Using Predictive Analytics to Guide Patient Care and Research in a National Health System

Nelson, Karin M.; Chang, Ernest S.; Zulman, Donna M.; Rubenstein, Lisa V.; Kirkland, Freddy D; Fihn, Stephan D.

doi:10.1007/s11606-019-04961-4

Cited by 19 publications

(15 citation statements)

References 5 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To control for health status, Care Assessment Needs scores, which predict likelihood of hospitalization and mortality in VA populations, were included as of February 28, 2020. 13 …”

Section: Methodsmentioning

confidence: 99%

Racial/Ethnic Variation in Veterans Health Administration COVID-19 Vaccine Uptake

Haderlein

Wong

Jones

et al. 2022

American Journal of Preventive Medicine

View full text Add to dashboard Cite

Introduction Equitable coronavirus disease 2019 (COVID-19) vaccine access is imperative to addressing disproportionate negative impacts of COVID-19 among racial/ethnic minorities. U.S. racial/ethnic minorities have lower COVID-19 vaccination rates than Whites despite higher COVID-19 death/case rates. The Veterans Health Administration (VA) COVID-19 vaccine rollout provides the unique context of a managed care system with few access barriers. This study aims to evaluate race/ethnicity as a predictor of VA COVID-19 vaccination. Methods The cohort comprised Veteran VA outpatient users aged ≥65 years (N=3,474,874). COVID-19 vaccination was assessed between December 14, 2020 and February 23, 2021 via procedure codes. Multivariable logistic regressions clustered by VA facility were conducted, controlling for demographics, medical comorbidity, and influenza vaccination history. Based on reports of high COVID-19 vaccine uptake among American Indian/Alaska Natives (AI/ANs), proximity to Indian Health Service Contract Health Service Delivery Areas was tested as a moderating variable. Data analyses were conducted during 2021. Results Blacks (OR=1.28, 95% CI=1.17, 1.40), Hispanics (OR=1.15, 95% CI=1.05, 1.25), and Asians (OR=1.21, 95% CI=1.02, 1.43) were more likely than Whites to receive VA COVID-19 vaccinations. AI/ANs were less likely than Whites to receive VA COVID-19 vaccinations, but only those residing in Contract Health Service Delivery Area counties (OR= 0.58, 95% CI= 0.47, 0.72). Influenza vaccine history positively predicted COVID-19 vaccine uptake (OR= 2.28, 95% CI=2.22, 2.34). Conclusions In the VA, compared with the general U.S. population, COVID-19 vaccine receipt is higher among most racial/ethnic minority groups than Whites, suggesting reduced vaccination barriers compared with non-VA care. The Indian Health Service may provide a safety net effective at reaching AI/AN populations. Addressing vaccination access barriers in non-VA settings can potentially reduce racial/ethnic disparities.

show abstract

“…To control for health status, Care Assessment Needs scores, which predict likelihood of hospitalization and mortality in VA populations, were included as of February 28, 2020. 13 …”

Section: Methodsmentioning

confidence: 99%

Racial/Ethnic Variation in Veterans Health Administration COVID-19 Vaccine Uptake

Haderlein

Wong

Jones

et al. 2022

American Journal of Preventive Medicine

View full text Add to dashboard Cite

show abstract

“…In a slightly different context, a case in point of such a tool is the Care Assessment Need (CAN) score deployed for almost a decade by the Veterans Health Administration in the US. It calculates weekly CAN scores for all Veterans who receive primary care services within the VA, including 90-days and 1-year mortality endpoints 34 . This tool has also been shown to be amenable to COVID-19 mortality risk stratification repurposing to support clinical decision making in a system under duress 35 .…”

Section: Discussionmentioning

confidence: 99%

Peeking into a black box, the fairness and generalizability of a MIMIC-III benchmarking model

2022

View full text Add to dashboard Cite

As artificial intelligence (AI) makes continuous progress to improve quality of care for some patients by leveraging ever increasing amounts of digital health data, others are left behind. Empirical evaluation studies are required to keep biased AI models from reinforcing systemic health disparities faced by minority populations through dangerous feedback loops. The aim of this study is to raise broad awareness of the pervasive challenges around bias and fairness in risk prediction models. We performed a case study on a MIMIC-trained benchmarking model using a broadly applicable fairness and generalizability assessment framework. While open-science benchmarks are crucial to overcome many study limitations today, this case study revealed a strong class imbalance problem as well as fairness concerns for Black and publicly insured ICU patients. Therefore, we advocate for the widespread use of comprehensive fairness and performance assessment frameworks to effectively monitor and validate benchmark pipelines built on open data resources.

show abstract

“…Such impact studies in ML are rare, and some have demonstrated clinically insignificant improvements 41 or even inferior accuracy 42 . Prediction models may work no better than pre‐existing regression models, 43 and even if they do, physicians may use them infrequently 44 . The frequency, costs, logistics and clinical effects of downstream actions triggered by model predictions must also be considered.…”

Section: Key Operational Issuesmentioning

confidence: 99%

“…42 Prediction models may work no better than pre-existing regression models, 43 and even if they do, physicians may use them infrequently. 44 The frequency, costs, logistics and clinical effects of downstream actions triggered by model predictions must also be considered. Higher efficacy standards must apply as models move from narrow diagnostic imaging applications to more demanding screening and therapeutic scenarios.…”

Section: Model Utility and Safetymentioning

confidence: 99%

Demystifying machine learning: a primer for physicians

Scott

2021

Internal Medicine Journal

View full text Add to dashboard Cite

Machine learning is a tool for analysing digitised data sets and formulating predictions that can optimise clinical decision‐making. It aims to identify complex patterns in large data sets and encode them into models that can then classify new unseen cases or make predictions on new data. Machine learning methods take several forms and individual models can be of many different types. More than 50 models have been approved for use in routine healthcare, and the numbers continue to grow exponentially. The reliability and robustness of any model depends on multiple factors, including the quality and quantity of the data used to develop the models, and the selection of features in the data considered most important to maximising accuracy. In ensuring models are safe, effective and reproducible in routine care, physicians need to have some understanding of how these models are developed and evaluated, and to collaborate with data and computer scientists in their design and validation. This narrative review introduces principles, methods and examples of machine learning in a way that does not require mastery of highly complex statistical and computational concepts.

show abstract

Using Predictive Analytics to Guide Patient Care and Research in a National Health System

Cited by 19 publications

References 5 publications

Racial/Ethnic Variation in Veterans Health Administration COVID-19 Vaccine Uptake

Racial/Ethnic Variation in Veterans Health Administration COVID-19 Vaccine Uptake

Peeking into a black box, the fairness and generalizability of a MIMIC-III benchmarking model

Demystifying machine learning: a primer for physicians

Contact Info

Product

Resources

About