Beyond Turing
Introduction
The convergence of Artificial Intelligence (AI), Internet of Things (IoT) and Big Data is radically transforming the healthcare sector.
In this article, I analyse three development directions I consider particularly promising, based on research projects and scientific publications conducted in recent years.
1. Wearable Devices and Telerehabilitation
Wearable devices (smartwatches, biometric sensors, cardiac patches) have reached a technological maturity that enables continuous monitoring of physiological parameters with clinical precision. Integration with IoT platforms and machine learning algorithms now allows us to:
Detect early anomalies in cardiac, respiratory and metabolic function
Support telerehabilitation with real-time feedback to patient and clinician
Build digital twins of patients to simulate responses to personalised therapies
Our research published in Healthcare (2023) demonstrated how low-cost wearable devices, combined with open-source platforms, can effectively support home telerehabilitation programs with significantly higher patient adherence rates compared to traditional protocols.
2. Big Data Analytics and Public Health
The volume of healthcare data generated daily - electronic health records, diagnostic imaging, genomics, environmental sensors - has reached proportions that make Big Data technologies indispensable. Distributed architectures like Spark and Hadoop, combined with cloud data warehouses, enable us to:
Correlate environmental and clinical factors to identify epidemiological patterns
Optimise healthcare resource management through predictive analytics
Personalise therapeutic pathways based on cohorts of similar patients
A particularly relevant result from our research (June 2024, Applied Sciences) focused on the combined use of AI, IoT and Big Data to monitor tele-exercise effects on fitness and psychological well-being, integrating physical performance indicators with mental health metrics.
3. AI and Enterprise Information Systems in Healthcare
The integration of artificial intelligence into Hospital Information Systems (HIS) represents perhaps the most strategic frontier. It is not just about automating processes, but about transforming the healthcare organisation into a self-learning system. The most concrete applications include:
Intelligent triage based on NLP of patient histories
Clinical decision support with expert systems based on knowledge graphs
Predictive management of patient and resource flows
Our work published in December 2023 analysed how AI and IoT are transforming Enterprise Information Systems, identifying three critical challenges: interoperability, data governance, and end-user trust.
Stanford Specialisation: A New Frontier
Completing the AI in Healthcare Specialisation at Stanford University has consolidated my understanding of how deep learning, reinforcement learning and clinical decision support systems are redefining medical practice. Particularly relevant aspects include:
Federated Learning for privacy-preserving multi-institutional training
Explainable AI (XAI) for clinical trust and regulatory compliance
Bias detection in medical datasets
Integration with FHIR/HL7 clinical standards
This framework allows me to integrate Stanford's scientific rigor with the project management experience acquired over three decades of applied research.
Epistemology and Innovation: A Reflection
As an engineer with philosophical training, I believe the adoption of these technologies must be accompanied by rigorous epistemological reflection. AI does not replace clinical judgement - it augments it. The central question is not "what can AI do?", but "what should AI do, within which ethical and methodological constraints?".
This is the heart of my ongoing research on Knowledge Engineering: building bridges between scientific method, logic, epistemology and emerging technologies, to ensure that technological innovation always serves the person.
Conclusions and Perspectives
The AI-IoT-Big Data convergence in healthcare is no longer a future prospect: it is already operational reality in many contexts. The main challenges for the coming years will concern:
Standardisation and interoperability of data
Training healthcare personnel in critical use of technologies
Ethical governance and regulatory compliance (European AI Act, GDPR)
Equitable access to technologies, avoiding new inequalities
Applied research in this field requires multidisciplinary skills and a systemic approach. This is why, in my courses at eCampus University (Big Data, Intelligent Devices for Health and Well-being, Enterprise Information Systems), I strive to combine engineering rigor with humanistic perspective.