Leveraging digital sample tracking and robotics to improve laboratory processes

With 70% of clinical decisions affected by diagnostic laboratory test results, medical labs are critical in impacting patient outcomes.¹ Within the U.S., over 14 billion lab samples are ordered every year.² Unfortunately, studies show that in North American and European hospitals, a single pre-pre-analytical error costs an average of $208, and a total of approximately 0.7% in operating costs.^3,4 The healthcare industry has been strongly pushing to incorporate systems that help prevent these errors, ensuring that patient samples are processed accurately, efficiently, and in a timely fashion.²

At the same time, labs are already struggling with an acute shortage of skilled labor. According to the Professional Association of German Laboratory Doctors (BDL), 32% of specialists in labs will retire in the next five years, with German laboratories facing a severe labor shortage due to a lack of individuals available who can fill those roles.⁵ A study by LABO magazine showed that 87% of German laboratories do not have the required employees to handle the daily testing of of the 4,500 laboratory samples that need to be analyzed per shift.⁶

Implementing processes and platforms in the laboratory that digitize manual procedures and leveraging robotics, artificial intelligence (AI), and automation could help lab leaders deliver the highest-quality results to clinicians while addressing staff shortages and operating costs due to errors. This approach would enable rapid and informed diagnostic and treatment decisions that can significantly impact patient outcomes.

The journey from sample collection to sample analysis involves many manual tasks of several operators, using siloed and disconnected systems. This means that there are multiple possibilities for errors. Surprisingly, almost 70% of errors occur in the pre-analytical phase before the samples reach the lab for testing.⁷ This is when mistakes can happen in test requests, patient identification, collection, transportation, and preparation,⁸ which can ultimately lead to re-work, such as re-sampling from the patient. Taking additional specimens from patients means significant costs to healthcare organizations, patient distrust, and treatment or diagnostic delays.⁴

Traditional labs have relied heavily on manual troubleshooting in the pre-analytical phase, with lab managers and technicians involved in figuring out where the problem occurred. However, with a shortage of medical laboratory scientists and technicians coupled with the growing demand for lab testing,⁹ healthcare systems are increasingly looking towards digital platforms as a first line of defense against these errors. These tools help decrease the burden on personnel while reducing the number of errors and thus, increasing the reliability of results.

Cloud-based digital solutions that allow labs to monitor the quality of samples and identify errors before they reach the lab are important for improving lab operations and reducing costs and time to results. Typically, digital solutions for pre-analytic sample tracking are fragmented, covering only a single part of the process and require individual connections to the LIS, which is cumbersome.

In a latest innovation, lab managers could have access to an ecosystem of various digital solutions from different companies that are connected to the lab via a single platform. The lab can thus pick and choose the solutions that suit their needs along the end-to-end pre-analytical process, from sample collection and transportation, to sample reception.

These types of solutions would be most beneficial to labs with many remote sample collection sites, with long distances where samples are transported. In addition, the solution could be used between labs and labs with high emphasis on testing quality, e.g. specialty labs. To that end, it’s critical for labs to meet accreditation standard ISO 15189, which includes tracking the quality of samples during transportation.

In addition to digital sample tracking, the laboratory can further reduce errors in the preanalytical phase through AI-based robotics capable of automated sample handling. Manual sorting of samples is a time-consuming, tedious, and repetitive process that can lead to significant errors and is limited in scale. 

Sample reception is a crucial step in the pre-analytical process. It is the interface to automated lab workflows with diagnostics instruments, so it is crucial for sorting out inadequate samples and flag errors to lab managers. Due to high complexity in sample boxes and tubes used, this is the area in the lab with most manual workers, and where an AI-based approach can help to handle this complexity and combine it with sample quality indicators provided by digital solutions. 

Today, companies are building robotic solutions that act as "automated lab sample receptions" that can work all day, handling different samples and container types from multiple suppliers efficiently and within different lab environmental conditions. This helps relieve labor shortages and operational inefficiencies, as manual intervention would only be needed when samples have the wrong labels and are incorrectly routed into analyzers.

The main benefits of AI robotics for the laboratory include:

• Flexible use: With AI, different types and sizes of sample tubes can be handled simultaneously.
• Reduced labor shortage: By automating the sample sorting process, labs reduce their need for manual labor, allowing employees to focus on value-added tasks.
• Increased throughput: AI-based sorting handles a high volume of incoming sample tubes fast and accurate which leads to a reduced turnaround time.
• Reduced error rate: AI robotics provides consistent performance, regardless of factors like employee fatigue or variability in manual handling techniques.
• Simply scalable: AI enables customizable applications depending on the volume or types of samples to be handled at any time.
• Seamless integration: Utilizing open interfaces allows communication with the LIS, digital sample tracking, and other systems to be easily integrated.

The aim of AI robotics is to automate in the direction of humans and never be a barrier that will be overly complicated. Therefore, one of its biggest advantages is easy implementation. Usability should be the main focus, with no robotics expertise required for operation. Through open interfaces, the system can also be seamlessly connected to the LIS or other software.

With the ever-increasing shortage of medical technicians, lab leaders are seeking digital solutions to improve efficiency and decrease errors in results. Health systems can consider how digitizing processes will affect the productivity of their labs. Utilizing a digital sample tracking system that seamlessly follows a sample from start to finish is essential in strengthening operational efficiency. 

For this, lab leaders can start by focusing on sample reception and leveraging AI-driven robotics, which is becoming increasingly commonplace, where even the smallest of labs can significantly scale sample handling while reducing manual burdens placed upon the personnel.

Furthermore, a connected, digital lab ecosystem can resolve more problems than manual troubleshooting, allowing lab leaders to minimize errors, get reliable results to clinicians faster and more efficiently, and positively impact patient outcomes.

Due to the ongoing demographic changes and labor shortages, the need for automation will further increase. Thanks to the latest developments in AI robotics, new solutions will provide support across various processes in the laboratory.  Robots in labs will be as commonplace as any other hardware component in today’s laboratories.