Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction. A group of 1,000 randomly selected clinical and hospital notes from eight different surgeons were collected for patients undergoing primary arthroplasty between 2012 and 2018. In all, 19 preoperative, 17 operative, and two postoperative variables of interest were manually extracted from these notes. A NLP algorithm was created to automatically extract these variables from a training sample of these notes, and the algorithm was tested on a random test sample of notes. Performance of the NLP algorithm was measured in Statistical Analysis System (SAS) by calculating the accuracy of the variables collected, the ability of the algorithm to collect the correct information when it was indeed in the note (sensitivity), and the ability of the algorithm to not collect a certain data element when it was not in the note (specificity).Aims
Methods
The number of surgical procedures performed each year to treat
femoroacetabular impingement (FAI) continues to rise. Although there
is evidence that surgery can improve symptoms in the short-term,
there is no evidence that it slows the development of osteoarthritis
(OA). We performed a feasibility study to determine whether patient
and surgeon opinion was permissive for a Randomised Controlled Trial
(RCT) comparing operative with non-operative treatment for FAI. Surgeon opinion was obtained using validated questionnaires at
a Specialist Hip Meeting (n = 61, 30 of whom stated that they routinely
performed FAI surgery) and patient opinion was obtained from clinical
patients with a new diagnosis of FAI (n = 31).Objectives
Methods
Persistent groin pain after seemingly successful
total hip replacement (THR) appears to have become more common.
Recent studies have indicated a high incidence after metal-on-polyethylene
and metal-on-metal conventional THR and it has been documented in
up to 18% of patients after metal-on-metal resurfacing. There are many
causes, including acetabular loosening, stress fracture, and iliopsoas
tendonitis and impingement. The evaluation of this problem requires
a careful history and examination, plain radiographs and an algorithmic approach
to special diagnostic imaging and tests. Non-operative treatment
is not usually successful. Specific operative treatment depending
on the cause of the pain usually involves revision of the acetabular
component, iliopsoas tenotomy or other procedures, and is usually
successful. Here, an appropriate algorithm is described.
A prospective cohort of 222 patients who underwent revision hip replacement between April 2001 and March 2004 was evaluated to determine predictors of function, pain and activity level between one and two years post-operatively, and to define quality of life outcomes using validated patient reported outcome tools. Predictive models were developed and proportional odds regression analyses were performed to identify factors that predict quality of life outcomes at one and two years post-operatively. The dependent outcome variables were the Western Ontario and McMaster Osteoarthritis Index (WOMAC) function and pain scores, and University of California Los Angeles activity scores. The independent variables included patient demographics, operative factors, and objective quality of life parameters, including pre-operative WOMAC, and the Short Form-12 mental component score. There was a significant improvement ( Predictors of quality of life outcomes after revision hip replacement were established. Although some patient-specific and surgery-specific variables were important, age, gender, Charnley class and pre-operative WOMAC function score had the most robust associations with outcome.
