Practical development and operationalization of a 12-hour hospital census prediction algorithm.
Ontology highlight
ABSTRACT:
SUBMITTER: Ryu AJ
PROVIDER: S-EPMC8344501 | biostudies-literature | 2021 Aug
REPOSITORIES: biostudies-literature
Publications
Practical development and operationalization of a 12-hour hospital census prediction algorithm.
Ryu Alexander J AJ Romero-Brufau Santiago S Shahraki Narges N Zhang Jiawei J Qian Ray R Kingsley Thomas C TC
Journal of the American Medical Informatics Association : JAMIA 20210801 9
Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop si ...[more]
Similar Datasets
Project description:Fatigue-related impairments in the nursing workforce contribute to a multitude of health, safety, and economic consequences at the individual, organizational and societal levels. Long and compressed work schedules are commonly worked in the healthcare industry, but more research is needed to understand the cumulative effects of multiple work shifts on physiology-based performance outcomes in nurses. The purpose of this study was to compare the effects of a single nursing work shift versus three compressed (one every 24 hours) 12 hour shifts on performance-based fatigue in nurses and aides. Twenty-six fulltime hospital working nurses and aides (age = 36.1 ± 13.3 years) reported to the lab for testing before, immediately after working a single 12 hour shift, and after working three 12 hour shifts in a 72 hour period. Outcome measures included vigilance-based reaction time, lapses of attention, and muscle function assessments (lower and upper body muscle strength, explosive strength and vertical jump performance). All variables except hand grip strength showed a significant decline following the three work shifts. The psychomotor vigilance reaction time and lapses of attention variables also generally showed a significant decline from the end of shift one to the end of shift three, indicting an accumulation of fatigue in these metrics with increasing number of shifts worked. Muscle function variables responded early in the duty cycle, showing a significant decline after a single work shift, but did no further decline by the end of the third shift. These findings use objective measures to substantiate that fatigue impairments occur from working a single 12 hour shift, and in several instances, increase further with more successive work shifts. Caution should be employed by personnel and administrators with work schedules involving multiple compressed 12 hour shifts. Fatigue management strategies may be used to improve risks and consequences from fatigue-related mishaps, and this study reports several variables that appear sensitive to identifying and tracking fatigue in this population.
| S-EPMC6366767 | biostudies-literature
Project description:Cardiovascular disease is a major global public health problem, and intelligent diagnostic approaches play an increasingly important role in the analysis of electrocardiograms (ECGs). Convenient wearable ECG devices enable the detection of transient arrhythmias and improve patient health by making it possible to seek intervention during continuous monitoring. We collected 658,486 wearable 12-lead ECGs, among which 164,538 were annotated, and the remaining 493,948 were without diagnostic. We present four data augmentation operations and a self-supervised learning classification framework that can recognize 60 ECG diagnostic terms. Our model achieves an average area under the receiver-operating characteristic curve (AUROC) and average F1 score on the offline test of 0.975 and 0.575. The average sensitivity, specificity and F1-score during the 2-month online test are 0.736, 0.954 and 0.468, respectively. This approach offers real-time intelligent diagnosis, and detects abnormal segments in long-term ECG monitoring in the clinical setting for further diagnosis by cardiologists.
| S-EPMC10290151 | biostudies-literature
Project description:Background The use of 12-h shifts for nursing staff has become common in many healthcare settings, including tertiary hospitals, due to its potential benefits such as reduced handover time and increased continuity of care. However, there is limited research on the experiences of nurses working 12-h shifts, particularly in the context of Qatar, where the healthcare system and nursing workforce may have unique characteristics and challenges. This study aimed to explore the experiences of nurses working 12-h shifts in a tertiary hospital in Qatar, including their perceptions of physical health, fatigue, stress, job satisfaction, service quality, and patient safety. Methods A mixed method study design was applied consisting of a survey and semi-structured interviews. Data was collected from 350 nurses through an online survey and from 11 nurses through semi-structured interviews. Data was analyzed using Shapiro–Wilk test and the difference between demographic variables and scores were examined using Whitney U test and Kruskal- Wallis test. Thematic analysis was used for qualitative interviews. Results The results from quantitative study revealed nurses perception in working 12-h shift has negative impact in their wellbeing, satisfaction as well as patient care outcomes. Thematic analysis revealed real stress and burnout and experienced an enormous amount of pressure going for work. Conclusions Our study provides an understanding of the nurse’s experience working 12-h shift in a tertiary level hospital in Qatar. A mixed method approach informed us that, nurses are not satisfied with the 12-h shift and interviews revealed high level of stress and burnout among nurses resulting in job dissatisfaction and negative health concerns. Nurses also reported that it is challenging to stay productive and focused throughout their new shift pattern. Supplementary Information The online version contains supplementary material available at 10.1186/s12912-023-01371-0.
| S-EPMC10280874 | biostudies-literature
Project description:Objectives12-hour shifts worked by nurses on acute hospital wards have been associated with increased rates of missed care reported by nurses. This study aimed to measure the association between nurses working shifts of at least 12 hours and an objective measure of missed care: vital signs observations taken on time according to an acuity-based surveillance protocol.DesignA retrospective observational study using routinely collected data from March 2012 to March 2015.Setting32 general inpatient wards at a large acute hospital in England.Participants658 628 nursing shifts nested in 24 069 ward days.Outcome measuresThe rate of daily delayed and missed vital signs observations. We focused on situations where vital signs observations were required at least every 4 hours and measured the number of instances where observations were delayed or missed, per 24-hour period. For each ward and each day, shift patterns were characterised in terms of proportion of care hours per patient day deriving from 'long' shifts (≥12 hours) for both registered nurses and healthcare assistants.ResultsOn 99 043 occasions (53%), observations were significantly delayed, and on 81 568 occasions (44%), observations were missed. Observations were more likely to be delayed when a higher proportion of the hours worked by healthcare assistants were part of long shifts (IRR=1.05; 95% CI 1.00 to 1.10). No significant association was found in relation to the proportion of hours registered nurses worked as long shifts.ConclusionOn days when a higher proportion of hours worked by healthcare assistants are from long shifts, the risk of delaying vital signs observations is higher, suggesting lower job performance. While longer shifts are thought to require fewer staff resources to maintain nurse-to-patient ratios, any benefits may be lost if staff become less productive.
| S-EPMC6361343 | biostudies-literature
Project description:BackgroundCOVID-19 underscored the importance of building resilient health systems and hospitals. Nevertheless, evidence on hospital resilience is limited without consensus on the concept, its application, or measurement, with practical guidance needed for action at the facility-level.AimThis study establishes a baseline for understanding hospital resilience, exploring its 1) conceptualization, 2) operationalization, and 3) evaluation in the empirical literature.MethodsFollowing Arksey and O'Malley's model, a scoping review was conducted, and a total of 38 articles were included for final extraction.Findings and discussionIn this review, hospital resilience is conceptualized by its components, capacities, and outcomes. The interdependence of six components (1) space, 2) stuff, 3) staff, 4) systems, 5) strategies, and 6) services) influences hospital resilience. Resilient hospitals must absorb, adapt, transform, and learn, utilizing all these capacities, sometimes simultaneously, through prevention, preparedness, response, and recovery, within a risk-informed and all-hazard approach. These capacities are not static but rather are dynamic and should improve continuously occur over time. Strengthening hospital resilience requires both hard and soft resilience. Hard resilience encompasses the structural (or constructive) and non-structural (infrastructural) aspects, along with agility to rearrange the space while hospital's soft resilience requires resilient staff, finance, logistics, and supply chains (stuff), strategies and systems (leadership and coordination, community engagement, along with communication, information, and learning systems). This ultimately results in hospitals maintaining their function and providing quality and continuous critical, life-saving, and essential services, amidst crises, while leaving no one behind. Strengthening hospital resilience is interlinked with improving health systems and community resilience, and ultimately contributes to advancing universal health coverage, health equity, and global health security. The nuances and divergences in conceptualization impact how hospital resilience is applied and measured. Operationalization and evaluation strategies and frameworks must factor hospitals' evolving capacities and varying risks during both routine and emergency times, especially in resource-restrained and emergency-prone settings.ConclusionStrengthening hospital resilience requires consensus regarding its conceptualization to inform a roadmap for operationalization and evaluation and guide meaningful and effective action at facility and country level. Further qualitative and quantitative research is needed for the operationalization and evaluation of hospital resilience comprehensively and pragmatically, especially in fragile and resource-restrained contexts.
| S-EPMC9614418 | biostudies-literature
Project description:ObjectiveSepsis remains a costly and prevalent syndrome in hospitals; however, machine learning systems can increase timely sepsis detection using electronic health records. This study validates a gradient boosted ensemble machine learning tool for sepsis detection and prediction, and compares its performance to existing methods.Materials and methodsRetrospective data was drawn from databases at the University of California, San Francisco (UCSF) Medical Center and the Beth Israel Deaconess Medical Center (BIDMC). Adult patient encounters without sepsis on admission, and with at least one recording of each of six vital signs (SpO2, heart rate, respiratory rate, temperature, systolic and diastolic blood pressure) were included. We compared the performance of the machine learning algorithm (MLA) to that of commonly used scoring systems. Area under the receiver operating characteristic (AUROC) curve was our primary measure of accuracy. MLA performance was measured at sepsis onset, and at 24 and 48 h prior to sepsis onset.ResultsThe MLA achieved an AUROC of 0.88, 0.84, and 0.83 for sepsis onset and 24 and 48 h prior to onset, respectively. These values were superior to those of SIRS (0.66), MEWS (0.61), SOFA (0.72), and qSOFA (0.60) at time of onset. When trained on UCSF data and tested on BIDMC data, sepsis onset AUROC was 0.89.Discussion and conclusionThe MLA predicts sepsis up to 48 h in advance and identifies sepsis onset more accurately than commonly used tools, maintaining high performance for sepsis detection when trained and tested on separate datasets.
| S-EPMC6556419 | biostudies-literature
Project description:BackgroundThe ability to accurately forecast census counts in hospital departments has considerable implications for hospital resource allocation. In recent years several different methods have been proposed forecasting census counts, however many of these approaches do not use available patient-specific information.MethodsIn this paper we present an ensemble-based methodology for forecasting the census under a framework that simultaneously incorporates both (i) arrival trends over time and (ii) patient-specific baseline and time-varying information. The proposed model for predicting census has three components, namely: current census count, number of daily arrivals and number of daily departures. To model the number of daily arrivals, we use a seasonality adjusted Poisson Autoregressive (PAR) model where the parameter estimates are obtained via conditional maximum likelihood. The number of daily departures is predicted by modeling the probability of departure from the census using logistic regression models that are adjusted for the amount of time spent in the census and incorporate both patient-specific baseline and time varying patient-specific covariate information. We illustrate our approach using neonatal intensive care unit (NICU) data collected at Women & Infants Hospital, Providence RI, which consists of 1001 consecutive NICU admissions between April 1st 2008 and March 31st 2009.ResultsOur results demonstrate statistically significant improved prediction accuracy for 3, 5, and 7 day census forecasts and increased precision of our forecasting model compared to a forecasting approach that ignores patient-specific information.ConclusionsForecasting models that utilize patient-specific baseline and time-varying information make the most of data typically available and have the capacity to substantially improve census forecasts.
| S-EPMC3680345 | biostudies-literature
Project description:Genomic prediction is an effective way for predicting complex traits, and it is becoming more essential in horticultural crop breeding. In this study, we applied genomic prediction in the breeding of cucumber plants. Eighty-one cucumber inbred lines were genotyped and 16,662 markers were identified to represent the genetic background of cucumber. Two populations, namely, diallel cross population and North Carolina II population, having 268 combinations in total were constructed from 81 inbred lines. Twelve cucumber commercial traits of these two populations in autumn 2018, spring 2019, and spring 2020 were collected for model training. General combining ability (GCA) models under five-fold cross-validation and cross-population validation were applied to model validation. Finally, the GCA performance of 81 inbred lines was estimated. Our results showed that the predictive ability for 12 traits ranged from 0.38 to 0.95 under the cross-validation strategy and ranged from -0.38 to 0.88 under the cross-population strategy. Besides, GCA models containing non-additive effects had significantly better performance than the pure additive GCA model for most of the investigated traits. Furthermore, there were a relatively higher proportion of additive-by-additive genetic variance components estimated by the full GCA model, especially for lower heritability traits, but the proportion of dominant genetic variance components was relatively small and stable. Our findings concluded that a genomic prediction protocol based on the GCA model theoretical framework can be applied to cucumber breeding, and it can also provide a reference for the single-cross breeding system of other crops.
| S-EPMC8421847 | biostudies-literature
Project description:BackgroundThe Practical, Robust Implementation and Sustainability Model (PRISM) was developed in 2008 as a contextually expanded version of the broadly used Reach, Adoption, Effectiveness, Implementation, and Maintenance (RE-AIM) framework. PRISM provides researchers a pragmatic and intuitive model to improve translation of research interventions into clinical and community practice. Since 2008, the use of PRISM increased across diverse topics, populations, and settings. This citation analysis and scoping systematic review aimed to assess the use of the PRISM framework and to make recommendations for future research.MethodsA literature search was conducted using three databases (PubMed, Web of Science, Scopus) for the period of 2008 and September 2020. After exclusion, reverse citation searches and invitations to experts in the field were used to identify and obtain recommendations for additional articles not identified in the original search. Studies that integrated PRISM into their study design were selected for full abstraction. Unique research studies were abstracted for information on study characteristics (e.g., setting/population, design), PRISM contextual domains, and RE-AIM outcomes.ResultsA total of 180 articles were identified to include PRISM to some degree. Thirty-two articles representing 23 unique studies integrated PRISM within their study design. Study characteristics varied widely and included studies conducted in diverse contexts, but predominately in high-income countries and in clinical out-patient settings. With regards to use, 19 used PRISM for evaluation, 10 for planning/development, 10 for implementation, four for sustainment, and one for dissemination. There was substantial variation across studies in how and to what degree PRISM contextual domains and RE-AIM outcomes were operationalized and connected. Only two studies directly connected individual PRISM context domains with RE-AIM outcomes, and another four included RE-AIM outcomes without direct connection to PRISM domains.ConclusionsThis is the first systematic review of the use of PRISM in various contexts. While there were low levels of 'integrated' use of PRISM and few reports on linkage to RE-AIM outcomes, most studies included important context domains of implementation and sustainability infrastructure and external environment. Recommendations are provided for more consistent and comprehensive use of and reporting on PRISM to inform both research and practice on contextual factors in implementation.
| S-EPMC9509575 | biostudies-literature
Project description:ObjectiveTo examine the effect of census caps and unit-based admissions on resident workload, conference attendance, duty hour compliance, and patient safety.Participants and methodsWe implemented a census cap of 14 patients on 6 Mayo Clinic internal medicine resident hospital services and a unit-based admissions process in which patients and care teams were consolidated within hospital units. All 280 residents and 15,926 patient admissions to resident and nonresident services 1 year before the intervention (September 1, 2006, through August 31, 2007) and 1 year after the intervention (May 1, 2008, through April 30, 2009) were included. Residents' workload, conference attendance, and duty hours were tracked electronically. Patient safety variables including Rapid Response Team and cardiopulmonary resuscitation events, intensive care unit transfers, Patient Safety Indicators, and 30-day readmissions were compared preintervention and postintervention.ResultsAfter the intervention, residents' mean (SE) ratings of workload appropriateness improved (3.10 [0.08] vs 3.87 [0.08] on a 5-point scale; P<.001), as did conference attendance (1523 [56. 8%] vs 1700 [63.5%] conferences attended; P<.001). Duty hour violations for working more than 30 consecutive hours and not having 10 hours off between duty periods decreased from 77 of 9490 possible violations (0.81%) to 27 (0.28%) and from 70 (0.74%) to 14 (0.15%) violations, respectively (both, P<.001). Thirty-day readmissions to resident services decreased (1010 [18.14%] vs 682 [15. 37%]; P<.001). All other patient safety measures remained unchanged. After adjustment for illness severity, there were no significant differences in patient outcomes between resident and nonresident services.ConclusionCensus caps and unit-based admissions were associated with improvements in resident workload, conference attendance, duty hour compliance, and readmission rates while patient outcomes were maintained.
| S-EPMC3538463 | biostudies-literature