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
Tranexamic acid (TXA) is proven to reduce blood loss following total knee arthroplasty (TKA), but there are limited data on the impact of similar dosing regimens in revision TKA. The purpose of this multicentre randomized clinical trial was to determine the optimal regimen to maximize the blood-sparing properties of TXA in revision TKA. From six-centres, 233 revision TKAs were randomized to one of four regimens: 1 g of intravenous (IV) TXA given prior to the skin incision, a double-dose regimen of 1 g IV TXA given both prior to skin incision and at time of wound closure, a combination of 1 g IV TXA given prior to skin incision and 1 g of intraoperative topical TXA, or three doses of 1950 mg oral TXA given two hours preoperatively, six hours postoperatively, and on the morning of postoperative day one. Randomization was performed based on the type of revision procedure to ensure equivalent distribution among groups. Power analysis determined that 40 patients per group were necessary to identify a 1 g/dl difference in the reduction of haemoglobin postoperatively between groups with an alpha of 0.05 and power of 0.80. Per-protocol analysis involved regression analysis and two one-sided Aims
Patients and Methods
