Emerging Technologies of the Future Lab: A Webinar Recap

In an era of rapidly transforming healthcare, an important roundtable discussion brought together industry thought leaders to explore the current state of technology and its potential impact on the future of laboratory science. 

The conversation was rich with insights, covering topics from artificial intelligence (AI) in personalized medicine to the shift toward value-based care and the untapped potential of longitudinal data. 

The Panelists

Suren Avunjian, CEO of LigoLab, moderated the roundtable discussion. The panel was comprised of:

• Bruce Friedman, Professor Emeritus, University of Michigan Medical School
• Stan Schofield, Managing Principal of The Compass Group
• Khosrow R. Shotorbani, President, Executive Director, Project Santa Fe Foundation - Lab 2.0
• Dennis Winsten, President, Dennis Winsten & Associates, Healthcare Systems Consultants

The Digital Transformation of Laboratory Science

The panelists began by acknowledging the digital transformation sweeping various industries, including laboratory medicine. They emphasized how advancements in AI, LIS system software automation, and digital pathology solutions have significantly transformed the modern laboratory landscape.

As clinical laboratories and pathology groups grapple with disruptions from technological advancements, regulatory changes, and evolving healthcare landscapes, the panelists emphasized the need for medical labs to be proactive. It includes adopting new technologies, optimizing laboratory workflow management, and investing in staff training and development.

By embracing change and focusing on delivering high-quality, cost-effective services, clinical laboratories and pathology groups can continue to play a vital role in the healthcare ecosystem.

Discover More: Can Your Laboratory Information System Support the Latest LIS System Technology?

The Importance of Laboratory Information System Software Integration

The panelists explored the complexities of laboratory information system (LIS) software, highlighting how laboratory information system vendors play a pivotal role in helping labs understand the crucial distinction between integration and interfacing, and why this difference matters for lab efficiency, data quality, and business intelligence.

Lab Information System Integration vs. Interfacing: Understanding the Difference

Dennis Winsten emphasized the difference between integration and interfacing. He explained that many people use these terms interchangeably, but they should not.

Interfacing transmits transactions and messages between disparate laboratory software systems. In contrast, integration unifies all data within a single system.

"Many people claim their systems are integrated, but in reality, they only interface them," he said. 

The Challenges of Laboratory Information System Interfacing

Laboratory information system interfacing presents significant challenges. Modifications between interfaced diagnostic lab software often lead to retesting, downtime, and data remapping, as well as potential inconsistencies in how each system displays information. If one goes offline, it creates uncertainty about data accuracy, redundancy, and which system contains the most up-to-date records.

The Benefits of Laboratory Information System Integration

A fully integrated LIS software platform delivers a comprehensive solution where all data is readily accessible, eliminating silos between clinical and financial information and enabling real-time visibility across the system. It ensures consistent, unambiguous data while strengthening business intelligence and analytics across the entire operational and financial landscape (without the need to reconcile disparate systems).

Discover More: Why Integrated LIS System and Lab RCM Software is a Catalyst for Growth

AI: The Game Changer in Personalized Medicine

The webinar continued with a robust discussion on the role of AI in personalized medicine. 

Bruce Friedman expressed confidence that the lab industry will readily absorb AI. 

“I’m confident because laboratory personnel and professionals are very comfortable working with automation and technology, and our industry will provide that for us," he said. 

The panelists highlighted AI's potential to revolutionize healthcare by validating data, predicting disease, and enhancing clinical decision-making. 

Discover More: Best Practices for Preparing Medical Labs for AI Integration in Technical and Financial Operations

Ensuring Data Quality with AI

A key point of discussion was the importance of data quality in AI applications. Winsten cautioned against the "garbage in, garbage out" pitfall. 

"Artificial intelligence is not going to solve problems if it's dealing with garbage," he noted. 

Winsten emphasized that AI plays a critical role in maintaining data integrity within longitudinal databases. He noted that AI can function as a quality control layer, detecting inconsistencies in incoming data and ensuring that analysts rely only on accurate, high-quality information for decision-making.

Predictive Analytics: A Glimpse into the Future of Patient Care

Winsten envisioned a future in which AI, using predictive analytics, could identify potential diseases a patient might develop over time based on variations within the normal range.

"We've now moved into a predictive model. This model has enough capability to determine what could happen, and what is likely to happen, based on the analysis of historical data,” he added. 

Prescriptive Analytics: The Next Evolution

Winsten went further, discussing the next evolution beyond predictive analytics, prescriptive analytics.

“With artificial intelligence and machine learning, where the machine learns from the new data it's getting, it can alter what it suggests,” he said. “Prescriptive suggests decision options most likely to optimize outcomes. It indicates what should happen or the best course of action." 

The Success of AI: A Data-Dependent Story

The discussion underscored a critical point: the success of AI in revolutionizing personalized medicine hinges entirely on the quality of data it operates on. 

Industry Insights: Healthcare AI Has Crossed the Line From Experiment to Infrastructure

The Transition to Value-Based Care: A New Era in Healthcare

The conversation next focused on the future of healthcare, with Stan Schofield raising the shift from volume-based to value-based care.

The panelists concurred that this shift would necessitate significant changes in healthcare, with laboratories playing pivotal roles.

Laboratories: The Bridge to Patients

The panelists urged laboratories to move beyond their traditional roles and bridge the gap with patients, actively guiding them through the health system efficiently and cost-effectively.

"Get closer to the patient. Work with your data analytics and financial people doing the contracting,” recommended Schofield. 

Understanding Costs and Contracting

The panelists underscored the importance of labs understanding their costs and working closely with data analytics and financial teams during contract negotiations for value-based care.

"No health system should ever sign a value-based care contract without a lab's input," Schofield strongly suggested. 

The Proactive Approach to Value-Based Care

The panelists emphasized that labs must be more than passive providers of test results; they must be active participants in the healthcare journey, driving patient care and outcomes. The success of this transition hinges on labs stepping out of their traditional roles and taking an active role in patient care.

Get Insight: Leveraging LigoLab for Optimal Return on LIS Investment: A Guide for Lab Directors

Longitudinal Data: The Power to Predict and Prevent

The power of longitudinal data emerged as a central theme of the webinar. Khosrow Shotorbani highlighted its value as a potential foundation for the future care model.

“This model lets us proactively stratify risk, even when patients show no symptoms, a crucial requirement for value-based care," he said. 

Using Longitudinal Data to Diagnose Pre-Disease States

The panelists discussed the transformative potential of longitudinal data, painting a picture of a future where it could enable early diagnosis and disease prevention, leading to cost savings and improved patient care.

"We need to stop talking about just a test and start talking about the change in a test, which is that longitudinal data, even within the normal range," added Shotorbani. 

The Challenge of Retesting Drugs for Pre-Disease States

Shotorbani also pointed out that diagnosing pre-disease states will require the industry to retest drugs for those states. This requirement poses a new challenge that the industry must address as this model evolves.

Industry Insights: Laboratory Information Systems and Their Key Role in Lab Data Analytics

Medical Laboratories: The Unsung Heroes of Patient Care

The role of medical laboratories in patient care emerged as a consistent theme throughout the webinar. Panelists encouraged labs to take a proactive approach, gain a clear understanding of their costs, and better align data analytics with laboratory billing processes. They described laboratories as often-overlooked drivers of care, rich in data that can be leveraged to improve patient outcomes.

“Lab data is the biggest bargain in healthcare today,” said Friedman. 

Labs as Catalysts

Shotorbani highlighted the untapped potential of labs in the healthcare system, suggesting they could serve as catalysts for value-based care, helping guide patients through the system efficiently and cost-effectively.

The Unidirectional Nature of Labs

Friedman raised a significant structural limitation in how a lab currently operates. 

"The lab maintains a one-way connection to patient care. It receives samples, performs tests, and sends out results, but it seldom learns the specific outcomes for those patients," he said. 

This lack of feedback prevents labs from understanding the full impact of their contributions to patient care, and represents one of the key areas where change is needed.

Discover More: Four Game-Changing Business Strategies to Improve Laboratory Processes

Charting the Course for the Future

The webinar concluded with statements of optimism and anticipation. The panelists called for continued collaboration and innovation to harness the potential of technology in personalized medicine, reshape the future of clinical laboratory management, and ultimately improve patient outcomes.

The insights from this roundtable served as a roadmap for the future, a collective effort to navigate the evolving landscape of the clinical laboratory industry. From the potential of AI and longitudinal data to the pivotal role of labs in patient care, the future promises to be a journey of discovery and innovation.

On-Demand Webinar: Emerging Technologies of the Future Lab

Discover More: Browse All Archived LigoLab Webinars 

Frequently Asked Questions About Emerging Lab Technologies

What were the main topics covered in this webinar?

The roundtable covered the digital transformation of laboratory science, the distinction between laboratory information system integration and interfacing, the role of artificial intelligence in personalized medicine, the transition to value-based care, and the transformative potential of longitudinal data for predicting and preventing disease.

What is the difference between LIS system integration and LIS system interfacing?

Interfacing allows two separate laboratory software systems to exchange data through messages or transactions, while each maintains its own database. In contrast, integration brings all data into a single unified informatics platform. This approach eliminates data silos, minimizes inconsistencies, and enables real-time access to both clinical and financial information, without the need to reconcile records across multiple systems.

Why does data quality matter so much for AI in healthcare?

AI is only as effective as the data it analyzes. If a lab's data is incomplete, inconsistent, or inaccurate, AI models will produce unreliable outputs, regardless of how sophisticated the algorithm is. The panelists emphasized that AI should be viewed as a quality control tool that validates incoming data, not a fix for poor data hygiene.

What is the difference between predictive and prescriptive analytics?

Predictive analytics leverages historical data to anticipate future outcomes, such as identifying a patient’s risk of developing a condition. Prescriptive analytics builds on these insights by recommending the actions or decisions most likely to achieve optimal results. Both are driven by AI and machine learning, and rely on high-quality longitudinal data to deliver accurate insights.

What is longitudinal data, and why is it important for labs?

Longitudinal data refers to repeated measurements of the same patient over time. Rather than evaluating a single test result in isolation, longitudinal data tracks changes within a patient's normal range, enabling earlier detection of disease progression, proactive risk stratification, and more personalized care. The panelists described it as a foundational element of the future value-based care model.

What is value-based care, and how does it affect laboratories?

Value-based care transitions healthcare reimbursement away from the fee-for-service model, where providers are paid per test or procedure, toward models based on patient outcomes and the overall value delivered. For laboratories, this shift requires evolving from a passive role of reporting results to a more active role in patient management, cost analysis, and contract strategy. Panelists emphasized that no health system should enter a value-based care agreement without direct input from its laboratory.

What does it mean that labs have a "unidirectional" connection to patient care?

Currently, labs receive samples, perform tests, and send results, but rarely receive feedback on the patient's outcome afterward. This one-way flow limits a lab's ability to understand the downstream impact of its work, improve diagnostic accuracy over time, or contribute meaningfully to outcome-based care models. Closing this feedback loop was identified as a key opportunity for the industry.

How can labs prepare for the future technologies discussed in this webinar?

The panelists recommended four actions: adopting modern LIS software from reliable laboratory information system companies with true integration rather than interfacing, investing in data quality infrastructure to support AI applications, building closer relationships with financial and analytics teams to prepare for value-based contracting, and taking a proactive rather than reactive stance toward technological and regulatory change.