A new artificial intelligence tool called SepsisLab is revolutionizing clinician decision-making in hospitals by addressing the critical issue of sepsis risk prediction. Developed based on feedback from emergency department and ICU healthcare professionals, SepsisLab stands apart from existing AI-assisted tools by integrating clinician input with electronic health records to provide a more accurate patient risk prediction.
The innovative system not only predicts a patient’s sepsis risk within four hours but also has the remarkable ability to identify missing patient information, quantify its importance, and visually demonstrate to clinicians how specific data will impact the final risk prediction. In fact, incorporating just 8% of the recommended additional data improved the system’s sepsis prediction accuracy by a remarkable 11%.
By addressing the limitations of existing tools and harnessing the power of AI to enhance predictive performance, SepsisLab has the potential to significantly improve patient outcomes and revolutionize sepsis management in clinical settings.
“The existing model represents a more traditional human-AI competition paradigm, generating numerous annoying false alarms in ICUs and emergency rooms without listening to clinicians,” said senior study author Ping Zhang, associate professor of computer science and engineering and biomedical informatics at Ohio State.
“The idea is we need to involve AI in every intermediate step of decision-making by adopting the ‘AI-in-the-human-loop’ concept. We’re not just developing a tool – we also recruited physicians into the project. This is a real collaboration between computer scientists and clinicians to develop a human-centered system that puts the physician in the driver’s seat.”
Sepsis is a life-threatening medical emergency with the potential to rapidly lead to organ failure. Its elusive nature makes diagnosis challenging, as its symptoms closely mimic those of other conditions. Building on a groundbreaking machine learning model developed by Zhang and colleagues, this work focuses on determining the most effective timing for administering antibiotics to patients suspected of having sepsis.
The innovative SepsisLab operates swiftly to provide risk predictions, generating updated assessments every hour as new patient data is incorporated into the system.
“When a patient first comes in, there are many missing values, especially for lab tests,” said first author Changchang Yin, a computer science and engineering PhD student in Zhang’s Artificial Intelligence in Medicine lab.
In most AI models, missing data points are accounted for with a single assigned value – a process called imputation – “but the imputation model could suffer from the uncertainty that can be propagated to the downstream prediction model,” Yin said.
“If the imputation model cannot accurately impute the missing value, which is a very important value, the variable should be observed. Our active sensing algorithm aims to find such missing values and tell clinicians what additional variables they might need to observe – variables that can make the prediction model more accurate.”
Removing uncertainty from the system over time is crucial, but equally important is providing clinicians with actionable recommendations. These include lab tests ranked based on their value to the diagnostic process and estimates of how a patient’s sepsis risk would change based on specific clinical treatments.
The results of this experiment are compelling: adding just 8% of new data from lab tests, vital signs, and other high-value variables led to a remarkable 70% reduction in propagated uncertainty in the model, contributing to an impressive 11% improvement in sepsis risk accuracy.
“The algorithm can select the most important variables, and the physician’s action reduces the uncertainty,” said Zhang, also a core faculty member in Ohio State’s Translational Data Analytics Institute. “This fundamental mathematics work is the most important technical innovation – the backbone of the research.”
Zhang envisions human-centered AI as an integral part of the future of medicine. However, for this vision to become a reality, AI must engage with clinicians in a manner that builds trust in the system.
“This is not about building an AI system that can conquer the world,” he said. “The center of medicine is hypothesis testing and making decisions minute after minute that are not just ‘yes’ or ‘no.’ We envision a person at the center of the interaction using AI to help that human feel superhuman.”
Journal reference:
- Changchang Yin, Pin-Yu Chen, Bingsheng Yao, Dakuo Wang, Jeffrey Caterino, Ping Zhang. SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing. DOI: 10.1145/3637528.3671586