Clinical discoveries are heralded by observing unique and unusual clinical cases. The effort of identifying such cases rests on the shoulders of busy clinicians. We assess the feasibility and applicability of an augmented intelligence framework to accelerate the rate of clinical discovery in preeclampsia and hypertensive disorders of pregnancy-an area that has seen little change in its clinical management.
Methods
We conducted a retrospective exploratory outlier analysis of participants enrolled in the folic acid clinical trial (FACT, N=2,301) and the Ottawa and Kingston birth cohort (OaK, N=8,085). We applied two outlier analysis methods: extreme misclassification contextual outlier and isolation forest point outlier. The extreme misclassification contextual outlier is based on a random forest predictive model for the outcome of preeclampsia in FACT and hypertensive disorder of pregnancy in OaK. We defined outliers in the extreme misclassification approach as mislabelled observations with a confidence level of more than 90%. Within the isolation forest approach, we defined outliers as observations with an average path length z score less or equal to -3, or more or equal to 3. Content experts reviewed the identified outliers and determined if they represented a potential novelty that could conceivably lead to a clinical discovery.
Results
In the FACT study, we identified 19 outliers using the isolation forest algorithm and 13 outliers using the random forest extreme misclassification approach. We determined that three (15.8%) and 10 (76.9%) were potential novelties, respectively. Out of 8,085 participants in the OaK study, we identified 172 outliers using the isolation forest algorithm and 98 outliers using the random forest extreme misclassification approach; four (2.3%) and 32 (32.7%), respectively, were potential novelties. Overall, the outlier analysis part of the augmented intelligence framework identified a total of 302 outliers. These were subsequently reviewed by content experts, representing the human part of the augmented intelligence framework. The clinical review determined that 49 of the 302 outliers represented potential novelties.
Conclusions
Augmented intelligence using extreme misclassification outlier analysis is a feasible and applicable approach for accelerating the rate of clinical discoveries. The use of an extreme misclassification contextual outlier analysis approach has resulted in a higher proportion of potential novelties than using the more traditional point outlier isolation forest approach. This finding was consistent in both the clinical trial and real-world cohort study data. Using augmented intelligence through outlier analysis has the potential to speed up the process of identifying potential clinical discoveries. This approach can be replicated across clinical disciplines and could exist within electronic medical records systems to automatically identify outliers within clinical notes to clinical experts.
Keywords: augmented intelligence; clinical discovery; clinical trials; hdp; hypertensive disorders of pregnancy; preeclampsia treatment; preeclampsia-eclampsia; real-world data; research methods and design.
FAQs
What is augmented intelligence and how is it used in clinical discovery?
Augmented intelligence refers to the collaboration between human expertise and artificial intelligence (AI) to enhance decision-making and discovery processes. In this study, it was used to accelerate clinical discoveries in hypertensive disorders of pregnancy by identifying unique and unusual cases through outlier analysis.
What methods were used to identify potential clinical discoveries in this study?
The study employed two outlier analysis methods: extreme misclassification contextual outlier analysis and isolation forest point outlier analysis. These methods were applied to data from the folic acid clinical trial (FACT) and the Ottawa and Kingston birth cohort (OaK) to identify cases that could represent potential clinical discoveries.
What were the key findings from the outlier analysis in this study?
The study found that the extreme misclassification contextual outlier analysis identified a higher proportion of potential novelties compared to the isolation forest approach. Specifically, 76.9% of outliers identified using the extreme misclassification method in the FACT study and 32.7% in the OaK study were considered potential novelties by clinical experts.
How can augmented intelligence benefit clinical research in hypertensive disorders of pregnancy?
Augmented intelligence can significantly speed up the process of identifying potential clinical discoveries by automating the identification of unusual and unique cases. This approach allows for faster and more efficient discovery of novel clinical insights that could improve the management and treatment of hypertensive disorders of pregnancy.
Can the outlier analysis approach used in this study be applied to other clinical disciplines?
Yes, the outlier analysis approach demonstrated in this study can be replicated across various clinical disciplines. It has the potential to be integrated into electronic medical records systems, where it could automatically flag outliers in clinical notes for further review by experts, thereby facilitating faster clinical discoveries.
What is the significance of identifying outliers in clinical trials and real-world cohort studies?
Identifying outliers in clinical trials and real-world cohort studies is crucial as these outliers may represent novel or rare cases that could lead to significant clinical discoveries. By focusing on these outliers, researchers can uncover new insights that may not be apparent in the general data, potentially leading to advancements in medical knowledge and patient care.
