Using machine learning models to predict falls in hospitalised adults.

BACKGROUND: Identifying patients at high risk of falling is crucial in implementing effective fall prevention programs. While the integration of information systems is becoming more widespread in the healthcare industry, it poses a significant challenge in analysing vast amounts of data to identify factors that could enhance patient safety. OBJECTIVE: To determine fall-associated factors and develop high-performance prediction tools for at-risk patients in acute and sub-acute care services in Australia. METHODS: A retrospective study of 672,400 patients admitted to acute and sub-acute care services within a large metropolitan tertiary health service in Victoria, Australia, between January 1, 2019, and December 31, 2021. Data were obtained from four sources: the Department of Health Victorian Admitted Episodes Dataset, RiskManTM, electronic health records, and the health workforce dataset. Machine learning techniques, including Random Forest and Deep Neural Network models, were used to analyse the data, predict patient falls, and identify the most important risk factors for falls in this population. Model performance was evaluated using accuracy, F1-score, precision, recall, specificity, Matthew's correlation coefficient, and the area under the receiver operating characteristic curve (AUC). RESULTS: The deep neural network and random forest models were highly accurate in predicting hospital patient falls. The deep neural network model achieved an accuracy of 0.988 and a specificity of 0.999, while the RF achieved an accuracy of 0.989 and a specificity of 1.000. The top 20 variables impacting falls were compared across both models, and 12 common factors were identified. These factors can be broadly classified into three categories: patient-related factors, staffing-related factors, and admission-related factors. Although not all factors are modifiable, they must be considered when planning fall prevention interventions. CONCLUSION: The study demonstrated machine learning's potential to predict falls and identify key risk factors. Further validation across diverse populations and settings is essential for broader applicability.

Laryngeal amyloidosis: diagnosis, pathophysiology and management.

BACKGROUND: Laryngeal amyloidosis represents approximately 1 per cent of all benign laryngeal lesions, and can cause variable symptoms depending on anatomical location and size. Treatment ranges from observation through to endoscopic microsurgery, laser excision and laryngectomy. OBJECTIVES: To highlight the diversity of presentations, increase awareness of paediatric amyloidosis and update the reader on current management. CASE SERIES: Five cases are illustrated. Four adult patients were female, and the one child, the second youngest in the literature, was male. Amyloid deposits were identified in all laryngeal areas, including the supraglottis, glottis and subglottis. Treatment consisted of balloon dilatation, endoscopic excision, laser cruciate incision, and resection with carbon dioxide laser, a microdebrider and coblation wands. CONCLUSION: Laryngeal amyloidosis remains a rare and clinically challenging condition. Diagnosis should be considered for unusual appearing submucosal laryngeal lesions. Treatment of this disease needs to be evaluated on a case-by-case basis and managed within an appropriate multidisciplinary team.

Melioidosis in a patient with chronic rhinosinusitis.

BACKGROUND: Melioidosis is a serious infection caused by soil-dwelling Gram-negative bacillus Burkholderia pseudomallei. It is most commonly reported in Northern Australia, Southeast and Southern Asia, China, and Taiwan. METHODS: A case report and short review of the literature are presented. Presentation, diagnosis including genomic sequencing, and acute and long-term management are discussed. RESULTS: A 58-year-old female presented with chronic rhinosinusitis secondary to melioidosis. This is the third reported incidence of sinusitis secondary to melioidosis, which occurred in an otherwise well female with no risk factors and no apparent cause of exposure. Treatment involved an acute phase in which meropenem was administered parenterally for two weeks, followed by a prolonged oral course of trimethoprim-sulfamethoxazole for three months, as per recommended guidelines. CONCLUSION: In patients presenting with refractory chronic rhinosinusitis, ENT surgeons should consider the presence of unusual causative pathogens such as B pseudomallei, particularly in those with recent travel history to Northern Queensland and/or Southeast Asia.

Venous thromboembolism prophylaxis audit in two Queensland hospitals.

BACKGROUND: Venous thromboembolism (VTE) represents a major public health problem in Australia and worldwide, contributing to hundreds of thousands of deaths each year. AIM: To assess adherence to recommended guidelines in a range of clinical settings. METHODS: Retrospective, observational study of 955 medical (M), surgical (S) and orthopaedic (O) patient charts of all M, S and O patients admitted during March 2011. Patients on warfarin were excluded from the analysis. Appropriate or inappropriate prophylaxis was assessed according to high, medium and low risk stratification. Patient risk stratification for VTE, suitability of prophylaxis given, adverse events and length of stay were recorded. RESULTS: Nine hundred and thirteen eligible patients were assessed, 54% male, mean age 57 ± 21 years. Regarding the 372 M patients, 235 (63%) were on appropriate prophylaxis, compared with 84% (273/326) S and 78% (168/215) O patients (M to S, P < 0.0001; M to O, P = 0.0002; S to O, P = 0.113). High risk prevalence was 56% in M, 9% in S and 12% in O patients (P < 0.0001). Nine confirmed or possible VTE events occurred (seven M, with five of these on inappropriate prophylaxis). All three bleeding events (one fatal) were in M patients, two of whom had appropriate prophylaxis. Average length of stay was 4.1 ± 5.0, 2.1 ± 3.3 and 2.1 ± 3.8 days (P < 0.001) for M, S and O patients respectively. CONCLUSION: Better adherence to prophylaxis guidelines is required, especially in M patients where the prevalence of high-risk VTE is greater.