Search

Purpose: Patient-reported outcome measures (PROMs) are important measures of success after total knee arthroplasty (TKA) and being able to predict their improvements could enhance preoperative decision-making. Our study aims to compare the predictive performance of machine learning (ML) algorithms and preoperative PROM thresholds in predicting minimal clinically important difference (MCID) attainment at 2 years after TKA. Methods: Prospectively collected data of 2840 primary TKA performed between 2008 and 2018 was extracted from our joint replacement registry and split into a training set (80%) and test set (20%). Using the training set, ML algorithms were developed using patient demographics, comorbidities and preoperative PROMs, whereas the optimal preoperative threshold was determined using ROC analysis. Both methods were used to predict MCID attainment for the SF-36 PCS, MCS and WOMAC at 2 years postoperatively, with predictive performance evaluated on the independent test set. Results: ML algorithms and preoperative PROM models performed similarly in predicting MCID for the SF-36 PCS (AUC: 0.77 vs 0.74), MCS (AUC: 0.95 vs 0.95) and WOMAC (AUC: 0.89 vs 0.88). For each outcome, the most important predictor of MCID attainment was the patient's preoperative PROM score. ROC analysis also identified optimal preoperative threshold values of 33.6, 54.1 and 72.7 for the SF-36 PCS, MCS and WOMAC, respectively. Conclusion: ML algorithms did not perform significantly better than preoperative PROM thresholds in predicting MCID attainment after TKA. Future research should routinely compare the predictive ability of ML algorithms with existing methods and determine the type of clinical problems which may benefit the most from it. Level of evidence: II. [ABSTRACT FROM AUTHOR]

Purpose: Evidence guiding the use of CT and MRI scans in blunt trauma patients who are obtunded remains controversial. This study aims to determine and predict if computed tomography (CT) scans alone can be performed without risking oversight of substantial injuries found on follow-up magnetic resonance imaging (MRI).Methods: This is a retrospective cohort study of 63 blunt trauma patients with a Glasgow Coma Scale of < 8. Data were collated from electronic medical records and included patient demographics, premorbid mobility, mechanism of injury, suspected level of injury and neurological examination findings. Patients were urgently evaluated using CT scans, followed by non-contrast MRI scans within 48 h of admission. The accuracy of CT scan was evaluated using MRI as a reference. Adjusted multivariable analysis was also performed to identify predictors for findings detected on MRI but not on CT.Results: The mean age of patients was 42.3 years and 90.5% were males. CT scans had a high specificity of 100% and sensitivity of 87.2%. Predictors of MRI abnormalities include females, patients with relatively milder mechanisms of injury, patients with suspected thoracic spine injury, and CT scan findings of facet dislocation and intracranial haemorrhage. There was no predictor for spinal cord oedema.Conclusions: MRI should be performed in the presence of the aforementioned predictive factors and in the presence of neurological deficits. Otherwise, patients can be treated medically without the fear of missing a substantial cervical injury. [ABSTRACT FROM AUTHOR]

The pattern of psychiatric consultation in Hong Kong is examined among 226 patients at a public outpatient clinic and 56 patients at a private psychiatric clinic. The approach to psychiatric services is marked by lengthy delay during which patients get help from their family members or close friends. Arrival at the present psychiatric clinic was diverted through other medical resources, primarily Western-style medical services, and to some extent, traditional Chinese medicine. Individual routes were diverse, characterized by frequent switches among resources especially in the private sector. The nature of the patients' presenting complaints as well as the conceptualization of their initial complaints were multi-faceted, including both psychological and somatic factors. The overall consultation pattern of patients in Hong Kong is compared with other studies on Chinese and Western patients. Questions are raised for further analysis. [ABSTRACT FROM AUTHOR]