Modern intrapartum fetal health assessments are currently limited to monitoring heart rate and spatial parameters, neglecting critical biomarkers that remain unmeasurable with today's clinical devices without performing surgery. Without precise evaluations of oxygen levels and blood acidity, clinicians are forced to rely on postnatal assessments to gauge fetal well-being, a delay that may obscure timely intervention. Fetal blood pH is a vital indicator of acid-base balance and cellular health, as any deviation could indicate potential health risks such as hypoxia and acidemia. In this study, we leverage the indirect relationship between pH and oxygen saturation to estimate fetal blood pH non-invasively using near-infrared (NIR) spectroscopy with wavelengths optimized for light transmission depth and oxygen saturation measurements. A convolutional neural network (CNN) extracts features from the acquired data, enabling accurate prediction of fetal blood pH using our machine learning (ML) model. Evaluation using hypoxic sheep models demonstrated an average prediction error of just 0.023 pH units, with all rounds maintaining errors below 0.05 pH units.

Evaluation of fetal health during pregnancy is highly dependent on monitoring of fetal heart rate (FHR). New technologies emerge, such as the transabdominal fetal pulse oximeter (TFO), a non-invasive, light-based measurement device, to provide obstetricians with additional fetal physiological markers such as fetal oxygen saturation. Estimation of FHR from TFO's acquired photoplethysmogram (PPG) signals is necessary for deriving oxygen saturation. Non-invasive optical sensing of deep fetal tissue is inherently challenged by low signal-to-noise ratio, and unpredictable anatomical and physiological dynamics, which render a particular sensor design suboptimal. Multiple sensors can conceptually enable the system to operate more robustly under such dynamics, assuming the data acquired by different sensors can be adaptively integrated to form a coherent view of the tissue. In this paper, we present an algorithm for data fusion at several levels of information abstraction, raw data, feature, and decision levels, to improve FHR estimation. We validate the proposed technique via in-vivo data collected in gold-standard pregnant ewe experiments using TFO. The root-mean-squared error of our three-level hierarchical data fusion compared to a single-level and two-level fusion improved by over 59% and 51%, respectively. This underscores the robustness of our approach in overcoming optical deep tissue sensing challenges.

We present a method, referred to as Deep Harmonic Finesse (DHF), for separation of non-stationary quasi-periodic signals when limited data is available. The problem frequently arises in wearable systems in which, a combination of quasi-periodic physiological phenomena give rise to the sensed signal, and excessive data collection is prohibitive. Our approach utilizes prior knowledge of time-frequency patterns in the signals to mask and in-paint spectrograms. This is achieved through an application-inspired deep harmonic neural network coupled with an integrated pattern alignment component. The network's structure embeds the implicit harmonic priors within the time-frequency domain, while the pattern-alignment method transforms the sensed signal, ensuring a strong alignment with the network. The effectiveness of the algorithm is demonstrated in the context of non-invasive fetal monitoring using both synthesized and in vivo data. When applied to the synthesized data, our method exhibits significant improvements in signal-to-distortion ratio (26% on average) and mean squared error (80% on average), compared to the best competing method. When applied to in vivo data captured in pregnant animal studies, our method improves the correlation error between estimated fetal blood oxygen saturation and the ground truth by 80.5% compared to the state of the art.

Quasi-periodic signal separation poses a significant challenge in wearable systems with limited data, particularly when the measured signal, influenced by multiple physiological sources, is under-represented. Addressing this issue, we introduce Deep Quasi-Periodic Priors (DQPP), a signal separation method for non-stationary, single-detector, quasi-periodic signals using an isolated input data. This approach incorporates masking and in-painting of the time-frequency spectrogram, while integrating prior harmonic and temporal patterns within the deep neural network structure. Moreover, a pattern alignment unit transforms the input signal's time-frequency patterns to closely align with the deep harmonic neural structure. The efficacy of DQPP is demonstrated in non-invasive fetal oxygen monitoring, using both synthetic and in vivo data, underscoring its applicability and potential in wearable technology.

Dicrotic Notch (DN), one of the most significant and indicative features of the arterial blood pressure (ABP) waveform, becomes less pronounced and thus harder to identify as a matter of aging and pathological vascular stiffness. Generalizable and automatic DN identification for such edge cases is even more challenging in the presence of unexpected ABP waveform deformations that happen due to internal and external noise sources or pathological conditions that cause hemodynamic instability. We propose a physics-aware approach, named Physiowise (PW), that first employs a cardiovascular model to augment the original ABP waveform and reduce unexpected deformations, then apply a set of predefined rules on the augmented signal to find DN locations. We have tested the proposed method on in-vivo data gathered from 14 pigs under hemorrhage and sepsis study. Our result indicates 52% overall mean error improvement with 16% higher detection accuracy within the lowest permitted error range of 30 ms. An additional hybrid methodology is also proposed to allow combining augmentation with any application-specific user-defined rule set.

In wearable optical sensing applications whose target tissue is not superficial, such as deep tissue oximetry, the task of embedded system design has to strike a balance between two competing factors. On one hand, the sensing task is assisted by increasing the radiated energy into the body, which in turn, improves the signal-to-noise ratio (SNR) of the deep tissue at the sensor. On the other hand, patient safety consideration imposes a constraint on the amount of radiated energy into the body. In this paper, we study the trade-offs between the two factors by exploring the design space of the light source activation pulse. Furthermore, we propose BASS, an algorithm that leverages the activation pulse design space exploration, which further optimizes deep tissue SNR via spectral averaging, while ensuring the radiated energy into the body meets a safe upper bound. The effectiveness of the proposed technique is demonstrated via analytical derivations, simulations, and in vivo measurements in both pregnant sheep models and human subjects.

Current intrapartum fetal well-being assessment is performed using electronic fetal monitoring (EFM), technically referred to as cardiotocography (CTG), which transabdominally monitors fetal heart rate (FHR) in relationship to maternal uterine contractions. Sometimes the deceleration in FHR following a uterine contraction can be sign of fetal hypoxic distress, but it may also be a normal physiological response. Multiple studies have shown that EFM has a high false positive rate for detecting fetal hypoxia. This has caused a rise in emergency Cesarean section (C-section) deliveries performed in the US over the years, while the rates of various conditions associated with anoxic brain injury at birth remain unchanged. The underlying problem is that many factors other than hypoxia can cause non-reassuring CTG traces and a more objective measure of oxygen supply to the fetal brain is not conveniently available. We are working to develop a transabdominal fetal pulse oximetry (TFO) system to non-invasively measure fetal arterial blood oxygen saturation (FSpO2) in order to enhance intrapartum fetal monitoring. This paper gives an overview of the past and ongoing work performed to develop TFO, highlights the main engineering and clinical challenges faced and presents preliminary results that demonstrate feasibility of TFO in both pregnant sheep models and human subjects.

Non-invasive transabdominal fetal oximetry (TFO) has the potential to improve delivery outcomes by providing physicians with an objective metric of fetal well-being during labor. Fundamentally, the technology is based on sending light through the maternal abdomen to investigate deep fetal tissue, followed by detection and processing of the light that returns (via scattering) to the outside of the maternal abdomen. The placement of the photodetector in relation to the light source critically impacts TFO system performance, including its operational robustness in the face of fetal depth variation. However, anatomical differences between pregnant women cause the fetal depths to vary drastically, which further complicates the optical probe (optode) design optimization. In this paper, we present a methodology to solve this problem. We frame optode design space exploration as a multi-objective optimization problem, where hardware complexity (cost) and performance across a wider patient population (robustness) form competing objectives. We propose a model-based approach to characterize the Pareto-optimal points in the optode design space, through which a specific design is selected. Experimental evaluation via simulation and in vivo measurement on pregnant sheep support the efficacy of our approach.