The review, conducted by Edwin Ho Yin Lui and Ralph Jasper Mobbs of the University of New South Wales and the NeuroSpine Surgery Research Group in Sydney, followed the PRISMA-ScR reporting guidelines and searched PubMed, Embase, and Scopus for peer-reviewed studies that used a smartphone’s internal inertial measurement unit, or IMU, to quantify mobility, gait, or postural transitions. From an initial yield of 1,063 records, 84 studies made the final cut. The researchers then charted each study across four domains: the clinical target and purpose, the methodological implementation, the technological infrastructure, and the extracted metrics and validation standards. The goal was not to pool results into a meta-analysis — the field is far too heterogeneous for that — but to map where the science actually stands and where it stalls on the road to the clinic.

The headline finding is that smartphone-based mobility analysis has spread far beyond the engineering lab. Neurology dominated the clinical landscape, accounting for 36.9 percent of studies, with Parkinson’s disease alone featured in 19 percent and multiple sclerosis in 6 percent. Geriatrics followed at 14.3 percent and orthopedics at 13.1 percent, with smaller contributions from rheumatology and oncology. Perhaps more striking is what researchers are trying to do with the data: only 10.7 percent of studies were primarily validation exercises, while the overwhelming majority — 89.3 percent — pursued clinically directed aims such as diagnosis (36.9 percent), prognostication (38.1 percent), or longitudinal monitoring (14.3 percent). In other words, the field has largely moved past asking whether phones can measure movement and is now asking whether those measurements mean something for patients.

The clinical logic is compelling. Walking speed and gait characteristics have been repeatedly linked to cognitive decline, mortality, neurodegenerative trajectories, and disease progression — leading some researchers to call gait the sixth vital sign. Yet routine assessment still relies heavily on patient-reported questionnaires and episodic clinic visits, which capture only a snapshot of function under artificial conditions. Laboratory gait analysis, with its three-dimensional optoelectronic motion capture and force plates, offers exquisite precision but is expensive, immobile, and utterly unsuited to continuous monitoring. Dedicated research wearables fare better but impose costs and sustained-use burdens of their own. Smartphones, by contrast, are already carried by billions of people every day, making them arguably the most scalable mobility-sensing platform ever deployed.

But the review’s detailed breakdown reveals a deep methodological disconnect between the promise and the practice. More than half of the studies — 54.8 percent — confined their assessments to controlled clinical or laboratory environments, and 67.9 percent required a clinician or researcher to supervise the test. A striking 73.8 percent depended on active testing protocols, in which participants deliberately performed structured tasks such as short walk tests, the timed up-and-go, or the six-minute walk test. Only 23.8 percent of studies captured passive, free-living mobility — the spontaneous, unscripted walking that happens in kitchens, sidewalks, and shopping malls. Similarly, 63.1 percent collected a single cross-sectional snapshot rather than continuous longitudinal data. The very feature that makes smartphones revolutionary — their unobtrusive presence in daily life — remains largely untapped.

The technological infrastructure tells a similar story of fragmentation. In 71.4 percent of studies, participants had to secure the phone to a fixed anatomical location, typically the waist or lower back, using belts, straps, or pouches — a constraint that partly recreates the burden of dedicated wearables and may be impractical for older adults or people with cognitive impairment. Software is even more fragmented: 82.1 percent of studies relied on custom-built applications or proprietary research platforms such as mPower, GaitTrack, and GaitMate, while only 7.1 percent integrated with native operating-system health platforms like Apple HealthKit or Google Fit. This patchwork of bespoke pipelines makes it difficult to compare results across studies, reproduce findings, or transport algorithms from one device model to another. Differences in accelerometer resolution, sampling frequency, timestamp accuracy, calibration, and sensor-fusion pipelines — not to mention operating-system updates and aggressive power-management policies that can silently interrupt background data collection — all conspire to undermine reproducibility.

What are researchers actually extracting from these sensors? The most common measures are the macro-mobility staples: gait speed appeared in 38.1 percent of studies, step count in 33.3 percent, cadence in 32.1 percent, and step length in 28.6 percent. Gait-quality metrics — stance-to-swing ratios, asymmetry indices, temporal variability, and nonlinear measures such as approximate entropy — were reported less often, despite their potential to reveal neurological and musculoskeletal dysfunction that simple step counts miss. Notably, nearly a third of studies skipped interpretable kinematic parameters altogether, feeding raw triaxial acceleration into machine-learning classifiers. Validation, where performed, typically involved comparison against three-dimensional motion capture, pressure mats, dedicated wearables, or clinical rating scales. The review’s authors are careful to distinguish what such comparisons prove: technical validity, meaning the measure is accurate and reliable; clinical validity, meaning it associates with or predicts a meaningful health state; and clinical utility, meaning it actually changes clinical decisions or improves patient outcomes. The mapped literature demonstrates the first two in progress — but routine clinical utility has not been established.

The ecological question looms largest. Free-living monitoring can capture fatigue, diurnal fluctuations, and long-term variability that a brief clinic visit cannot, and the review argues that passive and structured assessment should be treated as complementary rather than interchangeable. Yet real-world data come with real-world noise: walking surface, gradient, footwear, assistive devices, crowding, and whether the phone is in a pocket, hand, or bag can all shift the measured signal independently of any clinical change. Crucially, the authors argue, this contextual variation is not always noise to be eliminated — it may reveal how environmental demands shape functional performance. Emerging analytical strategies, including placement-robust models, automated detection and segmentation of walking bouts, steady-state filtering, and within-person longitudinal comparison, aim to separate context-related from health-related variation. The experience of the mPower study, which enrolled more than 12,000 participants remotely for Parkinson’s research but suffered substantial attrition, underscores that scalability does not guarantee sustained engagement — a burden that passive background architectures may help relieve.

Privacy and equity complete the translation checklist. Continuous passive sensing, even without GPS, can expose daily routines, periods of inactivity, and changes in health status, demanding transparent consent, data minimization, on-device processing where feasible, encryption, and predefined retention and deletion policies. Governance must also confront data ownership, linkage with health records, third-party access, and accountability for missed deterioration — plus equitable alternatives for patients who do not own or consistently carry compatible smartphones. The review’s bottom line is measured but optimistic: smartphones are genuinely promising candidate platforms for multidimensional mobility sensing, and the field’s shift from validation toward diagnosis and prognostication shows real momentum. What stands between promising digital measures and routine clinical practice is disciplined translation — standardized acquisition and reporting, cross-device and cross-platform validation, context-aware interpretation, privacy-preserving governance, and prospective trials proving that these pocket-sized sensors actually improve clinical decisions and patients’ lives.

Subject of Research: Smartphone-based mobility and gait analysis for clinical assessment

Article Title: Clinical utility and methodological implementation of smartphone-based mobility analysis: a scoping review

Article References: Lui, E. H. Y., & Mobbs, R. J. (2026). Clinical utility and methodological implementation of smartphone-based mobility analysis: a scoping review. Journal of Neurology, 273(10), Article 597. https://doi.org/10.1007/s00415-026-14131-2

Image Credits: AI Generated

DOI: 10.1007/s00415-026-14131-2

Keywords: smartphones, gait analysis, mobility, digital biomarkers, neurology, Parkinson's disease, wearable technology, inertial measurement units, mHealth, scoping review, clinical utility, passive monitoring

The review identifies four foundational concerns that constrain the translation of AI dementia diagnostics into everyday practice, and the first is deceptively mundane: the data itself. Most diagnostic models are trained and tested on highly specialized research cohorts, populations recruited through memory clinics, imaging studies or longitudinal registries that bear little resemblance to the mixed, often messy patient population a general practitioner actually sees. This creates selection bias of a profound kind. Patients who volunteer for research studies tend to be younger, better educated, more health-conscious and more thoroughly worked up than the average person shuffling into a primary care appointment worried about forgetting names. When a model calibrated on such a pristine sample is deployed in the wild, its performance can collapse. The problem is compounded by data leakage, where hidden overlaps between training and test sets inflate reported accuracy far beyond what any independent evaluation would support, producing area-under-the-curve statistics that look spectacular on paper and evaporate in practice.

The second concern strikes at something deeper: the very ground truth against which these algorithms are judged is itself uncertain. A diagnosis of dementia, particularly in its earliest stages or in mild cognitive impairment, is not a neat, objective label waiting to be predicted. It is a probabilistic clinical judgment, shaped by which specialist saw the patient, which criteria were applied, which cognitive assessments such as the Mini-Mental State Examination or the Montreal Cognitive Assessment were administered, and how symptoms happened to present on a given day. Autopsy-confirmed pathology frequently disagrees with lifetime clinical labels, and disagreements between expert raters are common. The authors point out that when the labels themselves are noisy, the entire enterprise of performance evaluation becomes unstable. A model scoring 95 percent accuracy against an imperfect reference standard is not necessarily 95 percent correct; it may simply have learned to mimic the systematic quirks of the clinicians who generated the labels. This places hard, structural limits on how meaningful any reported model performance can be.

Third, the review takes aim at what it calls circular logic, coining a memorable phrase for algorithms that act as complexity launderers. The idea is this: many AI systems are fed exactly the same clinical data that doctors already use, cognitive test scores, demographic information, existing diagnoses, and then repackaged to produce a prediction. The model does not add new information; it merely reshuffles and obscures what was already on the chart, lending the output an aura of algorithmic authority and computational sophistication. A clinician could be forgiven for thinking the machine has discovered something novel, when in fact it has simply re-expressed the same signal through thousands of learned parameters. Unless a tool ingests genuinely new data modalities, such as retinal imaging, speech biomarkers or longitudinal patterns invisible to human observers, it risks being an elaborate and expensive restatement of existing knowledge, providing the illusion of insight without the substance.

The fourth concern may be the most consequential: a clinical-ethical mismatch between where these tools are built and where they are meant to be used. AI diagnostic systems are typically designed with specialist memory clinics in mind, settings where patients have already been referred, assessed and often expect a definitive workup. But the greatest potential for early detection lies in primary care, where the population is unselected and the stakes of a wrong prediction are different in kind. The authors warn of an ethical burden of prediction when algorithms flag possible dementia in a setting with limited therapeutic options and thin support infrastructure. A false positive in a memory clinic can be clarified by a specialist; a false positive delivered by a screening algorithm in primary care may trigger years of anxiety, stigma, insurance implications and altered family dynamics for a person who never had the disease. Conversely, a false negative can falsely reassure a family while the underlying neurodegeneration advances unchecked. Predicting is cheap; carrying the consequences of prediction is not.

Underlying all four concerns is a sobering epidemiological reality. Dementia affects tens of millions of people worldwide, and the window for intervening meaningfully, particularly with the new generation of disease-modifying therapies targeting amyloid pathology, is believed to be early, often before overt symptoms dominate. This creates enormous commercial and academic pressure to push diagnostic AI to market quickly, and that pressure is precisely what makes the field vulnerable to solutionism. The review does not argue that AI is useless; it argues that the current incentive structure rewards the wrong things, benchmark performance rather than patient benefit, novelty rather than generalizability, and publication-worthy metrics rather than demonstrable impact on outcomes that matter to patients and their families.

In response, the authors propose a paradigm shift: abandoning the narrow obsession with accuracy in favor of comprehensive value evaluation, operationalized through a mandatory four-axis framework that any new diagnostic tool should satisfy before entering clinical use. The first axis is analytical validity, meaning the tool must demonstrably measure what it claims to measure, with evaluation methods that explicitly account for the uncertainty in diagnostic ground truth labels rather than treating them as gospel. The second is clinical validity, demonstrated in the relevant populations, not in curated research cohorts, with performance tested in primary care settings where the tools will actually be deployed and where case mix, comorbidity and presentation differ radically from memory clinics.

The third axis is clinical utility, and it demands the hardest question of all: does the tool improve outcomes that are meaningful to patients and families? A model that detects dementia six months earlier is worthless, perhaps harmful, if that earlier detection changes nothing about treatment, care planning, access to support or quality of life. Utility must be demonstrated on endpoints that patients themselves would recognize, such as delayed institutionalization, better-informed advance planning, reduced crisis events or improved caregiver wellbeing, not merely on statistical discrimination measured by area under the curve. The fourth axis is ethical, legal and social viability, abbreviated ELSI, which requires that any deployed tool come with integrated support pathways. A positive prediction must trigger something: counseling, follow-up assessment, access to services, a plan. Without such pathways, screening becomes a mechanism for generating anxiety at scale, and the ethical cost falls on the patients least equipped to bear it.

Notably, the framework resonates with established regulatory thinking, including the concept of the total product life cycle, which treats a diagnostic tool not as a finished artifact validated once but as a living system requiring continuous monitoring, revalidation and post-market surveillance as populations, data streams and clinical practices evolve. The authors, whose work was supported by the Shenzhen Medical Research Fund and the National Natural Science Foundation of China, argue that adopting this rigorous, multi-dimensional standard is essential to guide AI from promising technology toward mature clinical science. The message to the field is bracing but constructive: stop asking how accurate your algorithm is, and start asking whether it makes any real difference, for anyone, anywhere, under real-world conditions. For a technology that promises to reshape how humanity confronts one of its most feared diseases, that may be the most important diagnostic test of all.

Subject of Research: The challenges of translating artificial intelligence tools for early dementia diagnosis from research into clinical practice

Article Title: AI in early dementia diagnosis: Beyond technological solutionism in clinical practice

Article References: Chen, S., Underwood, B. R., Mueller, C., Amin, J., Zeng, H., Li, J., Li, X., Jing, Q., Cao, X., & Jiang, F. (2026). AI in early dementia diagnosis: Beyond technological solutionism in clinical practice. BMC Medicine. https://doi.org/10.1186/s12916-026-05248-2

Image Credits: AI Generated

DOI: 10.1186/s12916-026-05248-2

Keywords: artificial intelligence, dementia diagnosis, early detection, machine learning, clinical validation, primary care, technological solutionism, mild cognitive impairment, predictive medicine, data leakage, clinical utility, medical ethics

The study, led by Kristina Tomra Nielsen and colleagues as part of the Danish Intentional Relationship Model research program, set out to evaluate the clinical utility of three Danish-language questionnaires known collectively as the D-CAMQs. These instruments are adapted from the Clinical Assessment of Modes, developed by Renee Taylor to operationalize her Intentional Relationship Model. That model proposes that therapists draw on six distinct interpersonal communication styles, called therapeutic modes: Advocating, Collaborating, Empathizing, Encouraging, Instructing and Problem-solving. Advocating means helping clients access community resources; Collaborating shifts decision-making power to the client; Empathizing involves non-judgmental validation of thoughts and feelings; Encouraging instills hope and courage; Instructing structures, teaches and provides feedback; and Problem-solving guides clients through strategic reasoning about options. According to the model, no single mode is superior, and skilled therapists shift fluidly between them depending on what each client needs in the moment.

To capture how these modes play out in real therapy, the Clinical Assessment of Modes comes in three parts. Before therapy begins, clients complete the CAM-C1, rating how important each mode is to them on a five-point importance scale. After therapy concludes, clients fill in the CAM-C2, reporting how frequently they perceived their therapist actually using each mode. In parallel, the therapist completes the CAM-T, describing their own perception of how often they used each mode with that specific client. The Danish research team had previously translated and culturally adapted all three questionnaires following international guidelines for patient-reported outcome measures, establishing face validity and cultural relevance. What remained unknown was whether the instruments would function usefully in day-to-day clinical practice, not just in the psychometric laboratory.

Clinical utility, in this context, is a four-dimensional concept drawn from Andrew Smart’s multi-dimensional model. Appropriateness asks whether the instrument is relevant and improves clinical decision-making. Accessibility weighs the resources required, especially time, against the benefits gained. Practicability concerns whether instructions and functionality work smoothly, and acceptability addresses ethical, social and psychological concerns around use. The Danish team designed parallel surveys for clients and therapists, each mapped onto these four dimensions, and embedded the questionnaires into genuine therapy courses rather than staged research encounters. Clients completed their pre-therapy questionnaire at the first session, and therapists used the clients’ stated preferences to frame an explicit conversation about how they would work together. At the final session, clients reported on what they had experienced, and the paired results were discussed openly.

Eleven occupational therapists and forty-seven clients aged 23 to 97 took part, recruited from settings ranging from acute hospitals and municipal rehabilitation to psychiatry, home care and specialized neurorehabilitation. Most clients had been referred for neurological conditions. The therapists were all women and none had prior familiarity with the Intentional Relationship Model, making them genuine newcomers to the framework. Recruitment, originally targeting thirty therapists, was hampered by the COVID-19 pandemic, a constraint the authors acknowledge as a major limitation that renders the study exploratory rather than definitive.

The descriptive results painted a coherent picture. Clients rated all six modes as relevant, with median importance scores ranging from 15 to 20 out of a possible 25. Instructing emerged as the most important mode, while Advocating ranked lowest, a pattern echoed in the post-therapy ratings, where clients perceived frequent use of five modes but only occasional use of Advocating. Therapists’ self-ratings followed the same shape, with Advocating rarely used. At the group level, clients and therapists appeared to agree: no obvious discrepancies surfaced between the median profiles.

But when the researchers moved from group medians to individual-level statistics, a more complicated story emerged. Correlations between clients’ preferred modes before therapy and their perceived mode use afterward were moderate to weak, with Spearman’s rho values between 0.26 and 0.48. More strikingly, agreement between clients’ perceptions of mode use and therapists’ self-reported use was weak to trivial, and some correlations were negative, meaning that when a client perceived a mode being used more often, the therapist sometimes reported using it less. In other words, therapists and clients sitting across from each other for weeks of therapy frequently disagreed about the very communication style that defined their collaboration. The authors interpret this cautiously, noting that preferences and perceptions come from different perspectives and may converge differently, but they emphasize that such single-case discrepancies underscore why continuous dialogue about communication is essential rather than optional.

On the utility surveys, clients were largely enthusiastic. Fifty-seven percent felt it was highly relevant to share their communication preferences before therapy, 44 percent found it highly relevant to report and discuss experiences afterward, and 51 percent said discussing preferences significantly shaped the therapy process. Sixty percent judged the time spent on these discussions to be well justified by the benefits, 61 percent found the questionnaire instructions highly sufficient, and 86 percent reported no challenges discussing their preferences with their therapist. Acceptability exceeded 80 percent across both groups.

The therapists were harder to win over. Only 14 percent considered knowledge of client preferences highly relevant to specific therapy processes, and not a single therapist rated information about client experiences as highly relevant for future collaborations. Nearly half felt the time clients spent completing two full questionnaires was not matched by the insight gained, although 86 percent considered their own completion of the therapist form at least somewhat worthwhile. Free-text comments revealed practical friction: some clients, particularly those with cognitive challenges, were overwhelmed by the number of questions or misunderstood the items, requiring substantial assistance. Still, the therapists broadly endorsed the instruments’ acceptability, with one noting that the process had given her direct insight into what worked in individual patient courses, what to attend to, and what to do more or less of in her own therapeutic style.

The study’s significance lies less in any single number than in what it demonstrates about measuring something as elusive as interpersonal style. Structured questionnaires can open a conversation that might otherwise never happen, giving clients a legitimate voice in how they are treated and giving therapists a mirror for their own habits. The Danish versions of the Clinical Assessment of Modes questionnaires appear fit for that purpose, particularly the pre-therapy form, which seems well suited to framing the initial collaboration. At the same time, the authors caution that knowing a client’s preferences will not automatically change the relationship; therapists need deeper training in the six modes and in deliberately shifting between them to avoid suboptimal patterns such as mixing modes or missing a client’s needs entirely. With a small, pandemic-constrained sample and no prior IRM knowledge among participating therapists, the findings demand confirmation in larger, more representative studies, ideally supplemented by qualitative interviews. But the core message stands: clients and therapists do not always perceive the same therapy, and giving both sides a structured way to compare notes may be one of the most practical steps toward genuinely client-centred care.

Subject of Research: Clinical utility of Danish versions of the Clinical Assessment of Modes questionnaires in occupational therapy practice

Article Title: Clinical utility of the Danish versions of the Clinical Assessment of Modes Questionnaires

Article References: Nielsen, K. T., Pilegaard, M. S., Larsen, A. E., & Wæhrens, E. E. (2025). Clinical utility of the Danish versions of the Clinical Assessment of Modes Questionnaires. Scandinavian Journal of Occupational Therapy, 32(1), 1-12. https://doi.org/10.1080/11038128.2026.2615565

Image Credits: AI Generated

DOI: 10.1080/11038128.2026.2615565

Keywords: occupational therapy, therapeutic relationship, Intentional Relationship Model, therapeutic modes, clinical utility, questionnaires, client-therapist discrepancy, communication, psychometrics, Denmark, client-centred practice, rehabilitation

Preeclampsia remains one of the leading causes of maternal and perinatal morbidity and mortality globally. The condition, which typically arises after the twentieth week of gestation, is characterized by new-onset hypertension and, in many cases, proteinuria, and it can progress rapidly toward seizures, stroke, hepatic and renal failure, placental abruption, and fetal growth restriction. The clinical difficulty is that its early presentation is notoriously nonspecific. Headache, edema, elevated blood pressure, and abnormal laboratory results overlap substantially with ordinary pregnancy discomforts and with unrelated disorders, which means that large numbers of women are evaluated, admitted, and observed for a disease that only a minority of them actually have or will develop.

This diagnostic uncertainty is precisely where placental growth factor enters the picture. PlGF is an angiogenic protein, a member of the vascular endothelial growth factor family, that plays a central role in placental development. In normal pregnancies, circulating levels of PlGF rise through the second trimester and peak in the third. In pregnancies complicated by placental dysfunction, the biological substrate of most early-onset preeclampsia, PlGF production falls measurably, sometimes weeks before the syndrome becomes clinically manifest. The inverse relationship between low PlGF and imminent preeclampsia has been replicated across numerous cohort and case-control studies, and commercial immunoassays measuring the protein have been developed and, in some jurisdictions, approved for clinical use.

The promise of a PlGF-based triage test lies in its negative predictive value. When a woman presents with suspected preeclampsia, a PlGF concentration above a predefined threshold substantially lowers the probability that she will require delivery within the following one to two weeks. Several health technology assessments, including guidance issued by national bodies such as NICE in the United Kingdom, have acknowledged this property, and PlGF-based tests have been recommended to help rule out preeclampsia in women presenting with suspicion of the disease between twenty and roughly forty weeks of gestation. The tests are not stand-alone diagnostic tools; results must always be interpreted alongside blood pressure, symptoms, and laboratory findings. But as a rule-out instrument, they have demonstrated an ability to redirect low-risk women away from hospital admission and toward community-based monitoring.

What the new analysis in npj Women’s Health sets out to interrogate is the distance between demonstration and deployment. Demonstrating that a biomarker correlates with disease is one thing; proving that measuring it changes decisions, decisions change outcomes, and outcomes improve enough to justify the cost and workflow disruption is quite another. This chain of evidence, sometimes called the analytic-validation-clinical validation-clinical utility framework, is the standard against which any proposed triage test must be judged, and each link in the chain has historically been weaker than the one before it for PlGF.

The clinical utility link deserves particular scrutiny. Randomized controlled trials evaluating PlGF-guided management have generally shown that knowledge of the biomarker result can reduce the time to preeclampsia diagnosis in women who ultimately develop the disease and can shorten hospital stays for those who do not. Whether these intermediate benefits translate into fewer adverse maternal or neonatal events is far less clear. Major adverse perinatal outcomes are comparatively rare in the populations enrolled in such trials, and trials powered to detect reductions in hard endpoints such as eclampsia, maternal death, or perinatal death would need to be very large, very expensive, and logistically demanding. In their absence, evidence of utility rests largely on surrogate outcomes and decision-modeling studies.

Cost-effectiveness modeling has nonetheless been broadly favorable. Because the alternative to biomarker triage is often prolonged inpatient observation of large numbers of women who never develop the disease, even a modestly accurate rule-out test can free up bed capacity, reduce staffing burden, and lower direct costs per episode of suspected preeclampsia. Health economic analyses in several national contexts have concluded that PlGF-based triage is likely to be cost-saving or at least highly cost-effective when used within structured pathways that specify exactly how clinicians should act on low, intermediate, and high results. The critical phrase is structured pathways: a biomarker result that arrives without an agreed management algorithm attached risks becoming an unused number, or worse, a source of unwarranted reassurance.

The analysis also engages with the limits of the technology that clinicians and laboratory directors must keep in view. PlGF performs best as a rule-out test for early-onset, placenta-driven disease. Its utility in late-term and term presentations is weaker, because preeclampsia at term frequently arises through mechanisms that are less tightly coupled to angiogenic imbalance. Assays from different manufacturers are not interchangeable, with differing thresholds and units, and results can be influenced by gestational age, multiple pregnancy, fetal sex, chronic hypertension, and intercurrent illness. Point-of-care and laboratory-based platforms also differ in turnaround time, which matters when the triage question is whether a woman can go home tonight or needs to be admitted for observation and possible delivery within days.

There are further implementation questions that any health system adopting PlGF triage must answer before the test can deliver on its potential. Who is eligible for testing, and at what gestational age? How quickly must the result be available for it to influence the same-day decision? What happens to women with intermediate values, which account for a meaningful fraction of tested patients and for whom the evidence is thinnest? How should repeated testing be used, given that serial PlGF measurements can add prognostic information but also generate anxiety and uncertainty when trajectories hover near thresholds? And how should clinicians communicate a favorable result to a woman without leaving her dismissive of genuine symptoms that the test cannot exclude?

Equity considerations compound these operational ones. The burden of preeclampsia falls disproportionately on women in low- and middle-income countries and on marginalized populations within high-income countries, precisely the settings where laboratory infrastructure, trained staffing, and follow-up capacity may be weakest. A triage strategy that works in a well-resourced maternity unit with round-the-clock laboratory support may fail, or even widen disparities, if deployed without the surrounding systems that make an outpatient monitoring pathway safe. Conversely, if low-cost point-of-care PlGF assays can be validated and integrated into referral networks, the same technology could improve risk stratification where it is needed most.

On balance, the evidence assembled across this literature supports a measured but genuine role for placental growth factor as a triage test in suspected preeclampsia. Its strength is not in diagnosing the disease but in identifying the substantial majority of evaluated women who can be safely managed without admission, thereby concentrating specialist attention on those at highest risk. Its weaknesses, including limited performance at term, unresolved questions about hard clinical endpoints, and demanding implementation prerequisites, are real but addressable through standardized pathways, assay harmonization, and continued prospective evaluation. As the npj Women’s Health analysis makes plain, the question facing maternity services is no longer whether PlGF carries clinically meaningful information, but how to embed it responsibly in the daily triage of pregnancy, where the test’s true value will be decided by the systems built around it.

Subject of Research: Use of placental growth factor blood testing to triage women with suspected preeclampsia in maternity care.

Article Title: Analyzing the clinical utility of placental growth factor as a triage test

Article References: Neff, N. L., Chen, H.-Y., Sibai, B. M., & Parchem, J. G. (2026). Analyzing the clinical utility of placental growth factor as a triage test. npj Women's Health. https://doi.org/10.1038/s44294-026-00145-8

Image Credits: AI Generated

DOI: 10.1038/s44294-026-00145-8

Keywords: placental growth factor, preeclampsia, triage test, biomarker, pregnancy, maternal health, angiogenic factors, diagnostics, prenatal care, clinical utility, health economics, obstetrics