participants were drawn from the Framingham Foot Study (2002-2008). C-reactive protein (CRP), interleukin-6 (IL-6), and tumor necrosis factor alpha (TNF-α) were each examined for associations with foot pain, forefoot pain, hindfoot pain, hallux valgus, hallux rigidus, and toe deformities (claw, hammer, or overlapping toes). Unadjusted and adjusted (age, body mass index, physical activity, smoking status) sex-specific logistic regression was performed. RESULTS: Of 909 participants, 54% were women (mean age 65 [Formula: see text] 9 years), 20% had foot pain, 29% had hallux valgus, 3% had hallux rigidus, and 27% had toe deformities. In unadjusted models, higher CRP (OR [95% CI] = 1.5 [1.1, 2.0]) and IL-6 (OR [95% CI] = 1.8 [1.2, 2.6]) were associated with foot pain among men; higher CRP was associated with foot pain (OR [95% CI] = 1.3 [1.0, 1.5]) among women. Higher CRP (OR [95% CI] = 1.9 [1.1, 3.2]) and IL-6 (OR [95% CI] = 2.4 [1.2, 4.7]) were associated with forefoot pain in men. Higher CRP was associated with hindfoot pain ([95% CI] = 1.8 [1.2, 2.6]) in women. After adjustment, CRP ([95% CI] = 1.5 [1.1, 2.0]) and IL-6 ([95% CI] = 1.8 [1.2, 2.6]) remained associated with foot pain in men, and IL-6 with forefoot pain ([95% CI] = 2.9 [1.4, 6.1]) in men. No associations with structural foot disorders were observed. CONCLUSIONS: Inflammation may impact foot pain. Future work assessing whether inflammation is part of the mechanism linking obesity to foot pain may identify areas for intervention and prevention.

Early prediction of severe acute pancreatitis using machine learning.

BACKGROUND: Acute pancreatitis (AP) is one of the most common causes of gastrointestinal-related hospitalizations in the United States. Severe AP (SAP) is associated with a mortality rate of nearly 30% and is distinguished from milder forms of AP. Risk stratification to identify SAP cases needing inpatient treatment is an important aspect of AP diagnosis. METHODS: We developed machine learning algorithms to predict which patients presenting with AP would require treatment for SAP. Three models were developed using logistic regression, neural networks, and XGBoost. Models were assessed in terms of area under the receiver operating characteristic (AUROC) and compared to the Harmless Acute Pancreatitis Score (HAPS) and Bedside Index for Severity in Acute Pancreatitis (BISAP) scores for AP risk stratification. RESULTS: 61,894 patients were used to train and test the machine learning models. With an AUROC value of 0.921, the model developed using XGBoost outperformed the logistic regression and neural network-based models. The XGBoost model also achieved a higher AUROC than both HAPS and BISAP for identifying patients who would be diagnosed with SAP. CONCLUSIONS: Machine learning may be able to improve the accuracy of AP risk stratification methods and allow for more timely treatment and initiation of interventions.

Social Isolation and Falls Risk: Lack of Social Contacts Decreases the Likelihood of Bathroom Modification Among Older Adults With Fear of Falling.

Fall prevention strategies exist, but little is known about factors that influence whether they are used. We assessed whether social isolation modifies the association between fear of falling (FOF) and bathroom environmental modification. Data were included from 2858 Medicare beneficiaries in the National Health and Aging Trends Study. FOF and social isolation were assessed at baseline (2011); new bathroom modifications were assessed 1-year post-baseline. Social network size was dichotomized as any versus no social contacts. Logistic regression assessed associations between FOF and bathroom modification. Effect modification between FOF and social isolation was assessed with multiplicative interaction terms. FOF was associated with increased odds of bathroom modification. We observed a statistically significant interaction between FOF and social isolation (p = 0.03). Among those with no social contacts, FOF was associated with reduced odds bathroom modification that did not reach statistical significance (OR 0.5, 95% CI 0.2-1.3).

Personalized stratification of hospitalization risk amidst COVID-19: A machine learning approach.

Objective: In the wake of COVID-19, the United States (U.S.) developed a three stage plan to outline the parameters to determine when states may reopen businesses and ease travel restrictions. The guidelines also identify subpopulations of Americans deemed to be at high risk for severe disease should they contract COVID-19. These guidelines were based on population level demographics, rather than individual-level risk factors. As such, they may misidentify individuals at high risk for severe illness, and may therefore be of limited use in decisions surrounding resource allocation to vulnerable populations. The objective of this study was to evaluate a machine learning algorithm for prediction of serious illness due to COVID-19 using inpatient data collected from electronic health records. Methods: The algorithm was trained to identify patients for whom a diagnosis of COVID-19 was likely to result in hospitalization, and compared against four U.S. policy-based criteria: age over 65; having a serious underlying health condition; age over 65 or having a serious underlying health condition; and age over 65 and having a serious underlying health condition. Results: This algorithm identified 80% of patients at risk for hospitalization due to COVID-19, versus 62% identified by government guidelines. The algorithm also achieved a high specificity of 95%, outperforming government guidelines. Conclusions: This algorithm may identify individuals likely to require hospitalization should they contract COVID-19. This information may be useful to guide vaccine distribution, anticipate hospital resource needs, and assist health care policymakers to make care decisions in a more principled manner.

A machine learning approach to predicting risk of myelodysplastic syndrome.

BACKGROUND: Early myelodysplastic syndrome (MDS) diagnosis can allow physicians to provide early treatment, which may delay advancement of MDS and improve quality of life. However, MDS often goes unrecognized and is difficult to distinguish from other disorders. We developed a machine learning algorithm for the prediction of MDS one year prior to clinical diagnosis of the disease. METHODS: Retrospective analysis was performed on 790,470 patients over the age of 45 seen in the United States between 2007 and 2020. A gradient boosted decision tree model (XGB) was built to predict MDS diagnosis using vital signs, lab results, and demographics from the prior two years of patient data. The XGB model was compared to logistic regression (LR) and artificial neural network (ANN) models. The models did not use blast percentage and cytogenetics information as inputs. Predictions were made one year prior to MDS diagnosis as determined by International Classification of Diseases (ICD) codes, 9th and 10th revisions. Performance was assessed with regard to area under the receiver operating characteristic curve (AUROC). RESULTS: On a hold-out test set, the XGB model achieved an AUROC value of 0.87 for prediction of MDS one year prior to diagnosis, with a sensitivity of 0.79 and specificity of 0.80. The XGB model was compared against LR and ANN models, which achieved an AUROC of 0.838 and 0.832, respectively. CONCLUSIONS: Machine learning may allow for early MDS diagnosis MDS and more appropriate treatment administration.

Predicting ventilator-associated pneumonia with machine learning.

ABSTRACT: Ventilator-associated pneumonia (VAP) is the most common and fatal nosocomial infection in intensive care units (ICUs). Existing methods for identifying VAP display low accuracy, and their use may delay antimicrobial therapy. VAP diagnostics derived from machine learning (ML) methods that utilize electronic health record (EHR) data have not yet been explored. The objective of this study is to compare the performance of a variety of ML models trained to predict whether VAP will be diagnosed during the patient stay.A retrospective study examined data from 6126 adult ICU encounters lasting at least 48 hours following the initiation of mechanical ventilation. The gold standard was the presence of a diagnostic code for VAP. Five different ML models were trained to predict VAP 48 hours after initiation of mechanical ventilation. Model performance was evaluated with regard to the area under the receiver operating characteristic (AUROC) curve on a 20% hold-out test set. Feature importance was measured in terms of Shapley values.The highest performing model achieved an AUROC value of 0.854. The most important features for the best-performing model were the length of time on mechanical ventilation, the presence of antibiotics, sputum test frequency, and the most recent Glasgow Coma Scale assessment.Supervised ML using patient EHR data is promising for VAP diagnosis and warrants further validation. This tool has the potential to aid the timely diagnosis of VAP.

Machine Learning as a Precision-Medicine Approach to Prescribing COVID-19 Pharmacotherapy with Remdesivir or Corticosteroids.

PURPOSE: Coronavirus disease-2019 (COVID-19) continues to be a global threat and remains a significant cause of hospitalizations. Recent clinical guidelines have supported the use of corticosteroids or remdesivir in the treatment of COVID-19. However, uncertainty remains about which patients are most likely to benefit from treatment with either drug; such knowledge is crucial for avoiding preventable adverse effects, minimizing costs, and effectively allocating resources. This study presents a machine-learning system with the capacity to identify patients in whom treatment with a corticosteroid or remdesivir is associated with improved survival time. METHODS: Gradient-boosted decision-tree models used for predicting treatment benefit were trained and tested on data from electronic health records dated between December 18, 2019, and October 18, 2020, from adult patients (age ≥18 years) with COVID-19 in 10 US hospitals. Models were evaluated for performance in identifying patients with longer survival times when treated with a corticosteroid versus remdesivir. Fine and Gray proportional-hazards models were used for identifying significant findings in treated and nontreated patients, in a subset of patients who received supplemental oxygen, and in patients identified by the algorithm. Inverse probability-of-treatment weights were used to adjust for confounding. Models were trained and tested separately for each treatment. FINDINGS: Data from 2364 patients were included, with men comprising slightly more than 50% of the sample; 893 patients were treated with remdesivir, and 1471 were treated with a corticosteroid. After adjustment for confounding, neither corticosteroids nor remdesivir use was associated with increased survival time in the overall population or in the subpopulation that received supplemental oxygen. However, in the populations identified by the algorithms, both corticosteroids and remdesivir were significantly associated with an increase in survival time, with hazard ratios of 0.56 and 0.40, respectively (both, P = 0.04). IMPLICATIONS: Machine-learning methods have the capacity to identify hospitalized patients with COVID-19 in whom treatment with a corticosteroid or remdesivir is associated with an increase in survival time. These methods may help to improve patient outcomes and allocate resources during the COVID-19 crisis.

COVID-19 Evidence Accelerator: A parallel analysis to describe the use of Hydroxychloroquine with or without Azithromycin among hospitalized COVID-19 patients.

BACKGROUND: The COVID-19 pandemic remains a significant global threat. However, despite urgent need, there remains uncertainty surrounding best practices for pharmaceutical interventions to treat COVID-19. In particular, conflicting evidence has emerged surrounding the use of hydroxychloroquine and azithromycin, alone or in combination, for COVID-19. The COVID-19 Evidence Accelerator convened by the Reagan-Udall Foundation for the FDA, in collaboration with Friends of Cancer Research, assembled experts from the health systems research, regulatory science, data science, and epidemiology to participate in a large parallel analysis of different data sets to further explore the effectiveness of these treatments. METHODS: Electronic health record (EHR) and claims data were extracted from seven separate databases. Parallel analyses were undertaken on data extracted from each source. Each analysis examined time to mortality in hospitalized patients treated with hydroxychloroquine, azithromycin, and the two in combination as compared to patients not treated with either drug. Cox proportional hazards models were used, and propensity score methods were undertaken to adjust for confounding. Frequencies of adverse events in each treatment group were also examined. RESULTS: Neither hydroxychloroquine nor azithromycin, alone or in combination, were significantly associated with time to mortality among hospitalized COVID-19 patients. No treatment groups appeared to have an elevated risk of adverse events. CONCLUSION: Administration of hydroxychloroquine, azithromycin, and their combination appeared to have no effect on time to mortality in hospitalized COVID-19 patients. Continued research is needed to clarify best practices surrounding treatment of COVID-19.

A Machine Learning Approach to Predict Deep Venous Thrombosis Among Hospitalized Patients.

Deep venous thrombosis (DVT) is associated with significant morbidity, mortality, and increased healthcare costs. Standard scoring systems for DVT risk stratification often provide insufficient stratification of hospitalized patients and are unable to accurately predict which inpatients are most likely to present with DVT. There is a continued need for tools which can predict DVT in hospitalized patients. We performed a retrospective study on a database collected from a large academic hospital, comprised of 99,237 total general ward or ICU patients, 2,378 of whom experienced a DVT during their hospital stay. Gradient boosted machine learning algorithms were developed to predict a patient's risk of developing DVT at 12- and 24-hour windows prior to onset. The primary outcome of interest was diagnosis of in-hospital DVT. The machine learning predictors obtained AUROCs of 0.83 and 0.85 for DVT risk prediction on hospitalized patients at 12- and 24-hour windows, respectively. At both 12 and 24 hours before DVT onset, the most important features for prediction of DVT were cancer history, VTE history, and internal normalized ratio (INR). Improved risk stratification may prevent unnecessary invasive testing in patients for whom DVT cannot be ruled out using existing methods. Improved risk stratification may also allow for more targeted use of prophylactic anticoagulants, as well as earlier diagnosis and treatment, preventing the development of pulmonary emboli and other sequelae of DVT.

Is Machine Learning a Better Way to Identify COVID-19 Patients Who Might Benefit from Hydroxychloroquine Treatment?-The IDENTIFY Trial.

Therapeutic agents for the novel coronavirus disease 2019 (COVID-19) have been proposed, but evidence supporting their use is limited. A machine learning algorithm was developed in order to identify a subpopulation of COVID-19 patients for whom hydroxychloroquine was associated with improved survival; this population might be relevant for study in a clinical trial. A pragmatic trial was conducted at six United States hospitals. We enrolled COVID-19 patients that were admitted between 10 March and 4 June 2020. Treatment was not randomized. The study endpoint was mortality; discharge was a competing event. Hazard ratios were obtained on the entire population, and on the subpopulation indicated by the algorithm as suitable for treatment. A total of 290 patients were enrolled. In the subpopulation that was identified by the algorithm, hydroxychloroquine was associated with a statistically significant (p = 0.011) increase in survival (adjusted hazard ratio 0.29, 95% confidence interval (CI) 0.11-0.75). Adjusted survival among the algorithm indicated patients was 82.6% in the treated arm and 51.2% in the arm not treated. No association between treatment and mortality was observed in the general population. A 31% increase in survival at the end of the study was observed in a population of COVID-19 patients that were identified by a machine learning algorithm as having a better outcome with hydroxychloroquine treatment. Precision medicine approaches may be useful in identifying a subpopulation of COVID-19 patients more likely to be proven to benefit from hydroxychloroquine treatment in a clinical trial.

A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study.

BACKGROUND: Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. OBJECTIVE: The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. METHODS: Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care-III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). RESULTS: The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P<.001, respectively). CONCLUSIONS: This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial.

BACKGROUND: Currently, physicians are limited in their ability to provide an accurate prognosis for COVID-19 positive patients. Existing scoring systems have been ineffective for identifying patient decompensation. Machine learning (ML) may offer an alternative strategy. A prospectively validated method to predict the need for ventilation in COVID-19 patients is essential to help triage patients, allocate resources, and prevent emergency intubations and their associated risks. METHODS: In a multicenter clinical trial, we evaluated the performance of a machine learning algorithm for prediction of invasive mechanical ventilation of COVID-19 patients within 24 h of an initial encounter. We enrolled patients with a COVID-19 diagnosis who were admitted to five United States health systems between March 24 and May 4, 2020. RESULTS: 197 patients were enrolled in the REspirAtory Decompensation and model for the triage of covid-19 patients: a prospective studY (READY) clinical trial. The algorithm had a higher diagnostic odds ratio (DOR, 12.58) for predicting ventilation than a comparator early warning system, the Modified Early Warning Score (MEWS). The algorithm also achieved significantly higher sensitivity (0.90) than MEWS, which achieved a sensitivity of 0.78, while maintaining a higher specificity (p < 0.05). CONCLUSIONS: In the first clinical trial of a machine learning algorithm for ventilation needs among COVID-19 patients, the algorithm demonstrated accurate prediction of the need for mechanical ventilation within 24 h. This algorithm may help care teams effectively triage patients and allocate resources. Further, the algorithm is capable of accurately identifying 16% more patients than a widely used scoring system while minimizing false positive results.