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
We report 17 patients (20 hips) in whom metal-on-metal resurfacing had been performed and who presented with various symptoms and a soft-tissue mass which we termed a pseudotumour. Each patient underwent plain radiography and in some, CT, MRI and ultrasonography were also performed. In addition, histological examination of available samples was undertaken. All the patients were women and their presentation was variable. The most common symptom was discomfort in the region of the hip. Other symptoms included spontaneous dislocation, nerve palsy, a noticeable mass or a rash. The common histological features were extensive necrosis and lymphocytic infiltration. To date, 13 of the 20 hips have required revision to a conventional hip replacement. Two are awaiting revision. We estimate that approximately 1% of patients who have a metal-on-metal resurfacing develop a pseudotumour within five years. The cause is unknown and is probably multifactorial. There may be a toxic reaction to an excess of particulate metal wear debris or a hypersensitivity reaction to a normal amount of metal debris. We are concerned that with time the incidence of these pseudotumours may increase. Further investigation is required to define their cause.
