skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, October 10 until 2:00 AM ET on Friday, October 11 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the NSF-PAR

Title: Investigation of Methods to Extract Fetal Electrocardiogram from the Mother’s Abdominal Signal in Practical Scenarios
Monitoring of fetal electrocardiogram (fECG) would provide useful information about fetal wellbeing as well as any abnormal development during pregnancy. Recent advances in flexible electronics and wearable technologies have enabled compact devices to acquire personal physiological signals in the home setting, including those of expectant mothers. However, the high noise level in the daily life renders long-entrenched challenges to extract fECG from the combined fetal/maternal ECG signal recorded in the abdominal area of the mother. Thus, an efficient fECG extraction scheme is a dire need. In this work, we intensively explored various extraction algorithms, including template subtraction (TS), independent component analysis (ICA), and extended Kalman filter (EKF) using the data from the PhysioNet 2013 Challenge. Furthermore, the modified data with Gaussian and motion noise added, mimicking a practical scenario, were utilized to examine the performance of algorithms. Finally, we combined different algorithms together, yielding promising results, with the best performance in the F1 score of 92.61% achieved by an algorithm combining ICA and TS. With the data modified by adding different types of noise, the combination of ICA–TS–ICA showed the highest F1 score of 85.4%. It should be noted that these combined approaches required higher computational complexity, including execution time and allocated memory compared with other methods. Owing to comprehensive examination through various evaluation metrics in different extraction algorithms, this study provides insights into the implementation and operation of state-of-the-art fetal and maternal monitoring systems in the era of mobile health.  more » « less
Award ID(s):
1917105
NSF-PAR ID:
10215665
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Technologies
Volume:
8
Issue:
2
ISSN:
2227-7080
Page Range / eLocation ID:
33
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ( , Sensors)
    null (Ed.)
    The invasive method of fetal electrocardiogram (fECG) monitoring is widely used with electrodes directly attached to the fetal scalp. There are potential risks such as infection and, thus, it is usually carried out during labor in rare cases. Recent advances in electronics and technologies have enabled fECG monitoring from the early stages of pregnancy through fECG extraction from the combined fetal/maternal ECG (f/mECG) signal recorded non-invasively in the abdominal area of the mother. However, cumbersome algorithms that require the reference maternal ECG as well as heavy feature crafting makes out-of-clinics fECG monitoring in daily life not yet feasible. To address these challenges, we proposed a pure end-to-end deep learning model to detect fetal QRS complexes (i.e., the main spikes observed on a fetal ECG waveform). Additionally, the model has the residual network (ResNet) architecture that adopts the novel 1-D octave convolution (OctConv) for learning multiple temporal frequency features, which in turn reduce memory and computational cost. Importantly, the model is capable of highlighting the contribution of regions that are more prominent for the detection. To evaluate our approach, data from the PhysioNet 2013 Challenge with labeled QRS complex annotations were used in the original form, and the data were then modified with Gaussian and motion noise, mimicking real-world scenarios. The model can achieve a F1 score of 91.1% while being able to save more than 50% computing cost with less than 2% performance degradation, demonstrating the effectiveness of our method. 
    more » « less
  2. ; ; ; ; ; ( , Sensors)
    Fetal electrocardiogram (fECG) assessment is essential throughout pregnancy to monitor the wellbeing and development of the fetus, and to possibly diagnose potential congenital heart defects. Due to the high noise incorporated in the abdominal ECG (aECG) signals, the extraction of fECG has been challenging. And it is even a lot more difficult for fECG extraction if only one channel of aECG is provided, i.e., in a compact patch device. In this paper, we propose a novel algorithm based on the Ensemble Kalman filter (EnKF) for non-invasive fECG extraction from a single-channel aECG signal. To assess the performance of the proposed algorithm, we used our own clinical data, obtained from a pilot study with 10 subjects each of 20 min recording, and data from the PhysioNet 2013 Challenge bank with labeled QRS complex annotations. The proposed methodology shows the average positive predictive value (PPV) of 97.59%, sensitivity (SE) of 96.91%, and F1-score of 97.25% from the PhysioNet 2013 Challenge bank. Our results also indicate that the proposed algorithm is reliable and effective, and it outperforms the recently proposed extended Kalman filter (EKF) based algorithm. 
    more » « less
  3. ; ; ; ; ; ; ; ( , Biomedical Optics Express)

    Noninvasive transabdominal fetal pulse oximetry can provide clinicians critical assessment of fetal health and potentially contribute to improved management of childbirth. Conventional pulse oximetry through continuous wave (CW) light has challenges measuring the signals from deep tissue and separating the weak fetal signal from the strong maternal signal. Here, we propose a new approach for transabdominal fetal pulse oximetry through interferometric near-infrared spectroscopy (iNIRS). This approach provides pathlengths of photons traversing the tissue, which facilitates the extraction of fetal signals by rejecting the very strong maternal signal from superficial layers. We use a multimode fiber combined with a mode-field converter at the detection arm to boost the signal of iNIRS. Together, we can detect signals from deep tissue (>∼1.6 cm in sheep abdomen and in human forearm) at merely 1.1 cm distance from the source. Using a pregnant sheep model, we experimentally measured and extracted the fetal heartbeat signals originating from deep tissue. This validated a key step towards transabdominal fetal pulse oximetry through iNIRS and set a foundation for further development of this method to measure the fetal oxygen saturation.

     
    more » « less
  4. ; ; ; ; ; ; ( , BMC Medical Informatics and Decision Making)
    Abstract Background Diabetic retinopathy (DR) is a leading cause of blindness in American adults. If detected, DR can be treated to prevent further damage causing blindness. There is an increasing interest in developing artificial intelligence (AI) technologies to help detect DR using electronic health records. The lesion-related information documented in fundus image reports is a valuable resource that could help diagnoses of DR in clinical decision support systems. However, most studies for AI-based DR diagnoses are mainly based on medical images; there is limited studies to explore the lesion-related information captured in the free text image reports. Methods In this study, we examined two state-of-the-art transformer-based natural language processing (NLP) models, including BERT and RoBERTa, compared them with a recurrent neural network implemented using Long short-term memory (LSTM) to extract DR-related concepts from clinical narratives. We identified four different categories of DR-related clinical concepts including lesions, eye parts, laterality, and severity, developed annotation guidelines, annotated a DR-corpus of 536 image reports, and developed transformer-based NLP models for clinical concept extraction and relation extraction. We also examined the relation extraction under two settings including ‘gold-standard’ setting—where gold-standard concepts were used–and end-to-end setting. Results For concept extraction, the BERT model pretrained with the MIMIC III dataset achieve the best performance (0.9503 and 0.9645 for strict/lenient evaluation). For relation extraction, BERT model pretrained using general English text achieved the best strict/lenient F1-score of 0.9316. The end-to-end system, BERT_general_e2e, achieved the best strict/lenient F1-score of 0.8578 and 0.8881, respectively. Another end-to-end system based on the RoBERTa architecture, RoBERTa_general_e2e, also achieved the same performance as BERT_general_e2e in strict scores. Conclusions This study demonstrated the efficiency of transformer-based NLP models for clinical concept extraction and relation extraction. Our results show that it’s necessary to pretrain transformer models using clinical text to optimize the performance for clinical concept extraction. Whereas, for relation extraction, transformers pretrained using general English text perform better. 
    more » « less
  5. ; ; ; ; ( , Integrating Materials and Manufacturing Innovation)
    Advances in materials science require leveraging past findings and data from the vast published literature. While some materials data repositories are being built, they typically rely on newly created data in narrow domains because extracting detailed data and metadata from the enormous wealth of publications is immensely challenging. The advent of large language models (LLMs) presents a new opportunity to rapidly and accurately extract data and insights from the published literature and transform it into structured data formats for easy query and reuse. In this paper, we build on initial strategies for using LLMs for rapid and autonomous data extraction from materials science articles in a format curatable by materials databases. We presented the subdomain of polymer composites as our example use case and demonstrated the success and challenges of LLMs on extracting tabular data. We explored diferent table representations for use with LLMs, fnding that a multimodal model with an image input yielded the most promising results. This model achieved an accuracy score of 0.910 for composition information extraction and an F1 score of 0.863 for property name information extraction. With the most conservative evaluation for the property extraction requiring exact match in all the details, we obtained an F1 score of 0.419. We observed that by allowing varying degrees of fexibility in the evaluation, the score can increase to 0.769. We envision that the results and analysis from this study will promote further research directions in developing information extraction strategies from materials information sources. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email