scholarly journals COVID-19 mortality and BCG vaccination: defining the link using machine learning

2020 ◽  
Author(s):  
Nathan A. Brooks ◽  
Ankur Puri ◽  
Sanya Garg ◽  
Swapnika Nag ◽  
Jacomo Corbo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
A Priori ◽  
Target Function ◽  
Population Level ◽  
Bcg Vaccination ◽  
Level Data ◽  
Confounding Variables ◽  
Prospective Trials ◽  
Definition Of

Abstract Population-level data have suggested that bacille Calmette-Guerin (BCG) vaccination may lessen the severity of COVID-19; prior reports have demonstrated conflicting results. We leveraged publicly available databases and unsupervised machine learning, adjusting for established confounders designated a priori, to assign countries into similar clusters. The primary outcome was the association of deaths per million related to COVID-19 (CSM) 30 days after each included country reported 100 cases with several factors including vaccination. Validation was performed using linear regression and country-specific modeling. This protocol details the statistical analyses used to establish an association between BCG vaccination and CSM, which includes : Definition of the target function, data processing, exploratory factor analysis for variable selection, k-means clustering and step wise linear regression for validation. This protocol is differentiated from previous works on the same subject by its' comprehensive nature which considers the effect of several confounding variables while studying the association between BCG vaccination and CSM. There are still several potential measured and unmeasured confounding variables which could not be included in this study. It is also unclear if the protection from neonatal vaccination with BCG is transferable to those receiving vaccination as an adult and how long such protection lasts. The authors advise caution against routine BCG vaccination for the prevention of COVID-19 until prospective trials are completed.

scholarly journals The association of Coronavirus Disease-19 mortality and prior bacille Calmette-Guerin vaccination: a robust ecological analysis using unsupervised machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nathan A. Brooks ◽  
Ankur Puri ◽  
Sanya Garg ◽  
Swapnika Nag ◽  
Jacomo Corbo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Population Level ◽  
Ecological Analysis ◽  
Bacille Calmette Guerin ◽  
Vaccination Programs ◽  
Bcg Vaccination ◽  
Level Data ◽  
Specific Modeling ◽  
Related Mortality ◽  
Country Specific

AbstractPopulation-level data have suggested that bacille Calmette-Guerin (BCG) vaccination may lessen the severity of Coronavirus Disease-19 (COVID-19) prompting clinical trials in this area. Some reports have demonstrated conflicting results. We performed a robust, ecologic analysis comparing COVID-19 related mortality (CRM) between strictly selected countries based on BCG vaccination program status utilizing publicly available databases and machine learning methods to define the association between active BCG vaccination programs and CRM. Validation was performed using linear regression and country-specific modeling. CRM was lower for the majority of countries with a BCG vaccination policy for at least the preceding 15 years (BCG15). CRM increased significantly for each increase in the percent population over age 65. A higher total population of a country and BCG15 were significantly associated with improved CRM. There was a consistent association between countries with a BCG vaccination for the preceding 15 years, but not other vaccination programs, and CRM. BCG vaccination programs continued to be associated with decreased CRM even for populations < 40 years old where CRM events are less frequent.

scholarly journals The association of Coronavirus Disease-19 mortality and prior bacille Calmette-Guerin vaccination: a robust ecological evaluation using unsupervised machine learning

2020 ◽  
Author(s):  
Nathan A Brooks ◽  
Ankur Puri ◽  
Sanya Garg ◽  
Swapnika Nag ◽  
Noshir Kaka ◽  
...  
Keyword(s):  
Machine Learning ◽  
Population Level ◽  
Bacille Calmette Guerin ◽  
Ecological Evaluation ◽  
Vaccination Programs ◽  
Bcg Vaccination ◽  
Level Data ◽  
Specific Modeling ◽  
Related Mortality ◽  
Country Specific

Abstract Population-level data have suggested that bacille Calmette-Guerin (BCG) vaccination may lessen the severity of Coronavirus Disease-19 (COVID-19) prompting clinical trials in this area. Some reports have demonstrated conflicting results. We performed a robust, ecologic analysis comparing COVID-19 related mortality (CSM) between strictly selected countries based on BCG vaccination program status utilizing publicly available databases and machine learning to define the association between active BCG vaccination programs and CSM. Validation was performed using linear regression and country-specific modeling. CSM was lower for 80% of similarly clustered countries with a BCG vaccination policy for at least the preceding 15 years (BCG15). CSM increased significantly for each increase in the percent population over age 65. The total population of a country and BCG15 were significantly associated with improved CSM. There was a consistent association between countries with a BCG vaccination for the preceding 15 years, but not other vaccination programs, and CSM.

Impact of Primary Care Worksite Health and Wellness Clinics on HbA1c Level Among Prediabetic or Diabetic Employees

2020 ◽  
Vol 35 (1) ◽  
pp. 13-19
Author(s):  
Catherine C. Cohen ◽  
Simon Hollands ◽  
Harry H. Liu
Keyword(s):  
Hemoglobin A1c ◽  
Multivariate Analyses ◽  
Population Level ◽  
Wellness Programs ◽  
Health And Wellness ◽  
Central California ◽  
Level Data ◽  
Worksite Health ◽  
Definition Of ◽  
Employee Data

Purpose: To determine whether the use of worksite health and wellness clinics reduced hemoglobin A1c (HbA1c) for prediabetic and diabetic employees. Design: Hemoglobin A1c values were compared between clinic users and matched non-users. Setting: The Wonderful Company’s (TWC’s) agricultural and packaging sites in Central California. Sample: TWC’s 2016 to 2017 employees who used clinics (n = 445, defined below) and clinic non-users (n = 217) who had HbA1c screening and worked at TWC for 3 or more months each year. Intervention: A unique worksite health and wellness clinic that offers multidisciplinary primary medical care in synergy with TWC’s overall wellness programs. Measures: Exposure was clinic use, defined by frequency and patterns of visits. Hemoglobin A1c was the outcome of interest. Analysis: Users and non-users were propensity score matched using the 2016 employee data including HbA1c, and then 2017 HbA1c values were compared between the 2 groups. Results: The 2017 HbA1c of diabetic employees was lower among clinic users compared to non-users (7.42 vs 8.53, P < .001). Differences in HbA1c among prediabetics or diabetics and prediabetics aggregated were not statistically significant, despite TWC’s population-level data showing a reduction in prediabetes prevalence. The clinic impact results were robust to multivariate analyses and an alternative definition of utilization. Conclusion: The implementation of TWC’s Health and Wellness clinics was associated with reductions in HbA1c among diabetics, but further research is needed on prediabetics.

scholarly journals Precision Health–Enabled Machine Learning to Identify Need for Wraparound Social Services Using Patient- and Population-Level Data Sets: Algorithm Development and Validation (Preprint)

2019 ◽  
Author(s):  
Suranga N Kasthurirathne ◽  
Shaun Grannis ◽  
Paul K Halverson ◽  
Justin Morea ◽  
Nir Menachemi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Determinants Of Health ◽  
Social Services ◽  
Performance Measures ◽  
Social Determinants ◽  
Population Level ◽  
Decision Models ◽  
Data Sets ◽  
Level Data ◽  
Precision Health

BACKGROUND Emerging interest in precision health and the increasing availability of patient- and population-level data sets present considerable potential to enable analytical approaches to identify and mitigate the negative effects of social factors on health. These issues are not satisfactorily addressed in typical medical care encounters, and thus, opportunities to improve health outcomes, reduce costs, and improve coordination of care are not realized. Furthermore, methodological expertise on the use of varied patient- and population-level data sets and machine learning to predict need for supplemental services is limited. OBJECTIVE The objective of this study was to leverage a comprehensive range of clinical, behavioral, social risk, and social determinants of health factors in order to develop decision models capable of identifying patients in need of various wraparound social services. METHODS We used comprehensive patient- and population-level data sets to build decision models capable of predicting need for behavioral health, dietitian, social work, or other social service referrals within a safety-net health system using area under the receiver operating characteristic curve (AUROC), sensitivity, precision, F1 score, and specificity. We also evaluated the value of population-level social determinants of health data sets in improving machine learning performance of the models. RESULTS Decision models for each wraparound service demonstrated performance measures ranging between 59.2%% and 99.3%. These results were statistically superior to the performance measures demonstrated by our previous models which used a limited data set and whose performance measures ranged from 38.2% to 88.3% (behavioural health: F1 score <i>P</i>&lt;.001, AUROC <i>P</i>=.01; social work: F1 score <i>P</i>&lt;.001, AUROC <i>P</i>=.03; dietitian: F1 score <i>P</i>=.001, AUROC <i>P</i>=.001; other: F1 score <i>P</i>=.01, AUROC <i>P</i>=.02); however, inclusion of additional population-level social determinants of health did not contribute to any performance improvements (behavioural health: F1 score <i>P</i>=.08, AUROC <i>P</i>=.09; social work: F1 score <i>P</i>=.16, AUROC <i>P</i>=.09; dietitian: F1 score <i>P</i>=.08, AUROC <i>P</i>=.14; other: F1 score <i>P</i>=.33, AUROC <i>P</i>=.21) in predicting the need for referral in our population of vulnerable patients seeking care at a safety-net provider. CONCLUSIONS Precision health–enabled decision models that leverage a wide range of patient- and population-level data sets and advanced machine learning methods are capable of predicting need for various wraparound social services with good performance.

scholarly journals Precision Health–Enabled Machine Learning to Identify Need for Wraparound Social Services Using Patient- and Population-Level Data Sets: Algorithm Development and Validation

10.2196/16129 ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. e16129 ◽  
Author(s):  
Suranga N Kasthurirathne ◽  
Shaun Grannis ◽  
Paul K Halverson ◽  
Justin Morea ◽  
Nir Menachemi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Determinants Of Health ◽  
Social Services ◽  
Performance Measures ◽  
Social Determinants ◽  
Population Level ◽  
Decision Models ◽  
Data Sets ◽  
Level Data ◽  
Precision Health

Background Emerging interest in precision health and the increasing availability of patient- and population-level data sets present considerable potential to enable analytical approaches to identify and mitigate the negative effects of social factors on health. These issues are not satisfactorily addressed in typical medical care encounters, and thus, opportunities to improve health outcomes, reduce costs, and improve coordination of care are not realized. Furthermore, methodological expertise on the use of varied patient- and population-level data sets and machine learning to predict need for supplemental services is limited. Objective The objective of this study was to leverage a comprehensive range of clinical, behavioral, social risk, and social determinants of health factors in order to develop decision models capable of identifying patients in need of various wraparound social services. Methods We used comprehensive patient- and population-level data sets to build decision models capable of predicting need for behavioral health, dietitian, social work, or other social service referrals within a safety-net health system using area under the receiver operating characteristic curve (AUROC), sensitivity, precision, F1 score, and specificity. We also evaluated the value of population-level social determinants of health data sets in improving machine learning performance of the models. Results Decision models for each wraparound service demonstrated performance measures ranging between 59.2%% and 99.3%. These results were statistically superior to the performance measures demonstrated by our previous models which used a limited data set and whose performance measures ranged from 38.2% to 88.3% (behavioural health: F1 score P<.001, AUROC P=.01; social work: F1 score P<.001, AUROC P=.03; dietitian: F1 score P=.001, AUROC P=.001; other: F1 score P=.01, AUROC P=.02); however, inclusion of additional population-level social determinants of health did not contribute to any performance improvements (behavioural health: F1 score P=.08, AUROC P=.09; social work: F1 score P=.16, AUROC P=.09; dietitian: F1 score P=.08, AUROC P=.14; other: F1 score P=.33, AUROC P=.21) in predicting the need for referral in our population of vulnerable patients seeking care at a safety-net provider. Conclusions Precision health–enabled decision models that leverage a wide range of patient- and population-level data sets and advanced machine learning methods are capable of predicting need for various wraparound social services with good performance.

scholarly journals Indigenous and Tribal Peoples Data Governance in Health Research: A Systematic Review

2021 ◽  
Vol 18 (19) ◽  
pp. 10318
Author(s):  
Kalinda E. Griffiths ◽  
Jessica Blain ◽  
Claire M. Vajdic ◽  
Louisa Jorm
Keyword(s):  
Systematic Review ◽  
Health Research ◽  
A Priori ◽  
Population Level ◽  
Research Literature ◽  
Data Governance ◽  
Institutional Ethics ◽  
Level Data ◽  
Governance Strategies ◽  
Data Stewardship

There is increasing potential to improve the research and reporting on the health and wellbeing of Indigenous and Tribal peoples through the collection and (re)use of population-level data. As the data economy grows and the value of data increases, the optimization of data pertaining to Indigenous peoples requires governance that defines who makes decisions on behalf of whom and how these data can and should be used. An international a priori PROSPERO (#CRD42020170033) systematic review was undertaken to examine the health research literature to (1) identify, describe, and synthesize definitions and principles; (2) identify and describe data governance frameworks; and (3) identify, describe, and synthesize processes, policies and practices used in Indigenous Data Governance (ID-GOV). Sixty-eight articles were included in the review that found five components that require consideration in the governance of health research data pertaining to Indigenous people. This included (1) Indigenous governance; (2) institutional ethics; (3) socio-political dynamics; (4) data management and data stewardship; and (5) overarching influences. This review provides the first systematic international review of ID-GOV that could potentially be used in a range of governance strategies moving forward in health research.

What Are the Most Important Predictors of Subjective Well-Being? Insights From Machine Learning and Linear Regression Approaches on the MIDUS Datasets

2021 ◽  
Author(s):  
Seth Margolis ◽  
Jacob Elder ◽  
Brent Hughes ◽  
Sonja Lyubomirsky
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Regression Models ◽  
Stress Reactivity ◽  
A Priori ◽  
Life Quality ◽  
Well Being ◽  
The United States ◽  
Learning Approaches ◽  
Subjective Well Being

What are the most important predictors of subjective well-being? Using a nationally representative publicly available dataset from the Midlife in the United States project (N = 4,378), we applied linear regression, which often relies on assumptions of linearity and a priori interactions, and advanced machine learning approaches, which maximize prediction by thoroughly exploring nonlinear effects and higher-order interactions, to determine the ordering and characteristics of predictors of well-being. Advanced machine learning models generally did not predict well-being more accurately than did regression models, suggesting that many predictors of well-being may be linear and non-interactive. Consistent with this implication, the introduction of product and squared terms in regression models improved prediction, but only nominally. Our findings replicated previous research, with sociability, physical health, disengagement from goals, sex life quality, wealth, and religious activity emerging as the strongest predictors of well-being, and demographic factors emerging as relatively weak predictors. Furthermore, self-reported “aches” (the strongest “objective” predictor of well-being), stress reactivity, and disengagement negatively predicted well-being, reinforcing the role of stress in psychological maladjustment. Finally, unlike prior research, control over one’s life—and control over financial and work matters in particular—strongly predicted well-being.

Marginality and team building in collaborative crowdsourcing

2020 ◽  
Vol 44 (4) ◽  
pp. 827-846
Author(s):  
Rong Wang
Keyword(s):  
Team Building ◽  
Population Level ◽  
Content Type ◽  
Team Members ◽  
Individual Level ◽  
Exponential Random Graph Modeling ◽  
Exponential Random Graph ◽  
Level Data ◽  
Collaboration Dynamics ◽  
Definition Of

PurposeExisting studies on crowdsourcing have focused on analyzing isolated contributions by individual participants and thus collaboration dynamics among them are under-investigated. The value of implementing crowdsourcing in problem solving lies in the aggregation of wisdom from a crowd. This study examines how marginality affects collaboration in crowdsourcing.Design/methodology/approachWith population level data collected from a global crowdsourcing community (openideo.com), this study applied social network analysis and in particular bipartite exponential random graph modeling (ERGM) to examine how individual level marginality variables (measured as the degree of being located at the margin) affect the team formation in collaboration crowdsourcing.FindingsSignificant effects of marginality are attributed to collaboration skills, number of projects won, community tenure and geolocation. Marginality effects remain significant after controlling for individual level and team level attributes. However, marginality alone cannot explain collaboration dynamics. Participants with leadership experience or more winning ideas are also more likely to be selected as team members.Originality/valueThe core contribution this research makes is the conceptualization and definition of marginality as a mechanism in influencing collaborative crowdsourcing. This study conceptualizes marginality as a multidimensional concept and empirically examines its effect on team collaboration, connecting the literature on crowdsourcing to online collaboration.

Personalized stratification of back to work risk amidst COVID-19: A machine learning approach (Preprint)

2020 ◽  
Author(s):  
Carson Lam ◽  
Jacob Calvert ◽  
Gina Barnes ◽  
Emily Pellegrini ◽  
Anna Lynn-Palevsky ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Learning Algorithm ◽  
Severe Disease ◽  
High Specificity ◽  
Population Level ◽  
The United States ◽  
Health Condition ◽  
Available P ◽  
Severe Illness

BACKGROUND In the wake of COVID-19, the United States has 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 that should continue to stay at home due to being 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 who should therefore not return to work until vaccination or widespread serological testing is available. OBJECTIVE This study evaluated a machine learning algorithm for the 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 at most 62% that are identified by government guidelines. The algorithm also achieved a high specificity of 95%, outperforming government guidelines. CONCLUSIONS This algorithm may help to enable a broad reopening of the American economy while ensuring that patients at high risk for serious disease remain home until vaccination and testing become available.

scholarly journals Population-Level Prevalence, Bother, and Treatment Behavior for Urinary Incontinence in an Eastern European Country: Findings from the LUTS POLAND Study

2021 ◽  
Vol 10 (11) ◽  
pp. 2314
Author(s):  
Mikolaj Przydacz ◽  
Marcin Chlosta ◽  
Piotr Chlosta
Keyword(s):  
Quality Of Life ◽  
Urinary Incontinence ◽  
Rural Areas ◽  
Eastern European Country ◽  
Population Level ◽  
Eastern European ◽  
Level Data ◽  
Urban And Rural Areas ◽  
Eastern European Countries

Objectives: Population-level data are lacking for urinary incontinence (UI) in Central and Eastern European countries. Therefore, the objective of this study was to estimate the prevalence, bother, and behavior regarding treatment for UI in a population-representative group of Polish adults aged ≥ 40 years. Methods: Data for this epidemiological study were derived from the larger LUTS POLAND project, in which a group of adults that typified the Polish population were surveyed, by telephone, about lower urinary tract symptoms. Respondents were classified by age, sex, and place of residence. UI was assessed with a standard protocol and established International Continence Society definitions. Results: The LUTS POLAND survey included 6005 completed interviews. The prevalence of UI was 14.6–25.4%; women reported a greater occurrence compared with men (p < 0.001). For both sexes, UI prevalence increased with age. Stress UI was the most common type of UI in women, and urgency UI was the most prevalent in men. We did not find a difference in prevalence between urban and rural areas. Individuals were greatly bothered by UI. For women, mixed UI was the most bothersome, whereas for men, leak for no reason was most annoying. More than half of respondents (51.4–62.3%) who reported UI expressed anxiety about the effect of UI on their quality of life. Nevertheless, only around one third (29.2–38.1%) of respondents with UI sought treatment, most of whom received treatment. Persons from urban and rural areas did not differ in the degrees of treatment seeking and treatment receiving. Conclusion: Urinary incontinence was prevalent and greatly bothersome among Polish adults aged ≥ 40 years. Consequently, UI had detrimental effects on quality of life. Nonetheless, most affected persons did not seek treatment. Therefore, we need to increase population awareness in Poland about UI and available treatment methods, and we need to ensure adequate allocation of government and healthcare system resources.

Sign in / Sign up

Export Citation Format

Share Document