JTSA: an open source framework for time series abstractions.

BACKGROUND AND OBJECTIVE: The evaluation of the clinical status of a patient is frequently based on the temporal evolution of some parameters, making the detection of temporal patterns a priority in data analysis. Temporal abstraction (TA) is a methodology widely used in medical reasoning for summarizing and abstracting longitudinal data. METHODS: This paper describes JTSA (Java Time Series Abstractor), a framework including a library of algorithms for time series preprocessing and abstraction and an engine to execute a workflow for temporal data processing. The JTSA framework is grounded on a comprehensive ontology that models temporal data processing both from the data storage and the abstraction computation perspective. The JTSA framework is designed to allow users to build their own analysis workflows by combining different algorithms. Thanks to the modular structure of a workflow, simple to highly complex patterns can be detected. The JTSA framework has been developed in Java 1.7 and is distributed under GPL as a jar file. RESULTS: JTSA provides: a collection of algorithms to perform temporal abstraction and preprocessing of time series, a framework for defining and executing data analysis workflows based on these algorithms, and a GUI for workflow prototyping and testing. The whole JTSA project relies on a formal model of the data types and of the algorithms included in the library. This model is the basis for the design and implementation of the software application. Taking into account this formalized structure, the user can easily extend the JTSA framework by adding new algorithms. Results are shown in the context of the EU project MOSAIC to extract relevant patterns from data coming related to the long term monitoring of diabetic patients. CONCLUSIONS: The proof that JTSA is a versatile tool to be adapted to different needs is given by its possible uses, both as a standalone tool for data summarization and as a module to be embedded into other architectures to select specific phenotypes based on TAs in a large dataset.

A generic telemedicine infrastructure for monitoring an artificial pancreas trial.

Telemedicine systems are seen as a possible solution for the remote monitoring of physiological parameters and can be particularly useful for chronic patients treated at home. Implementing those systems however has always required spending a great effort on the underlying infrastructure instead of focusing on the application cores as perceived by their users. This paper proposes an abstract unifying infrastructure for telemedicine services which is loosely based on the multi-agent paradigm. It provides the capability of transferring to the clinic any remotely acquired information, and possibly sending back updates to the patient. The infrastructure is a layered one, with the bottom layer acting at the data level and implemented in terms of a software library targeting a wide set of hardware devices. On top of this infrastructure several services can be written shaping the functionality of the telemedicine application while at the highest level, adhering to a simple agent model, it is possible to reuse those functional components porting the application to different platforms. The infrastructure has been successfully used for implementing a telemonitoring service for a randomized controlled study aimed at testing the effectiveness of the artificial pancreas as a treatment within the AP@home project funded by the European Union.

Utilizing information technologies for lifelong monitoring in diabetes patients.

BACKGROUND: Information and communication technologies have long been acknowledged to support information sharing along the whole chain of care, from the clinic to the homes of patients and their relatives. Thus they are increasingly being considered for improving the delivery of health care services also in light of clinical and technological achievements that propose new treatments requiring a tighter interaction among patients and physicians. METHODS: The multiagent paradigm has been utilized within an architecture for delivering telemedicine services to chronic outpatients at their domiciles and enforcing cooperation among patients, caregivers, and different members of the health care staff. The architecture sees each communication device such as a palmtop, smart phone, or personal digital assistant as a separate agent upon which different services are deployed, including telemetry, reminders, notifications, and alarms. Decoupling services from agents account for a highly configurable environment applicable to almost any context that can be customized as needed. RESULTS: The architecture has been used for designing and implementing a prototypical software infrastructure, called LifePhone, that runs on several communication devices. A basic set of services has been devised with which we were able to configure two different applications that address long-term and short-term monitoring scenarios for diabetes patients. The long-term scenario encompasses telemetry and reminder services for patients undergoing peritoneal dialysis, which is a treatment for chronic renal failure, a diabetes complication. The short-term scenario incorporates telemetry and remote alarms and is applicable for training patients to use an artificial pancreas. CONCLUSIONS: Our experiments proved that an infrastructure such as LifePhone can be used successfully for bridging the interaction gap that exists among all the components of a health care delivery process, improving the quality of service and possibly reducing the overall costs of health care. Furthermore, the modularity of services allows for more complex scenarios encompassing data analysis or even involving actors at multiple institutions in order to better support the overall health care organization.

Bringing the artificial pancreas home: telemedicine aspects.

The design and implementation of telemedicine systems able to support the artificial pancreas need careful choices to cope with technological requirements while preserving performance and decision support capabilities. This article addresses the issue of designing a general architecture for the telemedicine components of an artificial pancreas and illustrates a viable solution that is able to deal with different use cases and is amenable to support mobile-health implementations. The goal is to enforce interoperability among the components of the architecture and guarantee maximum flexibility for the ensuing implementations. Thus, the design stresses modularity and separation of concerns along with adoption of clearly defined protocols for interconnecting the necessary components. This accounts for the implementation of integrated telemedicine systems suitable as short-term monitoring devices for supporting validation of closed-loop algorithms as well as devices meant to provide a lifelong tighter control on the patient state once the artificial pancreas has become the preferred treatment for patients with diabetes.

A configurable home care platform for monitoring patients with reminder messaging and compliance tracking services.

This paper illustrates a platform based on a general architecture for implementing home care services for chronic patients composed of a Remote Care Unit located at a patient's home and a Health Care Center Unit located at the treating center. The Remote Care Unit may be deployed on multiple platforms including PCs, mobile phones and even embedded devices not equipped with monitor, and may be configured to support many interoperability issues occurring among the parties involved in a health care delivery process. The platform may be tailored to match the specific issues of any chronic disease supporting either data acquisition as well as customized reminders and notifications from the center. Remote Care Unit platforms are also able to exploit multiple channels for acquiring data, including wireless links with medical devices, speech interaction and graphical user interaction. In this paper a couple of applications addressing the needs of diabetic and nephropatic patients developed on top of that platform are also introduced.

Going mobile with a multiaccess service for the management of diabetic patients.

BACKGROUND: Diabetes mellitus is one of the chronic diseases exploiting the largest number of telemedicine systems. Our research group has been involved since 1996 in two projects funded by the European Union proposing innovative architectures and services according to the best current medical practices and advances in the information technology area. METHOD: We propose an enhanced architecture for telemedicine giving rise to a multitier application. The lower tier is represented by a mobile phone hosting the patient unit able to acquire data and provide first-level advice to the patient. The patient unit also facilitates interaction with the health care center, representing the higher tier, by automatically uploading data and receiving back any therapeutic plan supplied by the physician. On the patient's side the mobile phone exploits Bluetooth technology and therefore acts as a hub for a wireless network, possibly including several devices in addition to the glucometer. RESULTS: A new system architecture based on mobile technology is being used to implement several prototypes for assessing its functionality. A subsequent effort will be undertaken to exploit the new system within a pilot study for the follow-up of patients cared at a major hospital located in northern Italy. CONCLUSION: We expect that the new architecture will enhance the interaction between patient and caring physician, simplifying and improving metabolic control. In addition to sending glycemic data to the caring center, we also plan to automatically download the therapeutic protocols provided by the physician to the insulin pump and collect data from multiple sensors.