Rural-urban Differences in Long-term Mortality and Readmission Following COVID-19 Hospitalization, 2020 to 2023.

Background: We compared long-term mortality and readmission rates after COVID-19 hospitalization based on rural-urban status and assessed the impact of COVID-19 vaccination introduction on clinical outcomes by rurality. Methods: The study comprised adults hospitalized for COVID-19 at 17 hospitals in 4 US states between March 2020 and July 2022, followed until May 2023. The main analysis included all patients, whereas a sensitivity analysis focused on residents from 4 states containing 17 hospitals. Additional analyses compared the pre- and postvaccination periods. Results: The main analysis involved 9325 COVID-19 hospitalized patients: 31% were from 187 rural counties in 31 states; 69% from 234 urban counties in 44 states; the mean age was 65 years (rural, 66 years; urban, 64 years); 3894 women (rural, 41%; urban, 42%); 8007 Whites (rural, 87%; urban, 83%); 1738 deaths (rural, 21%; urban, 17%); and 2729 readmissions (rural, 30%; urban, 29%). During a median follow-up of 602 days, rural residence was associated with a 22% higher all-cause mortality (log-rank, P < .001; hazard ratio, 1.22; 95% confidence interval, 1.10-1.34, P < .001), and a trend toward a higher readmission rate (log-rank, P = .038; hazard ratio, 1.06; 95% confidence interval, .98-1.15; P = .130). The results remained consistent in the sensitivity analysis and in both pre- and postvaccination time periods. Conclusions and Relevance: Patients from rural counties experienced higher mortality and tended to be readmitted more frequently following COVID-19 hospitalization over the long term compared with those from urban counties, a difference that remained even after the introduction of COVID-19 vaccines.

Inclusion of Rurality and Social Determinants of Health in Documents for the Primary Prevention of Type 2 Diabetes: A Systematic Review.

Purpose: The type 2 diabetes (T2D) burden is disproportionately concentrated in low- and middle-income economies, particularly among rural populations. The purpose of the systematic review was to evaluate the inclusion of rurality and social determinants of health (SDOH) in documents for T2D primary prevention. Methods: This systematic review is reported following Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. We searched 19 databases, from 2017-2023, for documents on rurality and T2D primary prevention. Furthermore, we searched online for documents from the 216 World Bank economies, categorized by high, upper-middle, lower-middle, and low income status. We extracted data on rurality and the ten World Health Organization SDOH. Two authors independently screened documents and extracted data. Findings: Based on 3318 documents (19 databases and online search), we selected 15 documents for data extraction. The 15 documents applied to 32 economies; 12 of 15 documents were from nongovernment sources, none was from low-income economies, and 10 of 15 documents did not define or describe rurality. Among the SDOH, income and social protection (SDOH 1) and social inclusion and nondiscrimination (SDOH 8) were mentioned in documents for 25 of 29 high-income economies, while food insecurity (SDOH 5) and housing, basic amenities, and the environment (SDOH 6) were mentioned in documents for 1 of 2 lower-middle-income economies. For U.S. documents, none of the authors was from institutions in noncore (most rural) counties. Conclusions: Overall, documents on T2D primary prevention had sparse inclusion of rurality and SDOH, with additional disparity based on economic status. Inclusion of rurality and/or SDOH may improve T2D primary prevention in rural populations.

Development and internal validation of machine learning-based models and external validation of existing risk scores for outcome prediction in patients with ischaemic stroke.

Aims: We developed new machine learning (ML) models and externally validated existing statistical models [ischaemic stroke predictive risk score (iScore) and totalled health risks in vascular events (THRIVE) scores] for predicting the composite of recurrent stroke or all-cause mortality at 90 days and at 3 years after hospitalization for first acute ischaemic stroke (AIS). Methods and results: In adults hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models [random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBOOST)] and externally validated the iScore and THRIVE scores for predicting the composite outcomes after AIS hospitalization, using data from 721 patients and 90 potential predictor variables. At 90 days and 3 years, 11 and 34% of patients, respectively, reached the composite outcome. For the 90-day prediction, the area under the receiver operating characteristic curve (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year prediction, the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE. Conclusion: The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for long-term outcome prediction. Our findings warrant comparative analyses of ML and existing statistical method-based risk prediction tools for outcome prediction after AIS in new data sets.

Validating the performance of 3 sepsis screening tools in patients with clinical chorioamnionitis.

BACKGROUND: Maternal sepsis is a leading cause of maternal death in the United States. Approximately two-thirds of maternal deaths because of sepsis are related to delayed recognition or treatment. New early warning systems using a 2-step approach have been developed for the early recognition of sepsis in obstetrics; however, their performance has not been validated. OBJECTIVE: This study aimed to assess the performance of 3 primary screening tools introduced by the Society of Obstetric Medicine Australia and New Zealand and the California Maternal Quality Care Collaborative for use in the first step of their 2-step early warning systems. The obstetrically modified quick Sequential (sepsis-related) Organ Failure Assessment score tool, the obstetrically modified Systemic Inflammatory Response Syndrome tool, and the obstetrically modified Systemic Inflammatory Response Syndrome 1 tool were evaluated for the early detection of sepsis in patients with clinically diagnosed chorioamnionitis. STUDY DESIGN: This was a retrospective cohort study using prospectively collected clinical data at a tertiary care center and an affiliated healthcare system. The electronic health records were searched to identify and verify cases with clinically diagnosed chorioamnionitis between November 2017 and September 2022. The flow sheet for every patient was reviewed to determine when criteria were met for any of the 3 tools. The performance of these tools was analyzed using their sensitivity, specificity, positive and negative predictive values, and receiver operating characteristic curve for the identification of sepsis. RESULTS: There were 545 cases that had the requisite data for inclusion in the analysis. Of note, 11 patients met the criteria for sepsis. Both the obstetrically modified Systemic Inflammatory Response Syndrome and obstetrically modified Systemic Inflammatory Response Syndrome 1 tools had overall similar test characteristics, which were notably different from the obstetrically modified quick Sequential Organ Failure Assessment tool. The screen-positive rate of the obstetrically modified quick Sequential Organ Failure Assessment tool (1.5%; 95% confidence interval, 0.6%-2.9%) was lower than that of the obstetrically modified Systemic Inflammatory Response Syndrome tool (60.0%; 95% confidence interval, 55.7%-64.1%) and the obstetrically modified Systemic Inflammatory Response Syndrome 1 tool (50.0%; 95% confidence interval, 45.8%-54.3%). The sensitivities of the obstetrically modified Systemic Inflammatory Response Syndrome tool (100.0%; 95% confidence interval, 71.5%-100.0%) and the obstetrically modified Systemic Inflammatory Response Syndrome 1 tool (100.0%; 95% confidence interval, 71.5%-100.0%) were higher than that of the obstetrically modified quick Sequential Organ Failure Assessment tool (18.0%; 95% confidence interval, 2.3%-51.8%). All 3 tools had high negative predictive values; however, their positive predictive values were poor. CONCLUSION: This study demonstrated that all 3 tools had limitations in screening for sepsis among patients with a clinical diagnosis of chorioamnionitis. The obstetrically modified quick Sequential Organ Failure Assessment tool missed more than half of the sepsis cases and, thus, had poor performance as a primary screening tool for sepsis. Both the obstetrically modified Systemic Inflammatory Response Syndrome and obstetrically modified Systemic Inflammatory Response Syndrome 1 tools captured all sepsis cases; however, they tended to overdetect sepsis.

Guidelines, position statements, and advisories for the primary prevention of type 2 diabetes, hypertension, and cardiovascular disease in rural populations: A systematic review protocol.

INTRODUCTION: Globally, noncommunicable diseases (NCDs), which include type 2 diabetes (T2D), hypertension, and cardiovascular disease (CVD), are associated with a high burden of morbidity and mortality. Health disparities exacerbate the burden of NCDs. Notably, rural, compared with urban, populations face greater disparities in access to preventive care, management, and treatment of NCDs. However, there is sparse information and no known literature synthesis on the inclusion of rural populations in documents (i.e., guidelines, position statements, and advisories) pertaining to the prevention of T2D, hypertension, and CVD. To address this gap, we are conducting a systematic review to assess the inclusion of rural populations in documents on the primary prevention of T2D, hypertension, and CVD. METHODS AND ANALYSIS: This protocol follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched 19 databases including EMBASE, MEDLINE, and Scopus, from January 2017 through October 2022, on the primary prevention of T2D, hypertension, and CVD. We conducted separate Google® searches for each of the 216 World Bank economies. For primary screening, titles and/or abstracts were screened independently by two authors (databases) or one author (Google®). Documents meeting selection criteria will undergo full-text review (secondary screening) using predetermined criteria, and data extraction using a standardized form. The definition of rurality varies, and we will report the description provided in each document. We will also describe the social determinants of health (based on the World Health Organization) that may be associated with rurality. ETHICS AND DISSEMINATION: To our knowledge, this will be the first systematic review on the inclusion of rurality in documents on the primary prevention of T2D, hypertension, and CVD. Ethics approval is not required since we are not using patient-level data. Patients are not involved in the study design or analysis. We will present the results at conferences and in peer-reviewed publication(s). TRIAL REGISTRATION: PROSPERO Registration Number: CRD42022369815.

A Novel AUC Maximization Imbalanced Learning Approach for Predicting Composite Outcomes in COVID-19 Hospitalized Patients.

The COVID-19 patient data for composite outcome prediction often comes with class imbalance issues, i.e., only a small group of patients develop severe composite events after hospital admission, while the rest do not. An ideal COVID-19 composite outcome prediction model should possess strong imbalanced learning capability. The model also should have fewer tuning hyperparameters to ensure good usability and exhibit potential for fast incremental learning. Towards this goal, this study proposes a novel imbalanced learning approach called Imbalanced maximizing-Area Under the Curve (AUC) Proximal Support Vector Machine (ImAUC-PSVM) by the means of classical PSVM to predict the composite outcomes of hospitalized COVID-19 patients within 30 days of hospitalization. ImAUC-PSVM offers the following merits: (1) it incorporates straightforward AUC maximization into the objective function, resulting in fewer parameters to tune. This makes it suitable for handling imbalanced COVID-19 data with a simplified training process. (2) Theoretical derivations reveal that ImAUC-PSVM has the same analytical solution form as PSVM, thus inheriting the advantages of PSVM for handling incremental COVID-19 cases through fast incremental updating. We built and internally and externally validated our proposed classifier using real COVID-19 patient data obtained from three separate sites of Mayo Clinic in the United States. Additionally, we validated it on public datasets using various performance metrics. Experimental results demonstrate that ImAUC-PSVM outperforms other methods in most cases, showcasing its potential to assist clinicians in triaging COVID-19 patients at an early stage in hospital settings, as well as in other prediction applications.

An artificial intelligence approach for predicting death or organ failure after hospitalization for COVID-19: development of a novel risk prediction tool and comparisons with ISARIC-4C, CURB-65, qSOFA, and MEWS scoring systems.

BACKGROUND: We applied machine learning (ML) algorithms to generate a risk prediction tool [Collaboration for Risk Evaluation in COVID-19 (CORE-COVID-19)] for predicting the composite of 30-day endotracheal intubation, intravenous administration of vasopressors, or death after COVID-19 hospitalization and compared it with the existing risk scores. METHODS: This is a retrospective study of adults hospitalized with COVID-19 from March 2020 to February 2021. Patients, each with 92 variables, and one composite outcome underwent feature selection process to identify the most predictive variables. Selected variables were modeled to build four ML algorithms (artificial neural network, support vector machine, gradient boosting machine, and Logistic regression) and an ensemble model to generate a CORE-COVID-19 model to predict the composite outcome and compared with existing risk prediction scores. The net benefit for clinical use of each model was assessed by decision curve analysis. RESULTS: Of 1796 patients, 278 (15%) patients reached primary outcome. Six most predictive features were identified. Four ML algorithms achieved comparable discrimination (P > 0.827) with c-statistics ranged 0.849-0.856, calibration slopes 0.911-1.173, and Hosmer-Lemeshow P > 0.141 in validation dataset. These 6-variable fitted CORE-COVID-19 model revealed a c-statistic of 0.880, which was significantly (P < 0.04) higher than ISARIC-4C (0.751), CURB-65 (0.735), qSOFA (0.676), and MEWS (0.674) for outcome prediction. The net benefit of the CORE-COVID-19 model was greater than that of the existing risk scores. CONCLUSION: The CORE-COVID-19 model accurately assigned 88% of patients who potentially progressed to 30-day composite events and revealed improved performance over existing risk scores, indicating its potential utility in clinical practice.

Characteristics, Treatment Patterns, and Clinical Outcomes After Heart Failure Hospitalizations During the COVID-19 Pandemic, March to October 2020.

OBJECTIVE: To compare clinical characteristics, treatment patterns, and 30-day all-cause readmission and mortality between patients hospitalized for heart failure (HF) before and during the coronavirus disease 2019 (COVID-19) pandemic. PATIENTS AND METHODS: The study was conducted at 16 hospitals across 3 geographically dispersed US states. The study included 6769 adults (mean age, 74 years; 56% [5033 of 8989] men) with cumulative 8989 HF hospitalizations: 2341 hospitalizations during the COVID-19 pandemic (March 1 through October 30, 2020) and 6648 in the pre-COVID-19 (October 1, 2018, through February 28, 2020) comparator group. We used Poisson regression, Kaplan-Meier estimates, multivariable logistic, and Cox regression analysis to determine whether prespecified study outcomes varied by time frames. RESULTS: The adjusted 30-day readmission rate decreased from 13.1% (872 of 6648) in the pre-COVID-19 period to 10.0% (234 of 2341) in the COVID-19 pandemic period (relative risk reduction, 23%; hazard ratio, 0.77; 95% CI, 0.66 to 0.89). Conversely, all-cause mortality increased from 9.7% (645 of 6648) in the pre-COVID-19 period to 11.3% (264 of 2341) in the COVID-19 pandemic period (relative risk increase, 16%; number of admissions needed for one additional death, 62.5; hazard ratio, 1.19; 95% CI, 1.02 to 1.39). Despite significant differences in rates of index hospitalization, readmission, and mortality across the study time frames, the disease severity, HF subtypes, and treatment patterns remained unchanged (P>0.05). CONCLUSION: The findings of this large tristate multicenter cohort study of HF hospitalizations suggest lower rates of index hospitalizations and 30-day readmissions but higher incidence of 30-day mortality with broadly similar use of HF medication, surgical interventions, and devices during the COVID-19 pandemic compared with the pre-COVID-19 time frame.

Natural Language Processing CAM Algorithm Improves Delirium Detection Compared With Conventional Methods.

Delirium is known to be underdiagnosed and underdocumented. Delirium detection in retrospective studies occurs mostly by clinician diagnosis or nursing documentation. This study aims to assess the effectiveness of natural language processing-confusion assessment method (NLP-CAM) algorithm when compared to conventional modalities of delirium detection. A multicenter retrospective study analyzed 4351 COVID-19 hospitalized patient records to identify delirium occurrence utilizing three different delirium detection modalities namely clinician diagnosis, nursing documentation, and the NLP-CAM algorithm. Delirium detection by any of the 3 methods is considered positive for delirium occurrence as a comparison. NLP-CAM captured 80% of overall delirium, followed by clinician diagnosis at 55%, and nursing flowsheet documentation at 43%. Increase in age, Charlson comorbidity score, and length of hospitalization had increased delirium detection odds regardless of the detection method. Artificial intelligence-based NLP-CAM algorithm, compared to conventional methods, improved delirium detection from electronic health records and holds promise in delirium diagnostics.