scholarly journals Incorporating machine learning and social determinants of health indicators into prospective risk adjustment for health plan payments

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Jeremy A. Irvin ◽  
Andrew A. Kondrich ◽  
Michael Ko ◽  
Pranav Rajpurkar ◽  
Behzad Haghgoo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Determinants Of Health ◽  
Health Plan ◽  
Social Determinants ◽  
Risk Adjustment ◽  
Health Indicators ◽  
Determinants Of Health ◽  
Prospective Risk

scholarly journals Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee

2021 ◽  
Vol 28 (1) ◽  
pp. e100439
Author(s):  
Lukasz S Wylezinski ◽  
Coleman R Harris ◽  
Cody N Heiser ◽  
Jamieson D Gray ◽  
Charles F Spurlock
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
Determinants Of Health ◽  
Learning Models ◽  
Vaccination Rates ◽  
Data Framework ◽  
The Impact ◽  
Machine Learning Models

IntroductionThe SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the USA, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities.MethodsWe combined county-level COVID-19 testing data, COVID-19 vaccination rates and SDOH information in Tennessee. Between February and May 2021, we trained machine learning models on a semimonthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance.ResultsOur results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased.ConclusionIncorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policy-makers with additional data resources to improve health equity and resilience to future public health emergencies.

scholarly journals Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee

2021 ◽  
Author(s):  
Lukasz S Wylezinski ◽  
Coleman R Harris ◽  
Cody N Heiser ◽  
Jamieson D Gray ◽  
Charles F Spurlock
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
The United States ◽  
Determinants Of Health ◽  
Learning Models ◽  
Vaccination Rates ◽  
The Impact ◽  
Machine Learning Models

The SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the United States, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities. We combined county-level COVID-19 testing data, COVID-19 vaccination rates, and SDOH information in Tennessee. Between February-May 2021, we trained machine learning models on a semi-monthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance. Our results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race, and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased. Incorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policymakers with additional data resources to improve health equity and resilience to future public health emergencies.

Social Connection as a Public Health Issue: The Evidence and a Systemic Framework for Prioritizing the “Social” in Social Determinants of Health

2022 ◽  
Vol 43 (1) ◽  
Author(s):  
Julianne Holt-Lunstad
Keyword(s):  
Public Health ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
Social Connectedness ◽  
Health Indicators ◽  
Determinants Of Health ◽  
Public Health Issue ◽  
Annual Review ◽  
Publication Date ◽  
Social Connection

There is growing interest in and renewed support for prioritizing social factors in public health both in the USA and globally. While there are multiple widely recognized social determinants of health, indicators of social connectedness (e.g., social capital, social support, social isolation, loneliness) are often noticeably absent from the discourse. This article provides an organizing framework for conceptualizing social connection and summarizes the cumulative evidence supporting its relevance for health, including epidemiological associations, pathways, and biological mechanisms. This evidence points to several implications for prioritizing social connection within solutions across sectors, where public health work, initiatives, and research play a key role in addressing gaps. Therefore, this review proposes a systemic framework for cross-sector action to identify missed opportunities and guide future investigation, intervention, practice, and policy on promoting social connection and health for all. Expected final online publication date for the Annual Review of Public Health, Volume 43 is April 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Influence of social determinants of health on oncology care quality rankings.

2021 ◽  
Vol 39 (28_suppl) ◽  
pp. 139-139
Author(s):  
Benjamin Urick ◽  
Sabree Burbage ◽  
Christopher Baggett ◽  
Jennifer Elston Lafata ◽  
Hanna Kelly Sanoff ◽  
...  
Keyword(s):  
Social Determinants Of Health ◽  
Social Determinants ◽  
Risk Adjustment ◽  
Social Deprivation ◽  
Care Quality ◽  
Determinants Of Health ◽  
Social Risk ◽  
Patient Level ◽  
Provider Quality ◽  
Oncology Care

139 Background: Adjustment for social determinants of health (SDOH) when assessing provider care quality remains limited. The Oncology Care Model (OCM), for example, includes low-income status/dual eligibility (LIS/DE) as a part of the risk adjustment model for some quality measures, but does not account for any social risk variables in the hospice measure. No measures within the OCM account for additional social risk factors beyond LIS/DE such as patients’ race, rurality, and social deprivation. Additional SDOH adjustment could increase the accuracy of provider quality rankings and better align performance-based payments with true provider quality. Methods: North Carolina Medicare claims from 2015-2017 comprised the data for this study. The year 2015 was used to establish baseline covariates. Episodes were attributed to physician practices’ Tax Identification Number (TIN), lasted 6 months, and were divided into performance years beginning 1/1/2016 and 7/1/2016. Three measures were used: 1) all-cause hospital admissions; 2) all-cause emergency department visits or observation stays; and 3) admission to hospice for 3 days or more among patients who died. SDOH included patient-level race as well as county-level rurality and social deprivation, measured using the social deprivation index (SDI). TIN-level scores with and without expanded SDOH variables were divided into quintiles and compared descriptively as well as using weighted kappa statistics. Results: No SDOH were significantly associated with the hospitalization outcome (P = 0.118-0.944). For the ED measure, Black patients and rural patients were significantly more likely to have an ED visit or observation stay during an episode than white patients and urban patients (P < 0.0001). For the hospice measure, greater SDI values were associated with less hospice use (P < 0.05). Accordingly, including SDOH variables for ED visit/observation stay and hospice measures had a greater impact on TIN rankings than for the hospitalization measure (Table). Conclusions: Because quintile rankings in determine potential shared savings under models like the OCM, differences in rankings due to additional SDOH variables could have a meaningful impact on TIN-level revenue. Additional work is needed to expand the scope of patient-level SDOH variables used for risk adjustment and to explore differences across TINs which contribute to SDOH-sensitive changes in rankings.[Table: see text]

Sign in / Sign up

Export Citation Format

Share Document