AI digital twins help patients make smarter decisions about knee surgery, study finds

Schematic of the Artificial Intelligence-enabled Decision Aid (AI-DA) including exposure of the AI-DA components to control and intervention groups, and factors used to generate person-specific prediction outputs. aRisk defined as the likelihood of experiencing no change in condition or being worse off after undergoing surgery. bComplication rate defined as estimated complication rate due to joint infection within 90 days, pulmonary embolism or death within 30 days, and pneumonia, sepsis, or acute myocardial infarction within 7 days. cBenefit defined as inverse of risk prediction; Likelihood of experiencing at least a minimal clinically important difference in functional outcome based on knee stiffness, knee pain, and quality of life sub-domains of KOOSJR. Credit: eClinicalMedicine (2025). DOI: 10.1016/j.eclinm.2025.103545

An AI-powered tool helped patients make more confident, personalized decisions about knee replacement surgery—and led to better outcomes months later—according to a new study from researchers at Dell Medical School at The University of Texas at Austin.

Published in eClinicalMedicine, the study found that patients who used the tool reported higher decision quality, less regret and better knee function compared to those who received educational materials alone. The tool uses artificial intelligence to create a digital twin—a virtual simulation that predicts surgical risks and benefits for each patient based on their own health data—and helps clarify treatment preferences through a guided, personalized process.

“This isn’t about replacing the surgeon—it’s about giving people the power to make informed, confident decisions about their care,” said Prakash Jayakumar, M.D., lead author of the study and assistant professor in the Department of Surgery and Perioperative Care at Dell Med. “We found that a personalized, AI-supported approach helped patients feel more prepared and satisfied—and that can translate into better outcomes.”

The randomized clinical trial enrolled more than 200 people with advanced knee osteoarthritis at the Musculoskeletal Institute at UT Health Austin. Patients who used the AI tool had better treatment alignment with their personal goals and were more likely to reach meaningful improvements in knee health within 6 to 9 months after their consultation.

Patients who used the AI tool were also more likely to choose a treatment that aligned with their personal goals—whether surgical or non-surgical—and experienced greater improvement in knee-specific health over time. The results suggest that integrating AI-powered tools into routine care could help patients and clinicians make more informed, personalized decisions, especially for conditions like osteoarthritis where outcomes can vary widely.

More information:
Prakash Jayakumar et al, Shared decision making using digital twins in knee osteoarthritis care: a randomized clinical trial of an AI-enabled decision aid versus education alone on decision quality, physical function, and user experience, eClinicalMedicine (2025). DOI: 10.1016/j.eclinm.2025.103545

Provided by
University of Texas at Austin


Citation:
AI digital twins help patients make smarter decisions about knee surgery, study finds (2025, October 30)
retrieved 30 October 2025
from https://medicalxpress.com/news/2025-10-ai-digital-twins-patients-smarter.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.




Source link

Exit mobile version