Rawan S. Abdulsadig

Ms. Rawan S. Abdulsadig

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 March 2024 in Frontiers in Digital Health
Verified
Journal Article
Open access
PDF file
RARawan S. Abdulsadig
Rawan S. Abdulsadig
EREsther Rodriguez-Villegas
Esther Rodriguez-Villegas
Class imbalance is a common challenge that is often faced when dealing with classification tasks aiming to detect medical events that are particularly infrequent. Apnoea is an example of such events. This challenge can however be mitigated using class rebalancing algorithms. This work investigated 10 widely used data-level class imbalance mitigation methods aiming towards building a random forest (RF) model that attempts to detect apnoea events from photoplethysmography (PPG) signals acquired from the neck. Those methods are random undersampling (RandUS), random oversampling (RandOS), condensed nearest-neighbors (CNNUS), edited nearest-neighbors (ENNUS), Tomek’s links (TomekUS), synthetic minority oversampling technique (SMOTE), Borderline-SMOTE (BLSMOTE), adaptive synthetic oversampling (ADASYN), SMOTE with TomekUS (SMOTETomek) and SMOTE with ENNUS (SMOTEENN). Feature-space transformation using PCA and KernelPCA was also examined as a potential way of providing better representations of the data for the class rebalancing methods to operate. This work showed that RandUS is the best option for improving the sensitivity score (up to 11%). However, it could hinder the overall accuracy due to the reduced amount of training data. On the other hand, augmenting the data with new artificial data points was shown to be a non-trivial task that needs further development, especially in the presence of subject dependencies, as was the case in this work.

16 February 2023 in IEEE Access
Verified
Journal Article
Open access
RARawan S. Abdulsadig
Rawan S. Abdulsadig
Esther Rodriguez-VillegasEsther Rodriguez-Villegas
Esther Rodriguez-Villegas
Sleep position identification and monitoring is important in the context of certain healthcare conditions, such as obstructive sleep apnoea and epilepsy. Many studies have thoroughly investigated automatic sleep detection using various sensing channels located in optimum body locations. However, this has not been the case for detection using physiological data acquired from a single sensing channel on the neck. In certain healthcare contexts the neck can, however, be an attractive location despite being suboptimal for position monitoring; the reason being that it enables better extraction of more critical biomarkers from other sensing modalities, making possible multimodal monitoring using just one wearable. This work focuses on investigating methods of automatic sleep position detection using one wearable channel of accelerometry data sensed on the neck. Three different models are explored. These are based on: decision trees (DT), extra-trees classifier (ET) and long-short term memory neural networks (LSTM-NN). The paper also investigates for the first time what would be optimum design choices when considering that wearables are power and memory-constrained, but performance in the type of healthcare applications where a single location multimodal sensing is important must not be compromised. This includes looking into how changing the sampling rate and window sizes would affect the performance of the different models. It is demonstrated that a sampling rate as low as 5 Hz, and a window size as short as 1 second, still lead to high classification performance (around 0.945, 0.975 and 0.965 mean f1-score when using the DT, ET and LSTM-NN models, respectively, and at least 98% average accuracy in all three models); and that the DT model occupies the least memory space (1.765 KB) and takes the least mean prediction time across all window sizes (around 0.8 ms).

27 September 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RARawan S. Abdulsadig
Rawan S. Abdulsadig
EREsther Rodriguez-Villegas
Esther Rodriguez-Villegas
Pulse rate (PR) and respiratory rate (RR) are two of the most important vital signs. Monitoring them would benefit from easy-to-use technologies. Hence, wearable devices would, in principle, be ideal candidates for such systems. The neck, although highly susceptible to artifacts, presents an attractive location for a diverse pool of physiological biomarkers monitoring purposes such as airflow sensing in a non-obstructive manner. This paper presents a methodology for PR and RR estimation using photoplethysmography (PPG) and accelerometry (Acc) sensors placed on the neck. Neck PPG and Acc signals were recorded from 22 healthy participants for RR estimation, where the resting subjects performed guided breathing following a visual metronome. Neck PPG signals were obtained from 16 healthy participants who breathed through an altitude generator machine in order to acquire a wider range of PR readings while at rest. The proposed methodology was able to provide rate estimates via a combination of recursive FFT-based dominance scoring coupled with an exponentially weighted moving average (EWMA)-driven aggregation scheme. The recursion aimed at bypassing sudden intra-window amplitude deviations caused by momentary artifacts, while the EWMA-based aggregation was utilized for handling inter-window artifact-induced deviations. To further improve estimation stability and confidence, estimates were calculated in the form of rate bands taking into account the relevant clinically acceptable error margins, and results when considering rate values and rate bands are presented and discussed. The framework was able to achieve an overall pulse rate value accuracy of $$93.67\pm 7.64$$ 93.67 ± 7.64 % within the clinically acceptable ± 5 BPM with reference to the gold-standard reference devices while providing an overall respiratory rate value accuracy within the clinically appropriate ± 3 BrPM of $$94.94\pm 3.56$$ 94.94 ± 3.56 % with reference to the guiding visual metronome, and $$88.4\pm 7.63$$ 88.4 ± 7.63 % with respect to the gold-standard reference device. The proposed methodology achieves acceptable PR and RR estimation capabilities, even when signals are acquired from an unusual location such as the neck. This work introduces novel ideas that can lead to the development of medical device outputs for PR and RR monitoring, especially capitalizing on the advantages of the neck as a multi-modal physiological monitoring location.

27 November 2024 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
RARawan S. Abdulsadig
Rawan S. Abdulsadig
NDNikesh Devani
Nikesh Devani
SSSukhpreet Singh
Sukhpreet Singh
ZPZaibaa Patel
Zaibaa Patel
RPRenard Xaviero Adhi Pramono
Renard Xaviero Adhi Pramono
Esther Rodriguez-VillegasEsther Rodriguez-Villegas
Esther Rodriguez-Villegas
Objectives: Respiratory rate (RR) is a clinical measure of breathing frequency, a vital metric for clinical assessment. However, the recording and documentation of RR are considered to be extremely poor due to the limitations of the current approaches to measuring RR, including capnography and manual counting. We conducted a validation of the automatic RR measurement capability of AcuPebble RE100 (Acurable, London, UK) against a gold-standard capnography system and a type-III cardiorespiratory polygraphy system in two independent prospective and retrospective studies. Methods: The experiment for the prospective study was conducted at Imperial College London. Data from AcuPebble RE100 (Acurable, London, UK) and the reference capnography system (Capnostream™35, Medtronic, Minneapolis, MN, USA) were collected simultaneously from healthy volunteers. The data from a previously published study were used in the retrospective study, where the patients were recruited consecutively from a standard Obstructive Sleep Apnea (OSA) diagnostic pathway in a UK hospital. Overnight data during sleep were collected using the AcuPebble SA100 (Acurable, London, UK) sensor and a type-III cardiorespiratory polygraphy system (Embletta MPR Sleep System, Natus Medical, Pleasanton, CA, USA) at the patients’ homes. Data from 15 healthy volunteers were used in the prospective study. For the retrospective study, 150 consecutive patients had been referred for OSA diagnosis and successfully completed the study. Results: The RR output of AcuPebble RE100 (Acurable, London, UK) was compared against the reference device in terms of the Root Mean Squared Deviation (RMSD), mean error, and standard deviation (SD) of the difference between the paired measurements. In both the prospective and retrospective studies, the AcuPebble RE100 algorithms provided accurate RR measurements, well within the clinically relevant margin of error, typically used by FDA-approved respiratory rate monitoring devices, with the RMSD under three breaths per minute (BPM) and mean errors of 1.83 BPM and 1.4 BPM, respectively. Conclusions: The evaluation results provide evidence that AcuPebble RE100 (Acurable, London, UK) algorithms produce reliable results and are hence suitable for overnight monitoring of RR.

10 July 2025 in IEEE Access
Verified
Journal Article
Open access
YCYichen Cao
Yichen Cao
RARawan S. Abdulsadig
Rawan S. Abdulsadig
Esther Rodriguez-VillegasEsther Rodriguez-Villegas
Esther Rodriguez-Villegas
Jugular venous (JV) assessment can be a fundamental component of cardiovascular examination, providing valuable insights into right-sided heart function and central venous pressure. Traditional methods are subjective and prone to inter-observer variability, affecting diagnostic accuracy. Technological advancements offer potential solutions by providing objective, consistent, and reproducible measurements. This review aims to present a comprehensive analysis of technology based JV assessment techniques reported in the literature from 2015 to 2024, focusing on their technical characteristics, diagnostic performance, clinical applications, and associated limitations. This represents the first systematic review across all technological platforms for JV assessment, providing evidence-based recommendations for method selection based on clinical context, accuracy requirements, and resource availability. A total of 44 studies were included, comprising a diverse range of JV assessment techniques. Ultrasound-based methods were the most extensively studied, demonstrating strong correlations with invasive measurements and high diagnostic accuracy confirming their suitability for acute care settings where high diagnostic accuracy is essential. Optical and camera-based methods, including photoplethysmographic imaging and infrared thermography, showed promise for non-contact and remote JV assessment, making them well-suited for applications in telemedicine and infection control. Wearable devices and sensors, such as plethysmography and gyroscope sensors, offer promising solutions for continuous and real-time monitoring in ambulatory and chronic disease management contexts. Other specialized modalities, such as MRI and near-infrared spectroscopy (NIRS), were primarily applied to specific populations, including pregnant women and dialysis patients, where conventional techniques may be limited. Despite these advancements, challenges such as small sample sizes, variability in methodologies, and technological limitations were identified. Recent advancements in JV assessment techniques offer enhancements in cardiovascular diagnostics and patient care. Future research should focus on standardizing measurement protocols, conducting larger multi-center studies to properly validate these technological approaches, and evaluating the integration of these innovative techniques into clinical practice to improve diagnostic precision and patient outcomes.

20 July 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RARawan S. Abdulsadig
Rawan S. Abdulsadig
EREsther Rodriguez-Villegas
Esther Rodriguez-Villegas
Photoplethysmography (PPG) is a widely used non-invasive sensing technique for monitoring cardiovascular and respiratory parameters, however, its measurements are highly susceptible to artifacts, which can degrade signal quality and, in turn, the accuracy of derived vital signs. Reliable PPG signal quality assessment (SQA) is therefore critical, yet existing SQA methods often rely on handcrafted features or ad-hoc thresholds and tend to be dataset-specific, limiting their generalizability across different sensor locations and users. To address these gaps, this paper proposes a novel SQA approach for PPG that is real-time compatible and sensor-location invariant. The method leverages deep representation learning by fine-tuning a pre-trained PPG transformer (PPG-PT) with a triplet loss to learn an embedding space where PPG segments are meaningfully partitioned based on their morphology. Signal quality is then quantified by computing each window’s embedding distance to a set of reference embeddings representing high-quality PPG segments, yielding a flexible reference-based quality score without requiring any model retraining when adapting to new devices or domains. The proposed framework was evaluated on three PPG datasets: the Complex System Laboratory (CSL) dataset providing finger PPG, the Wearable and Clinical Devices (WCS) for wrist PPG signals, and the Apnea and Artifacts (AA) dataset representing neck PPG signals, encompassing a wide range of artifact types and recording conditions. The model achieved strong agreement with expert annotations on the CSL dataset, with an F1-score of $$\approx$$ 90%. It also demonstrated robust generalization on the WCS wearable dataset: using a generalized reference set drawn from multiple subjects, the approach attained a high F1-score of about $$\approx$$ 95% on wrist PPG data, highlighting the method’s potential for population-level deployment. Performance on the AA neck PPG dataset was moderately acceptable with $$\approx$$ 70% F1-score, likely due to the complexity and varying executions of the different artifacts presented in the dataset. The proposed methodology provides a deep learning SQA framework capable of generalizing across different PPG sensor locations and devices.