Maniaci, Michael J.

Objectives Mayo Clinic’s hospital-at-home program, Advanced Care at Home (ACH), launched in 2020. While hospital-at-home literature reported safe and effective care for the general patient population and those with COVID, comparative outcomes between these two groups were unknown. The aim of this retrospective analysis was to compare the outcomes of COVID and non-COVID patients enrolled in ACH and evaluate if COVID patients can be safely treated in this setting. Methods Demographics, clinical characteristics, and safety outcomes were retrospectively analyzed to compare COVID and non-COVID patients discharged from ACH between November 2020 and May 2022. Patient characteristics analyzed included severity of illness (SOI) and risk of mortality (ROM), calculated using All Patient Refined Diagnosis Related Groups (APR-DRG). Hospitalization-specific variables included length of stay (LOS), escalation of care, and 30-day readmission rates. Results Of 1051 patients, 173 (16%) had COVID, and 878 (84%) were non-COVID patients. The average age in the COVID cohort was 66.6 (15.3) years, compared with 72.2 (14.0) in the non-COVID cohort. Extreme SOI was higher in the COVID group (43.3% versus 17.4%), as was extreme ROM (46.2% versus 16.2%), but LOS was shorter (5.7 versus 7 days). Escalation of care (7.5% in COVID cohort versus 8.4%) and 30-day readmission outcomes (9.2% for COVID patients versus 12.9%) were not statistically different between the groups. Conclusions Despite higher SOI and ROM, COVID patients had shorter LOS with outcomes that were not statistically different from non-COVID patients. COVID patients can be safely and efficiently cared for in ACH.

The primary objective of this study was to develop a risk-based readmission prediction model using the EMR data available at discharge. This model was then validated with the LACE plus score. The study cohort consisted of about 310,000 hospital admissions of patients with cardiovascular and cerebrovascular conditions. The EMR data of the patients consisted of lab results, vitals, medications, comorbidities, and admit/discharge settings. These data served as the input to an XGBoost model v1.7.6, which was then used to predict the number of days until the next readmission. Our model achieved remarkable results, with a precision score of 0.74 (±0.03), a recall score of 0.75 (±0.02), and an overall accuracy of approximately 82% (±5%). Notably, the model demonstrated a high accuracy rate of 78.39% in identifying the patients readmitted within 30 days and 80.81% accuracy for those with readmissions exceeding six months. The model was able to outperform the LACE plus score; of the people who were readmitted within 30 days, only 47.70 percent had a LACE plus score greater than 70, and, for people with greater than 6 months, only 10.09 percent had a LACE plus score less than 30. Furthermore, our analysis revealed that the patients with a higher comorbidity burden and lower-than-normal hemoglobin levels were associated with increased readmission rates. This study opens new doors to the world of differential patient care, helping both clinical decision makers and healthcare providers make more informed and effective decisions. This model is comparatively more robust and can potentially substitute the LACE plus score in cardiovascular and cerebrovascular settings for predicting the readmission risk.

AbstractBackgroundHospital‐at‐home has become a more recognized way to care for patients requiring inpatient hospitalization. At times, these patients may require escalation of care (transfer from home back to the brick‐and‐mortar (BAM) hospital for ongoing hospitalization care needs), a process that has not been extensively studied.ObjectiveTo evaluate what patient factors contribute to escalations of care in the hospital‐at‐home delivery model.Designs, Settings, and ParticipantsWe conducted a retrospective review of all patients admitted to Mayo Clinic's Advanced Care at Home (ACH) program from January 1, 2022 to December 31, 2022.InterventionNone.Main Outcomes and MeasuresPatient information was collected via electronic health record including demographic, socioeconomic, and clinical status. The primary outcome was the of occurrence of an escalation.ResultsA total of 904 patients were included, of whom 80 (8.8%) required an escalation of care. In multivariable analysis, risk of an escalation was significantly higher for patients who were married or had a life partner (HR: 1.82, 95% CI: 1.05–3.23, p = .033) for patients admitted with procedure‐related disorders (HR: 2.61, 95% CI: 1.35–5.05, p = .005) and patients with an increased mortality risk score (HR [per each 1–category increase] = 1.86, 95% CI: 1.39–2.50, p < .001).

This study aims to explore how artificial intelligence can help ease the burden on caregivers, filling a gap in current research and healthcare practices due to the growing challenge of an aging population and increased reliance on informal caregivers. We conducted a search with Google Scholar, PubMed, Scopus, IEEE Xplore, and Web of Science, focusing on AI and caregiving. Our inclusion criteria were studies where AI supports informal caregivers, excluding those solely for data collection. Adhering to PRISMA 2020 guidelines, we eliminated duplicates and screened for relevance. From 947 initially identified articles, 10 met our criteria, focusing on AI’s role in aiding informal caregivers. These studies, conducted between 2012 and 2023, were globally distributed, with 80% employing machine learning. Validation methods varied, with Hold-Out being the most frequent. Metrics across studies revealed accuracies ranging from 71.60% to 99.33%. Specific methods, like SCUT in conjunction with NNs and LibSVM, showcased accuracy between 93.42% and 95.36% as well as F-measures spanning 93.30% to 95.41%. AUC values indicated model performance variability, ranging from 0.50 to 0.85 in select models. Our review highlights AI’s role in aiding informal caregivers, showing promising results despite different approaches. AI tools provide smart, adaptive support, improving caregivers’ effectiveness and well-being.

Home hospital programs continue to grow across the United States. There are limited studies around the process of patient selection and successful acquisition from the emergency department. The article describes how an interdisciplinary team used quality improvement methodology to significantly increase the number of admissions directly from the emergency department to the Advanced Care at Home program.

Advanced Care at Home is a Mayo Clinic hospital-at-home (HaH) program that provides hospital-level care for patients. The study examines patient- and community-level factors that influence health outcomes. The authors performed a retrospective study using patient data from July 2020 to December 2022. The study includes 3 Mayo Clinic centers and community-level data from the Agency for Healthcare Research and Quality. The authors conducted binary logistic regression analyses to examine the relationship among the independent variables (patient- and community-level characteristics) and dependent variables (30-day readmission, mortality, and escalation of care back to the brick-and-mortar hospital). The study examined 1433 patients; 53% were men, 90.58% were White, and 68.2% were married. The mortality rate was 2.8%, 30-day readmission was 11.4%, and escalation back to brick-and-mortar hospitals was 8.7%. At the patient level, older age and male gender were significant predictors of 30-day mortality ( P -value <0.05), older age was a significant predictor of 30-day readmission ( P -value <0.05), and severity of illness was a significant predictor for readmission, mortality, and escalation back to the brick-and-mortar hospital ( P -value <0.01). Patients with COVID-19 were less likely to experience readmission, mortality, or escalations ( P -value <0.05). At the community level, the Gini Index and internet access were significant predictors of mortality ( P -value <0.05). Race and ethnicity did not significantly predict adverse outcomes ( P -value >0.05). This study showed promise in equitable treatment of diverse patient populations. The authors discuss and address health equity issues to approximate the vision of inclusive HaH delivery.

AbstractBackgroundHospital‐at‐home (HaH) is a growing model of care that has been shown to improve patient outcomes, satisfaction, and cost‐effectiveness. However, selecting appropriate patients for HaH is challenging, often requiring burdensome manual screening by clinicians. To facilitate HaH enrollment, electronic health record (EHR) tools such as best practice advisories (BPAs) can be used to alert providers of potential HaH candidates.ObjectiveTo describe the development and implementation of a BPA for identifying HaH eligible patients in Mayo Clinic's Advanced Care at Home (ACH) program, and to evaluate the provider response and the patient characteristics that triggered the BPA.Design, Setting, and ParticipantsWe conducted a retrospective multicenter study of hospitalized patients who triggered the BPA notification for ACH eligibility between March and December 2021 at Mayo Clinic in Jacksonville, FL and Mayo Clinic Health System in Eau Claire, WI. We extracted demographic and diagnosis data from the patients as well as characteristics of the providers who received the BPA notification.InterventionThe BPA was developed based on the ACH inclusion and exclusion criteria, which were derived from clinical guidelines, literature review, and expert consensus. The BPA was integrated into the EHR and displayed a pop‐up message to the provider when a patient met the criteria for ACH eligibility. The provider could choose to refer the patient to ACH, dismiss the notification, or defer the decision.Main Outcomes and MeasuresThe main outcomes were the number and proportion of BPA notifications that resulted in a referral to ACH, and the number and proportion of referrals that were accepted by the ACH clinical team and transferred to ACH. We also analyzed the factors associated with the provider's decision to refer or not refer the patient to ACH, such as the provider's role, location, and specialty.ResultsDuring the study period, 8962 notifications were triggered for 2847 patients. Providers opted to refer 711 (11.4%) of the total notifications linked to 324 unique patients. After review by the ACH clinical team, 31 of the 324 referrals (9.6%) met clinical and social criteria and were transferred to ACH. In multivariable analysis, Wisconsin nurses, physician assistants, and in‐training personnel had lower odds of referring the patients to ACH when compared to attending physicians.

Key Clinical Messages This case report demonstrates a virtual hybrid hospital‐at‐home program can provide inpatient‐level postoperative and rehabilitative care after total knee arthroplasty to a medically complex patient in the comfort of their own home. Abstract Advanced Care at Home combines virtual providers with in‐home care delivery. We report a case of virtual postoperative and rehabilitative care in a medically complex patient who underwent a total knee arthroplasty. This new model of care delivery allows effective patient‐provider communication and meets patient needs in the postoperative period.