Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Predicting Risk of Unplanned Knee Surgery Following Anterior Cruciate Ligament Reconstruction

Poploski, Kathleen M (2023) Predicting Risk of Unplanned Knee Surgery Following Anterior Cruciate Ligament Reconstruction. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img] PDF (ETD)
Primary Text
Restricted to University of Pittsburgh users only until 17 November 2025.

Download (1MB) | Request a Copy


Anterior cruciate ligament reconstruction (ACLR) is a common orthopaedic surgery to restore knee stability and enable return to prior level of activity after ACL injury. Any additional unplanned subsequent knee surgery after initial ACLR is further disruptive to the patient and costly to the health care system. The overall goal of this dissertation was to identify risk factors associated with unplanned subsequent knee surgery following ACLR using electronic health record (EHR) data. This was accomplished by developing a data set of individuals who underwent ACLR within the University of Pittsburgh Medical Center (UPMC) Health System between 2013-2021.
Potential predictors of subsequent knee surgery after ACLR, including patient, injury, and surgery-related factors, are often only found within ACLR operative reports. We, therefore, developed natural language processing (NLP) pipelines to extract relevant factors and evaluated the performance on an independent test set. We were able to attain an acceptable level of performance for several variables, including the side of surgery, ACL procedure performed, ACL graft type, and meniscal involvement.
Next, phenotyping algorithms for identifying the outcome of interest, subsequent knee surgeries after ACLR, were developed from EHR data elements, and performance was evaluated on an independent test set. Procedure codes alone were sufficient for differentiating individuals who underwent a subsequent knee surgery from those who did not, but algorithms using a combination of procedure and diagnosis codes and information extracted from the operative report were needed to accurately identify specific procedures performed.
Finally, survival analysis was used to identify risk factors associated with any subsequent knee surgery and the most common specific procedures, including revision, contralateral ACLR, subsequent meniscus surgery, and subsequent procedure for loss of motion. Risk factors varied by the specific type of subsequent procedure, though there were overlapping factors between models and changes in risk over time for sex with regard to revision and age with regard to contralateral ACLR.
The completion of these projects informs the feasibility and accuracy of using EHR-based data to develop clinical decision-support models to prevent subsequent knee surgeries and other adverse outcomes following ACLR.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Poploski, Kathleen Mkmp174@pitt.edukmp1740000-0002-0554-2787
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairIrrgang, James Jjirrgang@pitt.edu0000-0002-7529-2672
Committee MemberBoyce, Richard Drdb20@pitt.edurdb200000-0002-2993-2085
Committee MemberMusahl, Volkermusahlv@upmc.eduvom20000-0001-8881-6212
Committee MemberRothenberger, Scottrothenberger@pitt.edu0000-0001-8300-5947
Thesis AdvisorSwitzer, Galengswitzer@pitt.edu0000-0001-8541-9449
Date: 17 November 2023
Date Type: Publication
Defense Date: 5 July 2023
Approval Date: 17 November 2023
Submission Date: 7 July 2023
Access Restriction: 2 year -- Restrict access to University of Pittsburgh for a period of 2 years.
Number of Pages: 132
Institution: University of Pittsburgh
Schools and Programs: School of Medicine > Clinical and Translational Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: anterior cruciate ligament; anterior cruciate ligament reconstruction; natural language processing; orthopaedic
Date Deposited: 17 Nov 2023 18:55
Last Modified: 17 Nov 2023 18:55


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item