Systematic Review on COVID-19 Readmission and Risk Factors: Future of Machine Learning in COVID-19 Readmission Studies

Abstract

In this review, current studies on hospital readmission due to infection of COVID-19 were discussed, compared, and further evaluated in order to understand the current trends and progress in mitigation of hospital readmissions due to COVID-19. Boolean expression of (“COVID-19” OR “covid19” OR “covid” OR “coronavirus” OR “Sars-CoV-2”) AND (“readmission” OR “re-admission” OR “rehospitalization” OR “rehospitalization”) were used in five databases, namely Web of Science, Medline, Science Direct, Google Scholar and Scopus. From the search, a total of 253 articles were screened down to 26 articles. In overall, most of the research focus on readmission rates than mortality rate. On the readmission rate, the lowest is 4.2% by Ramos-Martínez et al. from Spain, and the highest is 19.9% by Donnelly et al. from the United States. Most of the research (n = 13) uses an inferential statistical approach in their studies, while only one uses a machine learning approach. The data size ranges from 79 to 126,137. However, there is no specific guide to set the most suitable data size for one research, and all results cannot be compared in terms of accuracy, as all research is regional studies and do not involve data from the multi region. The logistic regression is prevalent in the research on risk factors of readmission post-COVID-19 admission, despite each of the research coming out with different outcomes. From the word cloud, age is the most dominant risk factor of readmission, followed by diabetes, high length of stay, COPD, CKD, liver disease, metastatic disease, and CAD. A few future research directions has been proposed, including the utilization of machine learning in statistical analysis, investigation on dominant risk factors, experimental design on interventions to curb dominant risk factors and increase the scale of data collection from single centered to multi centered.

Factors associated with 60‐day readmission among inpatients with COVID‐19 at 21 United States health systems

“…Although all age groups over 50 were at increased risk of readmission in univariate models (and greater risk of ICU admission or death on readmission), in multiple predictor models, being age 66‐74 years was associated with slightly lower risk of readmission relative to age 18–29 years. This differs from prior studies reporting positive associations between age and readmission risk 3–5,7 . The attenuation of age associations suggests that other factors, such as comorbidity burden and severity at index admission, may mediate associations with readmission.…”

“…The present study identified several risk factors for 60-day readmission in covariate-adjusted models, including: male sex (consistent with Akbari et al 7 ), noncommercial health insurance (consistent with Verna et al 5 ), living in an urban area, a history of cigarette smoking, longer index admission stays, and greater overall comorbidity burden. Consistent with prior research, 3,7,8 older age (in unadjusted models) and particular diagnoses were associated with readmission, including COPD, CAD/CHF, diabetes, renal failure, liver disease, diabetes, and cancer.…”

“…A meta‐analysis of 28 studies of COVID‐19 patients admitted in February–October 2020 found that older age, male sex, and White racial status were associated with higher readmission rates 7 . Specific co‐morbidities associated with readmission included cerebrovascular disease, cardiovascular disease, hypertension, ischemic heart disease, heart failure, diabetes, cancer, kidney disease, liver disease, and chronic obstructive pulmonary disease (COPD) 3,7,8 …”

“…Coronavirus disease 2019 (COVID‐19) is a complex illness resulting from severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) infection that may require ongoing clinical care 1,2 . Meta‐analyses and multisite electronic health record (EHR) studies have documented all‐cause readmission rates among patients hospitalized with COVID‐19 ranging from 4% to 19% 3–7 . Few studies have investigated factors associated with COVID‐19 readmission in large, diverse cohorts, and those that have were limited to the first months of the pandemic before COVID‐19 vaccines were available 3 .…”

Argument mining as rapid screening tool of COVID-19 literature quality: Preliminary evidence

“…The preliminary study presented in this paper clearly presents some limitations, which will be addressed in future work. First of all, a wider experimental study should be conducted, involving a larger number of reviewers and covering a variety of heterogeneous topics [e.g., also including COVID-19 readmission and risk factors ( 28 )]. This would enable a more comprehensive analysis of the differences in agreements amongst human reviewers, and between humans and AI/AM tools.…”