Real-Time Capacity Management and Patient Flow Optimization in Hospitals Using AI Methods

2020 ◽  
pp. 55-69
Author(s):  
Jyoti R. Munavalli ◽  
Henri J. Boersma ◽  
Shyam Vasudeva Rao ◽  
G. G. van Merode
Keyword(s):  
Real Time ◽  
Patient Flow ◽  
Capacity Management ◽  
Flow Optimization ◽  
Patient Flow Optimization

Using Real-Time Demand Capacity Management to Improve Hospitalwide Patient Flow

2011 ◽  
Vol 37 (5) ◽  
pp. 217-AP3 ◽  
Author(s):  
Roger Resar ◽  
Kevin Nolan ◽  
Deborah Kaczynski ◽  
Kirk Jensen
Keyword(s):  
Real Time ◽  
Patient Flow ◽  
Capacity Management

Patient Flow Optimization Using Knowledge Supernetworks and Lean Six Sigma

2016 ◽  
pp. 232-237 ◽  
Author(s):  
Chiara Cirrone ◽  
Eleonora Di Pietro ◽  
Aurelio La Corte ◽  
Alfina A. Torrisi
Keyword(s):  
Six Sigma ◽  
Patient Flow ◽  
Lean Six Sigma ◽  
Flow Optimization ◽  
Patient Flow Optimization

Principles of capacity management, applied in the mental health context

2018 ◽  
Vol 42 (4) ◽  
pp. 438
Author(s):  
Kathryn Zeitz ◽  
Darryl Watson
Keyword(s):  
Mental Health ◽  
Mental Health Problems ◽  
Average Length ◽  
Patient Flow ◽  
Waiting Times ◽  
Capacity Management ◽  
Mental Health Setting ◽  
Mental Health Consumer ◽  
Mental Health Consumers ◽  
Flow Improvement

Objective The aim of the paper was to describe a suite of capacity management principles that have been applied in the mental health setting that resulted in a significant reduction in time spent in two emergency departments (ED) and improved throughput. Methods The project consisted of a multifocal change approach over three phases that included: (1) the implementation of a suite of fundamental capacity management activities led by the service and clinical director; (2) a targeted Winter Demand Plan supported by McKinsey and Co.; and (3) a sustainability of change phase. Descriptive statistics was used to analyse the performance data that was collected through-out the project. Results This capacity management project has resulted in sustained patient flow improvement. There was a reduction in the average length of stay (LOS) in the ED for consumers with mental health presentations to the ED. At the commencement of the project, in July 2014, the average LOS was 20.5 h compared with 8.5 h in December 2015 post the sustainability phase. In July 2014, the percentage of consumers staying longer than 24 h was 26% (n = 112); in November and December 2015, this had reduced to 6% and 7 5% respectively (less than one consumer per day). Conclusion Improving patient flow is multifactorial. Increased attendances in public EDs by people with mental health problems and the lengthening boarding in the ED affect the overall ED throughput. Key strategies to improve mental health consumer flow need to focus on engagement, leadership, embedding fundamentals, managing and target setting. What is known about the topic? Improving patient flow in the acute sector is an emerging topic in the health literature in response to increasing pressures of access block in EDs. What does this paper add? This paper describes the application of a suite of patient flow improvement principles that were applied in the mental health setting that significantly reduced the waiting time for consumers in two EDs. What are the implications for practitioners? No single improvement will reduce access block in the ED for mental health consumers. Reductions in waiting times require a concerted, multifocal approach across all components of the acute mental health journey.

Real-Time Flow Optimization of Hydraulic Manipulator with One Degree of Redundancy Considering Joint Limit Constraint

2021 ◽  
Author(s):  
Linan Li ◽  
Min Cheng ◽  
Ruqi Ding ◽  
Junhui Zhang ◽  
Bing Xu
Keyword(s):  
Real Time ◽  
Projection Method ◽  
Jacobian Matrix ◽  
Gradient Projection ◽  
Redundancy Resolution ◽  
Flow Optimization ◽  
Hydraulic Manipulators ◽  
Time Flow ◽  
Hydraulic Manipulator ◽  
Joint Limit

Abstract Due to the complexity in unstructured environments (e.g., rescue response and forestry logging), more hydraulic manipulators are equipped with one redundant joint to improve their motion flexibility. In addition to considering joint limit constraint and maneuverability optimization like electrically driven manipulators, hydraulic manipulators can optimize flow consumption consider flow optimization aiming at energy saving and flow anti-saturation for redundancy resolution, since multiple joints are supplied by one pump. Therefore, this paper proposes a redundancy resolution method combining the gradient projection method with a weighted Jacobian matrix (GPM-WJM) for real-time flow optimization of the hydraulic manipulator with one degree of redundancy considering joint limit constraint. Its solution consists of two parts: a special solution (the weighted least-norm solution) and a general solution (the projection of the optimization index in the null space of the weighted task Jacobian matrix). Simulations are carried out to verify its effectiveness. The simulation result shows that GPM-WJM can meet the constraints of joint limit without affecting the tool center point (TCP) trajectory and utilize the remaining redundancy to optimize the flow consumption and manipulability in real-time, which can reduce average system flow by 10.45%. Compared with the gradient projection method (GPM) for flow optimization, GPM-WJM can reduce the maximum acceleration when avoiding the joint limits by 80% at the cost of slightly weakening the flow optimization effect, which is beneficial to improve the accuracy of the manipulator in practice.

scholarly journals Real-time prediction of inpatient length of stay for discharge prioritization

2015 ◽  
Vol 23 (e1) ◽  
pp. e2-e10 ◽  
Author(s):  
Sean Barnes ◽  
Eric Hamrock ◽  
Matthew Toerper ◽  
Sauleh Siddiqui ◽  
Scott Levin
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Health Information ◽  
Patient Flow ◽  
Supervised Machine Learning ◽  
Youden Index ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
High Resource ◽  
Sensitivity Specificity

Abstract Objective Hospitals are challenged to provide timely patient care while maintaining high resource utilization. This has prompted hospital initiatives to increase patient flow and minimize nonvalue added care time. Real-time demand capacity management (RTDC) is one such initiative whereby clinicians convene each morning to predict patients able to leave the same day and prioritize their remaining tasks for early discharge. Our objective is to automate and improve these discharge predictions by applying supervised machine learning methods to readily available health information. Materials and Methods The authors use supervised machine learning methods to predict patients’ likelihood of discharge by 2 p.m. and by midnight each day for an inpatient medical unit. Using data collected over 8000 patient stays and 20 000 patient days, the predictive performance of the model is compared to clinicians using sensitivity, specificity, Youden’s Index (i.e., sensitivity + specificity – 1), and aggregate accuracy measures. Results The model compared to clinician predictions demonstrated significantly higher sensitivity ( P  < .01), lower specificity ( P  < .01), and a comparable Youden Index ( P  > .10). Early discharges were less predictable than midnight discharges. The model was more accurate than clinicians in predicting the total number of daily discharges and capable of ranking patients closest to future discharge. Conclusions There is potential to use readily available health information to predict daily patient discharges with accuracies comparable to clinician predictions. This approach may be used to automate and support daily RTDC predictions aimed at improving patient flow.

Using a real-time location system to measure patient flow in a radiation oncology outpatient clinic

2018 ◽  
Vol 8 (5) ◽  
pp. 317-323 ◽  
Author(s):  
Kevin Conley ◽  
Chester Chambers ◽  
Shereef Elnahal ◽  
Amanda Choflet ◽  
Kayode Williams ◽  
...  
Keyword(s):  
Real Time ◽  
Outpatient Clinic ◽  
Radiation Oncology ◽  
Patient Flow ◽  
Location System ◽  
Real Time Location System
Sign in / Sign up

Export Citation Format

Share Document