AOAlexander Neergaard Olesen

Alexander Neergaard Olesen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alexander Neergaard Olesen has a total of 105 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    High-resolution sleep fragmentation assessment in narcolepsy type 1 and their non-narcoleptic siblings: a 5-s mini-epoch study

    by Louise Frøstrup Follin, Rannveig Viste, Janita Vevelstad, Kristin Langdalen, Berit Hjelde Hansen, Ragnhild Kristine Berling Grande, Tobias Kaufmann, Julie Anja Engelhard Christensen, Alexander Neergaard Zahid, Marte Kathrine Viken, et al.

    Study Objectives: Narcolepsy type 1 (NT1) is characterized by fragmented sleep, yet brief transitions may be concealed in traditional 30-s epochs. We therefore aimed to assess sleep fragmentation in NT1 patients and their non-narcoleptic siblings using 5-s mini-epochs. Methods: We analyzed sleep stages from human-scored 30-s epochs and automatically (U-Sleep) scored 5-s mini-epochs in polysomnographies from 125 NT1 patients and their 100 non-narcoleptic siblings. Sleep fragmentation was quantified using transition indices and probabilities in epochs and mini-epochs, furthermore, stratified by 1st and 2nd night-half. Predictors (H1N1-vaccination, CSF hypocretin-1 deficiency severity (low [40–150 pg/mL]; undetectable [<40 pg/mL]), HLA-DQB1*06:02-positivity, narcolepsy core symptom severity) for sleep transitions were explored. Results: NT1 patients had significantly higher all-stages and sleep–wake transition indices compared to siblings in epochs and mini-epochs. Both epoch and mini-epoch transition indices varied significantly from 1st to 2nd night-half. Only in mini-epochs, sleep–wake fragmentation was (a) higher in patients with severe core symptoms, and (b) increased in the 2nd night-half in NT1 patients with severe hypocretin-1 deficiency (<40 pg/mL) and/or severe core symptoms. Conclusions: Our findings suggest that sleep fragmentation, a core feature of NT1, is associated with disease severity and hypocretin deficiency severity when high-resolution sleep stages are analyzed. Five-second sleep staging and split-night analyses enhance detection of sleep instability and reveal new specific patterns and clinical associations. Automated mini-epoch analyses may improve future NT1 phenotyping and possibly its borderland by supplementing with clinically relevant high-resolution features otherwise hidden in traditional full-night 30-s epoch analyses. Statement of Significance This study demonstrates that high-resolution 5-s sleep staging provides more detailed sleep characterization than epochs and additionally uncovers clinically relevant sleep fragmentation patterns in narcolepsy type 1 which remain hidden in traditional 30-s analyses. By combining 5-s mini-epoch scoring with split-night analyses, we identified specific associations between disease severity and increased sleep–wake fragmentation. In mini-epochs, but not in epochs, sleep–wake fragmentation was significantly higher in patients with all core narcolepsy symptoms and increased significantly from the 1st to the 2nd night-half in patients with undetectable hypocretin-1 levels (<40 pg/mL) and/or all core narcolepsy symptoms. These findings highlight the clinical value of high-resolution, temporally sensitive sleep stage analyses for detailed phenotyping and detection of future disease biomarkers.


  • Open Access

    Optimizing automated sleep stage scoring of 5-s mini-epochs: a transfer learning study

    by Louise Frøstrup Follin, Julie Anja Engelhard Christensen, Janita Vevelstad, Hilde T Juvodden, Rannveig Viste, Berit Hjelde Hansen, Mathias Perslev, Tobias Kaufmann, Alexander Neergaard Zahid, Stine Knudsen-Heier

    Study Objectives: Conventional sleep staging relies on 30-s epochs, potentially concealing transient sleep stage intrusion and reducing precision. Building on our previous study of mini-epochs, we investigated whether U-Sleep, an existing automatic deep learning-based sleep staging model with high performance in epochs, could be optimized to similar performance level in 5-s mini-epoch scoring, thereby enabling more detailed sleep characterization. Methods: We created a dataset of 48 000 human-scored 5-s mini-epochs from 100 polysomnographies. We compared mini-epochs to human-scored epochs before U-Sleep was optimized using transfer learning and evaluated on a test set. Model performance was assessed using F1-scores, confusion matrices, stage distributions and transition rates comparing scorings of the original U-Sleep before, and the optimized U-Sleep after transfer learning to human-scored mini-epochs. Results: Compared to human-scored epochs, human-scored mini-epochs captured significantly more transitions (1.70/min vs. 0.21/min, p < .001), and significantly more wake (8.4 per cent vs. 5.4 per cent), N1 (7.2 per cent vs. 5.4 per cent), and N2 (51.8 per cent vs. 40.9 per cent), less N3 (15.4 per cent vs. 25.2 per cent), and REM sleep (16.7 per cent vs. 23.0 per cent) (all p < .001). Optimizing U-Sleep improved its performance significantly from F1 = 0.74 to F1 = 0.81 (p < .05) and gave increased transition rates in the test set (original U-Sleep: 1.06/min, optimized U-Sleep: 1.34/min, human-scored mini-epochs: 1.70/min). Stage distributions did not differ between optimized U-Sleep’s scorings and human-scored mini-epochs. Conclusion: After optimization, U-Sleep performance in mini-epochs matched the high performance levels previously reported in both human and automated 30-s epoch scoring. This demonstrates the feasibility of precise, automated high-resolution sleep staging. Future work should include external validation and application to full-night recordings. Statement of Significance Conventional 30-s epochs limit temporal resolution in sleep staging and may conceal transient intrusions of wake or sleep stages. However, no validated methods are available for high-resolution scoring. In this study, we trained and validated the state-of-the-art deep learning model U-Sleep for accurate automatic 5-s mini-epoch scoring using a large dataset of human-scored mini-epochs. The optimized model achieved a high performance, matching levels from previously reported automatic and human epoch scoring. Compared to epoch scoring, mini-epochs captured significantly more stage transitions, supporting their ability to uncover sleep dynamics that are otherwise lost. Our findings show the potential of high-resolution sleep staging for more detailed characterization of sleep architecture and demonstrate the feasibility of precise, automatic mini-epoch scoring.


  • Open Access

    Optimizing automated sleep stage scoring of 5-second mini-epochs: a transfer learning study

    by Louise Frøstrup Follin, Julie Anja Engelhard Christensen, Janita Vevelstad, Hilde T. Juvodden, Rannveig Viste, Berit Hjelde Hansen, Mathias Perslev, Tobias Kaufmann, Al-Exander Neergaard Zahid, Stine Knudsen-Heier

    Study objective: Conventional sleep staging relies on 30-second epochs, potentially concealing transient sleep stage intrusion and reducing precision. Building on our previous study of mini-epochs, we investigated whether U-Sleep, an existing automatic deep learning-based sleep staging model with high performance in epochs, could be optimized to similar performance level in 5-second mini-epoch scoring, thereby enabling more detailed sleep characterization. Methods: We created a dataset of 48,000 human-scored 5-second mini-epochs from 100 PSGs. We compared mini-epochs to human-scored epochs before U-Sleep was optimized using transfer learning and evaluated on a test set. Model performance was assessed using F1-scores, confusion matrices, stage distributions and transition rates comparing scorings of the original U-Sleep before, and the optimized U-Sleep after transfer learning to human-scored mini-epochs. Results: Compared to human-scored epochs, human-scored mini-epochs captured significantly more transitions (1.70/minute vs. 0.21/minute, p<0.001), and significantly more wake (8.4% versus 5.4%), N1 (7.2% versus 5.4%), and N2 (51.8% versus 40.9%), less N3 (15.4% versus 25.2%) and REM sleep (16.7% versus 23.0%) (all p<0.001). Optimizing U-Sleep improved its performance significantly from F1=0.74 to F1=0.81 (p<0.05) and gave increased transition rates in the test set (original U-Sleep: 1.06/minute, optimized U-Sleep: 1.34/minute, human-scored miniepochs: 1.70/minute). Stage distributions did not differ between optimized U-Sleep’s scorings and human-scored mini-epochs. Conclusions: After optimization, U-Sleep performance in mini-epochs matched the high performance levels previously reported in both human and automated 30-second epoch scoring. This demonstrates the feasibility of precise, automated high resolution sleep staging. Future work should include external validation and application to full-night recordings. Statement of significance: Conventional 30-second epochs limit temporal resolution in sleep staging and may conceal transient intrusions of wake or sleep stages. However, no validated methods are available for highresolution scoring. In this study, we trained and validated the state-of-the-art deep learning model U-Sleep for accurate automatic 5-second mini-epoch scoring using a large dataset of humanscored mini-epochs. The optimized model achieved a high performance, matching levels from previously reported automatic and human epoch scoring. Compared to epoch scoring, miniepochs captured significantly more stage transitions, supporting their ability to uncover sleep dynamics that are otherwise lost. Our findings show the potential of high-resolution sleep staging for more detailed characterization of sleep architecture and demonstrate the feasibility of precise, automatic mini-epoch scoring.


  • Open Access

    Probability estimation of narcolepsy type 1 in DTA mice using unlabeled EEG and EMG data

    by Laura Rose, Alexander Neergaard Zahid, Louise Piilgaard, Christine Egebjerg, Frederikke Lynge Sørensen, Mie Andersen, Tessa Radovanovic, Anastasia Tsopanidou, Stefano Bastianini, Chiara Berteotti, et al.

    The manual evaluation of mouse sleep studies is labor-intensive and time-consuming. Although several approaches for automatic sleep stage classification have been proposed, no automatic pipeline for detecting a specific mouse phenotype has yet been developed. Here, we present a fully automated pipeline for estimating the probability of Narcolepsy Type 1 (NT1) in the hypocretin-tTA;TetO-Diphteria toxin A (DTA) mouse model using unlabeled electroencephalographic (EEG) and electromyographic (EMG) data. The pipeline is divided into three modules: (1) automatic sleep stage classification, (2) feature extraction, and (3) phenotype classification. We trained two automatic sleep stage classifiers, UsleepEEG and UsleepEMG, using data from 83 wild-type (WT) mice. We next computed features such as EEG spectral power bands, EMG root mean square, and bout metrics from 11 WT and 19 DTA mice. The features were used to train an L1-penalized logistic regression classifier in a Leave-One-Subject-Out approach, achieving an accuracy of 97%. Finally, we validated the pipeline in a held-out dataset of EEG/EMG recordings at four different timepoints during disease development in seven DTA mice, finding that the pipeline captured disease progression in all mice. While our pipeline generalizes well to data from other laboratories, it is sensitive to artifacts, which should be considered in its application. With this study, we present a pipeline that facilitates a fast assessment of NT1 probability in the DTA model and thus can accelerate large-scale evaluations of NT1 treatments.


  • Open Access

    MSED: a multi-modal sleep event detection model for clinical sleep analysis

    by Alexander Neergaard Olesen, Poul Jennum, Emmanuel Mignot, Helge B. D. Sorensen

    Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. However, several studies have shown significant variability in manual scoring of clinically relevant discrete sleep events, such as arousals, leg movements, and sleep disordered breathing (apneas and hypopneas). We investigated whether an automatic method could be used for event detection and if a model trained on all events (joint model) performed better than corresponding event-specific models (single-event models). We trained a deep neural network event detection model on 1653 individual recordings and tested the optimized model on 1000 separate hold-out recordings. F1 scores for the optimized joint detection model were 0.70, 0.63, and 0.62 for arousals, leg movements, and sleep disordered breathing, respectively, compared to 0.65, 0.61, and 0.60 for the optimized single-event models. Index values computed from detected events correlated positively with manual annotations ($r^2$ = 0.73, $r^2$ = 0.77, $r^2$ = 0.78, respectively). We furthermore quantified model accuracy based on temporal difference metrics, which improved overall by using the joint model compared to single-event models. Our automatic model jointly detects arousals, leg movements and sleep disordered breathing events with high correlation with human annotations. Finally, we benchmark against previous state-of-the-art multi-event detection models and found an overall increase in F1 score with our proposed model despite a 97.5% reduction in model size. Source code for training and inference is available at https://github.com/neergaard/msed.git.

  • Open Access

    MSED: A Multi-Modal Sleep Event Detection Model for Clinical Sleep Analysis

    by Alexander Neergaard Zahid, Poul Jennum, Emmanuel Mignot, Helge B. D. Sorensen

    Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. However, several studies have shown significant variability in manual scoring of clinically relevant discrete sleep events, such as arousals, leg movements, and sleep disordered breathing (apneas and hypopneas). We investigated whether an automatic method could be used for event detection and if a model trained on all events (joint model) performed better than corresponding event-specific models (single-event models). We trained a deep neural network event detection model on 1653 individual recordings and tested the optimized model on 1000 separate hold-out recordings. F1 scores for the optimized joint detection model were 0.70, 0.63, and 0.62 for arousals, leg movements, and sleep disordered breathing, respectively, compared to 0.65, 0.61, and 0.60 for the optimized single-event models. Index values computed from detected events correlated positively with manual annotations (r 2 = 0.73, r 2 = 0.77, r 2 = 0.78, respectively). We furthermore quantified model accuracy based on temporal difference metrics, which improved overall by using the joint model compared to single-event models. Our automatic model jointly detects arousals, leg movements and sleep disordered breathing events with high correlation with human annotations. Finally, we benchmark against previous state-of-the-art multi-event detection models and found an overall increase in F1 score with our proposed model despite a 97.5% reduction in model size. Source code for training and inference is available at https://github.com/neergaard/msed.git


  • Open Access

    Automatic sleep stage classification with deep residual networks in a mixed-cohort setting

    by Alexander Neergaard Olesen, Poul Jørgen Jennum, Emmanuel Mignot, Helge Bjarup Dissing Sorensen

    Study Objectives: Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts. Methods: A deep neural network model was developed using 15,684 polysomnography studies from five different cohorts. We applied four different scenarios: (1) impact of varying timescales in the model; (2) performance of a single cohort on other cohorts of smaller, greater, or equal size relative to the performance of other cohorts on a single cohort; (3) varying the fraction of mixed-cohort training data compared with using single-origin data; and (4) comparing models trained on combinations of data from 2, 3, and 4 cohorts. Results: Overall classification accuracy improved with increasing fractions of training data (0.25%: 0.782 ± 0.097, 95% CI [0.777–0.787]; 100%: 0.869 ± 0.064, 95% CI [0.864–0.872]), and with increasing number of data sources (2: 0.788 ± 0.102, 95% CI [0.787–0.790]; 3: 0.808 ± 0.092, 95% CI [0.807–0.810]; 4: 0.821 ± 0.085, 95% CI [0.819–0.823]). Different cohorts show varying levels of generalization to other cohorts. Conclusions: Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.


  • Open Access

    Automatic sleep stage classification with deep residual networks in a mixed-cohort setting

    by Alexander Neergaard Olesen, Poul Jennum, Emmanuel Mignot, Helge B D Sorensen

    Study Objectives: Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts. Methods: A deep neural network model was developed using 15684 polysomnography studies from five different cohorts. We applied four different scenarios: 1) impact of varying time-scales in the model; 2) performance of a single cohort on other cohorts of smaller, greater or equal size relative to the performance of other cohorts on a single cohort; 3) varying the fraction of mixed-cohort training data compared to using single-origin data; and 4) comparing models trained on combinations of data from 2, 3, and 4 cohorts. Results: Overall classification accuracy improved with increasing fractions of training data (0.25$\%$: 0.782 $\pm$ 0.097, 95$\%$ CI [0.777-0.787]; 100$\%$: 0.869 $\pm$ 0.064, 95$\%$ CI [0.864-0.872]), and with increasing number of data sources (2: 0.788 $\pm$ 0.102, 95$\%$ CI [0.787-0.790]; 3: 0.808 $\pm$ 0.092, 95$\%$ CI [0.807-0.810]; 4: 0.821 $\pm$ 0.085, 95$\%$ CI [0.819-0.823]). Different cohorts show varying levels of generalization to other cohorts. Conclusions: Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.

  • Deep transfer learning for improving single-EEG arousal detection

    by Alexander Neergaard Olesen, Poul Jennum, Emmanuel Mignot, Helge B. D. Sorensen

    Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.


  • Open Access

    Deep transfer learning for improving single-EEG arousal detection

    by Alexander Neergaard Olesen, Poul Jennum, Emmanuel Mignot, Helge B. D. Sorensen

    Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.