Unit-based Model Research Articles

Space-time data-driven modeling of precipitation-induced shallow landslides in South Tyrol, Italy

Shallow landslides represent potentially damaging processes in mountain areas worldwide. These geomorphic processes are usually caused by an interplay of predisposing, preparatory, and triggering environmental factors. At regional scales, data-driven methods have been used to model shallow landslides by addressing the spatial and temporal components separately. So far, few studies have explored the integration of space and time for landslide prediction. This research leverages generalized additive mixed models to develop an integrated approach to model shallow landslides in space and time. We built upon data on precipitation-induced landslide records from 2000 to 2020 in South Tyrol, Italy (7400 km2). The slope unit-based model predicts landslide occurrence as a function of static and dynamic factors while seasonal effects are incorporated. The model also accounts for spatial and temporal biases inherent in the underlying landslide data. We validated the resulting predictions through a suite of cross-validation techniques, obtaining consistent performance scores above 0.85. The analyses revealed that the best-performing model combines static ground conditions and two precipitation time windows: a short-term cumulative precipitation of 2 days before the landslide event and a medium-term cumulative precipitation of 14 days. We demonstrated the model's predictive capabilities by predicting the dynamic landslide probabilities over historical data associated with a heavy precipitation event on August 4th and August 5th, 2016, and hypothetical non-spatially explicit precipitation (what-if) scenarios. The novel approach shows the potential to integrate static and dynamic landslide factors for large areas, accounting for the underlying data structure and data limitations.

SoccerNet: A Gated Recurrent Unit-based model to predict soccer match winners.

Winning football matches is the major goal of all football clubs in the world. Football being the most popular game in the world, many studies have been conducted to analyze and predict match winners based on players' physical and technical performance. In this study, we analyzed the matches from the professional football league of Qatar Stars League (QSL) covering the matches held in the last ten seasons. We incorporated the highest number of professional matches from the last ten seasons covering from 2011 up to 2022 and proposed SoccerNet, a Gated Recurrent Unit (GRU)-based deep learning-based model to predict match winners with over 80% accuracy. We considered match- and player-related information captured by STATS platform in a time slot of 15 minutes. Then we analyzed players' performance at different positions on the field at different stages of the match. Our results indicated that in QSL, the defenders' role in matches is more dominant than midfielders and forwarders. Moreover, our analysis suggests that the last 15-30 minutes of match segments of the matches from QSL have a more significant impact on the match result than other match segments. To the best of our knowledge, the proposed model is the first DL-based model in predicting match winners from any professional football leagues in the Middle East and North Africa (MENA) region. We believe the results will support the coaching staff and team management for QSL in designing game strategies and improve the overall quality of performance of the players.

Team-based infection preventionist review improves interrater reliability in identification of hospital-acquired infections

Background: The University of Colorado Health (UCHealth) metropolitan region is composed of 4 hospitals. Therein, 10 infection preventionists (IPs) retrospectively review all cases of potential central-line–associated bloodstream infection (CLABSI), catheter-associated urinary tract infection (CAUTI), and surgical site infection (SSI) to adjudicate whether each case meets the NHSN definitions for hospital-acquired infection (HAI). In August 2021, the UCHealth IP team structure transitioned from a subject-matter expert model (in which each IP reviewed a specific HAI) to a unit-based model (in which each IP reviewed all HAIs and SSIs on their assigned units) to create redundancy in knowledge and skill. The IP team subsequently instituted a weekly meeting to review all potential cases of HAI. We hypothesized that this review structure would result in increased consistency in the application of NHSN definitions across the UCHealth hospitals and units. Methods: From August 17, 2022, through March 3, 2023, the UCHealth IPs, managers, and medical directors met weekly for 1 hour via teleconferencing. Each IP presented key details for all near-miss and confirmed cases of SSI or HAI on their respective units and received questions and feedback from their peers and medical directors. Case determination was based on team discussion and consensus. If there was discordance in the interpretation of an NHSN case definition, a formal inquiry was sent to resolve the uncertainty. The number of cases reviewed, case determinations changed, and formal inquiries to NHSN were tracked. Results: During the study period, the IP team convened weekly meetings and reviewed 248 patient cases—of which 208 (83.9%) were confirmed HAIs. Based on collaborative team discussion, 14 cases (5.6%) were changed from reportable to nonreportable. Three cases (1.2%) originally thought to be nonreportable were changed to reportable. The HAI determination of a reportable case (eg, revision of a “superficial” SSI to “deep” SSI) was changed for 9 (6.0%). Following team discussion, 13 formal inquiries were sent to the NHSN to clarify case definitions, and these responses were collated for future reference. Conclusions: Team-based IP review of HAI cases improves consistency in application of NHSN case definitions and highlights areas of uncertainty in their interpretation. This team-based model of case review is a useful educational and practical tool to increase interrater reliability in case adjudication across large teams of IPs, to create a systematic way to query NHSN, and to ensure that knowledge gained is disseminated for future benefit.Disclosures: None

Hospital Case Management: A Review: 2019-2022.

In June 2019, a Case Management Society of America (CMSA) task force published "The Practice of Hospital Case Management: A White Paper." This was an important first step to outline the value of hospital case managers (HCMs) and to put forward recommendations for how to operationalize a major change in most hospitals for how case managers can practice.The SARS-CoV2 (COVID-19) pandemic drastically changed the practice of all interdisciplinary work within hospitals. The White Paper recommended that HCMs follow a select patient population through the hospital. Hospital case manager leaders realized that HCMs can work remotely and communicate with patients because meeting them in person was not an option. Hospital case managers are still resistant to leaving the hospital unit-based model, even after they experienced the value of this concept during the height of the pandemic. Acute care hospitals. The White Paper recommended separating HCMs from utilization management. One unintended consequence is the loss of necessary knowledge and competencies. These are related to compliance with the Centers for Medicare & Medicaid Services Conditions of Participation and regulatory mandates that can affect patient care and financial well-being. Hospital case manager leaders must stay current with these government requirements for hospitals and for all levels of care and keep the case managers informed, proficient, and fluent when coordinating the care of patients. Hospital case manager practice is evolving; change is the single constant in health care. This review of the CMSA Hospital Case Management Whitepaper demonstrates that in just three short years, the landscape of health care can change dramatically.Today's HCM leader must proactively address a multigenerational workforce, lack of title protection, and the COVID-19-induced "Great Resignation." The value of the HCM has never been more apparent as during the pandemic as the need to "empty beds" is critical, and the HCM is the professional who has the skill to provide efficient and patient-centered care coordination. The HCM leader practices positive leadership techniques that benefit the leader, the HCM, and most importantly the patient.

Investigation of Automatic Speech Recognition Systems via the Multilingual Deep Neural Network Modeling Methods for a Very Low-Resource Language, Chaha

Automatic speech recognition (ASR) is vital for very low-resource languages for mitigating the extinction trouble. Chaha is one of the low-resource languages, which suffers from the problem of resource insufficiency and some of its phonological, morphological, and orthographic features challenge the development and initiatives in the area of ASR. By considering these challenges, this study is the first endeavor, which analyzed the characteristics of the language, prepared speech corpus, and developed different ASR systems. A small 3-hour read speech corpus was prepared and transcribed. Different basic and rounded phone unit-based speech recognizers were explored using multilingual deep neural network (DNN) modeling methods. The experimental results demonstrated that all the basic phone and rounded phone unit-based multilingual models outperformed the corresponding unilingual models with the relative performance improvements of 5.47% to 19.87% and 5.74% to 16.77%, respectively. The rounded phone unit-based multilingual models outperformed the equivalent basic phone unit-based models with relative performance improvements of 0.95% to 4.98%. Overall, we discovered that multilingual DNN modeling methods are profoundly effective to develop Chaha speech recognizers. Both the basic and rounded phone acoustic units are convenient to build Chaha ASR system. However, the rounded phone unit-based models are superior in performance and faster in recognition speed over the corresponding basic phone unit-based models. Hence, the rounded phone units are the most suitable acoustic units to develop Chaha ASR systems.

Learning and predicting operation strategies by sequence mining and deep learning

The operators of chemical technologies are frequently faced with the problem of determining optimal interventions. Our aim is to develop data-driven models by exploring the consequential relationships in the alarm and event-log database of industrial systems. Our motivation is twofold: (1) to facilitate the work of the operators by predicting future events and (2) analyse how consequent the event series is. The core idea is that machine learning algorithms can learn sequences of events by exploring connected events in databases. First, frequent sequence mining applications are utilised to determine how the event sequences evolve during the operation. Second, a sequence-to-sequence deep learning model is proposed for their prediction. The long short-term memory unit-based model (LSTM) is capable of evaluating rare operation situations and their consequential events. The performance of this methodology is presented with regard to the analysis of the alarm and event-log database of an industrial delayed coker unit.

A polyhedra-based model for moving regions in databases

ABSTRACT Moving objects databases store and process objects with a focus on their spatiotemporal behaviour. To achieve this, the model of the data must be suitable to efficiently store and process moving objects. Currently, a unit-based model is widely used, where each moving object is divided into one or more time intervals, during which the object behaves uniformly. This model is also used for a data type called moving regions, which resembles moving and shape changing regions as, for example, forest fires or cloud fields. However, this model struggles to support operations like union, difference or intersection of two moving regions; the resulting objects are unnecessarily bloated and uncomfortable to handle because the resulting number of units is generally very high. In this paper, an alternative model for moving regions is proposed, which is based on polyhedra. Furthermore, this work develops an isomorphism between moving regions and polyhedra including all relevant operations, which has the additional advantage that several implementations for those are already readily available; this is demonstrated by a reference implementation using the existing and well-tested Computational Geometry Algorithms Library (CGAL).

Geographical assignment of hospitalists in an urban teaching hospital: feasibility and impact on efficiency and provider satisfaction

ABSTRACTObjective: To evaluate whether implementation of a geographic model of assigning hospitalists is feasible and sustainable in a large hospitalist program and assess its impact on provider satisfaction, perceived efficiency and patient outcomes.Methods: Pre (3 months) – post (12 months) intervention study conducted from June 2014 through September 2015 at a tertiary care medical center with a large hospitalist program caring for patients scattered in 4 buildings and 16 floors. Hospitalists were assigned to a particular nursing unit (geographic assignment) with a goal of having over 80% of their assigned patients located on their assigned unit. Satisfaction and perceived efficiency were assessed through a survey administered before and after the intervention.Results: Geographic assignment percentage increased from an average of 60% in the pre-intervention period to 93% post-intervention. The number of hospitalists covering a 32 bed unit decreased from 8–10 pre to 2–3 post-intervention. A majority of physicians (87%) thought that geography had a positive impact on the overall quality of care. Respondents reported that they felt that geography increased time spent with patient/caregivers to discuss plan of care (p < 0.001); improved communication with nurses (p = 0.0009); and increased sense of teamwork with nurses/case managers (p < 0.001). Mean length of stay (4.54 vs 4.62 days), 30-day readmission rates (16.0% vs 16.6%) and patient satisfaction (79.9 vs 77.3) did not change significantly between the pre- and post-implementation period. The discharge before noon rate improved slightly (47.5% – 54.1%).Conclusions: Implementation of a unit-based model in a large hospitalist program is feasible and sustainable with appropriate planning and support. The geographical model of care increased provider satisfaction and perceived efficiency; it also facilitated the implementation of other key interventions such as interdisciplinary rounds.

A motor unit-based model of muscle fatigue.

Muscle fatigue is a temporary decline in the force and power capacity of skeletal muscle resulting from muscle activity. Because control of muscle is realized at the level of the motor unit (MU), it seems important to consider the physiological properties of motor units when attempting to understand and predict muscle fatigue. Therefore, we developed a phenomenological model of motor unit fatigue as a tractable means to predict muscle fatigue for a variety of tasks and to illustrate the individual contractile responses of MUs whose collective action determines the trajectory of changes in muscle force capacity during prolonged activity. An existing MU population model was used to simulate MU firing rates and isometric muscle forces and, to that model, we added fatigue-related changes in MU force, contraction time, and firing rate associated with sustained voluntary contractions. The model accurately estimated endurance times for sustained isometric contractions across a wide range of target levels. In addition, simulations were run for situations that have little experimental precedent to demonstrate the potential utility of the model to predict motor unit fatigue for more complicated, real-world applications. Moreover, the model provided insight into the complex orchestration of MU force contributions during fatigue, that would be unattainable with current experimental approaches.

Outcomes of Clinical Nurse Specialist Role Transformation to Population-Focused Model

In 2010, our comprehensive cancer center developed a professional practice model where the clinical nurse specialist role was transformed to proactively plan and facilitate evidence-based best practices in collaboration with a transdisciplinary, population-focused team that manages the patient across the cancer care continuum. Prior to this transition, practice was unit based, focused on nursing staff education, skills, and competencies, and practice varied widely based on the needs of the unit. This lack of role consistency resulted in decreased autonomy and collaboration and frustration with not consistently impacting positive outcomes. Nursing leadership worked with the clinical nurse specialists to develop and transition to a population-focused model. Some responsibilities in the unit-based model were retained, whereas others were transitioned to different roles. The reporting structure was centralized, and the role was realigned to focus on a specific patient population encompassing care from diagnosis throughout survivorship. Baseline job satisfaction data were collected prior to the transition and repeated at 6 and 12 months, then 2, 3, and 4 years after implementation. Over time, there was significant improvement in participation in decision making, support of leadership, and positive contributions to patients and staff, resulting in improved nursing-sensitive patient outcomes, an increase in evidence-based practice initiatives and nursing research projects, and substantial professional growth of clinical staff. With this practice model, clinical nurse specialists consistently and proactively plan and facilitate evidence-based best practice in collaboration with a transdisciplinary team that manages the patient from diagnosis through the cancer trajectory. Results of outcome measurement report job satisfaction at an all-time high. Significant impact is demonstrated for patients and families, the nursing staff, and the organization. Healthcare organizations should evaluate current roles and practice models for opportunities to incorporate innovations that will result in improved patient care and satisfaction.

Educational program for pharmacists at a multifacility academic medical center

An educational program for pharmacists in a multifacility health care setting is described. The expansion of pharmacy services at a university medical center from a centralized to a decentralized, unit-based model created the need for enhanced education of staff pharmacists. A steering committee with pharmacy department and school of pharmacy representation surveyed educational and professional needs related to the expanded services. Pharmacists indicated that they needed an educational program that was comprehensive, interactive, and accessible to all shifts. Pharmacy school clinical faculty members provided most of the initial educational sessions, which combined didactic presentations and case-based discussion. The needs survey was used in selecting topics that were most relevant to the pharmacists' expanded practice. Each major topic was covered in a series of one-hour sessions held at two-week intervals and scheduled at a time convenient for afternoon-shift pharmacists. Incentives were offered to encourage participation. The live presentations were recorded with video-streaming technology and made available via the Internet to pharmacists on all shifts in all facilities of the health system as well as to faculty members. Since program implementation in 2005, attendance at the live sessions has averaged 25. In postimplementation surveys, pharmacists indicated that the program was meeting their needs and improving patient care. Since 2008, pharmacists have been able to earn continuing-education (CE) credit for the sessions. A collaborative educational series with online access, clinical content, and CE credit has been effective in meeting pharmacists' needs in a multifacility health care setting.

Benefits of Psychosocial Rehabilitation Programming in a Treatment Mall

Psychiatric patients need educational interventions that help them recover and increase their ability to live and work independently following discharge from the hospital. The psychosocial rehabilitation treatment mall model is designed to meet this educational need. Treatment malls are a new approach to psychosocial rehabilitaion for patients in state psychiatric hospitals. Treatment malls provide psychoeducation and skill-building activities in a centralized, school-like setting for participants from all patient care units. It differs from traditional strategies that use decentralized one-on-one or unit-based models. Treatment malls provide a self-directed learning experience that meets the person-centered needs of participants. Evidence is increasing that this psychosocial educational model can provide lasting benefits for psychiatric patients, including symptom management, reduced psychiatric hospital readmission rates, and improved quality of life.

A pulp mill benchmark problem for control: application of plantwide control design

Abstract A heuristic for design of plantwide control strategies is introduced and applied to the millwide control of a previously presented pulp mill benchmark. Two control strategies (decentralized control and unit-based model predictive control) are compared according to their capacity to reduce the total error and maximize the operating profits. The control strategies are studied through closed-loop simulations of the process including several disturbances and setpoint changes in the digester, oxygen reactor, bleach plant, recausticizing plant and lime kiln.

Transformation of a Pharmacy Department: Impact on Pharmacist Interventions, Error Prevention, and Cost

Current medical literature supports the unit-based (UB) pharmacy concept as a best practice. In an effort to determine its feasibility, Huntsville Hospital (Huntsville, Alabama) conducted a pilot study to compare the central-based (CB) model with the UB model and then implemented the new model. Data were collected for two high-volume nursing units for 10 days for each model. Pharmacists practicing in the UB setting documented more interventions than the CB pharmacist by a factor of three to one, resulting in an 85% increase in cost avoidance. Converting the pharmacy services to a UB model entailed creating 16 new pharmacist positions. Extrapolation of the savings for the UB model ($520 per day) and the CB model ($280) for 1 year suggested that adoption of the UB model would generate an additional $87,600 in cost avoidance for these two nursing units. Each new pharmacist was trained for at least 3 months before being scheduled to work independently as a UB pharmacist. Clinical interventions by pharmacists greatly increased after implementation of the UB model. The baseline monthly average of interventions for the 6 months before implementation was 239, and the monthly cost avoidance was $21,300. In October 2001, the first full month of implementation, there were 1,315 interventions and a monthly cost avoidance of $130,192. Converting to the UB model has required a considerable increase in the number of pharmacist positions, yet there has been a dramatic increase in clinical pharmacy interventions, with a corresponding decrease in drug expenditures.

The Practice Environment Project

Evaluating the practice environment is essential to determine if the practice environment is conducive to the delivery of quality patient care. The Practice Environment Project (PEP) was created to provide a framework for current and ongoing evaluation of the practice environment. Major changes in the delivery of patient care services have focused attention on the evaluation of the effectiveness of these changes. The extent and type of change may vary throughout an institution. The identification of core variables to assess the effectiveness of these changes sets the framework for ongoing evaluation of new unit-based models for delivery of services. In part 1, quantitative data were collected from nursing staff members (job satisfaction, collaboration with physicians, autonomy), physicians (quality of nursing care, collaboration with nurses), and patients (satisfaction with nursing care). In part 2, focus groups were held with nursing personnel to discuss factors that affected the provision of services. Unit-based action plans were developed to manage barriers to the delivery of services. Patients and physicians reported a high degree of satisfaction with patient care. Physicians reported a higher level of collaboration with nurses than that reported by nurses. Nurses reported a high degree of autonomy in practice, however, in other areas of job satisfaction (development and recognition), they suggested areas for improvement. The PEP created a mechanism to evaluate the current state-of-the-practice environment by identifying core elements for evaluation of work redesign. It also provided a framework for managing barriers that disrupted the delivery of patient care services.