Friedreich's ataxia (FRDA) is the most common early onset inherited ataxia with clinical manifestations, including gradual progression of unremitting cerebellar-sensory ataxia, peripheral sensory loss, loss of lower limb tendon reflexes and hypertrophic cardiomyopathy. Although atrophy of the superior cerebellar peduncle (SCP) has been reported in several magnetic resonance imaging (MRI) studies of FRDA, the relationship of SCP changes to genetic and clinical features of FRDA has not been investigated. We acquired T1-weighted MRI scans in 12 right-handed individuals with FRDA, homozygous for a GAA expansion in intron 1 of FXN, as well as 13 healthy age-matched controls. The corrected cross-sectional areas of the right (left) SCP in the individuals with FRDA (R, 20 ± 7.9 mm(2); L, 25 ± 5.6 mm(2)) were significantly smaller than for controls (R, 68 ± 16 mm(2); L, 78 ± 17 mm(2)) (p < 0.001). The SCP volumes of individuals with FRDA were negatively correlated with Friedreich's ataxia rating scale score (r = -0.553) and disease duration (r = -0.541), and positively correlated with the age of onset (r = 0.548) (p < 0.05). These findings suggest that structural MR imaging of the SCP can provide a surrogate marker of disease severity in FRDA and support the potential role of structural MRI as a biomarker in the evaluation of neurodegenerative diseases and therapies.

Objective To demonstrate the potential of machine learning and capability of natural language processing (NLP) to predict disposition of patients based on triage notes in the ED. Methods A retrospective cohort of ED triage notes from St Vincent's Hospital (Melbourne) was used to develop a deep‐learning algorithm that predicts patient disposition. Bidirectional Encoder Representations from Transformers, a recent language representation model developed by Google, was utilised for NLP. Eighty percent of the dataset was used for training the model and 20% was used to test the algorithm performance. Ktrain library, a wrapper for TensorFlow Keras, was employed to develop the model. Results The accuracy of the algorithm was 83% and the area under the curve was 0.88. Sensitivity, specificity, precision and F1‐score of the algorithm were 72%, 86%, 56% and 63%, respectively. Conclusion Machine learning and NLP can be together applied to the ED triage note to predict patient disposition with a high level of accuracy. The algorithm can potentially assist ED clinicians in early identification of patients requiring admission by mitigating the cognitive load, thus optimises resource allocation in EDs.

No abstract