Model-driven survival prediction after congenital heart surgery.

OBJECTIVES: The objective of the study was to improve postoperative risk assessment in congenital heart surgery by developing a machine-learning model based on readily available peri- and postoperative parameters. METHODS: Our bicentric retrospective data analysis from January 2014 to December 2019 of established risk parameters for dismal outcome was used to train and test a model to predict postoperative survival within the first 30 days. The Freiburg training data consisted of 780 procedures; the Heidelberg test data comprised 985 procedures. STAT mortality score, age, aortic cross-clamp time and postoperative lactate values over 24 h were considered. RESULTS: Our model showed an area under the curve (AUC) of 94.86%, specificity of 89.48% and sensitivity of 85.00%, resulting in 3 false negatives and 99 false positives.The STAT mortality score and the aortic cross-clamp time each showed a statistically highly significant impact on postoperative mortality. Interestingly, a child's age was barely statistically significant. Postoperative lactate values indicated an increased mortality risk if they were either constantly at a high level or low during the first 8 h postoperatively with an increase afterwards.When considering parameters available before, at the end of and 24 h after surgery, the predictive power of the complete model achieved the highest AUC. This, compared to the already high predictive power alone (AUC 88.9%) of the STAT mortality score, translates to an error reduction of 53.5%. CONCLUSIONS: Our model predicts postoperative survival after congenital heart surgery with great accuracy. Compared with preoperative risk assessments, our postoperative risk assessment reduces prediction error by half. Heightened awareness of high-risk patients should improve preventive measures and thus patient safety.

Risk Assessment of Red Cell Transfusion in Congenital Heart Disease.

BACKGROUND: The storage time of packed red blood cells (pRBC) is an indicator of change in the product's pH, potassium, and lactate levels. Blood-gas analysis is a readily available bedside tool on every intensive care ward to measure these factors prior to application, thus facilitating a calculated decision on a transfusion's quantity and duration.Our first goal is to assess the impact of storage time on pH, potassium, and lactate levels in pRBC. The influence of those parameters in the transfused children will then be evaluated. METHODS: In this retrospective study, we conducted blood-gas analyses of pRBC units before they were administered over 4 hours to neonates, infants, and children in our pediatric cardiac intensive care ward. All patients underwent regular blood-gas analyses themselves, before and after transfusion. RESULTS: We observed a highly significant correlation between the storage time of pRBC units and a drop in pH, as well as an increase in potassium and lactate of stored red cells (p< 0.0001). Median age of recipients with a complete blood-gas dataset was 0.1 (interquartile range [IQR] = 0.0-0.7) years; median pRBC storage duration was 6 (IQR = 5-8) days. Further analyses showed no statistically significant effect on children's blood gases within 4 hours after transfusion, even after stratifying for pRBC storage time ≤7 days and >7 days. CONCLUSION: Stored red blood cells show a rapid decrease in pH and increase in potassium and lactate. Slow transfusion of these units had no adverse effects on the recipients' pH, potassium, and lactate levels.

Aphasia recovery by language training using a brain-computer interface: a proof-of-concept study.

Aphasia, the impairment to understand or produce language, is a frequent disorder after stroke with devastating effects. Conventional speech and language therapy include each formal intervention for improving language and communication abilities. In the chronic stage after stroke, it is effective compared with no treatment, but its effect size is small. We present a new language training approach for the rehabilitation of patients with aphasia based on a brain-computer interface system. The approach exploits its capacity to provide feedback time-locked to a brain state. Thus, it implements the idea that reinforcing an appropriate language processing strategy may induce beneficial brain plasticity. In our approach, patients perform a simple auditory target word detection task whilst their EEG was recorded. The constant decoding of these signals by machine learning models generates an individual and immediate brain-state-dependent feedback. It indicates to patients how well they accomplish the task during a training session, even if they are unable to speak. Results obtained from a proof-of-concept study with 10 stroke patients with mild to severe chronic aphasia (age range: 38-76 years) are remarkable. First, we found that the high-intensity training (30 h, 4 days per week) was feasible, despite a high-word presentation speed and unfavourable stroke-induced EEG signal characteristics. Second, the training induced a sustained recovery of aphasia, which generalized to multiple language aspects beyond the trained task. Specifically, all tested language assessments (Aachen Aphasia Test, Snodgrass & Vanderwart, Communicative Activity Log) showed significant medium to large improvements between pre- and post-training, with a standardized mean difference of 0.63 obtained for the Aachen Aphasia Test, and five patients categorized as non-aphasic at post-training assessment. Third, our data show that these language improvements were accompanied neither by significant changes in attention skills nor non-linguistic skills. Investigating possible modes of action of this brain-computer interface-based language training, neuroimaging data (EEG and resting-state functional MRI) indicates a training-induced faster word processing, a strengthened language network and a rebalancing between the language- and default mode networks.

Two Player Online Brain-Controlled Chess.

Brain-computer interfaces (BCIs) allow for translating brain signals into control commands, e.g. to control games. One of the biggest quests of the BCI community is to realize new exciting applications. In this paper, we present a two player online chess application where both players control their pieces solely with their brain activity. Control is realized in a two-step process where players first select the desired chess piece and then the field they want to move it to. A selection is accomplished with visual event-related potentials that are elicited by highlighting each possible piece or field one by one. Six healthy volunteers participated in our study by playing a game against each other in pairs over a free chess server. They successfully completed at least one match per pair. Our results show that even BCI-naive players obtain almost perfect control over the application. On average, 96% of the moves were correct. Most of the errors came from technical problems that can be corrected in future versions of the application. Given the high popularity of chess, this intuitive BCI game is an appealing new application for patients and for healthy users that want to explore BCIs.

Eyes-Closed Increases the Usability of Brain-Computer Interfaces Based on Auditory Event-Related Potentials.

Recent research has demonstrated how brain-computer interfaces (BCI) based on auditory stimuli can be used for communication and rehabilitation. In these applications, users are commonly instructed to avoid eye movements while keeping their eyes open. This secondary task can lead to exhaustion and subjects may not succeed in suppressing eye movements. In this work, we investigate the option to use a BCI with eyes-closed. Twelve healthy subjects participated in a single electroencephalography (EEG) session where they were listening to a rapid stream of bisyllabic words while alternatively having their eyes open or closed. In addition, we assessed usability aspects for the two conditions with a questionnaire. Our analysis shows that eyes-closed does not reduce the number of eye artifacts and that event-related potential (ERP) responses and classification accuracies are comparable between both conditions. Importantly, we found that subjects expressed a significant general preference toward the eyes-closed condition and were also less tensed in that condition. Furthermore, switching between eyes-closed and eyes-open and vice versa is possible without a severe drop in classification accuracy. These findings suggest that eyes-closed should be considered as a viable alternative in auditory BCIs that might be especially useful for subjects with limited control over their eye movements.

Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees.

OBJECTIVE: Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. METHOD: We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. RESULTS: Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. SIGNIFICANCE: The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP.

Selforganizing memory: active learning of landmarks used for navigation.

We propose a memory architecture that is suited to solve a specific task, namely homing, that is finding a not directly visible home place by using visually accessible landmarks. We show that an agent equipped with such a memory structure can autonomously learn the situation and can later use its memory to accomplish homing behaviour. The architecture is based on neuronal structures and grows in a self-organized way depending on experience. The basic architecture consists of three parts, (i) a pre-processor, (ii) a simple, one-layered feed-forward network, called distributor net, and (iii) a full recurrently connected net for representing the situation models to be stored. Apart from Hebbian learning and a local version of the delta-rule, explorative learning is applied that is not based on passive detection of correlations, but is actively searching for interesting hypotheses. Hypotheses are spontaneously introduced and are verified or falsified depending on how well the network representing the hypothesis approaches an internal error of zero. The stability of this approach is successfully tested by removal of one landmark or shifting the position of one or several landmarks showing results comparable to those found in biological experiments. Furthermore, we applied noise in two ways. The trained network was either due to sensory noise or to noise applied to the bias weights describing the memory content. Finally, we tested to what extent learning of the weights is affected by noisy input given to the sensor data. The architecture proposed is discussed to have some at least superficial similarity to the mushroom bodies of insects.

Elements for a general memory structure: properties of recurrent neural networks used to form situation models.

We study how individual memory items are stored assuming that situations given in the environment can be represented in the form of synaptic-like couplings in recurrent neural networks. Previous numerical investigations have shown that specific architectures based on suppression or max units can successfully learn static or dynamic stimuli (situations). Here we provide a theoretical basis concerning the learning process convergence and the network response to a novel stimulus. We show that, besides learning "simple" static situations, a nD network can learn and replicate a sequence of up to n different vectors or frames. We find limits on the learning rate and show coupling matrices developing during training in different cases including expansion of the network into the case of nonlinear interunit coupling. Furthermore, we show that a specific coupling matrix provides low-pass-filter properties to the units, thus connecting networks constructed by static summation units with continuous-time networks. We also show under which conditions such networks can be used to perform arithmetic calculations by means of pattern completion.