The COVID-19 emergency has exposed the fragility of many Health Care Systems around the world. Two major critical factors have been related to the management of critical care accesses and the availability of healthcare operators. COVID-like diseases are generally transmitted by airborne pathogens that grant a high contagion rate and rapidity. Unfortunately, health operators and medical doctors are the designated first victims of such epidemics. Infected operators (symptomatic or not) must be put at rest due to the potential contagion risk for the patients. In this manner, the healthcare systems end up almost depleted of operators. In this proposal we want to: 1) provide a preemptive planning strategy for intensive care units' accesses; 2) cope with the healthcare operators' shortage; 3) enforce middle and long term sustainability in pandemic scenarios; 4) enhance the quality of service for the patients. To achieve goal 1) we will implement machine learning algorithms to predict the bed availability in critical care units, as well as predicting the workload availability due to potential contagions of caregivers. As for goal 2) we will implement robots as acting remote interface for physicians at home in smart-working mode, to perform diagnostic tasks that do not require high precision manual interactions, and therefore decreasing the workload of physically available operators. In this manner we will be able to achieve 3) and also to improve the emergency management of hospital facilities. Finally, as for goal 4) the large scale implementation of robots will spare a large amount of time that is generally wasted by the caregivers in sanitization operations, tampering with number and duration of visits to patients who are normally left alone for a long time, also lowering the quality of service perceived by the patients, as well as harming them also on the psychological side, with significant fallbacks on the recovery speed.
The application proposed in this project would be the first of its kind in the field of hospital emergency management. The central kernel of the proposed research will use innovative algorithms based on machine learning and neural networks. These algorithms have already proven to be able to predict dynamic resource allocations, both in terms of energy, temporal and physical allocations, and even the progression and scheduling of entire dynamic workflows in the context of smart cities (for a long time this has been the mainstream research field of the principal investigator of this project). On the other hand, this would be the first time for these techniques to be applied to a highly sensitive and intermittent context such as the management of health emergencies caused by infectious pandemics. Another important and innovative asset will be the use of robots in the hospital. Until now the meaning of the words "hospital robot" has so far limited to highly sophisticated pieces of machinery that have been typically used in operating rooms for precision operations. In the case object of this proposed proposal, however, robots would be implemented as interactive physical interfaces, although remotely driven by a doctor. Many studies of the proponents have already shown the curiosity and interest with which people interact with robots, therefore this implementation would also lead to a positive side effect by increasing the morale of hospitalized patients. The real strength of this proposal, however, lies in the effective decrease in pressure on the healthcare system, which would continue to take advantage of the skills of doctors who, although infected, can still offer their work remotely. The transmission of data, controls, and audio-video flows constitute another technical aspect to consider and which requires innovative solutions. Data transmission is the most critical operation for mobile sensors networks in terms of energy waste. Particularly in pervasive healthcare sensors network, it is paramount to preserve the quality of service also employing energy-saving policies. In this project, we will implement also a novel data compression approach to obtain shorter transmissions due to data compression. This approach will be based on the evaluation of the absolute and relative entropy, as yet experienced in several works of the proponents (please see the publications of the principal investigator). Another key point that shows the novelty of the project also consists of the care for the regulatory and ethical aspects relating to the patient and the health personnel. The use of robotic interfaces will also include the application of policies to protect the personal data of patients and doctors, as well as to protect their privacy. The system will be equipped with all the security protocols and software solutions necessary to create an encrypted and secure system, which will fully comply with the European General Data Protection Regulation as well as several other privacy-related national and international regulations. This latter aspect has been. While latter aspect has already been addressed in literature as well as in several works by the proponents, and specifically on the field of privacy-preserving video recoding and privacy enforcing context recognition (please see the publications of the principal investigator), it has never been applied before in a challenging scenario such as intensive care units and hospital facilities in general. As far as we know, no study so far has been able to simultaneously predict the arrival of new patients, predicts the use of intensive care posts, as well as the duration of their use, predicts the trend of availability of the health workforce, increase this availability through robotic interfaces, and therefore provide hospital units with complete management of the allocation in the wards and consequent hospitalizations. We propose therefore to make it possible to develop software infrastructures that seamlessly activate healthcare workflow execution, also providing services by monitoring and enhances hospital units' dependability, all that taking into account the practical difficulties of the problem as well as the legal and ethical aspects. Finally, we should highlight the positive impact of the proposed application both on the perceived quality of the healthcare service, as well as the psychological impact. Finally, by adding to normal medical operations also psychological interventions or actions that improve the patient's psychological well-being, we will improve the patient's perceived care and effectiveness of the treatment. The expected outcomes will also determine an effective improvement of the healing probability and a shortened recovery time, with a twofold consequence impacting both the economical aspects of the emergency management and the middle/long term sustainability for the healthcare system.