Objectives: Approximately 20–30% of patients with COVID-19 require hospitalization, and 5–12% may require critical care in an intensive care unit (ICU). A rapid surge in cases of severe COVID-19 will lead to a corresponding surge in demand for ICU care. Because of constraints on resources, frontline healthcare workers may be unable to provide the frequent monitoring and assessment required for all patients at high risk of clinical deterioration. We developed a machine learning-based risk prioritization tool that predicts ICU transfer within 24 h, seeking to facilitate efficient use of care providers’ efforts and help hospitals plan their flow of operations. Methods: A retrospective cohort was comprised of non-ICU COVID-19 admissions at a large acute care health system between 26 February and 18 April 2020. Time series data, including vital signs, nursing assessments, laboratory data, and electrocardiograms, were used as input variables for training a random forest (RF) model. The cohort was randomly split (70:30) into training and test sets. The RF model was trained using 10-fold cross-validation on the training set, and its predictive performance on the test set was then evaluated. Results: The cohort consisted of 1987 unique patients diagnosed with COVID-19 and admitted to non-ICU units of the hospital. The median time to ICU transfer was 2.45 days from the time of admission. Compared to actual admissions, the tool had 72.8% (95% CI: 63.2–81.1%) sensitivity, 76.3% (95% CI: 74.7–77.9%) specificity, 76.2% (95% CI: 74.6–77.7%) accuracy, and 79.9% (95% CI: 75.2–84.6%) area under the receiver operating characteristics curve. Conclusions: A ML-based prediction model can be used as a screening tool to identify patients at risk of imminent ICU transfer within 24 h. This tool could improve the management of hospital resources and patient-throughput planning, thus delivering more effective care to patients hospitalized with COVID-19.

The objectives of this study are to illustrate the effects of immortal time bias (ITB) using an oncology outcomes database and quantify through simulations the magnitude and direction of ITB when different analytical techniques are used. A cohort of 11 626 women who received neoadjuvant chemotherapy and underwent mastectomy with pathologically positive lymph nodes were accrued from the National Cancer Database (2004-2008). Standard Cox regression, time-dependent (TD), and landmark models were used to compare overall survival in patients who did or did not receive postmastectomy radiation therapy (PMRT). Simulation studies showing ways to reduce the effect of ITB indicate that TD exposures should be included as variables in hazard-based analyses. Standard Cox regression models comparing overall survival in patients who did and did not receive PMRT showed a significant treatment effect (hazard ratio [HR]: 0.93, 95% confidence interval [CI]: 0.88-0.99). Time-dependent and landmark methods estimated no treatment effect with HR: 0.97, 95% CI: 0.92 to 1.03 and HR: 0.98, 95% CI, 0.92 to 1.04, respectively. In our simulation studies, the standard Cox regression model significantly overestimated treatment effects when no effect was present. Estimates of TD models were closest to the true treatment effect. Landmark model results were highly dependent on landmark timing. Appropriate statistical approaches that account for ITB are critical to minimize bias when examining relationships between receipt of PMRT and survival.

Early detection of patients at risk for clinical deterioration is crucial for timely intervention. Traditional detection systems rely on a limited set of variables and are unable to predict the time of decline. We describe a machine learning model called MEWS++ that enables the identification of patients at risk of escalation of care or death six hours prior to the event. A retrospective single-center cohort study was conducted from July 2011 to July 2017 of adult (age > 18) inpatients excluding psychiatric, parturient, and hospice patients. Three machine learning models were trained and tested: random forest (RF), linear support vector machine, and logistic regression. We compared the models’ performance to the traditional Modified Early Warning Score (MEWS) using sensitivity, specificity, and Area Under the Curve for Receiver Operating Characteristic (AUC-ROC) and Precision-Recall curves (AUC-PR). The primary outcome was escalation of care from a floor bed to an intensive care or step-down unit, or death, within 6 h. A total of 96,645 patients with 157,984 hospital encounters and 244,343 bed movements were included. Overall rate of escalation or death was 3.4%. The RF model had the best performance with sensitivity 81.6%, specificity 75.5%, AUC-ROC of 0.85, and AUC-PR of 0.37. Compared to traditional MEWS, sensitivity increased 37%, specificity increased 11%, and AUC-ROC increased 14%. This study found that using machine learning and readily available clinical data, clinical deterioration or death can be predicted 6 h prior to the event. The model we developed can warn of patient deterioration hours before the event, thus helping make timely clinical decisions.

Introduction: Statistical methods to assess the impact of an intervention are increasingly used in clinical research settings. However, a comprehensive review of the methods geared toward practitioners is not yet available. Methods and Materials: We provide a comprehensive review of three methods to assess the impact of an intervention: difference-in-differences (DID), segmented regression of interrupted time series (ITS), and interventional autoregressive integrated moving average (ARIMA). We also compare the methods, and provide illustration of their use through three important healthcare-related applications. Results: In the first example, the DID estimate of the difference in health insurance coverage rates between expanded states and unexpanded states in the post-Medicaid expansion period compared to the pre-expansion period was 5.93 (95% CI, 3.99 to 7.89) percentage points. In the second example, a comparative segmented regression of ITS analysis showed that the mean imaging order appropriateness score in the emergency department at a tertiary care hospital exceeded that of the inpatient setting with a level change difference of 0.63 (95% CI, 0.53 to 0.73) and a trend change difference of 0.02 (95% CI, 0.01 to 0.03) after the introduction of a clinical decision support tool. In the third example, the results from an interventional ARIMA analysis show that numbers of creatinine clearance tests decreased significantly within months of the start of eGFR reporting, with a magnitude of drop equal to − 0.93 (95% CI, − 1.22 to − 0.64) tests per 100,000 adults and a rate of drop equal to 0.97 (95% CI, 0.95 to 0.99) tests per 100,000 per adults per month. Discussion: When choosing the appropriate method to model the intervention effect, it is necessary to consider the structure of the data, the study design, availability of an appropriate comparison group, sample size requirements, whether other interventions occur during the study window, and patterns in the data.

Dementia and cancer occur commonly in older adults. Yet, little is known about the effect of dementia on cancer treatment and outcomes in patients diagnosed with cancer, and no guidelines exist. We performed a mixed studies review to assess the current knowledge and gaps on the impact of dementia on cancer treatment decision-making, cancer treatment, and mortality. A search in PubMed, Medline, and PsycINFO identified 55 studies on older adults with a dementia diagnosis before a cancer diagnosis and/or comorbid cancer and dementia published in English from January 2004 to February 2020. We described variability using range in quantitative estimates, ie, odds ratios (ORs), hazard ratios (HRs), and risk ratios (RR) when appropriate and performed narrative review of qualitative data. Patients with dementia were more likely to receive no curative treatment (including hospice or palliative care) (OR, HR, and RR range = 0.40-4.4, n = 8), while less likely to receive chemotherapy (OR and HR range = 0.11-0.68, n = 8), radiation (OR range = 0.24-0.56, n = 2), and surgery (OR range = 0.30-1.3, n = 4). Older adults with cancer and dementia had higher mortality than those with cancer alone (HR and OR range = 0.92-5.8, n = 33). Summarized findings from qualitative studies consistently revealed that clinicians, caregivers, and patients tended to prefer less aggressive care and gave higher priority to quality of life over life expectancy for those with dementia. Current practices in treatment-decision making for patients with both cancer and dementia are inconsistent. There is an urgent need for treatment guidelines for this growing patient population that considers patient and caregiver perspectives.

Background: Concerns exist regarding exacerbation of existing disparities in health care access with the rapid implementation of telemedicine during the coronavirus disease 2019 (COVID-19) pandemic. However, data on pre-existing disparities in telemedicine utilization is currently lacking. Objective: We aimed to study: (1) the prevalence of outpatient telemedicine visits before the COVID-19 pandemic by patient subgroups based on age, comorbidity burden, residence rurality, and median household income; and (2) associated diagnosis categories. Research Design: This was a retrospective cohort study. Subject: Commercial claims data from the Truven MarketScan database (2014−2018) representing n=846,461,609 outpatient visits. Measures: We studied characteristics and utilization of outpatient telemedicine services before the COVID-19 pandemic by patient subgroups based on age, comorbidity burden, residence rurality, and median household income. Disparities were assessed in unadjusted and adjusted (regression) analyses. Results: With overall telemedicine uptake of 0.12% (n=1,018,092/846,461,609 outpatient visits) we found that pre-COVID-19 disparities in telemedicine use became more pronounced over time with lower use in patients who were older, had more comorbidities, were in rural areas, and had lower median household incomes (all trends and effect estimates P<0.001). Conclusion: These results contextualize pre-existing disparities in telemedicine use and are crucial in the monitoring of potential disparities in telemedicine access and subsequent outcomes after the rapid expansion of telemedicine during the COVID-19 pandemic.