Artificial intelligence holds great potential to transform healthcare for the better — including reducing workflow inefficiencies, predicting health outcomes and speeding up diagnoses — so researchers have been piloting more studies exploring the technology in the past decade.
Six key AI studies that have been published recently:
- “Comparison of chest radiograph interpretations by artificial intelligence algorithm vs. radiology residents“: The research team found no statistical significance in sensitivity between the way the algorithm performed and the way the radiology residents did, but specificity and positive predictive value were statistically higher for the algorithm.
- “Development of a dynamic diagnosis grading system for infertility using machine learning“: This study established an infertility scoring system based on the health records of 60, 648 couples going through the in vitro fertilization process, finding its overall stability test result to be 96 percent.
- “Effect of integrating machine learning mortality estimates with behavioral nudges to clinicians on serious illness conversations among patients with cancer“: Researchers discovered the AI intervention led to a statistically significant increase in serious illness conversations from approximately 1 to 5 percent of all patient encounters and from approximately 4 to 15 percent of encounters involving patients with a high predicted mortality risk.
- “Cross-site transportability of an explainable artificial intelligence model for acute kidney injury prediction“: This study established a method to predict the transportability of AI models to expedite such technology’s adoption at hospital sites.
- “Deep learning-based clustering robustly identified two classes of sepsis with both prognostic and predictive values“: Researchers developed an inexpensive model for the prediction of sepsis class, finding it to have statistically high prognostic and predictive capabilities.
- “Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet“: The research team found the AI system they designed to detect rib fractures and segmentation in CT scans performed more efficiently than radiologists.