Artificial intelligence (AI) has an astonishing potential in assisting clinical decision making and revolutionizing the field of health care. A major open challenge that AI will need to address before its integration in the clinical routine is that of algorithmic bias. Most AI algorithms need big datasets to learn from, but several groups of the human population have a long history of being absent or misrepresented in existing biomedical datasets. If the training data is misrepresentative of the population variability, AI is prone to reinforcing bias, which can lead to fatal outcomes, misdiagnoses, and lack of generalization. Here, we describe the challenges in rendering AI algorithms fairer, and we propose concrete steps for addressing bias using tools from the field of open science.

We report on a CMOS-based microelectrode array (MEA) featuring 11, 011 metal electrodes and 126 channels, each of which comprises recording and stimulation electronics, for extracellular bidirectional communication with electrogenic cells, such as neurons or cardiomyocytes. The important features include: (i) high spatial resolution at (sub)cellular level with 3150 electrodes per mm² (electrode diameter 7 ¿m, electrode pitch 18 ¿m); (ii) a reconflgurable routing of the recording sites to the 126 channels; and (iii) low noise levels.

Deep learning is widely used in the most recent automatic sleep scoring algorithms. Its popularity stems from its excellent performance and from its ability to process raw signals and to learn feature directly from the data. Most of the existing scoring algorithms exploit very computationally demanding architectures, due to their high number of training parameters, and process lengthy time sequences in input (up to 12 minutes). Only few of these architectures provide an estimate of the model uncertainty. In this study we propose DeepSleepNet-Lite, a simplified and lightweight scoring architecture, processing only 90-seconds EEG input sequences. We exploit, for the first time in sleep scoring, the Monte Carlo dropout technique to enhance the performance of the architecture and to also detect the uncertain instances. The evaluation is performed on a single-channel EEG Fpz-Cz from the open source Sleep-EDF expanded database. DeepSleepNet-Lite achieves slightly lower performance, if not on par, compared to the existing state-of-the-art architectures, in overall accuracy, macro F1-score and Cohen’s kappa (on Sleep-EDF v1-2013 ±30mins: 84.0%, 78.0%, 0.78; on Sleep-EDF v2-2018 ±30mins: 80.3%, 75.2%, 0.73). Monte Carlo dropout enables the estimate of the uncertain predictions. By rejecting the uncertain instances, the model achieves higher performance on both versions of the database (on Sleep-EDF v1-2013 ±30mins: 86.1.0%, 79.6%, 0.81; on Sleep-EDF v2-2018 ±30mins: 82.3%, 76.7%, 0.76). Our lighter sleep scoring approach paves the way to the application of scoring algorithms for sleep analysis in real-time.

AASM guidelines are the result of decades of efforts aiming at standardizing sleep scoring procedure, with the final goal of sharing a worldwide common methodology. The guidelines cover several aspects from the technical/digital specifications, e.g., recommended EEG derivations, to detailed sleep scoring rules accordingly to age. Automated sleep scoring systems have always largely exploited the standards as fundamental guidelines. In this context, deep learning has demonstrated better performance compared to classical machine learning. Our present work shows that a deep learning-based sleep scoring algorithm may not need to fully exploit the clinical knowledge or to strictly adhere to the AASM guidelines. Specifically, we demonstrate that U-Sleep, a state-of-the-art sleep scoring algorithm, can be strong enough to solve the scoring task even using clinically non-recommended or non-conventional derivations, and with no need to exploit information about the chronological age of the subjects. We finally strengthen a well-known finding that using data from multiple data centers always results in a better performing model compared with training on a single cohort. Indeed, we show that this latter statement is still valid even by increasing the size and the heterogeneity of the single data cohort. In all our experiments we used 28528 polysomnography studies from 13 different clinical studies.