Advertisement for orthosearch.org.uk
Results 1 - 6 of 6
Results per page:
The Bone & Joint Journal
Vol. 98-B, Issue 2 | Pages 201 - 208
1 Feb 2016
Kingsbury SR Dube B Thomas CM Conaghan PG Stone MH

Aims

Increasing demand for total hip and knee arthroplasty (THA/TKA) and associated follow-up has placed huge demands on orthopaedic services. Feasible follow-up mechanisms are therefore essential.

Methods

We conducted an audit of clinical follow-up decision-making for THA/TKA based on questionnaire/radiograph review compared with local practice of Arthroplasty Care Practitioner (ACP)-led outpatient follow-up. In all 599 patients attending an ACP-led THA/TKA follow-up clinic had a pelvic/knee radiograph, completed a pain/function questionnaire and were reviewed by an ACP. An experienced orthopaedic surgeon reviewed the same radiographs and questionnaires, without patient contact or knowledge of the ACP’s decision. Each pathway classified patients into: urgent review, annual monitoring, routine follow-up or discharge.


The Bone & Joint Journal
Vol. 106-B, Issue 7 | Pages 688 - 695
1 Jul 2024
Farrow L Zhong M Anderson L

Aims. To examine whether natural language processing (NLP) using a clinically based large language model (LLM) could be used to predict patient selection for total hip or total knee arthroplasty (THA/TKA) from routinely available free-text radiology reports. Methods. Data pre-processing and analyses were conducted according to the Artificial intelligence to Revolutionize the patient Care pathway in Hip and knEe aRthroplastY (ARCHERY) project protocol. This included use of de-identified Scottish regional clinical data of patients referred for consideration of THA/TKA, held in a secure data environment designed for artificial intelligence (AI) inference. Only preoperative radiology reports were included. NLP algorithms were based on the freely available GatorTron model, a LLM trained on over 82 billion words of de-identified clinical text. Two inference tasks were performed: assessment after model-fine tuning (50 Epochs and three cycles of k-fold cross validation), and external validation. Results. For THA, there were 5,558 patient radiology reports included, of which 4,137 were used for model training and testing, and 1,421 for external validation. Following training, model performance demonstrated average (mean across three folds) accuracy, F1 score, and area under the receiver operating curve (AUROC) values of 0.850 (95% confidence interval (CI) 0.833 to 0.867), 0.813 (95% CI 0.785 to 0.841), and 0.847 (95% CI 0.822 to 0.872), respectively. For TKA, 7,457 patient radiology reports were included, with 3,478 used for model training and testing, and 3,152 for external validation. Performance metrics included accuracy, F1 score, and AUROC values of 0.757 (95% CI 0.702 to 0.811), 0.543 (95% CI 0.479 to 0.607), and 0.717 (95% CI 0.657 to 0.778) respectively. There was a notable deterioration in performance on external validation in both cohorts. Conclusion. The use of routinely available preoperative radiology reports provides promising potential to help screen suitable candidates for THA, but not for TKA. The external validation results demonstrate the importance of further model testing and training when confronted with new clinical cohorts. Cite this article: Bone Joint J 2024;106-B(7):688–695


Bone & Joint Open
Vol. 1, Issue 8 | Pages 508 - 511
26 Aug 2020
Morris JA Super J Huntley D Ashdown T Harland W Anakwe R

Aim. Restarting elective services presents a challenge to restore and improve many of the planned patient care pathways which have been suspended during the response to the COVID-19 pandemic. A significant backlog of planned elective work has built up representing a considerable volume of patient need. We aimed to investigate the health status, quality of life, and the impact of delay for patients whose referrals and treatment for symptomatic joint arthritis had been delayed as a result of the response to COVID-19. Methods. We interviewed 111 patients referred to our elective outpatient service and whose first appointments had been cancelled as a result of the response to the COVID-19 pandemic. Results. Patients reported significant impacts on their health status and quality of life. Overall, 79 (71.2%) patients reported a further deterioration in their condition while waiting, with seven (6.3%) evaluating their health status as ‘worse than death’. Conclusions. Waiting lists are clearly not benign and how to prioritize patients, their level of need, and access to assessment and treatment must be more sophisticated than simply relying on the length of time a patient has been waiting. This paper supports the contention that patients awaiting elective joint arthroplasty report significant impacts on their quality of life and health status. This should be given appropriate weight when patients are prioritized for surgery as part of the recovery of services following the COVID-19 pandemic. Elective surgery should not be seen as optional surgery—patients do not see it in this way


Bone & Joint Open
Vol. 4, Issue 2 | Pages 72 - 78
9 Feb 2023
Kingsbury SR Smith LKK Pinedo-Villanueva R Judge A West R Wright JM Stone MH Conaghan PG

Aims

To review the evidence and reach consensus on recommendations for follow-up after total hip and knee arthroplasty.

Methods

A programme of work was conducted, including: a systematic review of the clinical and cost-effectiveness literature; analysis of routine national datasets to identify pre-, peri-, and postoperative predictors of mid-to-late term revision; prospective data analyses from 560 patients to understand how patients present for revision surgery; qualitative interviews with NHS managers and orthopaedic surgeons; and health economic modelling. Finally, a consensus meeting considered all the work and agreed the final recommendations and research areas.


Bone & Joint Open
Vol. 4, Issue 5 | Pages 357 - 362
17 May 2023
Naathan H Ilo K Berber R Matar HE Bloch B

Aims

It is common practice for patients to have postoperative blood tests after total joint replacement (TJR). However, there have been significant improvements in perioperative care with arthroplasty surgery, and a drive to reduce the length of stay (LOS) and move towards day-case TJR. We should reconsider whether this intervention is necessary for all patients.

Methods

This retrospective study included all patients who underwent a primary unilateral TJR at a single tertiary arthroplasty centre during a one-year period. Electronic medical records of 1,402 patients were reviewed for patient demographics, LOS, and American Society of Anesthesiologists (ASA) grade. Blood tests were examined to investigate the incidence of postoperative anaemia, electrolyte abnormalities, and incidence of acute kidney injury (AKI).


The Bone & Joint Journal
Vol. 99-B, Issue 12 | Pages 1603 - 1610
1 Dec 2017
Dattilo J Gittings D Sloan M Charette R Hume E Lee G

Aims

To evaluate the effectiveness of an institutionally developed algorithm for evaluation and diagnosis of prosthetic joint injection and to determine the impact of this protocol on overall hospital re-admissions.p

Patients and Methods

We retrospectively evaluated 2685 total hip arthroplasty (THA) and total knee arthroplasty (TKA) patients prior to (1263) and following (1422) the introduction of an infection detection protocol. The protocol used conservative thresholds for C-reactive protein to direct the medical attendant to aspirate the joint. The protocol incorporated a clear set of laboratory and clinical criteria that allowed a patient to be discharged home if all were met. Patients were included if they presented to our emergency department within 120 days post-operatively with concerns for swelling, pain or infection and were excluded if they had an unambiguous infection or if their chief complaint was non-orthopaedic in nature.