The health of small babies, comprising both low birth weight (LBW) infants (birth weight of less than 2500 grams) and those born prematurely (gestational age less than 37 weeks), continues to pose a significant global health challenge, particularly in low- and middle-income countries [1, 2]. In 2020, out of 135 million live births globally, 23.4 million (1 in 5) were small for gestational age (SGA), and 13.4 million (1 in 10) were preterm. A total of 35.3 million (26.2%) were classified as small, vulnerable newborns (SVNs), born preterm, SGA, or both, comprising 99.5% of the world’s 20 million LBW cases. Nearly two-thirds (63%) of term SGA babies were in southern Asia [3]. In Indonesia, the LBW prevalence was 6.1% in 2023 [4].

These newborns face heightened risks of neonatal mortality [3], delayed physical and cognitive development [5, 6], obesity [7], and long-term non-communicable diseases [7, 8]. In Indonesia, the persistently high prevalence of small babies, as reported in national health surveys [4], underscores the urgent need for improved strategies in early detection, continuous monitoring, and comprehensive postnatal care.

Addressing this issue requires a multisectoral approach involving maternal nutrition, antenatal care quality, and equitable access to skilled birth attendants. Strengthening community-based health services and integrating data-driven interventions are also essential to reduce the burden of low birth weight and improve newborn outcomes [2, 9-12].

Accurate and timely anthropometric measurements are essential for the effective management and follow-up of children, including LBW and small babies [13, 14]. Key parameters, such as weight, length, and head circumference, are vital indicators of nutritional status and developmental progress [15]. However, manual measurement techniques, which are still widely used in frontline health services, especially in under-resourced settings, present significant limitations. These include human error, inconsistent methodology, and poorly calibrated tools factors that reduce measurement reliability and compromise the quality of infant health interventions [16-18].

Although digital health technologies have expanded in recent years, a major gap remains in the availability of anthropometric tools specifically designed for small babies and suitable for decentralized healthcare settings. Existing digital devices are often intended for newborns with normal birth weight [19] or the adult population [20, 21], lacking both precision and the integration of Internet of Things (IoT) features needed for real-time data transmission and centralized health monitoring. Moreover, limited research has addressed how such devices can be adapted for use in community contexts, considering factors like usability, connectivity, and interoperability.

Many existing digital anthropometry devices, as reported in previous research [22-24], primarily target newborns with normal birth weight and require either stable electricity or manual data recording, which may limit their use in low-resource or mobile health settings. Additionally, most commercially available tools lack integration with real-time digital health reporting platforms. They are not designed for seamless interoperability with national systems, such as e-PPGBM or SatuSehat. This presents a critical limitation in community-based healthcare systems that rely heavily on frontline workers with minimal training in digital tools. By contrast, the device proposed in this study is specifically tailored for SVNs. It is equipped with modular IoT features, cloud storage compatibility, ergonomic baby-friendly designs, and off-grid functionality. These features address real-world constraints, including limited infrastructure, time constraints during Posyandu visits, and the urgent need for valid data to inform stunting prevention strategies.

To address this gap, this study protocol outlines the development of an innovative digital anthropometry device embedded with IoT-based sensors for monitoring small babies. The device integrates microcontroller systems and smart sensors to support precise, consistent, and efficient measurement in community settings. This research fills a critical need by providing an evidence-based, context-sensitive, and scalable solution aligned with both national maternal-child health goals and global initiatives to reduce infant morbidity and mortality through technology-enabled care.

The expected outcome is a validated, user-friendly, and scalable digital anthropometry device with integrated IoT features, suitable for use in decentralized healthcare systems. The device will contribute to improved monitoring and early intervention for small babies in community health settings.

The development of a digital anthropometric device integrated with IoT technology specifically targets critical gaps in neonatal growth monitoring, especially for low birth weight (LBW) and preterm infants. Traditional measurement tools often suffer from inconsistencies due to operator dependency, limited accuracy, and the absence of seamless integration with digital health systems [17, 18, 20, 29, 30]. These limitations hinder early detection and timely intervention in cases of growth faltering, especially in remote or underserved areas. By focusing on high-risk neonatal populations, this research contributes to a broader effort to improve maternal and child health outcomes through digital innovation.

The tool aims to strengthen routine monitoring at the grassroots level and promote more effective surveillance practices. In the context of Indonesia or other similar countries, disparities in the capacity of health cadres, limited human resources, low motivation among volunteers, and the absence of reliable anthropometric tools remain persistent challenges [31-35]. This innovation offers a practical and scalable solution. By enabling accurate, automated, and real-time data collection integrated with national health information systems, the tool addresses long-standing issues of data inaccuracy, delayed reporting, fragmented health service delivery, and supporting nutrition surveillance. It empowers frontline workers with user-friendly technology, reduces their workload, enhances data-driven decision-making, and ultimately supports more equitable and efficient growth monitoring and stunting prevention efforts across diverse and often under-resourced community health settings.

This innovation combines ergonomic, child-safe hardware with smart technologies such as load cell and ultrasonic sensors for accurate measurement of infant weight and length, integrated via an ESP32 microcontroller that enables real-time data transmission through Wi-Fi or Bluetooth. The system automatically uploads measurements to an IoT-based dashboard, significantly reducing human error, improving workflow efficiency, and facilitating prompt responses to growth deviations. Its interoperability with national health platforms like e-PPGBM and SatuSehat enhances surveillance accuracy and accelerates follow-up actions for at-risk infants, aligning with Indonesia’s digital transformation strategy in stunting reduction [36, 37]. Furthermore, its potential integration into Posyandu and Puskesmas workflows, supported by automated data archiving and longitudinal monitoring features, demonstrates both its scalability and practical value in strengthening community-based child health services.

In ensuring practical applicability, the research emphasizes a user-centered design process [38-41]. Midwives, nurses, and health cadres participated in evaluating the tool’s usability, contributing to a culturally relevant and context-specific product. The use of the Design and Development Research (DDR) methodology allowed iterative testing and refinement, improving the tool’s functionality and user-friendliness [42]. Technical trials in both clinical and field settings revealed that the device operates within acceptable error margins, comparable to conventional instruments. This confirms not only the validity of the technology but also its acceptability and feasibility in real-world applications across diverse healthcare contexts, as stated by Rogers [43].

Despite these promising outcomes, challenges remain for full-scale implementation. Network connectivity issues in rural areas, device calibration maintenance, and the digital literacy of frontline health workers must be addressed to ensure long-term success. Moreover, standardized training modules are needed to support consistent and competent use of the tool at the community level. Future research should include large-scale pilot testing, cost-benefit analysis, and integration with predictive analytics to further enhance the impact of the program [44]. Ensuring robust data privacy and interoperability standards will also be essential as the device becomes more widely adopted. Addressing these factors will enhance sustainability and facilitate institutionalization within Indonesia’s primary healthcare system [45].

In conclusion, this study contributes valuable insights into the design and deployment of IoT-based anthropometric devices tailored for neonatal health surveillance. The innovation demonstrates strong potential to improve data quality, service efficiency, and evidence-based decision-making within community and primary care settings. Its integration with national platforms ensures strategic alignment with health system transformation goals. While refinements are necessary, the device presents a scalable and sustainable solution for stunting prevention in high-risk infant populations. Ultimately, the study reinforces the critical role of digital health technologies in addressing persistent public health challenges in Indonesia and similar low- and middle-income countries. Some of the limitations of this study include the limitations of internet connectivity in rural areas, the possibility of bias from small sample sizes that are not yet representative of the entire demographic context of Indonesia, as well as the need for ongoing technical training for frontline health workers in operating the equipment.

This study introduces a novel, sensor-integrated digital anthropometry device enhanced with IoT technology, specifically designed to improve the accuracy and efficiency of growth monitoring in small and vulnerable newborns within primary healthcare settings. Combining ultrasonic and load cell sensors, an ESP32 microcontroller, and real-time cloud connectivity enables automated, precise, and timely data capture that can seamlessly integrate with national health information systems, such as e-PPGBM. Its ergonomic, portable, and user-centered design makes it universally applicable for community-level use, particularly in Posyandu and rural settings. With strong potential to transform stunting prevention strategies through data-driven early detection and intervention, this innovation offers a scalable, sustainable solution that aligns with Indonesia’s digital health transformation and holds promise for adoption in other low- and middle-income countries facing similar public health challenges. In addition to providing concrete solutions for monitoring the growth of small babies, this tool also opens up opportunities for further integration with digital health systems, such as AI, for predictive stunting risk detection. This development also provides the basis for further research in the context of user-centered device design and the strengthening of data-driven health systems in developing countries.