IoT and Advanced Sensing for Precision Medicine in Oncology and Immunotherapy

03-Mar-2026 | 194 views

IoT and Advanced Sensing for Precision Medicine in Oncology and Immunotherapy 
Precision medicine in oncology is shifting the center of gravity from “standard care” to adaptive therapy: treatments designed around the biological profile of the individual patient and updated over time based on real-world response. In this scenario, the availability of high temporal resolution clinical data (frequent, continuous, or near-continuous) becomes an enabling factor: it is not enough to know a value “today”—we need to understand its evolution, variability, and early trends. 

The integration of IoT platforms, advanced sensing, and analytics enables the systematic collection of physiological, biochemical, and environmental parameters, generating data streams that can support both clinical practice and translational research. The rationale is clear: more relevant and timely data mean faster therapeutic decisions, more robust risk stratification, and a greater ability to prevent complications—especially in high-complexity treatments such as immunotherapy. 

Sensors, Biomarkers, and the “Critical” Issue of Precision pH (ISFET and Miniaturized Sensors) 
When discussing biomarkers, one often thinks of omics panels or laboratory tests; however, a significant portion of clinical information can also be generated by miniaturized sensors—provided that measurements are reliable, repeatable, and integrable into clinical workflows. 

Parameters such as temperature, heart rate, oxygen saturation, heart rate variability, activity, and sleep quality are now widely monitored. The next frontier is more continuous and patient-proximal biochemical and metabolic measurement, in controlled settings (day hospital, ward, follow-up) or even at home. 

In this perspective, pH is not a “generic number”: it is a transversal indicator linked to acid–base balance, metabolism, biological microenvironments, and inflammatory processes. In oncology and immunotherapy, where inflammatory status and adverse reactions can evolve rapidly, having stable and traceable measurements over time offers a tangible advantage for clinical management and research protocols. 

Here, a technology that leverages expertise in electronics, chemistry, and microsensing becomes central: ISFETs (Ion-Sensitive Field-Effect Transistors). Unlike conventional sensors, ISFETs convert ionic information (related to H⁺ ions) into an electrical signal compatible with miniaturization and integration into embedded systems. 

The key point is not “just” using an ISFET, but designing a system that makes the measurement clinically credible: 
- Reference electrode management 
- Noise and common-mode disturbance control 
- Analog/digital domain isolation 
- Long-term stability 
- Thermal compensation 
- Calibration and quality control procedures 

Our experience is rooted precisely here: in the development of high-sensitivity pH minisensors and in engineering the complete chain sensor → analog front-end → acquisition → filtering/compensation → data validation, with particular attention to phenomena that are often barely visible in laboratory settings but become decisive in the field (electromagnetic interference, parasitic currents, reference instability, drift, surface contamination). 

In medical applications, this approach translates into a simple philosophy: a biochemical datum is valuable only if it is repeatable, explainable, and traceable. For this reason, IoT 
architecture is not an “add-on” but an integral part of the measurement system. It enables association of critical metadata with each acquired value (temperature, timestamp, operating conditions, sensor status, signal quality), construction of historical series, and automatic consistency checks and alerts on significant deviations. 

Miniaturization also opens the path to sensors that can be integrated into dedicated monitoring devices, experimental setups for clinical research, or testing platforms that accelerate validation of new hypotheses. 

Real-Time Data: Edge Computing, Cloud, AI, and Integration with Predictive Telemedicine 
The value of IoT in oncology lies not only in connectivity, but in reaction time and interpretive quality. 

A modern architecture typically operates across three levels: 
- Local acquisition (sensor and microcontroller) 
- Edge processing (signal cleaning, computation of synthetic indicators, quality control, intelligent compression) 
- Central platform (cloud or on-premise) for integration with electronic health records, telemedicine systems, predictive models, and clinical studies 

Edge computing is particularly useful when immediate responses are required or when connectivity is imperfect: alert logic can be generated directly on the device, while the centralized platform preserves historical data, applies more complex models, and enables comparative analysis across patients and cohorts. 

Operationally, the main advantages of IoT sensing in oncology and immunotherapy can be summarized as follows: 
- Continuous or frequent monitoring of vital parameters and, where applicable, biochemical biomarkers, with early trend and deviation detection 
- Predictive telemedicine: not just remote monitoring, but early identification of patterns compatible with adverse event risk or clinical deterioration 
- Real-time analysis via cloud/edge pipelines and AI algorithms, with confidence levels and data quality indicators 
- Support for personalization: dynamic stratification, protocol adaptation, and structured data collection for clinical research and real-world evidence 

An often underestimated aspect is data governance: security, integrity, auditability, and consent management. In healthcare, platforms must be designed from the outset for data protection (encryption, access control, logging) and traceability of transformations (from raw signal to clinical datum). 

Here again, engineering expertise is crucial: a well-designed system prevents technological complexity from becoming operational fragility. In other words, useful innovation is innovation that integrates seamlessly into clinical workflows while simultaneously producing robust datasets for research. 

Application Example and What Makes the Expertise “Unique”: From Reliable Measurement to Clinical Action 
Consider a monitoring pathway for oncology patients undergoing immunotherapy: the goal is not to generate “more data,” but to detect weak signals of clinical change earlier and translate them into rapid action. 
In a typical scenario, a set of sensors (vital signs plus specific physiological/metabolic indicators) transmits data to a platform that calculates trends, deviations, and risk indicators. When dynamic thresholds are exceeded (calibrated on the individual patient rather than on standard values alone), the system generates an alert to the clinical team, providing readable context: 
- Trends over the last hours/days 
- Signal quality 
- Possible correlations (temperature, activity, ongoing therapy) 

The expected outcome is timely intervention: clinical evaluation, adjustment of timing, therapeutic modification, or activation of targeted diagnostics—reducing unnecessary visits and increasing the probability of intercepting events when they are still manageable. 

What truly distinguishes a technological partner, however, is the ability to bring robust—not “lab-fragile”—measurements into clinical practice. This is where ISFET-based sensing and precision pH analysis become distinctive: working with pH means addressing real-world issues of stability, electrochemical references, electrical disturbances, drift, and data validation. 

In practical terms, it means designing minisensors and IoT platforms that do not merely “measure,” but demonstrate measurement quality through consistency checks, self-diagnostics, error management, calibration, and repeatable procedures. 

This approach aligns perfectly with precision medicine: if therapy is personalized, the information guiding it must also be reliable, contextualized, and ready to be transformed into clinical decision-making.