Improving Healthcare Operational Efficiency Through Predictive Analytic Tools


According to research by Oleg S. Pianykh, the potential contribution of machine learning (ML) to healthcare operations and management has largely been unexplored. It is therefore against this backdrop that the operational sphere of healthcare has much to benefit from machine learning.

It is noted that the major hurdle healthcare systems  face is managing patient flow through the hospital from entry to discharge. If not managed effectively, patient flow can have negative ripple effects on the operational efficiency of the hospital and in  to the following negative consequences:

  • Delayed service provision to the patients.
  • Wrong bookings in the emergency department which leads to crowding.
  • Emergency Department (ED) crowding increases left-without-being-seen patients and time taken to attend to the admitted patients.
  • Patients having overnight stays in the post-operative recovery rooms when it is unnecessary.
  • Intensive Care Unit (ICU) re-admissions within 24hrs, which are associated with poor clinical outcomes, increased length of ICU and hospital stay, higher costs, surgery delays or cancellation as well as physicians, nurses, and staff being overloaded, resulting in increased burnout and fatigue.
  • Delays in transferring patients to appropriate units based on their clinical conditions, discharging patients and decreasing patient throughput.

In order to improve efficiency within the hospital, predictive analytic tools can be effective in improving patient flow and alleviate capacity strain burdens.  The goal of predictive analytic tools is not only to create predictive models, but to ultimately improve and in some instances fix, the challenges that arise from poor hospital patient flow by;

  • Reducing the need for regular surge plans.
  • Preventing diversions and overcrowding in emergency department.
  • Eliminating long waiting times  and delays for surgical procedures, treatments, and admissions to inpatient beds.
  • Improving staff schedules to match demand, while reducing excessive overtime.
  • Increasing the number of patients admitted to the appropriate inpatient unit based on a patient’s clinical condition.
  • Utilizing case management strategies to reduce the length of stay for outliers.
  • Improving discharge and bed capacity management planning.

Learning operational patterns from healthcare data can be helpful for predicting critical workflow events and identifying key features that define the process behavior. These operational features are key to building comprehensive predictive analytical tools. They include but not limited to delay in a medical facility, patient arrival time, time of day, complexity of examinations performed and bottlenecks in the operational environment. In order to achieve an effective machine learning, health care system should focus on three key areas to foster successful data science that will lead to improved hospital patient flow:

  1. Build a data science team.

Introducing the value of data science to executive leaders and taking a centralized approach to all data analytics within the health system fosters an environment for data science to succeed.

2. Create a machine learning (ML) pipeline to aggregate all data sources.

To leverage all the data available to a health system, the data science team should create an end-to-end machine learning (a way to codify and automate the workflow) pipeline aggregating the data. The pipeline should include all data sources, storage, transformation and modeling, and visualization components. It is vital that the machine learning pipeline  include every data source because if the data isn’t accurate or doesn’t provide a complete picture, the predictive models won’t identify the right areas for opportunity, resulting in wasted effort.

3. Form a comprehensive leadership team to govern data.

Another important piece for ML success is to include leaders from other departments. This has two benefits:

  • It ensures multiple viewpoints when discussing the data science strategy within the health system.
  • It helps garner support for data science from a variety of departments throughout the organization. For example, a comprehensive leadership team could include leaders from departments like operations, nursing, patient satisfaction, case management, and providers so that the data science team can develop champions for data science across other departments. Creating data science champions who are not members of the data science team makes data science implementation more likely to succeed and helps team members trust it more when they see their leaders whom they already trust and support it.

Way Forward

Hospital patient flow challenges are not a single department problem but a problem the entire health system should strive to overcome. To effectively improve hospital patient flow, it is imperative for operational and clinical leaders to be involved from the start in order to recognize the value of data science.

The data science team has a responsibility to democratize data and ensure its availability to decision makers at every level. However, access to data doesn’t mean that the interpretation of data will be uniform. The data science team should equip leaders with easy-to-understand models at first and work closely with them until they feel comfortable; as they slowly build their analytics acumen.

An agile approach to data science allows leaders to experience the data, not just review it. Agility within machine learning is crucial because with each model iteration, participation from a clinician or an administrative leader increases their understanding; and as a result, the accuracy of the predictive model increases. At this point, leaders throughout the organization are referencing data and then leveraging it to make decisions.

Machine learning models can improve hospital patient flow, but only do so effectively when leadership adds valuable perspectives through suggesting new variables to consider in the predictive models. When machine learning and committed team members come together, machine learning is more accurate because it is sensitive to a health system’s needs, schedules, insurance plans, and most importantly, its patients.

Authors: Eddie Opiyo & Dickson Ndoro