Annalisa Baronetto
Annalisa Baronetto has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Oliver Amft
University of Freiburg
5 shared publications - Luisa Graf
Chair of Digital Health, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany
2 shared publications Markus F. Neurath
Medical Clinic 1, University Hospital Erlangen, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany
2 shared publications- Markus Friedrich Neurath
Department of Medicine 1, Friedrich-Alexander-University Erlangen-Nürnberg, 91054 Erlangen, Germany
2 shared publications Sarah Fischer
Medical Clinic 1, University Hospital Erlangen, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany
2 shared publications- Sarah Fischer
Department of Medicine 1, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
2 shared publications
Latest Publications
- Open Access
- 13 March 2025
- Published by Frontiers Media SA in Frontiers in Digital Health
- Vol. 7, 1514757
Automated inflammatory bowel disease detection using wearable bowel sound event spotting
Introduction: Inflammatory bowel disorders may result in abnormal Bowel Sound (BS) characteristics during auscultation. We employ pattern spotting to detect rare bowel BS events in continuous abdominal recordings using a smart T-shirt with embedded miniaturised microphones. Subsequently, we investigate the clinical relevance of BS spotting in a classification task to distinguish patients diagnosed with inflammatory bowel disease (IBD) and healthy controls.Methods: Abdominal recordings were obtained from 24 patients with IBD with varying disease activity and 21 healthy controls across different digestive phases. In total, approximately 281 h of audio data were inspected by expert raters and thereof 136 h were manually annotated for BS events. A deep-learning-based audio pattern spotting algorithm was trained to retrieve BS events. Subsequently, features were extracted around detected BS events and a Gradient Boosting Classifier was trained to classify patients with IBD vs. healthy controls. We further explored classification window size, feature relevance, and the link between BS-based IBD classification performance and IBD activity.Results: Stratified group K-fold cross-validation experiments yielded a mean area under the receiver operating characteristic curve ≥0.83 regardless of whether BS were manually annotated or detected by the BS spotting algorithm.Discussion: Automated BS retrieval and our BS event classification approach have the potential to support diagnosis and treatment of patients with IBD.
- 13 March 2025
- Published by Frontiers Media SA in Frontiers in Digital Health
- Vol. 7, 1514757
Open AccessAutomated inflammatory bowel disease detection using wearable bowel sound event spotting
Introduction: Inflammatory bowel disorders may result in abnormal Bowel Sound (BS) characteristics during auscultation. We employ pattern spotting to detect rare bowel BS events in continuous abdominal recordings using a smart T-shirt with embedded miniaturised microphones. Subsequently, we investigate the clinical relevance of BS spotting in a classification task to distinguish patients diagnosed with inflammatory bowel disease (IBD) and healthy controls.Methods: Abdominal recordings were obtained from 24 patients with IBD with varying disease activity and 21 healthy controls across different digestive phases. In total, approximately 281 h of audio data were inspected by expert raters and thereof 136 h were manually annotated for BS events. A deep-learning-based audio pattern spotting algorithm was trained to retrieve BS events. Subsequently, features were extracted around detected BS events and a Gradient Boosting Classifier was trained to classify patients with IBD vs. healthy controls. We further explored classification window size, feature relevance, and the link between BS-based IBD classification performance and IBD activity.Results: Stratified group K-fold cross-validation experiments yielded a mean area under the receiver operating characteristic curve ≥0.83 regardless of whether BS were manually annotated or detected by the BS spotting algorithm.Discussion: Automated BS retrieval and our BS event classification approach have the potential to support diagnosis and treatment of patients with IBD.
- Open Access
- 10 July 2024
- Published by JMIR Publications Inc. in JMIR AI
- Vol. 3 (1) , e51118
Multiscale Bowel Sound Event Spotting in Highly Imbalanced Wearable Monitoring Data: Algorithm Development and Validation Study
Background: Abdominal auscultation (i.e., listening to bowel sounds (BSs)) can be used to analyze digestion. An automated retrieval of BS would be beneficial to assess gastrointestinal disorders noninvasively. Objective: This study aims to develop a multiscale spotting model to detect BSs in continuous audio data from a wearable monitoring system. Methods: We designed a spotting model based on the Efficient-U-Net (EffUNet) architecture to analyze 10-second audio segments at a time and spot BSs with a temporal resolution of 25 ms. Evaluation data were collected across different digestive phases from 18 healthy participants and 9 patients with inflammatory bowel disease (IBD). Audio data were recorded in a daytime setting with a smart T-Shirt that embeds digital microphones. The data set was annotated by independent raters with substantial agreement (Cohen κ between 0.70 and 0.75), resulting in 136 hours of labeled data. In total, 11,482 BSs were analyzed, with a BS duration ranging between 18 ms and 6.3 seconds. The share of BSs in the data set (BS ratio) was 0.0089. We analyzed the performance depending on noise level, BS duration, and BS event rate. We also report spotting timing errors. Results: Leave-one-participant-out cross-validation of BS event spotting yielded a median F1-score of 0.73 for both healthy volunteers and patients with IBD. EffUNet detected BSs under different noise conditions with 0.73 recall and 0.72 precision. In particular, for a signal-to-noise ratio over 4 dB, more than 83% of BSs were recognized, with precision of 0.77 or more. EffUNet recall dropped below 0.60 for BS duration of 1.5 seconds or less. At a BS ratio greater than 0.05, the precision of our model was over 0.83. For both healthy participants and patients with IBD, insertion and deletion timing errors were the largest, with a total of 15.54 minutes of insertion errors and 13.08 minutes of deletion errors over the total audio data set. On our data set, EffUNet outperformed existing BS spotting models that provide similar temporal resolution. Conclusions: The EffUNet spotter is robust against background noise and can retrieve BSs with varying duration. EffUNet outperforms previous BS detection approaches in unmodified audio data, containing highly sparse BS events.
- 10 July 2024
- Published by JMIR Publications Inc. in JMIR AI
- Vol. 3 (1) , e51118
Open AccessMultiscale Bowel Sound Event Spotting in Highly Imbalanced Wearable Monitoring Data: Algorithm Development and Validation Study
Background: Abdominal auscultation (i.e., listening to bowel sounds (BSs)) can be used to analyze digestion. An automated retrieval of BS would be beneficial to assess gastrointestinal disorders noninvasively. Objective: This study aims to develop a multiscale spotting model to detect BSs in continuous audio data from a wearable monitoring system. Methods: We designed a spotting model based on the Efficient-U-Net (EffUNet) architecture to analyze 10-second audio segments at a time and spot BSs with a temporal resolution of 25 ms. Evaluation data were collected across different digestive phases from 18 healthy participants and 9 patients with inflammatory bowel disease (IBD). Audio data were recorded in a daytime setting with a smart T-Shirt that embeds digital microphones. The data set was annotated by independent raters with substantial agreement (Cohen κ between 0.70 and 0.75), resulting in 136 hours of labeled data. In total, 11,482 BSs were analyzed, with a BS duration ranging between 18 ms and 6.3 seconds. The share of BSs in the data set (BS ratio) was 0.0089. We analyzed the performance depending on noise level, BS duration, and BS event rate. We also report spotting timing errors. Results: Leave-one-participant-out cross-validation of BS event spotting yielded a median F1-score of 0.73 for both healthy volunteers and patients with IBD. EffUNet detected BSs under different noise conditions with 0.73 recall and 0.72 precision. In particular, for a signal-to-noise ratio over 4 dB, more than 83% of BSs were recognized, with precision of 0.77 or more. EffUNet recall dropped below 0.60 for BS duration of 1.5 seconds or less. At a BS ratio greater than 0.05, the precision of our model was over 0.83. For both healthy participants and patients with IBD, insertion and deletion timing errors were the largest, with a total of 15.54 minutes of insertion errors and 13.08 minutes of deletion errors over the total audio data set. On our data set, EffUNet outperformed existing BS spotting models that provide similar temporal resolution. Conclusions: The EffUNet spotter is robust against background noise and can retrieve BSs with varying duration. EffUNet outperforms previous BS detection approaches in unmodified audio data, containing highly sparse BS events.
- Open Access
- 25 July 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Multiscale Bowel Sound Event Spotting in Highly Imbalanced Wearable Monitoring Data: Algorithm Development and Validation Study (Preprint)
BACKGROUND Abdominal auscultation (i.e., listening to bowel sounds (BSs)) can be used to analyze digestion. An automated retrieval of BS would be beneficial to assess gastrointestinal disorders noninvasively. OBJECTIVE This study aims to develop a multiscale spotting model to detect BSs in continuous audio data from a wearable monitoring system. METHODS We designed a spotting model based on the Efficient-U-Net (EffUNet) architecture to analyze 10-second audio segments at a time and spot BSs with a temporal resolution of 25 ms. Evaluation data were collected across different digestive phases from 18 healthy participants and 9 patients with inflammatory bowel disease (IBD). Audio data were recorded in a daytime setting with a smart T-Shirt that embeds digital microphones. The data set was annotated by independent raters with substantial agreement (Cohen κ between 0.70 and 0.75), resulting in 136 hours of labeled data. In total, 11,482 BSs were analyzed, with a BS duration ranging between 18 ms and 6.3 seconds. The share of BSs in the data set (BS ratio) was 0.0089. We analyzed the performance depending on noise level, BS duration, and BS event rate. We also report spotting timing errors. RESULTS Leave-one-participant-out cross-validation of BS event spotting yielded a median F1-score of 0.73 for both healthy volunteers and patients with IBD. EffUNet detected BSs under different noise conditions with 0.73 recall and 0.72 precision. In particular, for a signal-to-noise ratio over 4 dB, more than 83% of BSs were recognized, with precision of 0.77 or more. EffUNet recall dropped below 0.60 for BS duration of 1.5 seconds or less. At a BS ratio greater than 0.05, the precision of our model was over 0.83. For both healthy participants and patients with IBD, insertion and deletion timing errors were the largest, with a total of 15.54 minutes of insertion errors and 13.08 minutes of deletion errors over the total audio data set. On our data set, EffUNet outperformed existing BS spotting models that provide similar temporal resolution. CONCLUSIONS The EffUNet spotter is robust against background noise and can retrieve BSs with varying duration. EffUNet outperforms previous BS detection approaches in unmodified audio data, containing highly sparse BS events.
- 25 July 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessMultiscale Bowel Sound Event Spotting in Highly Imbalanced Wearable Monitoring Data: Algorithm Development and Validation Study (Preprint)
BACKGROUND Abdominal auscultation (i.e., listening to bowel sounds (BSs)) can be used to analyze digestion. An automated retrieval of BS would be beneficial to assess gastrointestinal disorders noninvasively. OBJECTIVE This study aims to develop a multiscale spotting model to detect BSs in continuous audio data from a wearable monitoring system. METHODS We designed a spotting model based on the Efficient-U-Net (EffUNet) architecture to analyze 10-second audio segments at a time and spot BSs with a temporal resolution of 25 ms. Evaluation data were collected across different digestive phases from 18 healthy participants and 9 patients with inflammatory bowel disease (IBD). Audio data were recorded in a daytime setting with a smart T-Shirt that embeds digital microphones. The data set was annotated by independent raters with substantial agreement (Cohen κ between 0.70 and 0.75), resulting in 136 hours of labeled data. In total, 11,482 BSs were analyzed, with a BS duration ranging between 18 ms and 6.3 seconds. The share of BSs in the data set (BS ratio) was 0.0089. We analyzed the performance depending on noise level, BS duration, and BS event rate. We also report spotting timing errors. RESULTS Leave-one-participant-out cross-validation of BS event spotting yielded a median F1-score of 0.73 for both healthy volunteers and patients with IBD. EffUNet detected BSs under different noise conditions with 0.73 recall and 0.72 precision. In particular, for a signal-to-noise ratio over 4 dB, more than 83% of BSs were recognized, with precision of 0.77 or more. EffUNet recall dropped below 0.60 for BS duration of 1.5 seconds or less. At a BS ratio greater than 0.05, the precision of our model was over 0.83. For both healthy participants and patients with IBD, insertion and deletion timing errors were the largest, with a total of 15.54 minutes of insertion errors and 13.08 minutes of deletion errors over the total audio data set. On our data set, EffUNet outperformed existing BS spotting models that provide similar temporal resolution. CONCLUSIONS The EffUNet spotter is robust against background noise and can retrieve BSs with varying duration. EffUNet outperforms previous BS detection approaches in unmodified audio data, containing highly sparse BS events.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (7) , 3164-3174
Segment-Based Spotting of Bowel Sounds Using Pretrained Models in Continuous Data Streams
We analyse pretrained and non-pretrained deep neural models to detect 10-seconds Bowel Sounds (BS) audio segments in continuous audio data streams. The models include MobileNet, EfficientNet, and Distilled Transformer architectures. Models were initially trained on AudioSet and then transferred and evaluated on 84 hours of labelled audio data of eighteen healthy participants. Evaluation data was recorded in a semi-naturalistic daytime setting including movement and background noise using a smart shirt with embedded microphones. The collected dataset was annotated for individual BS events by two independent raters with substantial agreement (Cohen's Kappa $\kappa =0.74$ ). Leave-One-Participant-Out cross-validation for detecting 10-second BS audio segments, i.e. segment-based BS spotting, yielded a best F1 score of 73% and 67%, with and without transfer learning respectively. The best model for segment-based BS spotting was EfficientNet-B2 with an attention module. Our results show that pretrained models could improve F1 score up to 26%, in particular, increasing robustness against background noise. Our segment-based BS spotting approach reduces the amount of audio data to be reviewed by experts from 84 h to 11 h, thus by $\sim$ 87%.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (7) , 3164-3174
Segment-Based Spotting of Bowel Sounds Using Pretrained Models in Continuous Data Streams
We analyse pretrained and non-pretrained deep neural models to detect 10-seconds Bowel Sounds (BS) audio segments in continuous audio data streams. The models include MobileNet, EfficientNet, and Distilled Transformer architectures. Models were initially trained on AudioSet and then transferred and evaluated on 84 hours of labelled audio data of eighteen healthy participants. Evaluation data was recorded in a semi-naturalistic daytime setting including movement and background noise using a smart shirt with embedded microphones. The collected dataset was annotated for individual BS events by two independent raters with substantial agreement (Cohen's Kappa $\kappa =0.74$ ). Leave-One-Participant-Out cross-validation for detecting 10-second BS audio segments, i.e. segment-based BS spotting, yielded a best F1 score of 73% and 67%, with and without transfer learning respectively. The best model for segment-based BS spotting was EfficientNet-B2 with an attention module. Our results show that pretrained models could improve F1 score up to 26%, in particular, increasing robustness against background noise. Our segment-based BS spotting approach reduces the amount of audio data to be reviewed by experts from 84 h to 11 h, thus by $\sim$ 87%.
- Open Access
- 21 September 2021
- Published by Association for Computing Machinery (ACM)
- p. 73-77
Simulation of Garment-Embedded Contact Sensor Performance under Motion Dynamics
We propose a simulation method to evaluate the performance of garment-embedded contact sensors while performing common Activities of Daily Living (ADL). Our method comprises four steps: dynamic 3D human body model generation, automated smart garment design, ADL simulation, dynamic sensor fitting and sensor displacement evaluation. We generated 100 3D human body models with varying body shapes and virtually dressed them with three differently fitted smart T-Shirts. We then analysed the sensor-body distance and sensor displacement while performing common ADLs. An Electrocardiogram (ECG) smart shirt was considered as an example application. Results show a decrease in sensor distance while BMI increases for both sexes. Compared to females, males show higher sensor displacement and displacement variance, whereas women show higher distance variance compared to men for all ADLs, especially in the region below the breast. Our method can be used to evaluate contact sensor performance for different body shapes, ADLs, and garment designs.
- 21 September 2021
- Published by Association for Computing Machinery (ACM)
- p. 73-77
Open AccessSimulation of Garment-Embedded Contact Sensor Performance under Motion Dynamics
We propose a simulation method to evaluate the performance of garment-embedded contact sensors while performing common Activities of Daily Living (ADL). Our method comprises four steps: dynamic 3D human body model generation, automated smart garment design, ADL simulation, dynamic sensor fitting and sensor displacement evaluation. We generated 100 3D human body models with varying body shapes and virtually dressed them with three differently fitted smart T-Shirts. We then analysed the sensor-body distance and sensor displacement while performing common ADLs. An Electrocardiogram (ECG) smart shirt was considered as an example application. Results show a decrease in sensor distance while BMI increases for both sexes. Compared to females, males show higher sensor displacement and displacement variance, whereas women show higher distance variance compared to men for all ADLs, especially in the region below the breast. Our method can be used to evaluate contact sensor performance for different body shapes, ADLs, and garment designs.