The research introduces what its authors call a cardiotocography age, an AI-derived measure modeled loosely on the idea of biological age. Rather than asking whether a fetal heart tracing looks reassuring or non-reassuring in the moment, the algorithm was trained to estimate where a given pregnancy sits along a developmental trajectory inferred from thousands of prior recordings. The gap between the cardiotocography age the model assigns and the actual gestational age of the fetus serves as the digital biomarker. When that gap widens in one direction, the researchers report, it flags pregnancies at elevated risk of adverse outcomes such as hypertensive complications, fetal growth restriction, and emergency operative delivery.

The underlying insight is that a fetal heart rate pattern is not merely a snapshot of moment-to-moment oxygenation but a composite signature of autonomic nervous system maturation, placental function, and intrauterine environment. Cardiologists learned something analogous when they discovered that a machine can read an electrocardiogram and estimate a patient’s physiological age; hearts that look older than their chronological age tend to belong to people at higher cardiovascular risk. The npj Women’s Health study transfers that logic to the fetus, arguing that the heart rate variability, baseline trends, accelerations, and decelerations inscribed on a cardiotocography strip encode a quantifiable signature of developmental maturity.

Technically, the approach rests on deep learning applied to raw cardiotocographic signals rather than to the summary indices clinicians typically compute. Conventional analysis reduces a tracing to a handful of features, such as baseline heart rate, variability bands, and the count of accelerations and decelerations, each defined by consensus criteria drafted before modern computing. These parameters are individually weak predictors, and large trials of computerized cardiotocography interpretation have historically failed to show that automated alerts improve outcomes, partly because the features were chosen by human intuition decades ago. The new model instead learns its own representations directly from the continuous signal, using architectures capable of detecting temporal patterns too subtle or too diffuse for the standard feature set to capture.

Training such a model requires careful handling of a notorious problem in fetal monitoring: the labels are noisy and the populations are imbalanced. Adverse outcomes are, fortunately, rare relative to the number of recordings collected, which means an algorithm can achieve deceptively high accuracy by simply predicting that everything is fine. The researchers addressed this through appropriate validation design, holding out complete cohorts for testing and evaluating the model against outcomes that had not yet occurred at the time of the recording. This temporal separation matters enormously. Many earlier machine learning studies in obstetrics tested their algorithms on tracings taken during labor and then predicted outcomes of that same labor, a design that risks simply detecting the crisis already underway. The cardiotocography age concept is explicitly forward-looking, derived from antenatal recordings and validated against complications arising later in the pregnancy.

The reported performance suggests the biomarker has genuine discriminative power. Pregnancies whose AI-assigned cardiotocography age lagged behind their gestational age clustered disproportionately among those that later developed hypertensive disorders of pregnancy, delivered growth-restricted infants, or required urgent cesarean sections for fetal compromise. The signal held up after adjustment for conventional risk factors, meaning the model was not merely rediscovering maternal age, body mass index, or pre-existing hypertension, information clinicians already collect. Instead, the fetal heart tracing itself appeared to contain additive information, a conclusion that, if replicated across diverse populations, would justify incorporating the measure into routine antenatal assessment alongside ultrasound and blood pressure monitoring.

Why should a heart rate pattern recorded weeks before symptoms predict a disorder like preeclampsia, which is conventionally understood as a placental disease manifesting through maternal hypertension? The most plausible explanation lies in the shared biology of placental insufficiency. When the placenta fails to establish adequate perfusion, the fetus adapts, redistributing blood flow and modulating autonomic tone in ways that subtly reshape heart rate dynamics long before growth falters or maternal blood pressure rises. These adaptations leave traces in the variability and periodicity of the fetal electrocardiographic signal captured at the maternal abdomen. In effect, the algorithm learns to recognize the physiological fingerprint of a struggling placenta, converting it into a number that clinicians can act on.

The digital biomarker framing carries implications beyond any single disease. Precision-medicine researchers have increasingly argued that pregnancy is an ideal proving ground for continuous, physiological, computationally interpretable data, because the obstetric population is monitored intensively and the outcomes are discrete and consequential. A validated cardiotocography age could function as a longitudinal vital sign for the fetus, tracked across visits like blood pressure or fetal growth percentiles. Deviation from the expected trajectory would trigger targeted surveillance: serial growth scans, Doppler studies of umbilical artery flow, or low-dose aspirin prophylaxis in cases where risk models currently rely on coarse demographic and biophysical screening. The measure could also serve as an endpoint in clinical trials of interventions designed to improve placental function, replacing months of waiting with a computable surrogate readout.

Significant hurdles remain before the metric enters practice. The study’s training data reflect the equipment, acquisition protocols, and population characteristics of the institutions that contributed recordings, and cardiotocographic signals are sensitive to gestational age in ways that demand robust calibration across the full range of pregnancy. Regulatory pathways for adaptive algorithms in medical devices are still maturing, and clinicians will reasonably ask what they should do with a risk score in the absence of trials demonstrating that acting on it improves outcomes. History counsels humility: electronic fetal monitoring itself was adopted worldwide on physiological plausibility alone, and only later did randomized trials reveal that its widespread use had reduced neonatal seizures while dramatically increasing cesarean rates without lowering cerebral palsy incidence. A new biomarker built on the same signal must clear a higher evidentiary bar than its predecessor did.

Yet the conceptual achievement is difficult to overstate. The study demonstrates that an ordinary, ubiquitous clinical recording, taken with equipment already installed in virtually every maternity unit on earth, contains information about future pregnancy health that decades of expert interpretation never systematically extracted. If subsequent multi-center validation confirms the findings across populations and devices, the cardiotocography age could join the growing family of AI-derived organ ages, alongside brain age, heart age, and retinal age, that are reshaping how medicine quantifies risk. For a field in which the central tools have remained essentially unchanged since the 1960s, the prospect of turning the labor ward’s oldest instrument into a predictive window on the pregnancy’s future marks a genuinely new chapter in fetal medicine.

Subject of Research: An AI-derived cardiotocography age biomarker that predicts future adverse pregnancy outcomes from routine fetal heart rate recordings

Article Title: AI-derived cardiotocography age as a digital biomarker for predicting future adverse pregnancy outcomes

Article References: Gu, J., Lin, Z., Ma, J., Wang, J., Zhang, L., Bai, R., Tu, Z., Jiang, Y., Xie, D., Zhou, Y., Liu, G., & Hong, S. (2026). AI-derived cardiotocography age as a digital biomarker for predicting future adverse pregnancy outcomes. npj Women's Health. https://doi.org/10.1038/s44294-026-00165-4

Image Credits: AI Generated

DOI: 10.1038/s44294-026-00165-4

Keywords: artificial intelligence, cardiotocography, digital biomarker, pregnancy outcomes, fetal heart rate monitoring, preeclampsia, fetal growth restriction, deep learning, maternal-fetal medicine, predictive analytics, placental insufficiency, npj Women's Health

The impetus behind this innovation stems from the challenges inherent in fetal monitoring. Fetuses are constantly moving, and their umbilical cords shift position unpredictably, complicating consistent measurement with existing technologies. The UC San Diego team overcame these barriers by integrating advanced autonomous tracking algorithms within the wearable patch. These algorithms precisely identify and follow the umbilical cord’s position amid fetal and maternal motion, enabling reliable and uninterrupted measurements of critical parameters such as blood flow velocity and cardiac signals. This autonomy is crucial for maintaining data integrity during hours-long monitoring sessions.

During rigorous clinical trials conducted at prominent medical centers including UC San Diego Health’s Jacobs Medical Center and the University of Oxford’s John Radcliffe Hospital, the patch demonstrated remarkable fidelity. It generated continuous readings closely mirroring those obtained from gold-standard handheld ultrasound devices. Notably, the system monitored 62 pregnancies featuring a spectrum of conditions, ranging from normal development to high-risk scenarios characterized by gestational diabetes, pre-eclampsia, and fetal growth abnormalities. This robust dataset validates the device’s versatility and reliability across a diverse patient population.

One of the most compelling clinical outcomes emerged when the patch detected prolonged abnormal fetal signals indicative of distress. This early warning precipitated a timely medical intervention leading to a preterm Cesarean delivery at 29 weeks. Physicians credit the continuous monitoring capability for potentially saving the infant’s life by enabling earlier detection than conventional episodic ultrasounds permit. The case highlights the immense potential of wearable ultrasound technology to shift prenatal care paradigms, facilitating proactive management of complications that were previously challenging to identify in a timely manner.

The core technology enabling this breakthrough is built on a decade of pioneering research led by Professor Sheng Xu within UC San Diego’s Department of Chemical and Nano Engineering. His laboratory has been at the forefront of developing wearable ultrasound devices with broad healthcare applications, including noninvasive blood pressure monitoring and mobile cardiac imaging. By leveraging flexible electronics and miniaturized transducers, this ultrasound patch melds comfort with unprecedented functional capability. The current iteration integrates bio-compatible materials that conform intimately to the skin, ensuring consistent acoustic coupling necessary for clear imaging.

Beyond clinical efficacy, the wearable patch holds promise for expanding access to quality prenatal care globally, particularly in low-resource settings where skilled sonographers and continuous monitoring equipment are scarce. The design enables simplified use without expert operators, potentially democratizing fetal health monitoring and reducing disparities in maternal-fetal health outcomes worldwide. Additionally, the team’s future objective includes developing a fully wireless, compact electronic system to further enhance the patch’s portability and user-friendliness.

Technical sophistication underlies the patch’s ability to capture complex hemodynamic parameters. It utilizes high-frequency ultrasound transducers arrayed in a flexible matrix, optimized to penetrate maternal tissue and visualize both the fetus and umbilical cord structures. The embedded machine-learning algorithms analyze returned signals to differentiate subtle variations in blood flow and structural motion, effectively filtering out artifacts from maternal movement. This real-time signal processing is essential for maintaining measurement precision during the natural movements and physiological changes encountered during pregnancy.

The research team also underscores the importance of autonomous operation in clinical contexts. Unlike conventional ultrasounds that necessitate manually repositioning probes to maintain image clarity, the wearable system’s software dynamically adjusts scanning parameters and focal zones based on ongoing feedback from tracking algorithms. This closed-loop control ensures continuous acquisition of diagnostically relevant data without disrupting maternal comfort or requiring frequent clinical visits. Such autonomy marks a significant evolution in non-invasive fetal diagnostics.

In terms of clinical adoption, the wearable ultrasound patch could integrate seamlessly into existing prenatal care frameworks. Physicians could remotely monitor patients through digital interfaces connected to the patch’s data stream, enabling timely interventions guided by continuous physiological insights. The technology aligns with emerging trends toward telemedicine and home-based health monitoring, especially critical during periods when in-person visits may be limited, such as during global health crises. This proactive approach could significantly enhance outcomes for mothers and their babies worldwide.

The research was disseminated in a recent publication in the prestigious journal Nature Biotechnology, underscoring its scientific rigor and potential impact. Funding support came from prominent agencies including the Wellcome Leap initiative and the National Institutes of Health, reflecting the project’s high priority in the biomedical research community. The cross-institutional collaboration—with contributions from UC San Diego and the University of Oxford—further emphasizes the global commitment to advancing maternal-fetal health technologies.

Looking ahead, the engineering team is focused on miniaturizing the electronics and incorporating wireless power and data transmission capabilities. These innovations will eliminate the need for tethered connections, enhancing maternal mobility and enabling long-term outpatient monitoring. Such advancements will facilitate integration with smartphone applications and healthcare provider systems, creating a comprehensive ecosystem for prenatal surveillance. This trajectory aligns with broader trends in wearable health technologies aiming to deliver continuous, real-time diagnostics beyond traditional clinical environments.

In summary, this wearable ultrasound patch signifies a paradigm shift in prenatal care. Marrying cutting-edge materials science, flexible electronics, and autonomous algorithms, it delivers continuous, high-fidelity fetal monitoring that was previously unattainable. The ability to detect complications earlier and operate without specialized operators opens new horizons in maternal and neonatal health. As development proceeds toward wireless, user-friendly designs, this technology promises to become an indispensable tool in safeguarding the next generation’s well-being from the earliest stages of life.

Subject of Research: Continuous fetal monitoring during pregnancy using wearable ultrasound technology
Article Title: Fetal monitoring for high-risk pregnancies using a wearable ultrasound patch
News Publication Date: 26-May-2026
Web References: 10.1038/s41587-026-03140-1
Image Credits: Geonho (Tom) Park

Keywords

Wearable ultrasound, prenatal monitoring, fetal health, umbilical cord tracking, high-risk pregnancy, continuous fetal monitoring, flexible electronics, autonomous algorithms, maternal-fetal diagnostics, non-invasive ultrasound patch, machine learning, biomedical innovation

Early screening for preeclampsia during the first trimester is a clinical priority, aiming to identify at-risk pregnancies to implement preventive treatments like low-dose aspirin. However, established screening protocols developed primarily in Western populations have shown mixed performance when applied in different ethnic and geographic contexts. This study distinctly addresses that gap by evaluating multiple combined screening strategies—including maternal history, biophysical markers, and biochemical parameters—within the Indonesian demographic framework. The researchers’ integrated methodology encompassed maternal characteristics, mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI), and serum biomarkers such as placental growth factor (PlGF) and pregnancy-associated plasma protein-A (PAPP-A).

Methodological rigor was evident through their prospective cohort design, enrolling a significant sample size representative of various Indonesian ethnic groups and geographic regions. By longitudinally collating clinical, hemodynamic, and serological data in the first trimester, the research cohort enabled robust statistical analyses of each screening approach’s sensitivity, specificity, positive predictive value, and overall predictive accuracy. The multi-modal screening frameworks were subjected to rigorous comparative analysis, highlighting nuances in biomarker performance linked with underlying genetic and environmental variability endemic to Indonesia.

One of the study’s pivotal findings demonstrated that the inclusion of Doppler ultrasound measurement of the uterine artery pulsatility index significantly enhances the accuracy of preeclampsia risk prediction beyond maternal history and biochemical markers alone. This hemodynamic parameter reflects impaired placental perfusion, a pathophysiological hallmark of early-onset preeclampsia, and may manifest differently across populations due to variances in vascular physiology. When coupled with serum PlGF levels—a marker of angiogenesis—screening efficacy was markedly elevated, enabling clinicians to stratify maternal risk profiles with unprecedented precision.

Interestingly, the research underscores how pregnancy-associated plasma protein-A (PAPP-A), despite its established role in aneuploidy screening, exhibited variable predictive power for preeclampsia within the Indonesian cohort. This differential performance suggests that universal biomarker thresholds may not be applicable globally, necessitating locally calibrated reference ranges and risk algorithms. Such a discovery calls for regional customization in prenatal screening protocols to mitigate false-negative and false-positive rates, thereby optimizing resource allocation in healthcare settings.

Moreover, the findings emphasize the synergistic effect of combining maternal clinical data with biophysical and biochemical markers to create an integrative risk prediction model. This multifactorial approach counters the limitations of relying on isolated parameters and addresses the complex etiology of preeclampsia, which involves immunological maladaptation, endothelial dysfunction, and genetic predisposition. The study cogently argues for an adaptive screening framework that incorporates population-specific variables and dynamically adjusts thresholds based on real-world epidemiological data.

In the context of Indonesian public health, where maternal mortality rates remain relatively high, these insights are particularly vital. The implementation of improved first-trimester screening algorithms can inform timely prophylactic interventions, reducing the incidence of severe preeclampsia and related obstetric complications such as eclampsia, preterm birth, and fetal growth restriction. Furthermore, the research highlights the logistical feasibility of integrating advanced ultrasound and biomarker assays into routine antenatal visits within Indonesia’s healthcare infrastructure, including regional hospitals and community clinics.

The research team also recognized socioeconomic and geographic disparities across Indonesia that may influence screening accessibility and outcomes. Their analysis factored in urban versus rural healthcare delivery disparities, variations in nutritional status, and environmental factors such as altitude and endemic diseases. These layers of complexity reinforce the need for comprehensive prenatal screening strategies that are not only clinically effective but also equitable and culturally sensitive.

The paper’s discussion extends to the technological and operational challenges inherent in scaling up combined screening protocols. While Doppler ultrasound and serum biomarker assays enhance predictive accuracy, their deployment requires trained personnel, advanced equipment, and consistent quality control measures. Investing in healthcare workforce training and infrastructure modernization emerges as a critical prerequisite for successful widescale implementation, ensuring that early prediction translates into meaningful clinical intervention.

From a scientific standpoint, this study fills an important void by contextualizing preeclampsia screening within the unique genetic admixture of the Indonesian population—a diverse archipelago with more than 300 distinct ethnic groups. The genetic heterogeneity potentially influences biomarker expression and vascular responses, underscoring the importance of population-tailored research. These findings contribute valuable data to the global effort aimed at refining predictive models to accommodate ethnic and geographical diversity, thereby enhancing the global applicability of screening tools.

At the molecular level, the research sheds light on the angiogenic imbalance implicated in preeclampsia pathogenesis. The pivotal role of PlGF, its interaction with anti-angiogenic factors like soluble fms-like tyrosine kinase-1 (sFlt-1), and the resulting endothelial dysfunction represent a fertile ground for novel diagnostic and therapeutic avenues. By validating PlGF-based assays in an Indonesian cohort, the study expands the evidence base, reinforcing the biomarker’s utility in diverse populations.

The study also suggests potential for integrating genetic and epigenetic markers into future screening paradigms. While such advanced molecular diagnostics were beyond the scope of the current research, the authors advocate for continued exploration of how genetic predisposition and environmental epigenetic modifications interact to influence preeclampsia susceptibility. Such integrative research may ultimately refine risk stratification algorithms and facilitate personalized prenatal care.

Importantly, this research may prompt policymakers and healthcare stakeholders in Indonesia and similar settings to reevaluate national prenatal screening guidelines. By demonstrating the superiority of combined screening approaches, especially those incorporating UtA-PI and PlGF, the study makes a compelling case for guideline updates. This could catalyze improved population health outcomes by mitigating the burden of hypertensive disorders in pregnancy.

The implications extend further, as early identification of at-risk pregnancies enables resource optimization, aligning frontline healthcare interventions with the needs of vulnerable mothers. Early preventive strategies, including low-dose aspirin prophylaxis initiated before 16 weeks gestation, are most effective when predicated on accurate risk prediction—a threshold that this study moves closer to achieving within the Indonesian context.

Finally, the publication of this comparative analysis in a high-impact perinatology journal reflects its significance in advancing obstetric medicine. The detailed insights into multicentric data, combined with rigorous statistical validation, provide a model framework for similar investigations in other ethnically diverse and resource-constrained regions globally, contributing to a broader agenda of equitable maternal health.

As the global medical community continues to grapple with the challenge of preeclampsia detection and prevention, such population-specific, integrative screening studies herald a new era of precision prenatal medicine. These insights not only promise to transform clinical pathways in Indonesia but also offer a blueprint for optimizing maternal-fetal health outcomes worldwide by tailoring screening technologies to the unique physiological and sociodemographic landscapes of diverse populations.

Subject of Research: First trimester combined screening methods for preeclampsia prediction in the Indonesian population

Article Title: Comparison of first trimester preeclampsia combined screening performances with various approaches in the Indonesian population

Article References:
Al Fattah, A.N., Mahindra, M.P., Yusrika, M.U. et al. Comparison of first trimester preeclampsia combined screening performances with various approaches in the Indonesian population. J Perinatol (2025). https://doi.org/10.1038/s41372-025-02316-y

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s41372-025-02316-y

The heart of Mirvie’s approach lies in the understanding and analysis of RNA molecules present within maternal blood. These molecules, known as messenger RNA, play a crucial role in cellular communication and function. By examining these RNAs, Mirvie intends to decode vital information regarding the health status of both the mother and the developing fetus. This unprecedented ability to analyze RNA during pregnancy presents an opportunity to identify risk factors that could lead to complications, enabling proactive management of maternal care.

Research indicates that complications during pregnancy can arise unexpectedly, often leading to life-threatening situations for both the mother and the child. However, Mirvie’s innovative technology harnesses the power of RNA sequencing to provide insights that were previously unattainable. This process involves studying the expression levels of various RNA transcripts that correspond to specific genes involved in pregnancy. By analyzing these levels, healthcare providers can gain real-time insights into potential risks associated with the pregnancy.

In recent studies, Mirvie has demonstrated its capability to discern between healthy pregnancies and those at risk for complications such as preeclampsia or fetal growth restriction. Armed with this information, healthcare providers can quickly develop customized care plans that mitigate risks and enhance monitoring of at-risk pregnancies. This individualized approach not only empowers healthcare professionals but also provides expectant mothers with peace of mind, knowing that their pregnancies are being monitored with cutting-edge technologies.

The implications of this research extend beyond merely identifying potential risks; they also encompass the ability to implement effective and timely interventions. Mirvie’s technology enables doctors to offer personalized recommendations that can lead to better health outcomes for mothers and their newborns. The focus on preventive strategies marks a significant departure from traditional reactive approaches to maternity care, promising a future where expectant mothers receive more comprehensive and anticipatory care.

By leveraging advanced machine learning algorithms and data analytics, Mirvie has developed a platform that continually learns and evolves. As more data is gathered, the algorithms refine their predictive capabilities, thus enhancing the precision of risk assessments. This creates a dynamic health-monitoring system that adapts to the changing needs of both mother and child throughout the pregnancy journey.

Moreover, the societal implications of such technology should not be overlooked. Pregnancy-related complications are not only a health issue but also a socio-economic one, as they often lead to increased healthcare costs, lost productivity, and immeasurable emotional stress. By implementing effective risk assessment and management strategies, there is a potential to alleviate some of these burdens on families and healthcare systems alike.

The use of RNA analysis through Mirvie’s innovative platform is revolutionary, as it represents a shift towards a more integrated form of healthcare where information is readily accessible and actionable. It empowers mothers to take control of their health journeys, thus promoting a shared decision-making process between healthcare providers and patients. This collaboration ensures that women are not only passive recipients of care but active participants in their health management.

As research in this field continues to expand, so too will the possibilities for improving maternal health outcomes. Mirvie is paving the way for a new era in obstetrics, where the integration of technology into pregnancy care becomes commonplace. It serves as a beacon of hope for millions of expectant mothers globally, emphasizing that the future of prenatal care lies in the combination of science, compassion, and innovation.

In conclusion, the advancements in maternal health diagnostics spearheaded by Mirvie mark a critical turning point in the management of pregnancy complications. The spotlight on RNA and its role in prenatal health underscores the potential for early detection and intervention to improve outcomes. As we look to the future, the promise of personalized, proactive care becomes a reality, fundamentally transforming the landscape of maternal health.

Subject of Research: RNA diagnostics in maternal health
Article Title: Transforming Maternal Health Through RNA Diagnostics
News Publication Date: [Date not provided]
Web References: [No references available]
References: [No references available]
Image Credits: Credit: Mirvie

Keywords: Maternal health, RNA diagnostics, pregnancy complications, prenatal care, personalized medicine, preventive strategies, fetal health, obstetrics, health technology.