A novel method for handling pre-existing conditions in multivariate prediction model development for COVID-19 death in the Department of Veterans Affairs

Abstract

Many mathematical models have been proposed to predict death following COVID-19; all started with comorbidity subsets for this still-little understood disease. Thus, we derived a novel predicted probability of death model (PDeathDx) upon all diagnostic codes documented in the Department of Veterans Affairs. We present the conceptual underpinnings and analytic approach in estimating the independent contribution of pre-existing conditions. This is the largest study to-date following patients with COVID-19 to predict mortality. Cases were identified with at least one positive nucleic acid amplification test (NAAT). Starting in 1997, we use diagnoses from the first time a patient sought care until 14 days before a positive NAAT. We demonstrate the clear advantage of using an unrestricted set of pre-existing conditions to model COVID-19 mortality, as models using conventional comorbidity indices often assign little weight or usually do not include some of the highest-risk conditions; the same is true of conditions associated with COVID-19 severity. Our findings suggest that it is risky to pick comorbidities for analysis without a systematic review of all those experienced by the cohort. Unlike conventional approaches, our comprehensive methodology provides the flexibility that has been advocated for comorbidity indices since 1993; such an approach can be readily adapted for other diseases and outcomes. With our comorbidity risk adjustment approach outperforming conventional indices for predicting COVID-19 mortality, it shows promise for predicting outcomes for other conditions of interest.

Associations between cohort derived dementia and COVID-19 serological diagnosis among older Black adults in rural South Africa

“…Although our analysis established a robust association between cohort derived dementia and COVID-19 diagnosis, we are unable to assess its relation to infection severity. Although prior research has linked ADRD to COVID-19 morbidity and mortality, our data were limited in their ability to assess this in our sample (24,(34)(35)(36). Moreover, prior research in Agincourt during a similar period (August 2021) indicated high rates of asymptomatic cases (approximately 85% of infected individuals) (27).…”

“…Community outreach through this approach has been effective in reducing the burden of other non-communicable diseases in South Africa and thus is a compelling option to apply to the ADRD population (41,42). Although great progress has been made in reducing the COVID-19-related burden of disease, it remains vital to consider targeted public health interventions for those with ADRD, because of their vulnerability for morbidity, mortality, and breakthrough infection (34,36,43).…”

Effect of vaccination on the case fatality rate for COVID-19 infections 2020–2021: multivariate modelling of data from the US Department of Veterans Affairs

“…PDeathDx refers to the predicted probability of death based on 153 ICD10 category diagnoses. 7 Pre-existing conditions were identified by reviewing all diagnoses entered into the electronic medical record during outpatient visits, as updates to the patient problem list, or at the time of hospital discharge. ‘Pre-existing’ refers to entries made up to 14 days before the COVID-19 diagnosis.…”

“…Our study used three novel parameters representing potential confounders from major domains of the medical record. PDeathDx refers to the predicted probability of death based on 153 ICD10 category diagnoses 7. Pre-existing conditions were identified by reviewing all diagnoses entered into the electronic medical record during outpatient visits, as updates to the patient problem list, or at the time of hospital discharge.…”

Machine Learning Approaches to Advanced Outlier Detection in Psychological Datasets

“…However, traditional techniques encounter substantial limitations when applied to multivariate datasets, especially those that lack predetermined labels for outlier identification. These constraints expose a significant gap in our methodological framework, emphasizing the immediate need for the design and implementation of advanced techniques [7]. Ideally, such techniques would be capable of effectively addressing the complex characteristics inherent in multivariate psychological datasets.…”