Early prediction of persistent organ failure (POF) is important for triage and timely treatment of patients with acute pancreatitis (AP). All AP patients were consecutively admitted within 48 h of symptom onset. A nomogram was developed to predict POF on admission using data from a retrospective training cohort, validated by two prospective cohorts. The clinical utility of the nomogram was defined by concordance index (C-index), decision curve analysis (DCA), and clinical impact curve (CIC), while the performance by post-test probability. There were 816, 398, and 880 patients in the training, internal and external validation cohorts, respectively. Six independent predictors determined by logistic regression analysis were age, respiratory rate, albumin, lactate dehydrogenase, oxygen support, and pleural effusion and were included in the nomogram (web-based calculator: https://shina.shinyapps.io/DynNomapp/). This nomogram had reasonable predictive ability (C-indexes 0.88/0.91/0.81 for each cohort) and promising clinical utility (DCA and CIC). The nomogram had a positive likelihood ratio and post-test probability of developing POF in the training, internal and external validation cohorts of 4.26/31.7%, 7.89/39.1%, and 2.75/41%, respectively, superior or equal to other prognostic scores. This nomogram can predict POF of AP patients and should be considered for clinical practice and trial allocation.
Background: Current approaches to predicting intervention needs and mortality have reached 65–85% accuracy, which falls below clinical decision-making requirements in patients with acute pancreatitis (AP). We aimed to accurately predict therapeutic intervention needs and mortality on admission, in AP patients, using machine learning (ML). Methods: Data were obtained from three databases of patients admitted with AP: one retrospective (Chengdu) and two prospective (Liverpool and Chengdu) databases. Intervention and mortality differences, as well as potential predictors, were investigated. Univariate analysis was conducted, followed by a random forest ML algorithm used in multivariate analysis, to identify predictors. The ML performance matrix was applied to evaluate the model’s performance. Results: Three datasets of 2846 patients included 25 potential clinical predictors in the univariate analysis. The top ten identified predictors were obtained by ML models, for predicting interventions and mortality, from the training dataset. The prediction of interventions includes death in non-intervention patients, validated with high accuracy (96%/98%), the area under the receiver-operating-characteristic curve (0.90/0.98), and positive likelihood ratios (22.3/69.8), respectively. The post-test probabilities in the test set were 55.4% and 71.6%, respectively, which were considerably superior to existing prognostic scores. The ML model, for predicting mortality in intervention patients, performed better or equally with prognostic scores. Conclusions: ML, using admission clinical predictors, can accurately predict therapeutic interventions and mortality in patients with AP.
We present a case of piriformis syndrome in a woman in her 30’s following low energy trauma, presenting with unilateral lower limb weakness, altered sensation and urinary retention. CT imaging revealed a bulky piriformis muscle which was further clarified on MRI as an intramuscular haematoma within the left piriformis causing compression of the left lumbosacral plexus. Haematoma formation was exacerbated due to use of an antiplatelet medication the patient was taking for Moyamoya disease, which carries an increased risk of cerebrovascular accident. Surgical exploration of the piriformis and sciatic nerve was undertaken and confirmed a haematoma within the piriformis. A full release of the piriformis tendon was undertaken, and the sciatic nerve was inspected, no further abnormality was found. After review in clinic post-discharge, the patient reported normal sensation and normal muscle power in her feet.
A 64-year-old man was referred to A&E by his general practitioner with worsening back and acute bilateral leg pain and weakness with urinary retention. His MRI scan demonstrated spinal canal stenosis at the level of L1–L2 and a diagnosis of cauda equina syndrome (CES) was made. CES is a rare neurological condition caused by compression of the central spinal nerves at the termination of the cord. CES is a surgical emergency requiring urgent assessment and treatment. The patient underwent urgent surgical decompression; however, he required a second surgery for further decompression as repeat MRI showed persistent stenosis with further extension. Intraoperative Doppler ultrasonography revealed an intradural lesion, which was surgically excised and found to be a sequestrated lumbar disc in the intrathecal space. The patient showed significant neurological improvement post revision decompression.
A 61-year-old polytrauma patient was admitted with a right distal comminuted metaphyseal femoral fracture with intra-articular extension (Orthopaedic Trauma Association 33C2.3 classification) among other injuries. Due to the high degree of comminution and massive bone loss, this was initially managed with a dual plating open reduction internal fixation. Dual plating has shown to be a superior fixation method than single variable angle locking compression plate (VA-LCP) plating providing greater fixation in metaphyseal bone. Our case reports the failure of dual plating which required removal of metalwork and subsequent fixation using intramedullary nail and plate technique. Failure of dual plating is not well documented in the literature. The most recent radiographs taken 15 months postrevision surgery show that the bone has started to heal with evidence of callus formation.