Search

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. [ABSTRACT FROM AUTHOR]

This article discusses the opportunities, challenges, and recommendations for the use of artificial intelligence (AI) in surgical services in Australia and New Zealand. The implementation of AI must be evidence-based, safe, and ethically cautious, and should serve as an adjunct to surgical staff rather than a replacement. The article highlights the need for greater engagement with non-surgical healthcare communities and the wider society, as well as the importance of developing guidelines and infrastructure for monitoring and auditing AI tools. Ethical considerations, such as bias in training data and the lack of transparency in AI decision-making processes, must also be addressed. The article concludes with recommendations for the future use of AI in surgical services, emphasizing the need for an evidence-based approach, close engagement with regulatory bodies, and education for surgical staff and patients. [Extracted from the article]

Regulation, particularly relating to intellectual property and commercial considerations are relatively unexplored, particularly when artificial intelligence algorithms are being implemented within public healthcare systems. Accordingly, a stepwise and rigorous process is required to demonstrate that artificial intelligence algorithms improve patient outcomes. As more artificial intelligence algorithms near clinical implementation, regulatory authorities and professional colleges and societies must carefully consider how these algorithms are evaluated. However, the regulation of the use of clinical artificial intelligence algorithms will be inherently related to evidenced generated through artificial intelligence clinical trials. [Extracted from the article]

Epilepsy due to encephaloceles of the temporal pole may be an under recognized, treatable cause of refractory temporal lobe epilepsy (TLE). We describe three adult patients initially labeled 'lesion negative' TLE. In all, video-electroencephalography (EEG) revealed ictal theta in the left temporal region and positron emission tomography (PET) showed temporal lobe hypometabolism, but neuropsychology revealed preserved verbal memory. Close inspection of structural magnetic resonance imaging (MRI) suggested subtle abnormalities at the tip of the left temporal lobe. High resolution computed tomography (CT) confirmed bony defects in the inner table of the skull. 3T MRI with fine coronal and sagittal slices indicated cerebrospinal fluid (CSF) and brain tissue protruding into the defects. All proceeded to resection of the temporal tip and became seizure free. Patients with 'lesion negative' TLE should have careful review of images covering the temporal pole. If encephalocele is suspected, further imaging with high-resolution CT and MRI can be helpful. Temporal polar resection, sparing mesial structures, appears to be curative. [ABSTRACT FROM AUTHOR]