Sankalp Khanna

Unravelling relationships: Hospital occupancy levels, discharge timing and emergency department access block

To investigate the effect of hospital occupancy levels on inpatient and ED patient flow parameters, and to simulate the impact of shifting discharge timing on occupancy levels.

The National Emergency Access Target (NEAT) and the 4-hour rule: time to review the target.

Objective: We explored the relationship between the National Emergency Access Target (NEAT) compliance rate, defined as the proportion of patients admitted or discharged from emergency departments (EDs) within 4 hours of presentation, and the risk‐adjusted in‐hospital mortality of patients admitted to hospital acutely from EDs.

New emergency department quality measure: from access block to National Emergency Access Target compliance.

The study aims to investigate the effect of time of day and ED occupancy on the ability of EDs to admit or discharge patients within 4 h in accordance with the National Emergency Access Target (NEAT), and to compare this with corresponding levels of access block, the measure for ED performance before NEAT.

Discharge timeliness and its impact on hospital crowding and emergency department flow performance.

The objective of this research is to identify optimal inpatient discharge time targets to help hospitals reduce crowding, improve patient flow through the ED and balance staff workload.

Probability of Severe Adverse Events as a Function of Hospital Occupancy

A unique application of regression modeling is described to compare hospital bed occupancy with reported severe adverse events amongst inpatients. The probabilities of the occurrence of adverse events as a function of hospital occupancy are calculated using logistic and multinomial regression models. All models indicate that higher occupancy rates lead to an increase in adverse events. The analysis identified that at an occupancy level of 100%, there is a 22% chance of one severe event occurring and a 28% chance of at least one severe event occurring. This modeling contributes evidence toward the management of hospital occupancy to benefit patient outcomes.

Using prediction to improve elective surgery scheduling

BACKGROUND An ageing population and higher rates of chronic disease increase the demand on health services. The Australian Institute of Health and Welfare reports a 3.6% per year increase in total elective surgery admissions over the past four years.1 The newly introduced National Elective Surgery Target (NEST) stresses the need for efficiency and necessitates the development of improved planning and scheduling systems in hospitals. AIMS To provide an overview of the challenges of elective surgery scheduling and develop a prediction based methodology to drive optimal management of scheduling processes. METHOD Our proposed two stage methodology initially employs historic utilisation data and current waiting list information to manage case mix distribution. A novel algorithm uses current and past perioperative information to accurately predict surgery duration. A NEST-compliance guided optimisation algorithm is then used to drive allocation of patients to the theatre schedule. RESULTS It is expected that the resulting improvement in scheduling processes will lead to more efficient use of surgical suites, higher productivity, and lower labour costs, and ultimately improve patient outcomes. CONCLUSION Accurate prediction of workload and surgery duration, retrospective and current waitlist as well as perioperative information, and NEST-compliance driven allocation of patients are employed by our proposed methodology in order to deliver further improvement to hospital operating facilities.

Automatic detection of tweets reporting cases of influenza like illnesses in Australia

Early detection of disease outbreaks is critical for disease spread control and management. In this work we investigate the suitability of statistical machine learning approaches to automatically detect Twitter messages (tweets) that are likely to report cases of possible influenza like illnesses (ILI). Empirical results obtained on a large set of tweets originating from the state of Victoria, Australia, in a 3.5 month period show evidence that machine learning classifiers are effective in identifying tweets that mention possible cases of ILI (up to 0.736 F-measure, i.e. the harmonic mean of precision and recall), regardless of the specific technique implemented by the classifier investigated in the study.

Hospital level analysis to improve patient flow.

The complexity of hospital operations ensures that one-size-fits-all solutions seldom work. As hospitals turn to evidence based strategies to redesign flow, it is critical that they tailor the strategies to suit their individual service. This paper analyses the effect of hospital occupancy on inpatient and emergency department patient flow parameters at the Caboolture hospital in Queensland, Australia, and identifies critical levels, or choke points, that result in performance decline. The effect of weekdays and weekends on patient flow is also investigated. We compare these findings to a previous study that has analysed patient flow across Queensland hospitals grouped by size, and discover several differences in the interaction between rising occupancy and patient flow parameters including rates of patient flow, length of stay, and access block. We also identify significantly higher choke points for Caboolture hospital as compared to other similarly sized Queensland hospitals, which suggest that patient flow here can be redesigned to operate at higher levels of occupancy without degrading flow performance. The findings support arguments for hospitals to analyse patient flow at a service level to deliver optimum service improvement.

Visualising patient flow

We describe the development of a method to distil routinely collected clinical data into patient flow information to aid hospital bed management. Using data from state-wide emergency department and inpatient clinical information systems, a user-friendly interface was developed to visualise patient flow conditions for a particular hospital. The historical snapshots employ a variable time scale, allowing flow to be visualised across a day, week, month or year. Flow information includes occupancy, arrival and departure rates, length-of-stay and access block observations, which can be filtered by age, departure status, diagnosis, elective status, triage category, and admission unit. The tool may be helpful in supporting hospital bed managers in their daily decision making.

Multiagent based scheduling of elective surgery

Scheduling of patients, staff, and resources for elective surgery in an under-resourced and overburdened public health system represents an inherently distributed class of problems. The complexity and dynamics of interacting factors demand a flexible, reactive and timely solution, in order to achieve a high level of utilization. In this paper, we present an Automated Scheduler for Elective Surgery (ASES) wherein we model the problem using the multiagent systems paradigm. ASES is designed to reflect and complement the existing manual methods of elective surgery scheduling, while offering efficient mechanisms for negotiation and optimization. Inter-agent negotiation in ASES is powered by a distributed constraint optimization algorithm. This strategy provides hospital departments with control over their individual schedules while ensuring conflict free optimal scheduling. We evaluate ASES to demonstrate the feasibility of our approach and demonstrate the effect of fluctuation in staffing levels on theatre utilization. We also discuss ongoing development of the system, mapping key challenges in the journey towards deployment.