@inbook{
 type = {inbook},
 year = {2023},
 pages = {395-411},
 publisher = {Springer International Publishing},
 city = {Cham},
 series = {Studies in Neuroscience, Psychology and Behavioral Economics},
 id = {c5c11669-885b-3da4-a86c-0e85e8fe2086},
 created = {2022-09-04T18:02:17.819Z},
 file_attached = {false},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-20T07:21:12.321Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Garatva2023},
 source_type = {inbook},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34},
 private_publication = {false},
 bibtype = {inbook},
 author = {Garatva, Patricia and Terhorst, Yannik and Meßner, Eva-Maria and Karlen, Walter and Pryss, Rüdiger and Baumeister, Harald},
 editor = {Montag, Christian and Baumeister, Harald},
 doi = {10.1007/978-3-030-98546-2_23},
 chapter = {Smart Sensors for Health Research and Improvement},
 title = {Digital Phenotyping and Mobile Sensing}
}

@article{
 title = {Auditory deep sleep stimulation in older adults at home: a randomized crossover trial},
 type = {article},
 year = {2022},
 pages = {30},
 volume = {2},
 websites = {https://www.nature.com/articles/s43856-022-00096-6},
 month = {12},
 publisher = {Springer US},
 day = {4},
 id = {932c108d-46e6-3566-98aa-5cbd9aeef910},
 created = {2022-06-13T22:57:57.941Z},
 file_attached = {true},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:12.637Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Lustenberger2022},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34,470e1c72-5ded-4e47-a429-6f5172e01dcb},
 private_publication = {false},
 abstract = {Auditory stimulation has emerged as a promising tool to enhance non-invasively sleep slow waves, deep sleep brain oscillations that are tightly linked to sleep restoration and are diminished with age. While auditory stimulation showed a beneficial effect in lab-based studies, it remains unclear whether this stimulation approach could translate to real-life settings. We present a fully remote, randomized, cross-over trial in healthy adults aged 62–78 years (clinicaltrials.gov: NCT03420677). We assessed slow wave activity as the primary outcome and sleep architecture and daily functions, e.g., vigilance and mood as secondary outcomes, after a two-week mobile auditory slow wave stimulation period and a two-week Sham period, interleaved with a two-week washout period. Participants were randomized in terms of which intervention condition will take place first using a blocked design to guarantee balance. Participants and experimenters performing the assessments were blinded to the condition. Out of 33 enrolled and screened participants, we report data of 16 participants that received identical intervention. We demonstrate a robust and significant enhancement of slow wave activity on the group-level based on two different auditory stimulation approaches with minor effects on sleep architecture and daily functions. We further highlight the existence of pronounced inter- and intra-individual differences in the slow wave response to auditory stimulation and establish predictions thereof. While slow wave enhancement in healthy older adults is possible in fully remote settings, pronounced inter-individual differences in the response to auditory stimulation exist. Novel personalization solutions are needed to address these differences and our findings will guide future designs to effectively deliver auditory sleep stimulations using wearable technology. Sleep’s restorative function is closely linked to slow waves, which are brain activity patterns that occur during deep sleep and are diminished with age. Those slow waves can be increased through auditory stimulation, a method that administers precisely-timed sounds during sleep. Here, we established whether the application of auditory stimulation can be performed in older adults over several nights remotely in their own homes. In a trial, we used a mobile device to deliver auditory stimulation during sleep and measured its effects on slow waves, mood, and vigilance. Although we showed robust increases in slow waves, we found large effect differences between participants and also between different nights within the same participants. We looked for predictors of these effect differences. Our study showed that in-home auditory stimulation is feasible, and may help to guide future auditory stimulation strategies. Lustenberger et al. perform a randomized crossover trial of auditory deep sleep stimulation in older adults, conducted over multiple weeks within the participants’ homes. The authors report substantial inter- and intra-individual differences in the slow wave response to auditory stimulation and identify predictors of response.},
 bibtype = {article},
 author = {Lustenberger, Caroline and Ferster, M. Laura and Huwiler, Stephanie and Brogli, Luzius and Werth, Esther and Huber, Reto and Karlen, Walter},
 doi = {10.1038/s43856-022-00096-6},
 journal = {Communications Medicine},
 number = {1}
}

Auditory stimulation has emerged as a promising tool to enhance non-invasively sleep slow waves, deep sleep brain oscillations that are tightly linked to sleep restoration and are diminished with age. While auditory stimulation showed a beneficial effect in lab-based studies, it remains unclear whether this stimulation approach could translate to real-life settings. We present a fully remote, randomized, cross-over trial in healthy adults aged 62–78 years (clinicaltrials.gov: NCT03420677). We assessed slow wave activity as the primary outcome and sleep architecture and daily functions, e.g., vigilance and mood as secondary outcomes, after a two-week mobile auditory slow wave stimulation period and a two-week Sham period, interleaved with a two-week washout period. Participants were randomized in terms of which intervention condition will take place first using a blocked design to guarantee balance. Participants and experimenters performing the assessments were blinded to the condition. Out of 33 enrolled and screened participants, we report data of 16 participants that received identical intervention. We demonstrate a robust and significant enhancement of slow wave activity on the group-level based on two different auditory stimulation approaches with minor effects on sleep architecture and daily functions. We further highlight the existence of pronounced inter- and intra-individual differences in the slow wave response to auditory stimulation and establish predictions thereof. While slow wave enhancement in healthy older adults is possible in fully remote settings, pronounced inter-individual differences in the response to auditory stimulation exist. Novel personalization solutions are needed to address these differences and our findings will guide future designs to effectively deliver auditory sleep stimulations using wearable technology. Sleep’s restorative function is closely linked to slow waves, which are brain activity patterns that occur during deep sleep and are diminished with age. Those slow waves can be increased through auditory stimulation, a method that administers precisely-timed sounds during sleep. Here, we established whether the application of auditory stimulation can be performed in older adults over several nights remotely in their own homes. In a trial, we used a mobile device to deliver auditory stimulation during sleep and measured its effects on slow waves, mood, and vigilance. Although we showed robust increases in slow waves, we found large effect differences between participants and also between different nights within the same participants. We looked for predictors of these effect differences. Our study showed that in-home auditory stimulation is feasible, and may help to guide future auditory stimulation strategies. Lustenberger et al. perform a randomized crossover trial of auditory deep sleep stimulation in older adults, conducted over multiple weeks within the participants’ homes. The authors report substantial inter- and intra-individual differences in the slow wave response to auditory stimulation and identify predictors of response.

@article{
 title = {Detect-and-segment: A deep learning approach to automate wound image segmentation},
 type = {article},
 year = {2022},
 keywords = {Chronic wounds,Generalizability,Machine learning,Semantic segmentation,Smartphone},
 pages = {100884},
 volume = {29},
 id = {12dafe98-05a4-318d-b4ec-735d0b9f69d4},
 created = {2022-09-04T18:02:17.480Z},
 file_attached = {false},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:04.568Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {SCEBBA2022100884},
 source_type = {article},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34},
 private_publication = {false},
 abstract = {Chronic wounds significantly impact quality of life. They can rapidly deteriorate and require close monitoring of healing progress. Image-based wound analysis is a way of objectively assessing the wound status by quantifying important features that are related to healing. However, high heterogeneity of the wound types and imaging conditions challenge the robust segmentation of wound images. We present Detect-and-Segment (DS), a deep learning approach to produce wound segmentation maps with high generalization capabilities. In our approach, dedicated deep neural networks detected the wound position, isolated the wound from the perturbing background, and computed a wound segmentation map. We tested this approach on a diabetic foot ulcers data set and compared it to a segmentation method based on the full image. To evaluate its generalizability on out-of-distribution data, we measured the performance of the DS approach on 4 additional independent data sets, with larger variety of wound types from different body locations. The Matthews’ correlation coefficient (MCC) improved from 0.29 (full image) to 0.85 (DS) on the diabetic foot ulcer data set. When the DS was tested on the independent data sets, the mean MCC increased from 0.17 to 0.85 . Furthermore, the DS enabled the training of segmentation models with up to 90% less training data without impacting the segmentation performance. The proposed DS approach is a step towards automating wound analysis and reducing efforts to manage chronic wounds.},
 bibtype = {article},
 author = {Scebba, Gaetano and Zhang, Jia and Catanzaro, Sabrina and Mihai, Carina and Distler, Oliver and Berli, Martin and Karlen, Walter},
 doi = {https://doi.org/10.1016/j.imu.2022.100884},
 journal = {Informatics in Medicine Unlocked}
}

Chronic wounds significantly impact quality of life. They can rapidly deteriorate and require close monitoring of healing progress. Image-based wound analysis is a way of objectively assessing the wound status by quantifying important features that are related to healing. However, high heterogeneity of the wound types and imaging conditions challenge the robust segmentation of wound images. We present Detect-and-Segment (DS), a deep learning approach to produce wound segmentation maps with high generalization capabilities. In our approach, dedicated deep neural networks detected the wound position, isolated the wound from the perturbing background, and computed a wound segmentation map. We tested this approach on a diabetic foot ulcers data set and compared it to a segmentation method based on the full image. To evaluate its generalizability on out-of-distribution data, we measured the performance of the DS approach on 4 additional independent data sets, with larger variety of wound types from different body locations. The Matthews’ correlation coefficient (MCC) improved from 0.29 (full image) to 0.85 (DS) on the diabetic foot ulcer data set. When the DS was tested on the independent data sets, the mean MCC increased from 0.17 to 0.85 . Furthermore, the DS enabled the training of segmentation models with up to 90% less training data without impacting the segmentation performance. The proposed DS approach is a step towards automating wound analysis and reducing efforts to manage chronic wounds.

@article{
 title = {Assessment of neonatal respiratory rate variability},
 type = {article},
 year = {2022},
 pages = {ahead of print},
 publisher = {Springer},
 id = {4f489fe1-5a9b-335b-8442-874cd98559ec},
 created = {2022-09-04T18:02:17.485Z},
 file_attached = {false},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:05.006Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {coleman2022assessment},
 source_type = {article},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34},
 private_publication = {false},
 abstract = {Accurate measurement of respiratory rate (RR) in neonates is challenging due to high neonatal RR variability (RRV). There is growing evidence that RRV measurement could inform and guide neonatal care. We sought to quantify neonatal RRV during a clinical study in which we compared multiparameter continuous physiological monitoring (MCPM) devices. Measurements of capnography-recorded exhaled carbon dioxide across 60-s epochs were collected from neonates admitted to the neonatal unit at Aga Khan University-Nairobi hospital. Breaths were manually counted from capnograms and using an automated signal detection algorithm which also calculated mean and median RR for each epoch. Outcome measures were between- and within-neonate RRV, between- and within-epoch RRV, and 95% limits of agreement, bias, and root-mean-square deviation. Twenty-seven neonates were included, with 130 epochs analysed. Mean manual breath count (MBC) was 48 breaths per minute. Median RRV ranged from 11.5% (interquartile range (IQR) 6.8-18.9%) to 28.1% (IQR 23.5-36.7%). Bias and limits of agreement for MBC vs algorithm-derived breath count, MBC vs algorithm-derived median breath rate, MBC vs algorithm-derived mean breath rate were - 0.5 (- 2.7, 1.66), - 3.16 (- 12.12, 5.8), and - 3.99 (- 11.3, 3.32), respectively. The marked RRV highlights the challenge of performing accurate RR measurements in neonates. More research is required to optimize the use of RRV to improve care. When evaluating MCPM devices, accuracy thresholds should be less stringent in newborns due to increased RRV. Lastly, median RR, which discounts the impact of extreme outliers, may be more reflective of the underlying physiological control of breathing.},
 bibtype = {article},
 author = {Coleman, Jesse and Ginsburg, Amy Sarah and Macharia, William M and Ochieng, Roseline and Chomba, Dorothy and Zhou, Guohai and Dunsmuir, Dustin and Karlen, Walter and Ansermino, J Mark},
 doi = {10.1007/s10877-022-00840-2},
 journal = {Journal of Clinical Monitoring and Computing}
}

Accurate measurement of respiratory rate (RR) in neonates is challenging due to high neonatal RR variability (RRV). There is growing evidence that RRV measurement could inform and guide neonatal care. We sought to quantify neonatal RRV during a clinical study in which we compared multiparameter continuous physiological monitoring (MCPM) devices. Measurements of capnography-recorded exhaled carbon dioxide across 60-s epochs were collected from neonates admitted to the neonatal unit at Aga Khan University-Nairobi hospital. Breaths were manually counted from capnograms and using an automated signal detection algorithm which also calculated mean and median RR for each epoch. Outcome measures were between- and within-neonate RRV, between- and within-epoch RRV, and 95% limits of agreement, bias, and root-mean-square deviation. Twenty-seven neonates were included, with 130 epochs analysed. Mean manual breath count (MBC) was 48 breaths per minute. Median RRV ranged from 11.5% (interquartile range (IQR) 6.8-18.9%) to 28.1% (IQR 23.5-36.7%). Bias and limits of agreement for MBC vs algorithm-derived breath count, MBC vs algorithm-derived median breath rate, MBC vs algorithm-derived mean breath rate were - 0.5 (- 2.7, 1.66), - 3.16 (- 12.12, 5.8), and - 3.99 (- 11.3, 3.32), respectively. The marked RRV highlights the challenge of performing accurate RR measurements in neonates. More research is required to optimize the use of RRV to improve care. When evaluating MCPM devices, accuracy thresholds should be less stringent in newborns due to increased RRV. Lastly, median RR, which discounts the impact of extreme outliers, may be more reflective of the underlying physiological control of breathing.

@article{
 title = {Feedback on Trunk Movements From an Electronic Game to Improve Postural Balance in People With Nonspecific Low Back Pain: Pilot Randomized Controlled Trial},
 type = {article},
 year = {2022},
 pages = {e31685},
 volume = {10},
 id = {9c0ab92a-01f8-3bc3-843d-bd9898b42510},
 created = {2022-09-04T18:02:17.553Z},
 file_attached = {false},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:05.405Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Meinke2022},
 source_type = {article},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34},
 private_publication = {false},
 bibtype = {article},
 author = {Meinke, Anita and Peters, Rick and Knols, Ruud and Swanenburg, Jaap and Karlen, Walter},
 doi = {10.2196/31685},
 journal = {JMIR Serious Games},
 number = {2}
}

@article{
 title = {Benchmarking real-time algorithms for in-phase auditory stimulation of low amplitude slow waves with wearable EEG devices during sleep},
 type = {article},
 year = {2022},
 pages = {2916-2925},
 volume = {69},
 id = {41ddaefc-33ee-30ee-9a51-3f35db7789bb},
 created = {2022-09-04T18:02:17.642Z},
 file_attached = {false},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:06.768Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {9730073},
 source_type = {article},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34},
 private_publication = {false},
 bibtype = {article},
 author = {Ferster, Maria Laura and Da Poian, Giulia and Menachery, Kiran and Schreiner, Simon and Lustenberger, Caroline and Maric, Angelina and Huber, Reto and Baumann, Christian and Karlen, Walter},
 doi = {10.1109/TBME.2022.3157468},
 journal = {IEEE Transactions on Biomedical Engineering},
 number = {9}
}

@article{
 title = {Multispectral Video Fusion for Non-Contact Monitoring of Respiratory Rate and Apnea},
 type = {article},
 year = {2021},
 pages = {350-9},
 volume = {68},
 websites = {https://ieeexplore.ieee.org/document/9091089/},
 id = {c07146f5-08bc-3d24-ad31-4c0bd3577f7c},
 created = {2020-05-15T21:25:26.537Z},
 file_attached = {false},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:11:59.886Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {