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
Currently, the US Center for Medicaid and Medicare Services (CMS) has been testing bundled payments for revision total joint arthroplasty (TJA) through the Bundled Payment for Care Improvement (BPCI) programme. Under the BPCI, bundled payments for revision TJAs are defined on the basis of diagnosis-related groups (DRGs). However, these DRG-based bundled payment models may not be adequate to account appropriately for the varying case-complexity seen in revision TJAs. The 2008-2014 Medicare 5% Standard Analytical Files (SAF5) were used to identify patients undergoing revision TJA under DRG codes 466, 467, or 468. Generalized linear regression models were built to assess the independent marginal cost-impact of patient, procedural, and geographic characteristics on 90-day costs.Aims
Methods
We aimed to characterise the effect of expeditious hip fracture
surgery in elderly patients within 24 hours of admission on short-term
post-operative outcomes. Patients age 65 or older that underwent surgery for closed femoral
neck and intertrochanteric hip fractures were identified from the
American College of Surgeons National Surgical Quality Improvement
Program between 2011 and 2014. Multivariable propensity-adjusted
logistic regressions were performed to determine associations between early
surgery within 24 hours and post-operative complications, controlling
for selection bias in patients undergoing early surgery based on
observable characteristics.Aims
Patients and Methods
Patellofemoral arthroplasty (PFA) has experienced significant
improvements in implant survivorship with second generation designs.
This has renewed interest in PFA as an alternative to total knee
arthroplasty (TKA) for younger active patients with isolated patellofemoral
osteoarthritis (PF OA). We analysed the cost-effectiveness of PFA We used a Markov transition state model to compare cost-effectiveness
between PFA and TKA. Simulated patients were aged 60 (base case)
and 50 years. Lifetime costs (2015 United States dollars), quality-adjusted
life year (QALY) gains and incremental cost-effectiveness ratio
(ICER) were calculated from a healthcare payer perspective. Annual rates
of revision were derived from the National Joint Registry for England,
Wales, Northern Ireland and the Isle of Man. Deterministic and probabilistic
sensitivity analysis was performed for all parameters against a
$50 000/QALY willingness to pay. Aims
Patients and Methods
The aim of this study was to evaluate improvements in the quality
and safety of paediatric spinal surgery following the implementation
of a specialist Paediatric Spinal Surgical Team (PSST) in the operating
theatre. A retrospective consecutive case study of paediatric spinal operations
before (between January 2008 and December 2009), and after (between
January 2012 and December 2013) the implementation of PSST, was
performed. A comparative analysis of outcome variables including
surgical site infection (SSI), operating time (ORT), blood loss (BL),
length of stay (LOS), unplanned staged procedures (USP) and transfusion
rates (allogenic and cell-saver) was performed between the two groups.
The rate of complications during the first two postoperative years
was also compared between the groups.Aims
Patients and Methods
‘Big data’ is a term for data sets that are so
large or complex that traditional data processing applications are
inadequate. Billions of dollars have been spent on attempts to build predictive
tools from large sets of poorly controlled healthcare metadata.
Companies often sell reports at a physician or facility level based
on various flawed data sources, and comparative websites of ‘publicly
reported data’ purport to educate the public. Physicians should
be aware of concerns and pitfalls seen in such data definitions,
data clarity, data relevance, data sources and data cleaning when
evaluating analytic reports from metadata in health care. Cite this article:
The October 2015 Hip &
Pelvis Roundup360 looks at: Smoking and complications in arthroplasty; Smoking cessation beneficial in arthroplasty; Intermediate care and arthroplasty; Do we still need cell salvage?; Femoroacetabular impingement in the Japanese population; Trunnionosis or taperosis and geometry; Decontamination for staphylococcus aureus works!; Policeman or opportunity? Quality improvement with registries; Death rates higher in readmission to other hospitals
The December 2014 Spine Roundup360 looks at: surgeon outcomes; complications and scoliosis surgery; is sequestrectomy enough in lumbar disc prolapse?; predicting outcomes in lumbar disc herniation; sympathectomy has a direct effect on the dorsal root ganglion; and distal extensions of fusion in adolescent idiopathic scoliosis.
The December 2014 Knee Roundup360 looks at: national guidance on arthroplasty thromboprophylaxis is effective; unicompartmental knee replacement has the edge in terms of short-term complications; stiff knees, timing and manipulation; neuropathic pain and total knee replacement; synovial fluid α-defensin and CRP: a new gold standard in joint infection diagnosis?; how to assess anterior knee pain?; where is the evidence? Five new implants under the spotlight; and a fresh look at ACL reconstruction
