Search

Diabetes is a chronic disease that affects a high percentage of the world population and produces different and serious complications to patients. Most diabetes complications may be avoided by controlling the blood glucose levels exhaustively. Moreover, a prediction of future glucose levels has shown to be fundamental in helping patients to plan and modify their treatment in real-time. In this paper, a glucose predictor based on long short-term memory neural networks is designed. Three input parameters are fed to the predictor: past glucose levels obtained from a continuous glucose monitoring sensor, the insulin units administered by an insulin pump and the patient’s carbohydrates intake. Different prediction times and input dimensions have been evaluated in order to provide the best prediction to patients. Results encourage the use of glucose predictions to avoid the occurrence of hypoglycemias, anticipate correction actions, and to increase the quality of life of these patients.

Background The automation of glucose control has been an important goal of diabetes treatment for many decades. The first artificial pancreas experiences were in-hospital, closely supervised, small-scale, and short-term studies that demonstrated their superiority over continuous subcutaneous insulin infusion therapy. At present, long-term outpatient studies are being conducted in free-living scenarios. Areas of uncertainty The integration of multiple devices increases patients' burden and the probability of technical risks. Control algorithms must be robust to manage disturbance variables, such as physical exercise, meal composition, stress, illness, and circadian variations in insulin sensitivity. Extra layers of safety could be achieved through remote supervision. Dual-hormone systems reduce the incidence and duration of hypoglycemia, but the availability of stable pumpable glucagon needs to be solved. Faster insulin analogues are expected to improve all types of artificial pancreas. Therapeutic advances Artificial pancreas safety and feasibility are being demonstrated in outpatient studies. Artificial pancreas use increases the time of sensor-measured glucose in near-normoglycemia and reduces the risk of hyperglycemia and hypoglycemia. The benefits are observed both in single- and dual-hormone algorithms and in full- or semi-closed loop control. A recent meta-analysis including 41 randomized controlled trials showed that artificial pancreas use achieves a reduction of time in hyperglycemia (2 hours less than control treatment) and in hypoglycemia (20 minutes less); mean levels of continuous glucose sensor fell by 8.6 mg/dL over 24 hours and by 14.6 mg/dL overnight. The OpenAPS community uses Do It Yourself artificial pancreas in the real world since 2013, and a recent retrospective cross-over study (n = 20) compared continuous glucose sensor readings before and after initiation: mean levels of blood glucose fell by 7.4 mg/dL over 24 hours and time in range increased from 75.8% to 82.2% (92 minutes more). Conclusions The outpatient use of artificial pancreas is safe and improves glucose control in outpatients with type 1 diabetes compared with the use of any type of insulin-based treatment. The availability of open-source solutions and data sharing is needed to foster the development of new artificial pancreas approaches and to promote the wide use of Big Data tools for knowledge discovery, decision support, and personalization.

The high prevalence of drug addiction is a major health challenge that pressures healthcare systems to respond with cost-effective treatments. To improve the treatment success of drug-dependent patients, it is necessary to identify the main associated risk factors for dropping out of treatment. Previous research shows disparate results due to the wide variety of approaches employed, the different and/or poorly defined metrics used, and the different target populations under study. This article presents the design and selection of a predictive model to estimate success of inpatient cocaine treatment based on a high-dimensional heterogeneous set of characteristics, with the aim of learning new associations between independent characteristics. We evaluated different feature selection techniques and machine learning algorithms to design the best predictive model in terms of accuracy, area under the receiver operating characteristic curve, recall, specificity, F1-score, and Matthews correlation coefficient. Random Forest was the top-performing model with a characteristic set consisting of 11 features selected with a wrapper evaluator and the Best First algorithm, achieving 82% accuracy, 0.81 of area under the receiver operating characteristic curve, 0.96 of recall, 0.47 of specificity, 0.89 of F1-measure and 0.53 of Matthews correlation coefficient. The predictive model's performance was enhanced by combining multiple dimensions with variables referring to previous treatments, mental exploration, cognitive functioning, personality, consumption habits, and pharmacological treatment. We have refined the use of machine learning techniques to predict drug addiction treatment success, which could represent a new step in treatment management especially when included in clinical decision support systems.

Highlights • Gestational diabetes mellitus is a disease that requires frequent hospital visits. • The current COVID-19 pandemic has brought telemedicine in the spotlight. • Decision support tools integrated into telemedicine systems can help clinicians. • SineDie© app analyses the data and makes recommendations regarding diet or insulin. • SineDie© app may be an excellent tool for GDM remote management., We describe our experience in the remote management of women with gestational diabetes mellitus during the COVID-19 pandemic. We used a mobile phone application with artificial intelligence that automatically classifies and analyses the data (ketonuria, diet transgressions, and blood glucose values), making adjustment recommendations regarding the diet or insulin treatment.

IntroductionPatients with type 1 diabetes (T1D) require the administration of insulin to maintain glycemic control. Currently, two modes of subcutaneous insulin delivery have gained wider acceptance: multiple daily injections (MDI) and continuous subcutaneous insulin infusion (CSII). Randomized controlled trials have shown that CSII is associated with a slightly lower glycated hemoglobin (HbA1c) level when compared with MDI.The case study on diabetes by the H2020 Next Generation Health Technology Assessment project aims to link evidence from randomized controlled trials to real-world data to estimate the impact of health technology on specific subgroups of patients, as a first step in building prediction models to personalize treatment strategies. This work aims to assess whether patients with T1D can be stratified according to the use of health technology for insulin delivery and associated glycemic control from real-world data.MethodsWe used a longitudinal prospective data repository of T1D patients from 83 clinics in the United States (T1D exchange). A data-driven two-step clustering analysis was done on adult individuals (n = 8,034) with more than five years of disease duration. Clusters were based on body mass index (BMI), sex, age at diagnosis, diabetes duration, HbA1c level, and insulin delivery method. The optimal number of clusters was estimated based on silhouette width.ResultsWe identified the following four clusters of T1D patients characterized by differences in gender and insulin delivery method: men and women with insulin injections or pens and men and women with CSII. Individuals that used CSII had lower HbA1c levels, a higher BMI, and longer diabetes duration than those using Injections or pens.ConclusionsThis preliminary work identified subgroups of T1D patients linked to insulin delivery methods. Future research includes the study of complications associated with different clusters and additional data sources. While the data were sourced from the T1D Exchange, the analyses, content, and conclusions presented have not been reviewed or approved by the T1D Exchange.

In the past decade diabetes management has been transformed by the addition of continuous glucose monitoring and insulin pump data. More recently, a wide variety of functions and physiologic variables, such as heart rate, hours of sleep, number of steps walked and movement, have been available through wristbands or watches. New data, hydration, geolocation, and barometric pressure, among others, will be incorporated in the future. All these parameters, when analyzed, can be helpful for patients and doctors’ decision support. Similar new scenarios have appeared in most medical fields, in such a way that in recent years, there has been an increased interest in the development and application of the methods of artificial intelligence (AI) to decision support and knowledge acquisition. Multidisciplinary research teams integrated by computer engineers and doctors are more and more frequent, mirroring the need of cooperation in this new topic. AI, as a science, can be defined as the ability to make computers do things that would require intelligence if done by humans. Increasingly, diabetes-related journals have been incorporating publications focused on AI tools applied to diabetes. In summary, diabetes management scenarios have suffered a deep transformation that forces diabetologists to incorporate skills from new areas. This recently needed knowledge includes AI tools, which have become part of the diabetes health care. The aim of this article is to explain in an easy and plane way the most used AI methodologies to promote the implication of health care providers—doctors and nurses—in this field.

Gestational diabetes (GDM) burden has been increasing progressively over the past years. Knowing that intrauterine exposure to maternal diabetes confers high risk for macrosomia as well as for future type 2 diabetes and obesity of the offspring, health care organizations try to provide effective control in spite of the limited resources. Artificial-intelligence-augmented telemedicine has been proposed as a helpful tool to facilitate an efficient widespread medical assistance to GDM. The aim of the study we present was to test the feasibility and acceptance of a mobile decision-support system for GDM, developed in the seventh framework program MobiGuide Project, which includes computer-interpretable clinical practice guidelines, access to data from the electronic health record as well as from glucose, blood pressure, and activity sensors. The results of this pilot study with 20 patients showed that the system is feasible. Compliance of patients with blood glucose monitoring was higher than that observed in a historical group of 247 patients, similar in clinical characteristics, who had been followed up for the 3 years prior to the pilot study. A questionnaire on the use of the telemedicine system showed a high degree of acceptance.

MobiGuide is a ubiquitous, distributed and personalized evidence-based decision-support system (DSS) used by patients and their care providers. Its central DSS applies computer-interpretable clinical guidelines (CIGs) to provide real-time patient-specific and personalized recommendations by matching CIG knowledge with a highly-adaptive patient model, the parameters of which are stored in a personal health record (PHR). The PHR integrates data from hospital medical records, mobile biosensors, data entered by patients, and recommendations and abstractions output by the DSS. CIGs are customized to consider the patients’ psycho-social context and their preferences; shared decision making is supported via decision trees instantiated with patient utilities. The central DSS “projects” personalized CIG-knowledge to a mobile DSS operating on the patients’ smart phones that applies that knowledge locally. In this paper we explain the knowledge elicitation and specification methodologies that we have developed for making CIGs patient-centered and enabling their personalization. We then demonstrate feasibility, in two very different clinical domains, and two different geographic sites, as part of a multi-national feasibility study, of the full architecture that we have designed and implemented. We analyze usage patterns and opinions collected via questionnaires of the 10 atrial fibrillation (AF) and 20 gestational diabetes mellitus (GDM) patients and their care providers. The analysis is guided by three hypotheses concerning the effect of the personal patient model on patients and clinicians’ behavior and on patients’ satisfaction. The results demonstrate the sustainable usage of the system by patients and their care providers and patients’ satisfaction, which stems mostly from their increased sense of safety. The system has affected the behavior of clinicians, which have inspected the patients’ models between scheduled visits, resulting in change of diagnosis for two of the ten AF patients and anticipated change in therapy for eleven of the twenty GDM patients.

Background and objective: In the last decade, several technological solutions have been proposed as artificial pancreas systems able to treat type 1 diabetes; most often they are built based on a control algorithm that needs to be validated before it is used with real patients. Control algorithms are usually tested with simulation tools that integrate mathematical models related mainly to the glucose-insulin dynamics, but other variables can be considered as well. In general, the simulators have a limited set of subjects. The main goal of this paper is to propose a new computational method to increase the number of virtual subjects, with physiological characteristics, included in the original mathematical models. Methods: A subject is defined by a set of parameters given by a mathematical model. From the available reduced number of subjects in the model, the covariance of each parameter of every subject is obtained to establish a mathematical relationship. Then, new sets of parameters are calculated using linear regression methods; this generates larger cohorts, which allows for testing insulin therapies in open-loop or closed-loop scenarios. The new method proposed here increases the number of subjects in a virtual cohort using two versions of Hovorka’s mathematical model. Results:Two covariant cohorts are obtained with linear regression. Both cohorts are clustered to avoid overlapping in the glucose-insulin dynamics and are compared in terms of their qualitative and quantitative behaviours in the normoglycemic range. As a result, there have been generated two larger cohorts (256 subjects) than the original population, which contributes to improving the variability in in-silico tests. In addition, for analysing the characteristics of the covariant generation method, two random cohorts have been generated, where the parameters are obtained individually and independently from each other, exhibiting only distribution limitations so that these cohorts do not have physiological subjects. Conclusions: The proposed methodology has enabled the generation of a large cohort of 256 subjects, with different characteristics that are plausible in the T1DM population, significantly increasing the number of available subjects in existing mathematical models. The proposed methodology does not limit the number of subjects that can be generated and thus, it can be used to increase the number of cohorts provided by other mathematical models in diabetes, or even other scientific problems.

Background: In type 1 diabetes mellitus (T1DM), patients play an active role in their own care and need to have the knowledge to adapt decisions to their daily living conditions. Artificial intelligence applications can help people with type 1 diabetes in decision making and allow them to react at time scales shorter than the scheduled face-to-face visits. This work presents a decision support system (DSS), based on glucose prediction, to assist patients in a mobile environment. Methods: The system’s impact on therapeutic corrective actions has been evaluated in a randomized crossover pilot study focused on interprandial periods. Twelve people with type 1 diabetes treated with insulin pump participated in two phases: In the experimental phase (EP) patients used the DSS to modify initial corrective decisions in presence of hypoglycemia or hyperglycemia events. In the control phase (CP) patients were asked to follow decisions without knowing the glucose prediction. A telemedicine platform allowed participants to register monitoring data and decisions and allowed endocrinologists to supervise data at the hospital. The study period was defined as a postprediction (PP) time window. Results: After knowing the glucose prediction, participants modified the initial decision in 20% of the situations. No statistically significant differences were found in the PP Kovatchev’s risk index change (–1.23 ± 11.85 in EP vs –0.56 ± 6.06 in CP). Participants had a positive opinion about the DSS with an average score higher than 7 in a usability questionnaire. Conclusion: The DSS had a relevant impact in the participants’ decision making while dealing with T1DM and showed a high confidence of patients in the use of glucose prediction.

We present a linear time-varying Luenberger observer (LTVLO) using compartmental models to estimate the unmeasurable states in patients with type 1 diabetes. The LTVLO proposed is based on the linearization in an operation point of the virtual patient (VP), where a linear time-varying system is obtained. LTVLO gains are obtained by selection of the asymptotic eigenvalues where the observability matrix is assured. The estimation of the unmeasurable variables is done using Ackermann's methodology. Additionally, it is shown the Lyapunov approach to prove the stability of the time-varying proposal. In order to evaluate the proposed methodology, we designed three experiments: A) VP obtained with the Bergman minimal model; B) VP obtained with the compartmental model presented by Hovorka in 2004; and C) real patients data set. For experiments A) and B), it is applied a meal plan to the VP, where the dynamic response of each state model is compared to the response of each variable of the time-varying observer. Once the observer is evaluated in experiment B), the proposal is applied to experiment C) with data extracted from real patients and the unmeasurable state space variables are obtained with the LTVLO. LTVLO methodology has the feature of being updated each instant of time to estimate the states under a known structure. The results are obtained using simulation with MatlabTM and SimulinkTM. The LTVLO estimates the unmeasurable states from in silico patients with high accuracy by means of the update of Luenberger gains at each iteration. The accuracy of the estimated state space variables is validated through fit parameter.

Background The growth of diabetes prevalence is causing an increasing demand in health care services which affects the clinicians’ workload as medical resources do not grow at the same rate as the diabetic population. Decision support tools can help clinicians with the inspection of monitoring data, providing a preliminary analysis to ease their interpretation and reduce the evaluation time per patient. This paper presents Sinedie, a clinical decision support system designed to manage the treatment of patients with gestational diabetes. Sinedie aims to improve access to specialized healthcare assistance, to prevent patients from unnecessary displacements, to reduce the evaluation time per patient and to avoid gestational diabetes adverse outcomes. Methods A web-based telemedicine platform was designed to remotely evaluate patients allowing them to upload their glycaemia data at home directly from their glucose meter, as well as report other monitoring variables like ketonuria and compliance to dietary treatment. Glycaemia values, not tagged by patients, are automatically labelled with their associated meal by a classifier based on the Expectation Maximization clustering algorithm and a C4.5 decision tree learning algorithm. Two finite automata are combined to determine the patient’s metabolic condition, which is analysed by a rule-based knowledge base to generate therapy adjustment recommendations. Diet recommendations are automatically prescribed and notified to the patients, whereas recommendations about insulin requirements are notified also to the physicians, who will decide if insulin needs to be prescribed. The system provides clinicians with a view where patients are prioritized according to their metabolic condition. A randomized controlled clinical trial was designed to evaluate the effectiveness and safety of Sinedie interventions versus standard care and its impact in the professionals’ workload in terms of the clinician’s time required per patient; number of face-to-face visits; frequency and duration of telematics reviews; patients’ compliance to self-monitoring; and patients’ satisfaction. Results Sinedie was clinically evaluated at “Parc Tauli University Hospital” in Spain during 17 months with the participation of 90 patients with gestational diabetes. Sinedie detected all situations that required a therapy adjustment and all the generated recommendations were safe. The time devoted by clinicians to patients’ evaluation was reduced by 27.389% and face-to-face visits per patient were reduced by 88.556%. Patients reported to be highly satisfied with the system, considering it useful and trusting in being well controlled. There was no monitoring loss and, in average, patients measured their glycaemia 3.890 times per day and sent their monitoring data every 3.477 days. Conclusions Sinedie generates safe advice about therapy adjustments, reduces the clinicians’ workload and helps physicians to identify which patients need a more urgent or more exhaustive examination and those who present good metabolic control. Additionally, Sinedie saves patients unnecessary displacements which contributes to medical centres’ waiting list reduction

In this work the design of a Luenberger observer is proposed to estimate the unmeasurable state space variables from Hovorka?s model. This model is linearized and evaluated in an operation point where Luenberger observer is designed using the Ackermann methodology. The observer is employed to estimate the unmeasurable variables of virtual patients which are generated by Bergman?s model. Once the unmeasurable state variables are obtained by the Luenberger observer using only the input-output information of the Bergman?s model, a control algorithm based on eigenvalues relocation trough Ackermann methodology for linear systems is applied. In this methodology, a constant feedback gain vector is obtained in order to compute the control signal (insulin) to be applied to virtual patient and keep on normoglycemia rank. The carbohydrates ingestion is considered as the main disturbances. In order to assess the proposed methodology, two tests are designed: the first one consists of changing the reference signal in order to evaluate the control sensitivity; and the second one includes different proportions of prandial insulin used in open-loop to try the controller response under distinct operation conditions. The results are obtained via simulation using Simulink of Matlab.

Objectives: The MobiGuide project aimed to establish a ubiquitous, user-friendly, patient-centered mobile decision-support system for patients and for their care providers, based on the continuous application of clinical guidelines and on semantically integrated electronic health records. Patients would be empowered by the system, which would enable them to lead their normal daily lives in their regular environment, while feeling safe, because their health state would be continuously monitored using mobile sensors and self-reporting of symptoms. When conditions occur that require medical attention, patients would be notified as to what they need to do, based on evidence-based guidelines, while their medical team would be informed appropriately, in parallel. We wanted to assess the system’s feasibility and potential effects on patients and care providers in two different clinical domains. Materials and methods: We describe MobiGuide’s architecture, which embodies these objectives. Our novel methodologies include a ubiquitous architecture, encompassing a knowledge elicitation process for parallel coordinated workflows for patients and care providers; the customization of computer-interpretable guidelines (CIGs) by secondary contexts affecting remote management and distributed decision-making; a mechanism for episodic, on demand projection of the relevant portions of CIGs from a centralized, backend decision-support system (DSS), to a local, mobile DSS, which continuously delivers the actual recommendations to the patient; shared decision-making that embodies patient preferences; semantic data integration; and patient and care provider notification services. MobiGuide has been implemented and assessed in a preliminary fashion in two domains: atrial fibril-lation (AF), and gestational diabetes Mellitus (GDM). Ten AF patients used the AF MobiGuide system in Italy and 19 GDM patients used the GDM MobiGuide system in Spain. The evaluation of the MobiGuide system focused on patient and care providers’ compliance to CIG recommendations and their satisfaction and quality of life. Results: Our evaluation has demonstrated the system’s capability for supporting distributed decision-making and its use by patients and clinicians. The results show that compliance of GDM patients to the most important monitoring targets – blood glucose levels (performance of four measurements a day: 0.87 ± 0.11; measurement according to the recommended frequency of every day or twice a week:0.99 ± 0.03), ketonuria (0.98 ± 0.03), and blood pressure (0.82 ± 0.24) – was high in most GDM patients, while compliance of AF patients to the most important targets was quite high, considering the required ECG measurements (0.65 ± 0.28) and blood-pressure measurements (0.75 ± 1.33). This outcome was viewed by the clinicians as a major potential benefit of the system, and the patients have demonstrated that they are capable of self-monitoring – something that they had not experienced before. In addition,the system caused the clinicians managing the AF patients to change their diagnosis and subsequent treatment for two of the ten AF patients, and caused the clinicians managing the GDM patients to start insulin therapy earlier in two of the 19 patients, based on system’s recommendations. Based on the end-of-study questionnaires, the sense of safety that the system has provided to the patients was its greatest asset. Analysis of the patients’ quality of life (QoL) questionnaires for the AF patients was inconclusive, because while most patients reported an improvement in their quality of life in the EuroQoL questionnaire, most AF patients reported a deterioration in the AFEQT questionnaire. Discussion: Feasibility and some of the potential benefits of an evidence-based distributed patient-guidance system were demonstrated in both clinical domains. The potential application of MobiGuide to other medical domains is supported by its standards-based patient health record with multiple electronic medical record linking capabilities, generic data insertion methods, generic medical knowledge representation and application methods, and the ability to communicate with a wide range of sensors. Future larger scale evaluations can assess the impact of such a system on clinical outcomes. Conclusion: MobiGuide’s feasibility was demonstrated by a working prototype for the AF and GDM domains, which is usable by patients and clinicians, achieving high compliance to self-measurement recommendations, while enhancing the satisfaction of patients and care providers.

Background: The use of telemedicine for diabetes care has evolved over time, proving that it contributes to patient self-monitoring, improves glycemic control, and provides analysis tools for decision support. The timely development of a safe and robust ambulatory artificial pancreas should rely on a telemedicine architecture complemented with automatic data analysis tools able to manage all the possible high-risk situations and to guarantee the patient's safety. Methods: The Intelligent Control Assistant system (INCA) telemedical artificial pancreas architecture is based on a mobile personal assistant integrated into a telemedicine system. The INCA supports four control strategies and implements an automatic data processing system for risk management (ADP-RM) providing short-term and medium-term risk analyses. The system validation comprises data from 10 type 1 pump-treated diabetic patients who participated in two randomized crossover studies, and it also includes in silico simulation and retrospective data analysis. Results: The ADP-RM short-term risk analysis prevents hypoglycemic events by interrupting insulin infusion. The pump interruption has been implemented in silico and tested for a closed-loop simulation over 30 hours. For medium-term risk management, analysis of capillary blood glucose notified the physician with a total of 62 alarms during a clinical experiment (56% for hyperglycemic events). The ADP-RM system is able to filter anomalous continuous glucose records and to detect abnormal administration of insulin doses with the pump. Conclusions: Automatic data analysis procedures have been tested as an essential tool to achieve a safe ambulatory telemedical artificial pancreas, showing their ability to manage short-term and medium-term risk situations.

Background: The risks associated with gestational diabetes (GD) can be reduced with an active treatment able to improve glycemic control. Advances in mobile health can provide new patient-centric models for GD to create personalized health care services, increase patient independence and improve patients’ self-management capabilities, and potentially improve their treatment compliance. In these models, decision-support functions play an essential role. Methods: The telemedicine system MobiGuide provides personalized medical decision support for GD patients that is based on computerized clinical guidelines and adapted to a mobile environment. The patient’s access to the system is supported by a smartphone-based application that enhances the efficiency and ease of use of the system. We formalized the GD guideline into a computer-interpretable guideline (CIG). Results: We identified several workflows that provide decision-support functionalities to patients and 4 types of personalized advice to be delivered through a mobile application at home, which is a preliminary step to providing decision-support tools in a telemedicine system: (1) therapy, to help patients to comply with medical prescriptions; (2) monitoring, to help patients to comply with monitoring instructions; (3) clinical assessment, to inform patients about their health conditions; and (4) upcoming events, to deal with patients’ personal context or special events. Conclusions: The whole process to specify patient-oriented decision support functionalities ensures that it is based on the knowledge contained in the GD clinical guideline and thus follows evidence-based recommendations but at the same time is patient-oriented, which could enhance clinical outcomes and patients’ acceptance of the whole system.

Automatic blood glucose classification may help specialists to provide a better interpretation of blood glucose data, downloaded directly from patients glucose meter and will contribute in the development of decision support systems for gestational diabetes. This paper presents an automatic blood glucose classifier for gestational diabetes that compares 6 different feature selection methods for two machine learning algorithms: neural networks and decision trees. Three searching algorithms, Greedy, Best First and Genetic, were combined with two different evaluators, CSF and Wrapper, for the feature selection. The study has been made with 6080 blood glucose measurements from 25 patients. Decision trees with a feature set selected with the Wrapper evaluator and the Best first search algorithm obtained the best accuracy: 95.92%.

Objective: This study assessed the efficacy of a closed-loop (CL) system consisting of a predictive rule-based algorithm (pRBA) on achieving nocturnal and postprandial normoglycemia in patients with type 1 diabetes mellitus (T1DM). The algorithm is personalized for each patient’s data using two different strategies to control nocturnal and postprandial periods. Research Design and Methods: We performed a randomized crossover clinical study in which 10 T1DM patients treated with continuous subcutaneous insulin infusion (CSII) spent two nonconsecutive nights in the research facility: one with their usual CSII pattern (open-loop [OL]) and one controlled by the pRBA (CL). The CL period lasted from 10 p.m. to 10 a.m., including overnight control, and control of breakfast. Venous samples for blood glucose (BG) measurement were collected every 20 min. Results: Time spent in normoglycemia (BG, 3.9–8.0 mmol/L) during the nocturnal period (12 a.m.–8 a.m.), expressed as median (interquartile range), increased from 66.6% (8.3–75%) with OL to 95.8% (73–100%) using the CL algorithm (P

We introduce the need for a distributed guideline-based decision sup-port (DSS) process, describe its characteristics, and explain how we implement-ed this process within the European Union?s MobiGuide project. In particular, we have developed a mechanism of sequential, piecemeal projection, i.e., 'downloading' small portions of the guideline from the central DSS server, to the local DSS in the patient's mobile device, which then applies that portion, us-ing the mobile device's local resources. The mobile device sends a callback to the central DSS when it encounters a triggering pattern predefined in the pro-jected module, which leads to an appropriate predefined action by the central DSS, including sending a new projected module, or directly controlling the rest of the workflow. We suggest that such a distributed architecture that explicitly defines a dialog between a central DSS server and a local DSS module, better balances the computational load and exploits the relative advantages of the cen-tral server and of the local mobile device.

The MobiGuide system provides patients with personalized decision support tools, based on computerized clinical guidelines, in a mobile environment. The generic capabilities of the system will be demonstrated applied to the clinical domain of Gestational Diabetes (GD). This paper presents a methodology to identify personalized recommendations, obtained from the analysis of the GD guideline. We added a conceptual parallel part to the formalization of the GD guideline called ”parallel workflow” that allows considering patient’s personal context and preferences. As a result of analysing the GD guideline and eliciting medical knowledge, we identified three different types of personalized advices (therapy, measurements and upcoming events) that will be implemented to perform patients’ guiding at home, supported by the MobiGuide system. These results will be essential to determine the distribution of functionalities between mobile and server decision support capabilities.

Background: Healthy diet and regular physical activity are powerful tools in reducing diabetes and cardiometabolic risk. Various international scientific and health organizations have advocated the use of new technologies to solve these problems. The PREDIRCAM project explores the contribution that a technological system could offer for the continuous monitoring of lifestyle habits and individualized treatment of obesity as well as cardiometabolic risk prevention. Methods: PREDIRCAM is a technological platform for patients and professionals designed to improve the effectiveness of lifestyle behavior modifications through the intensive use of the latest information and communication technologies. The platform consists of a web-based application providing communication interface with monitoring devices of physiological variables, application for monitoring dietary intake, ad hoc electronic medical records, different communication channels, and an intelligent notification system. A 2-week feasibility study was conducted in 15 volunteers to assess the viability of the platform. Results: The website received 244 visits (average time/session: 17 min 45 s). A total of 435 dietary intakes were recorded (average time for each intake registration, 4 min 42 s ± 2 min 30 s), 59 exercises were recorded in 20 heart rate monitor downloads, 43 topics were discussed through a forum, and 11 of the 15 volunteers expressed a favorable opinion toward the platform. Food intake recording was reported as the most laborious task. Ten of the volunteers considered long-term use of the platform to be feasible. Conclusions: The PREDIRCAM platform is technically ready for clinical evaluation. Training is required to use the platform and, in particular, for registration of dietary food intake.

The combination of telemedicine systems integrating mobile technologies with the use of continuous glucose monitors improves patients' glycemic control but demands a higher interaction with information technology tools that must be assessed. In this article, we analyze patients' behavior from the use-of-the-system point of view, identifying how continuous monitoring may change the interaction of patients with the mobile telemedicine system.Patients' behavior were evaluated in a clinical experiment consisting of a 2-month crossover randomized study with 10 type 1 diabetes patients. During the entire experiment, patients used the DIABTel telemedicine system, and during the intervention phase, they wore a continuous glucose monitor. Throughout the experiment, all user actions were automatically registered. This article analyzes the occurrence of events and the behavior patterns in blood glucose (BG) self-monitoring and insulin adjustments. A subjective evaluation was also performed based on the answers of the patients to a questionnaire delivered at the end of the study.The number of sessions established with the mobile Smart Assistant was considerably higher during the intervention period than in the control period (29.0 versus 18.8, p.05), and it was also higher than the number of Web sessions (29.0 versus 22.2, p.01). The number of daily boluses was higher during the intervention period than in the control period (5.27 versus 4.40, p.01). The number of daily BG measurements was also higher during the intervention period (4.68 versus 4.05, p.05) and, in percentage, patients increased the BG measurements not associated to meals while decreasing the percentage of preprandial measurements. The subjective evaluation shows that patients would recommend the use of DIABTel in routine care.The use of a continuous glucose monitor changes the way patients manage their diabetes, as observed in the increased number of daily insulin bolus, the increased number of daily BG measurements, and the differences in the distribution of BG measurements throughout the day. Continuous monitoring also increases the interaction of patients with the information system and modifies their patterns of use. We can conclude that mobile technologies are especially useful in scenarios of tight monitoring in diabetes, and they are well accepted by patients.

This work explores the automatic recognition of physical activity intensity patterns from multi-axial accelerometry and heart rate signals. Data collection was carried out in free-living conditions and in three controlled gymnasium circuits, for a total amount of 179.80 h of data divided into: sedentary situations (65.5%), light-to-moderate activity (17.6%) and vigorous exercise (16.9%). The proposed machine learning algorithms comprise the following steps: time-domain feature definition, standardization and PCA projection, unsupervised clustering (by k-means and GMM) and a HMM to account for long-term temporal trends. Performance was evaluated by 30 runs of a 10-fold cross-validation. Both k-means and GMM-based approaches yielded high overall accuracy (86.97% and 85.03%, respectively) and, given the imbalance of the dataset, meritorious F-measures (up to 77.88%) for non-sedentary cases. Classification errors tended to be concentrated around transients, what constrains their practical impact. Hence, we consider our proposal to be suitable for 24 h-based monitoring of physical activity in ambulatory scenarios and a first step towards intensity-specific energy expenditure estimators.

The growing availability of continuous data from medical devices in diabetes management makes it crucial to define novel information technology architectures for efficient data storage, data transmission, and data visualization. The new paradigm of care demands the sharing of information in interoperable systems as the only way to support patient care in a continuum of care scenario. The technological platforms should support all the services required by the actors involved in the care process, located in different scenarios and managing diverse information for different purposes. This article presents basic criteria for defining flexible and adaptive architectures that are capable of interoperating with external systems, and integrating medical devices and decision support tools to extract all the relevant knowledge to support diabetes care.

The DIABTel system, a Web-based telemedicine application, integrates a whole communication system (glucometer, insulin pump, wireless hand-held assistant) for medical remote advice. We sought to evaluate, in terms of glycemic control, the DIABTel system in a randomized crossover clinical study.Ten patients with type 1 diabetes [5 women, age 40.6 (21-62) years, diabetes duration 14.7 (3-52) years] were included. During the 4-week active phase, data sent by patients were analyzed by the physician and modifications of the basal rate and bolus were advised in the following 24 hours. During the control phase, patients sent glucose data without any feedback from the medical center.The mean numbers of daily glucose values and bolus sent by patients during the active period were 4.46 +/- 0.91 and 4.58 +/- 0.89, respectively. The personal digital assistant functionalities used more frequently by patients were (times per week) data visualization (8.1 +/- 6.8), data download from the insulin pump (6.8 +/- 3.3), and synchronization with the telemedicine server (8.5 +/- 4.9). After the experimental phase, serum fructosamine decreased significantly (393 +/- 32 vs 366 +/- 25 micromol/liter; p0.05) and hemoglobin A1c (HbA1c) tended to decrease (8.0 +/- 0.6 vs 7.78 +/- 0.6; p = 0.073), whereas no changes were observed during the control phase. The number of treatment modifications proposed and performed by the patients correlated with the change observed in HbA1c during the active phase (r = -0.729, p = 0.017).The DIABTel system, a telemedicine system that includes a wireless personal assistant for remote treatment advising, allows better glycemic control in pump-treated patients with type 1 diabetes. To our knowledge, this is the first study that demonstrates improved glycemic control with the use of a telemedicine system that incorporates insulin delivery data.

The accurate interpretation of Blood Glucose (BG) values is essential for diabetes care. However, BG monitoring data does not provide complete information about associated meal and moment of measurement, unless patients fulfil it manually. An automatic classification of incomplete BG data helps to a more accurate interpretation, contributing to Knowledge Management (KM) tools that support decision-making in a telemedicine system. This work presents a fuzzy rule-based classifier integrated in a KM agent of the DIABTel telemedicine architecture, to automatically classify BG measurements into meal intervals and moments of measurement. Fuzzy Logic (FL) tackles with the incompleteness of BG measurements and provides a semantic expressivity quite close to natural language used by physicians, what makes easier the system output interpretation. The best mealtime classifier provides an accuracy of 77.26% and does not increase significantly the KM analysis times. Results of classification are used to extract anomalous trends in the patient's data.

The integration of continuous subcutaneous insulin infusion (CSII) (insulin pump therapy) and continuous interstitial glucose monitoring (CGM) appears to be an excellent solution for obtaining the desirable metabolic control for most insulin-treated subjects (1–4). Several studies have suggested that CGM with readings in real-time (CGM-RT) further improves blood glucose control (5–9). The introduction of CGM and CSII into clinical practice has generated an inevitable increase in the amount of data to be managed and interpreted. Telemedicine facilitates data management and preprocessing to optimize therapy. Among other potential benefits, telemedicine improves communication among patients and health care providers, improves quantity and quality of data collection, and eases decision-making and therapy adjustment (10–12). DIABTel, a web-based telemedicine system, is a good example for a solution designed to supply these needs (13). PARIS (Pancreas Artificial Telemedico Inteligente) is a coordinated research project to develop and validate a telemedical artificial pancreas (TAP), a multi-access telemedicine system that integrates CGM-RT, insulin pump, a smart assistant (SA), and close-loop control algorithms. SA is a personal intelligent assistant based on a handheld digital device to provide both personal and remote loop strategies, using CGM, CSII, and mobile general packet radio service (GPRS) communication with a telemedicine central server (TMCS). This review summarizes acquired experiences with TAP, integrating these new technologies with the objective to improve glycemic control of type 1 diabetic patients. ### Description of the DIABTel telemedicine system The telemedicine architecture consists of two components: the medical unit (a telemedical central server) and the patient unit (a smart assistant). The TMCS at the diabetes center of the hospital continuously runs, receiving and processing patients' monitoring data, messages, and requests for professional advice. A previous publication already reported the benefits of DIABTel, allowing the implementation of an easy-to-use, user-tailored telemedicine system with a technological platform allowing tight …

Purpose: Advanced information technologies joined to the increasing use of continuous medical devices for monitoring and treatment, have made possible the definition of a new telemedical diabetes care scenario based on a hand-held Personal Assistant (PA). This paper describes the architecture, functionality and implementation of the PA, which communicates different medical devices in a personal wireless network. Description of the system: The PA is a mobile system for patients with diabetes connected to a telemedical center. The software design follows a modular approach to make the integration of medical devices or new functionalities independent from the rest of its components. Physicians can remotely control medical devices from the telemedicine server through the integration of the Common Object Request Broker Architecture (CORBA) and mobile GPRS communications. Data about PA modules' usage and patients' behavior evaluation come from a pervasive tracing system implemented into the PA. Results and discussion: The PA architecture has been technically validated with commercially available medical devices during a clinical experiment for ambulatory monitoring and expert feedback through telemedicine. The clinical experiment has allowed defining patients' patterns of usage and preferred scenarios and it has proved the Personal Assistant's feasibility. The patients showed high acceptability and interest in the system as recorded in the usability and utility questionnaires. Future work will be devoted to the validation of the system with automatic control strategies from the telemedical center as well as with closed-loop control algorithms. (C) 2008 Elsevier Ireland Ltd. All rights reserved.