Detection of EEG burst-suppression in neurocritical care patients using an unsupervised machine learning algorithm.

OBJECTIVE: The burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of various etiologies, as with hypoxia, drug related intoxication or deep anesthesia. The detection of bursts and the calculation of burst/suppression ratio are often used to monitor the level of anesthesia during treatment of status epilepticus. However, manual counting of bursts is a laborious process open to inter-rater variation and motivates a need for automatic detection. METHODS: We describe a novel unsupervised learning algorithm that detects bursts in EEG and generates burst-per-minute estimates for the purpose of monitoring sedation level in an intensive care unit (ICU). We validated the algorithm on 29 hours of burst annotated EEG data from 29 patients suffering from status epilepticus and hemorrhage. RESULTS: We report competitive results in comparison to neural networks learned via supervised learning. The mean absolute error (SD) in bursts per minute was 0.93 (1.38). CONCLUSION: We present a novel burst suppression detection algorithm that adapts to each patient individually, reports bursts-per-minute quickly, and does not require manual fine-tuning unlike previous approaches to burst-suppression pattern detection. SIGNIFICANCE: Our algorithm for automatic burst suppression quantification can greatly reduce manual oversight in depth of sedation monitoring.

Optimising equity of access: how should we allocate slots to the most competitive trials in Cystic Fibrosis (CF)?

BACKGROUND: Trial participation can allow people with CF early access to CFTR modulator therapies, with high potential for clinical benefit. Therefore, the number of people wishing to participate can substantially exceed the number of slots available. We aimed to understand how the CF community thinks slots to competitive trials should be allocated across the UK and whether this should be driven by clinical need, patients' engagement/adherence or be random. For the latter, we explored site-level versus registry-based, national randomisation processes. METHODS: We developed an online survey, recruiting UK-based stakeholders through social media, newsletters and personal contacts. Closed questions were analysed for frequencies and percentages of responses. Free-text questions were analysed using thematic analysis. RESULTS: We received 203 eligible responses. Overall, 75% of stakeholders favoured allocation of slots to individual sites based on patient population size, although pharma favoured allocation based on previous metrics. Currently, few centres have defined strategies for allocating slots locally. At face-value, stakeholders believe all eligible participants should have an equal chance of getting a slot. However, further questioning reveals preference for prioritisation strategies, primarily perceived treatment adherence, although healthcare professionals were less likely to favour this strategy than other stakeholder groups. The majority of stakeholders would prefer to allocate slots and participate in trials locally but 80% said if necessary, they would engage in a system of national allocation. CONCLUSIONS: Fair allocation to highly competitive trials does not appear to have a universally acceptable solution. Therefore, transparency and empathy remain critical to negotiate this uncertain territory.

Optimism as an indicator of psychological health: using psychological assessment wisely.

Healthy aspects of psychological functioning are often overlooked in traditional psychological assessment. When this happens, the client may become discouraged with his or her testing results, or perhaps worse, may feel that the assessor was not interested in obtaining a complete picture of who he or she is. Assessing healthy aspects of psychological functioning can be problematic, however; adding new instruments that only speak to one aspect of psychological functioning is not practical. A system is proposed in which one aspect of healthy psychological functioning--optimism--can be assessed using a standard projective test. Use of this scale can aid the assessor in conceptualizing the client's functioning and can also be a helpful tool to draw on in the course of treatment.