4 recent studies exploring AI in healthcare

In the past decade, medical researchers have become increasingly interested in artificial intelligence's potential to improve healthcare by reducing workflow inefficiencies, predicting health outcomes and speeding up diagnoses.

Below are four key AI studies that have been published recently:

  1. Development of electronic health record–based prediction models for 30-day readmission risk among patients hospitalized for acute myocardial infarction: The research team examined the efficacy of externally validated machine learning models that predicted the risk of 30-day readmission for more than 10,000 patients after hospitalization for acute myocardial infarction. Favorable discrimination performance was recorded at the development site, but the best discrimination did not result in the best calibration.

  2. Effect of a predictive model on planned surgical duration accuracy, patient wait time, and use of presurgical resources: Researchers developed a machine learning model that improved surgical duration accuracy, reduced patient wait time and reduced presurgical resource use.

  3. Effect of personalized incentives on dietary quality of groceries purchased: The research team tested whether the dietary quality of grocery purchases could be improved by a healthy food incentive intervention that uses an algorithm incorporating consumer preferences, purchase history and basic diet quality. The trial demonstrated preliminary evidence for the tool's efficacy.

  4. A genomic-pathologic annotated risk model to predict recurrence in early-stage lung adenocarcinoma: Researchers created a machine learning-powered prediction model to determine which patients were at risk of early lung adenocarcinoma recurrence, finding it outperformed traditional models. 

More articles on artificial intelligence:
UPMC develops AI tool to predict mortality for patients facing hospital transfer
How Amazon algorithms are spreading vaccine misinformation
Geisinger AI tool increases cardiac death risk prediction accuracy by 13%

© Copyright ASC COMMUNICATIONS 2021. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.