Search

As one of the most vocal marsupials in Australia, conservation of the yellow-bellied glider (Petaurus australis brevirostrum) (YBG) could benefit from the extraction of more information from their calls during acoustic monitoring. This pilot study investigates the variability of syllable components of full calls and identifies acoustic parameters that underlie variability in recorded calls from wild YBGs in North Queensland, Australia. Full calls with three syllables and with two syllables were distinguished. Using batch correlations and principal component analyses (PCAs), it was found that syllable two and syllable three show high variability in their duration and that maximum frequency is the strongest contributing sound parameter to the observed variability. However, because data collection was done in wild populations, the identity of call emitters remained unknown during call analyses, demanding further studies. Further subdivision of calls, and investigation into further acoustic parameters, could aid in decoding sexual, seasonal and individual-based meanings of calls. In Far North Queensland, passive acoustic monitoring has been used to study the yellow-bellied glider, a species threatened by habitat loss and fragmentation. However, because this species is very vocal, it is likely that more information – related to gender, season or individual-specific parameters – can be extracted from its calls. We present an attempt to analyse acoustic parameters and their variability in components of full calls of this species as a basis for more meaningful acoustic monitoring. [ABSTRACT FROM AUTHOR]

Objectives: To examine the scale of private equity investment in Australian health care delivery assets (clinics, hospitals, imaging facilities, other doctor‐led health care services). Study design, setting: Extraction of information about private equity acquisitions of hospitals, clinics, imaging centres and in vitro fertilisation facilities in Australia, 2008–2022, from a commercial database (PitchBook), supplemented by information from publicly available online media sources. Main outcome measures: Number and value of private equity acquisitions of health care assets, 2008–2022; numbers of clinic parent company and clinic acquisitions, 2017–2022. Results: A total of 75 private equity acquisitions of health care delivery assets in Australia during 2008–2022 were identified; the annual number rose from three acquisitions in 2008 to eighteen in 2022. During 2008–2010, five of seven acquisitions were of in vitro fertilisation providers; during 2020–2022, 22 of 39 acquisitions were of clinics or clinic groups, including eleven of eighteen in 2022. The total value of the 39 acquisitions for which purchase price could be ascertained (52%) was $24.1 billion. During 2017–2022, the clinic specialty with the greatest number of private equity acquisitions was general practice (256 of 446 clinics purchased within acquisitions). Seven companies owning ophthalmology clinics (24 clinics) were acquired by private equity. Four private equity acquisitions during 2017–2022 included 60 oncology clinics, all related to a single clinic group. Conclusions: The number of private equity acquisitions of Australian health care delivery assets increased during 2008–2022. Doctors should be aware of the motivations and dynamics of private equity companies, as they are increasingly likely to interact with these firms and assets owned by these firms. [ABSTRACT FROM AUTHOR]

Objective: Epilepsy surgery is known to be underutilized. Machine learning-natural language processing (ML-NLP) may be able to assist with identifying patients suitable for referral for epilepsy surgery evaluation., Methods: Data were collected from two tertiary hospitals for patients seen in neurology outpatients for whom the diagnosis of "epilepsy" was mentioned. Individual case note review was undertaken to characterize the nature of the diagnoses discussed in these notes, and whether those with epilepsy fulfilled prespecified criteria for epilepsy surgery workup (namely focal drug refractory epilepsy without contraindications). ML-NLP algorithms were then developed using fivefold cross-validation on the first free-text clinic note for each patient to identify these criteria., Results: There were 457 notes included in the study, of which 250 patients had epilepsy. There were 37 (14.8%) individuals who fulfilled the prespecified criteria for epilepsy surgery referral without described contraindications, 32 (12.8%) of whom were not referred for epilepsy surgical evaluation in the given clinic visit. In the prediction of suitability for epilepsy surgery workup using the prespecified criteria, the tested models performed similarly. For example, the random forest model returned an area under the receiver operator characteristic curve of 0.97 (95% confidence interval 0.93-1.0) for this task, sensitivity of 1.0, and specificity of 0.93., Significance: This study has shown that there are patients in tertiary hospitals in South Australia who fulfill prespecified criteria for epilepsy surgery evaluation who may not have been referred for such evaluation. ML-NLP may assist with the identification of patients suitable for such referral., Plain Language Summary: Epilepsy surgery is a beneficial treatment for selected individuals with drug-resistant epilepsy. However, it is vastly underutilized. One reason for this underutilization is a lack of prompt referral of possible epilepsy surgery candidates to comprehensive epilepsy centers. Natural language processing, coupled with machine learning, may be able to identify possible epilepsy surgery candidates through the analysis of unstructured clinic notes. This study, conducted in two tertiary hospitals in South Australia, demonstrated that there are individuals who fulfill criteria for epilepsy surgery evaluation referral but have not yet been referred. Machine learning-natural language processing demonstrates promising results in assisting with the identification of such suitable candidates in Australia., (© 2024 The Authors. Epilepsia Open published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.)

Photovoltaic (PV) power has attracted widespread attention from many countries around the world due to its clean and renewable characteristics. To ensure the stable operation of the power system, accurate PV power forecasting has become a mandatory and challenging task. Currently, deep learning methods have become a vital approach in the field of PV power forecasting. In this work, a multistage attention neural network based on neural ordinary differential equation (MANODE) is proposed to address the main limitations of previous deep learning methods applied to PV power forecasting. Based on the neural ordinary differential equation (NODE), MANODE optimizes the long short-term memory network (LSTM) and temporal convolutional neural network (TCN), and combines the attention mechanism to achieve fine-grained spatio-temporal information extraction of PV series. In addition, the proposed MANODE model is applied to three different PV series collected from the Alice Springs meteorological station. Compared to previous state-of-the-art methods, the proposed method reduces the PV power forecasting error by at least 12.05%, 13.15%, and 9.71% on three different PV datasets, in terms of mean absolute error metric. The average errors of the MANODE method in four-hour-ahead PV power forecasting on the three datasets are 0.321, 0.350, and 0.567. • A novel neural network method called MANODE is applied in PV power forecasting. • MANODE addresses drawbacks of previous PV forecasting methods using LSTMs or CNNs. • Three multivariate datasets located in Australia are adopted in this work. • MANODE outperforms previous state-of-the-art neural network method in PV forecasting. [ABSTRACT FROM AUTHOR]

A foundation for digitally enabling healthier living is the safe development and use of technology. The practice of digital health safety has emerged from patient harm attributed to failing technologies. The study aimed to investigate how to adopt and implement digital health safety guidelines at scale. Data was collected through an online survey, semi-structured interviews, focus groups, document review, and data mining of artefacts. The findings of this study capture the emerging practice from Australia in a way that offers insights into the problem of practice, patient safety practice, safety culture, and socio-technical factors. The research findings contribute to better understanding of the complexities of balancing digital innovation with patient safety. The four recommendations from the study and the provision of a logic model will support the audience to implement actions toward a safer digital health ecology.

Identifying potentially fraudulent or wasteful medical insurance claims can be difficult due to the large amounts of data and human effort involved. We applied unsupervised machine learning to construct interpretable models which rank variations in medical provider claiming behaviour in the domain of unilateral joint replacement surgery, using data from the Australian Medicare Benefits Schedule. For each of three surgical procedures reference models of claims for each procedure were constructed and compared analytically to models of individual provider claims. Providers were ranked using a score based on fees for typical claims made in addition to those in the reference model. Evaluation of the results indicated that the top-ranked providers were likely to be unusual in their claiming patterns, with typical claims from outlying providers adding up to 192% to the cost of a procedure. The method is efficient, generalizable to other procedures and, being interpretable, integrates well into existing workflows.

Identifying and determining the multitude of reasons behind school absences of students is often challenging. This study aims to uncover the hidden reasons for school absence in children and adolescents. The analysis is conducted on a national survey that includes 2967 Australian children and adolescents aged 11-17. The Apriori association rule generator of machine learning techniques and binary logistic regression are used to identify the significant predictors of school absences. Out of 2484, 83.7% (n = 2079) aged (11-17) years children and adolescents have missed school for various reasons, 42.28% (n = 879) are (11-15) years old, 24.52% (n = 609) and 16.9% (n = 420) are 16- and 17-years old adolescents respectively. A considerable proportion of adolescents, specifically 16.4% (n = 407) and 23.4% (n = 486) of 16 and 17 years old, respectively, have selected 'refused to say' as their reason for not attending school. It also highlights the negative outcomes associated with undisclosed reasons for school absence, such as bullying, excessive internet/gaming, reduced family involvement, suicide attempts, and existential hopelessness. The findings of the national survey underscore the importance of addressing these undisclosed reasons for school absence to improve the overall well-being and educational outcomes of children and adolescents., (© 2024. The Author(s).)