Process mining in healthcare: to allow focus on treatment and recovery

Healthcare benefits from highlighting vulnerabilities and cost generators in hospital management systems. The re-engineering of optimisable processes was shown to achieve e.g. 6%–10% increase in speed of throughput, 20% increase in bed utilization, 5% increase in operating room output, 5%–8% annual savings in operating budget.

Because hospital staff should exclusively focus on treatment options. And patients should exclusively focus on recovery.

Discover pathways in the healthcare system

Chart the stories (pathways) associated with the entities in your system, as they flow in reality:patient treatment journeys (transfers, referrals) through the hospital, allocation flow of medical personnel to various wards

To know your patient. Understand quickly where the patient’s story fits in the bigger picture.
To transfer knowledge easily. Help new employees get a thorough understanding of the stories they need to know about to get them up to speed, by showing them a snapshot of the the true modus operandi in the hospital / department / ward.
To support resource planning and uncover staff issues.

Measure

Quantify the stories (end-to-end average time delays, frequencies, fitness)

To assess the impact of organizational changes on your business. Minimize the fear of innovation, by bringing on the table an understanding of its effects on the inner workings of your organisation.

Pinpoint oddities: inefficiencies and noncompliance

Inefficiencies with respect to:
- resources: queues at a specific ward / lab test / surgery type, long chains of referrals (bottlenecks)
- cost: repetitive tasks that can be eliminated / automated (ping-pong referrals between wards due to unclear diagnosis)
- time: long waiting times for the patient; time demanding activities for personnel

Mismatches (noncompliance to business rules, weird succession of lab tests / ward referrals, etc), for single process steps, or for entire journeys. Are patients being attended to in line with established protocols?
- activities that were expected to happen, but didn’t
- activities (process steps) that occurred, but were not expected to happen
- successions of process steps that might be considered fraudulent activity

Optimize your healthcare system

Have your expert investigate possible causes of oddities found, and identify opportunities to minimize waste, reduce costs and increase customer satisfaction. Check where processes could be automated to bring improvements. Bring digital transformation to maximize asset utilisation and transparency into your systems.

Workload. Are resources incapacitated because of too much workload? Where exactly (department-wise / doctor-wise / activity-wise) are the bottlenecks (queues, high waiting times) in the process? What could be generating these bottlenecks?
Workload distribution. Is there a huge variation in the number of diagnostic tests / therapeutic treatments that are requested? Is there a huge variation in the number of patients treated for specific diagnostic groups in similar departments of different hospitals?
Habits. What are the most commonly followed / exceptional paths followed?
Compare. Look into the modus operandi across departments:
- Are there any differences between care paths followed by different patient groups?
- Is end-to-end waiting / prep / surgery time longer in one hospital versus another? If yes, is there a valid reason for this?
- What do cases in which patients have to endure long waiting times have in common?
- Any difference with regard to the location at which an intervention took place?
Resource availability. Are there enough resources? Will adding more doctors / nurses / medical equipment solve the problem?
Process complexity. Is it possible to simplify processes to some extent?
Demand. Is there a danger to crash the system because of an upsurge in need of medical care for specific pathologies? If yes, where are the weak points of the system? Where will failure occur first?
Islands of expertise / know-how (Bus Factor). Are there activities with a small user set?

Process mining brings quality to the doctor-patient relationship

Small optimization steps taken towards removing redundancies and unnecessary processes in the system could lead, in the long term, to positive changes from the patient’s viewpoint. For instance, provision of a holistic rather than myopic view of a patient’s condition would allow early detection of cases when multiple referrals are issued from differently specialized departments – the case of complicated diseases that are rare and generally hard to spot because they affect multiple systems in the body and generally have confusing symptom picture.

The possibility to maximize consultation time would be a way to move from I-It to an I-You doctor-patient relationship. Impaired communication largely predicts malpraxis accusations. Improvements in the quality of medical teams / doctor-patient relationships would lead to an increase of the overall quality of life for the medical personnel (less stress & frustration) while reducing legal costs.

ThiaperProcess on a sample healthcare dataset

For confidentiality reasons we are not showing ThiaperProcess results obtained for customer data, but for an open medical dataset. We use the real life event log of the conformance checking challenge 2019 (CCC19) to showcase how ThiaperProcess can discover medical procedure pathways and quantify performance metrics on top.

The log focuses on a medical training process: medical students learn how to install Central Venous Catheter (CVC) with ultrasound. The CVC procedure refers to installing a catheter (tube) in a central vein, aiding on delivering fluid or medications to the patient, among other uses.

The process map discovered is a birdview of all sequences of steps typically followed by the medical students while learning.

A close- up of the pathways found shows the average length of the pathway (in terms of average number of activities performed), end-to-end time delay and the frequency. The values of these indicators can further be used for clustering of the pathways found.