Machine learning based forecast for the prediction of inpatient bed demand.

BACKGROUND: Overcrowding is a serious problem that impacts the ability to provide optimal level of care in a timely manner. High patient volume is known to increase the boarding time at the emergency department (ED), as well as at post-anesthesia care unit (PACU). Furthermore, the same high volume increases inpatient bed transfer times, which causes delays in elective surgeries, increases the probability of near misses, patient safety incidents, and adverse events. OBJECTIVE: The purpose of this study is to develop a Machine Learning (ML) based strategy to predict weekly forecasts of the inpatient bed demand in order to assist the resource planning for the ED and PACU, resulting in a more efficient utilization. METHODS: The data utilized included all adult inpatient encounters at Geisinger Medical Center (GMC) for the last 5 years. The variables considered were class of inpatient encounter, observation, or surgical overnight recovery (SORU) at the time of their discharge. The ML based strategy is built using the K-means clustering method and the Support Vector Machine Regression technique (K-SVR). RESULTS: The performance obtained by the K-SVR strategy in the retrospective cohort amounts to a mean absolute percentage error (MAPE) that ranges between 0.49 and 4.10% based on the test period. Additionally, results present a reduced variability, which translates into more stable forecasting results. CONCLUSIONS: The results from this study demonstrate the capacity of ML techniques to forecast inpatient bed demand, particularly using K-SVR. It is expected that the implementation of this model in the workflow of bed capacity management will create efficiencies, which will translate in a more reliable, inexpensive and timely care for patients.

Optimizing Bed Utilization for COVID-19 Patient Flow Protocols in a Behavioral Health Inpatient Facility using Discrete Event Simulation.

In this paper, we propose utilizing a discrete event simulation model as a decision-support tool to optimize bed capacity and configuration of Geisinger's inpatient drug and alcohol treatment facility. During the COVID-19 pandemic patient flows and processes needed to adapt to new safety protocols. The existing bed configurations are not designed for social distancing and other COVID protocols. The data for this study was collected post implementation of COVID-19 protocols on patient arrivals, and process flows by level of care. The baseline model was validated and verified against retrospective data to ensure the model assumptions were reasonable. The model showed that current bed capacity can be reduced by approximately 14% and bed configurations can be modified without impacting patient flow and wait times. These results help stakeholders make data-driven decisions to reduce redundancies and realize efficiency gains while improving their ability to plan for the growth of the facility.

Simple contents and good readability: Improving health literacy for LEP populations.

Accessing and receiving quality healthcare in an unfamiliar health system is a significant challenge for many new immigrants and refugees. This study aims to provide a three-phase model to develop a web-based health information website that helps populations with limited English proficiency (LEP) increase health literacy and improve healthcare service access. METHOD: First, we conducted a needs assessment from community leaders and service providers. Second, we developed contents from credible sources and tested each item using multiple readability tests. Last, we revised each item to lower the readability and retest its readability. RESULTS: The average reading level for the original 99 topics was assessed at 10.84 (SD= 3.26). After revisions, we were able to lower the readability to 8.56 (SD= 2.96), which was around two grade levels lower, on average. CONCLUSION: the main purpose for building an English based health information website was to assist the population with LEP. By using simple English with lower readability, it will ease the translation process. This study demonstrates a process to develop suitable contents for populations in need. In the future, incorporating visual aid and other multimedia will be beneficial in user engagement and knowledge retention.

Causal analysis of the impact of homecare services on patient discharge disposition.

This study uses observational causal inference to evaluate the impact of different combinations of home care services (nursing, therapies, social work, home aides) on end-of-episode disposition for individuals with chronic diseases associated with the circulatory, endocrine, and musculoskeletal systems. The potential to generate actionable recommendations for personalizing home care services, or treatment plans, from limited clinical and care needs data is demonstrated. For patients with chronic disease in the circulatory or musculoskeletal systems, a 2.91% and 3.38% decrease, respectively, in acute care hospitalization rates could be obtained by providing patients with therapy and nursing services, rather than therapy services alone.

Chondrites isp. indicating late paleozoic atmospheric anoxia in Eastern Peninsular India.

Rhythmic sandstone-mudstone-coal succession of the Barakar Formation (early Permian) manifests a transition from lower braided-fluvial to upper tide-wave influenced, estuarine setting. Monospecific assemblage of marine trace fossil Chondrites isp. in contemporaneous claystone beds in the upper Barakar succession from two Gondwana basins (namely, the Raniganj Basin and the Talchir Basin) in eastern peninsular India signifies predominant marine incursion during end early Permian. Monospecific Chondrites ichnoassemblage in different sedimentary horizons in geographically wide apart (~400 km) areas demarcates multiple short-spanned phases of anoxia in eastern India. Such anoxia is interpreted as intermittent falls in oxygen level in an overall decreasing atmospheric oxygenation within the late Paleozoic global oxygen-carbon dioxide fluctuations.