Importance: Decision aids can help inform appropriate selection of total knee replacement (TKR) for advanced knee osteoarthritis (OA). However, few decision aids combine patient education, preference assessment, and artificial intelligence (AI) using patient-reported outcome measurement data to generate personalized estimations of outcomes to augment shared decision-making (SDM). Objective: To assess the effect of an AI-enabled patient decision aid that includes education, preference assessment, and personalized outcome estimations (using patient-reported outcome measurements) on decision quality, patient experience, functional outcomes, and process-level outcomes among individuals with advanced knee OA considering TKR in comparison with education only. Design, Setting, and Participants: This randomized clinical trial at a single US academic orthopedic practice included 129 new adult patients presenting for OA-related knee pain from March 2019 to January 2020. Data were analyzed from April to May 2020. Intervention: Patients were randomized into a group that received a decision aid including patient education, preference assessment, and personalized outcome estimations (intervention group) or a group receiving educational material only (control group) alongside usual care. Main Outcomes and Measures: The primary outcome was decision quality, measured using the Knee OA Decision Quality Instrument (K-DQI). Secondary outcomes were collaborative decision-making (assessed using the CollaboRATE survey), patient satisfaction with consultation (using a numerical rating scale), Knee Injury and Osteoarthritis Outcome Score Joint Replacement (KOOS JR) score, consultation time, TKR rate, and treatment concordance. Results: A total of 69 patients in the intervention group (46 [67%] women) and 60 patients in the control group (37 [62%] women) were included in the analysis. The intervention group showed better decisional quality (K-DQI mean difference, 20.0%; SE, 3.02; 95% CI, 14.2%-26.1%; P < .001), collaborative decision-making (CollaboRATE, 8 of 69 [12%] vs 28 of 60 [47%] patients below median; P < .001), satisfaction (numerical rating scale, 9 of 65 [14%] vs 19 of 58 [33%] patients below median; P = .01), and improved functional outcomes at 4 to 6 months (mean [SE] KOOS JR, 4.9 [2.24] points higher in intervention group; 95% CI, 0.8-9.0 points; P = .02). The intervention did not significantly affect consultation time (mean [SE] difference, 2.23 [2.18] minutes; P = .31), TKR rates (16 of 69 [23%] vs 7 of 60 [12%] patients; P = .11), or treatment concordance (58 of 69 [84%] vs 44 of 60 [73%] patients; P = .19). Conclusions and Relevance: In this randomized clinical trial, an AI-enabled decision aid significantly improved decision quality, level of SDM, satisfaction, and physical limitations without significantly impacting consultation times, TKR rates, or treatment concordance in patients with knee OA considering TKR. Decision aids using a personalized, data-driven approach can enhance SDM in the management of knee OA. Trial Registration: ClinicalTrials.gov Identifier: NCT03956004.
RCT Entities:
Importance: Decision aids can help inform appropriate selection of total knee replacement (TKR) for advanced knee osteoarthritis (OA). However, few decision aids combine patient education, preference assessment, and artificial intelligence (AI) using patient-reported outcome measurement data to generate personalized estimations of outcomes to augment shared decision-making (SDM). Objective: To assess the effect of an AI-enabled patient decision aid that includes education, preference assessment, and personalized outcome estimations (using patient-reported outcome measurements) on decision quality, patient experience, functional outcomes, and process-level outcomes among individuals with advanced knee OA considering TKR in comparison with education only. Design, Setting, and Participants: This randomized clinical trial at a single US academic orthopedic practice included 129 new adult patients presenting for OA-related knee pain from March 2019 to January 2020. Data were analyzed from April to May 2020. Intervention: Patients were randomized into a group that received a decision aid including patient education, preference assessment, and personalized outcome estimations (intervention group) or a group receiving educational material only (control group) alongside usual care. Main Outcomes and Measures: The primary outcome was decision quality, measured using the Knee OA Decision Quality Instrument (K-DQI). Secondary outcomes were collaborative decision-making (assessed using the CollaboRATE survey), patient satisfaction with consultation (using a numerical rating scale), Knee Injury and Osteoarthritis Outcome Score Joint Replacement (KOOS JR) score, consultation time, TKR rate, and treatment concordance. Results: A total of 69 patients in the intervention group (46 [67%] women) and 60 patients in the control group (37 [62%] women) were included in the analysis. The intervention group showed better decisional quality (K-DQI mean difference, 20.0%; SE, 3.02; 95% CI, 14.2%-26.1%; P < .001), collaborative decision-making (CollaboRATE, 8 of 69 [12%] vs 28 of 60 [47%] patients below median; P < .001), satisfaction (numerical rating scale, 9 of 65 [14%] vs 19 of 58 [33%] patients below median; P = .01), and improved functional outcomes at 4 to 6 months (mean [SE] KOOS JR, 4.9 [2.24] points higher in intervention group; 95% CI, 0.8-9.0 points; P = .02). The intervention did not significantly affect consultation time (mean [SE] difference, 2.23 [2.18] minutes; P = .31), TKR rates (16 of 69 [23%] vs 7 of 60 [12%] patients; P = .11), or treatment concordance (58 of 69 [84%] vs 44 of 60 [73%] patients; P = .19). Conclusions and Relevance: In this randomized clinical trial, an AI-enabled decision aid significantly improved decision quality, level of SDM, satisfaction, and physical limitations without significantly impacting consultation times, TKR rates, or treatment concordance in patients with knee OA considering TKR. Decision aids using a personalized, data-driven approach can enhance SDM in the management of knee OA. Trial Registration: ClinicalTrials.gov Identifier: NCT03956004.
Authors: Paul A Harris; Robert Taylor; Robert Thielke; Jonathon Payne; Nathaniel Gonzalez; Jose G Conde Journal: J Biomed Inform Date: 2008-09-30 Impact factor: 6.317
Authors: Kali N Stevens; Vidushan Nadarajah; Julio J Jauregui; Xuyang Song; Shaun H Medina; Michael P Smuda; Jonathan D Packer; R Frank Henn Journal: J Knee Surg Date: 2019-10-22 Impact factor: 2.757
Authors: R R Bannuru; M C Osani; E E Vaysbrot; N K Arden; K Bennell; S M A Bierma-Zeinstra; V B Kraus; L S Lohmander; J H Abbott; M Bhandari; F J Blanco; R Espinosa; I K Haugen; J Lin; L A Mandl; E Moilanen; N Nakamura; L Snyder-Mackler; T Trojian; M Underwood; T E McAlindon Journal: Osteoarthritis Cartilage Date: 2019-07-03 Impact factor: 6.576
Authors: Kevin J Bozic; Jeffrey Belkora; Vanessa Chan; Jiwon Youm; Tianzan Zhou; John Dupaix; Angela Nava Bye; Clarence H Braddock; Kate Eresian Chenok; James I Huddleston Journal: J Bone Joint Surg Am Date: 2013-09-18 Impact factor: 5.284
Authors: Karen Sepucha; Sandra Feibelmann; Yuchiao Chang; Catharine F Clay; Stephen A Kearing; Ivan Tomek; Theresa Yang; Jeffrey N Katz Journal: J Am Coll Surg Date: 2013-07-25 Impact factor: 6.113
Authors: Eugenia Lin; Lauren M Uhler; Erin P Finley; Prakash Jayakumar; Paul J Rathouz; Kevin J Bozic; Joel Tsevat Journal: BMJ Open Date: 2022-02-21 Impact factor: 2.692
Authors: Brocha Z Stern; Sarah Pila; Layla I Joseph; Nan E Rothrock; Patricia D Franklin Journal: BMC Musculoskelet Disord Date: 2022-08-23 Impact factor: 2.562
Authors: Thomas Y T Lam; Max F K Cheung; Yasmin L Munro; Kong Meng Lim; Dennis Shung; Joseph J Y Sung Journal: J Med Internet Res Date: 2022-08-25 Impact factor: 7.076
Authors: D K Lvov; G N Leonova; V L Gromashevsky; V L Shestakov; Y P Gofman; T M Skvortsova; S M Klimenko; L K Berezina; V A Zakaryan; A V Safronov; R V Belousova Journal: Acta Virol Date: 1978-11 Impact factor: 1.827