An automatic deep reinforcement learning bolus calculator for automated insulin delivery systems.

In hybrid automatic insulin delivery (HAID) systems, meal disturbance is compensated by feedforward control, which requires the announcement of the meal by the patient with type 1 diabetes (DM1) to achieve the desired glycemic control performance. The calculation of insulin bolus in the HAID system is based on the amount of carbohydrates (CHO) in the meal and patient-specific parameters, i.e. carbohydrate-to-insulin ratio (CR) and insulin sensitivity-related correction factor (CF). The estimation of CHO in a meal is prone to errors and is burdensome for patients. This study proposes a fully automatic insulin delivery (FAID) system that eliminates patient intervention by compensating for unannounced meals. This study exploits the deep reinforcement learning (DRL) algorithm to calculate insulin bolus for unannounced meals without utilizing the information on CHO content. The DRL bolus calculator is integrated with a closed-loop controller and a meal detector (both previously developed by our group) to implement the FAID system. An adult cohort of 68 virtual patients based on the modified UVa/Padova simulator was used for in-silico trials. The percentage of the overall duration spent in the target range of 70-180 mg/dL was 71.2 % and 76.2 % , < 70 mg/dL was 0.9 % and 0.1 % , and > 180 mg/dL was 26.7 % and 21.1 % , respectively, for the FAID system and HAID system utilizing a standard bolus calculator (SBC) including CHO misestimation. The proposed algorithm can be exploited to realize FAID systems in the future.

Generative deep learning for the development of a type 1 diabetes simulator.

BACKGROUND: Type 1 diabetes (T1D) simulators, crucial for advancing diabetes treatments, often fall short of capturing the entire complexity of the glucose-insulin system due to the imprecise approximation of the physiological models. This study introduces a simulation approach employing a conditional deep generative model. The aim is to overcome the limitations of existing T1D simulators by synthesizing virtual patients that more accurately represent the entire glucose-insulin system physiology. METHODS: Our methodology utilizes a sequence-to-sequence generative adversarial network to simulate virtual T1D patients causally. Causality is embedded in the model by introducing shifted input-output pairs during training, with a 90-min shift capturing the impact of input insulin and carbohydrates on blood glucose. To validate our approach, we train and evaluate the model using three distinct datasets, each consisting of 27, 12, and 10 T1D patients, respectively. In addition, we subject the trained model to further validation for closed-loop therapy, employing a state-of-the-art controller. RESULTS: The generated patients display statistical similarity to real patients when evaluated on the time-in-range results for each of the standard blood glucose ranges in T1D management along with means and variability outcomes. When tested for causality, authentic causal links are identified between the insulin, carbohydrates, and blood glucose levels of the virtual patients. The trained generative model demonstrates behaviours that are closer to reality compared to conventional T1D simulators when subjected to closed-loop insulin therapy using a state-of-the-art controller. CONCLUSIONS: These results highlight our approach's capability to accurately capture physiological dynamics and establish genuine causal relationships, holding promise for enhancing the development and evaluation of therapies in diabetes.

New therapies and treatments for type 1 diabetes (T1D) are often first tested on specialized computer programs called simulators before being tried on actual patients. Traditionally, these simulators rely on mathematical equations to mimic real-life patients, but they sometimes fail to provide reliable results because they do not consider everything that affects individuals with diabetes, such as lifestyle, eating habits, time of day, and weather. In our research, we suggest using computer programs based on artificial intelligence that can directly learn all these factors from real patient data. We tested our programs using information from different groups of patients and found that they were much better at predicting what would happen with a patient's diabetes. These new programs can understand how insulin, food, and blood sugar levels interact in the body, which makes them valuable for developing therapies for T1D.

An ensemble machine learning approach for the detection of unannounced meals to enhance postprandial glucose control.

BACKGROUND: Hybrid automated insulin delivery systems enhance postprandial glucose control in type 1 diabetes, however, meal announcements are burdensome. To overcome this, we propose a machine learning-based automated meal detection approach; METHODS:: A heterogeneous ensemble method combining an artificial neural network, random forest, and logistic regression was employed. Trained and tested on data from two in-silico cohorts comprising 20 and 47 patients. It accounted for various meal sizes (moderate to high) and glucose appearance rates (slow and rapid absorbing). To produce an optimal prediction model, three ensemble configurations were used: logical AND, majority voting, and logical OR. In addition to the in-silico data, the proposed meal detector was also trained and tested using the OhioT1DM dataset. Finally, the meal detector is combined with a bolus insulin compensation scheme; RESULTS:: The ensemble majority voting obtained the best meal detector results for both the in-silico and OhioT1DM cohorts with a sensitivity of 77%, 94%, 61%, precision of 96%, 89%, 72%, F1-score of 85%, 91%, 66%, and with false positives per day values of 0.05, 0.19, 0.17, respectively. Automatic meal detection with insulin compensation has been performed in open-loop insulin therapy using the AND ensemble, chosen for its lower false positive rate. Time-in-range has significantly increased 10.48% and 16.03%, time above range was reduced by 5.16% and 11.85%, with a minimal time below range increase of 0.35% and 2.69% for both in-silico cohorts, respectively, compared to the results without a meal detector; CONCLUSION:: To increase the overall accuracy and robustness of the predictions, this ensemble methodology aims to take advantage of each base model's strengths. All of the results point to the potential application of the proposed meal detector as a separate module for the detection of meals in automated insulin delivery systems to achieve improved glycemic control.

Optimizing Noninvasive Vagus Nerve Stimulation for Systemic Lupus Erythematosus: Protocol for a Multicenter Randomized Controlled Trial.

BACKGROUND: Systemic lupus erythematosus is a chronic, multisystem, inflammatory disease of autoimmune etiology occurring predominantly in women. A major hurdle to the diagnosis, treatment, and therapeutic advancement of this disease is its heterogeneous nature, which presents as a wide range of symptoms such as fatigue, fever, musculoskeletal involvement, neuropsychiatric disorders, and cardiovascular involvement with varying severity. The current therapeutic approach to this disease includes the administration of immunomodulatory drugs that may produce unfavorable secondary effects. OBJECTIVE: This study explores the known relationship between the autonomic nervous system and inflammatory pathways to improve patient outcomes by treating autonomic nervous system dysregulation in patients via noninvasive vagus nerve stimulation. In this study, data including biomarkers, physiological signals, patient outcomes, and patient quality of life are being collected and analyzed. After completion of the clinical trial, a computer model will be developed to identify the biomarkers and physiological signals related to lupus activity in order to understand how they change with different noninvasive vagus nerve stimulation frequency parameters. Finally, we propose building a decision support system with integrated noninvasive wearable technologies for continuous cardiovascular and peripheral physiological sensing for adaptive, patient-specific optimization of the noninvasive vagus nerve stimulation frequency parameters in real time. METHODS: The protocol was designed to evaluate the efficacy and safety of transauricular vagus nerve stimulation in patients with systemic lupus erythematosus. This multicenter, national, randomized, double-blind, parallel-group, placebo-controlled study will recruit a minimum of 18 patients diagnosed with this disease. Evaluation and treatment of patients will be conducted in an outpatient clinic and will include 12 visits. Visit 1 consists of a screening session. Subsequent visits up to visit 6 involve mixing treatment and evaluation sessions. Finally, the remaining visits correspond with early and late posttreatment follow-ups. RESULTS: On November 2022, data collection was initiated. Of the 10 participants scheduled for their initial appointment, 8 met the inclusion criteria, and 6 successfully completed the entire protocol. Patient enrollment and data collection are currently underway and are expected to be completed in December 2023. CONCLUSIONS: The results of this study will advance patient-tailored vagus nerve stimulation therapies, providing an adjunctive treatment solution for systemic lupus erythematosus that will foster adoption of technology and, thus, expand the population with systemic lupus erythematosus who can benefit from improved autonomic dysregulation, translating into reduced costs and better quality of life. TRIAL REGISTRATION: ClinicalTrials.gov NCT05704153; https://clinicaltrials.gov/study/NCT05704153. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48387.

Intermittent closed-loop blood glucose control for people with type 1 diabetes on multiple daily injections.

BACKGROUND AND OBJECTIVES: Recent advances in Automated Insulin Delivery systems have been shown to dramatically improve glycaemic control and reduce the risk of hypoglycemia in people with type 1 diabetes. However, they are complex systems that require specific training and are not affordable for most. Attempts to reduce the gap with closed-loop therapies using advanced dosing advisors have so far failed, mainly because they require too much human intervention. With the advent of smart insulin pens, one of the main constraints (having reliable bolus and meal information) disappears and new strategies can be employed. This is our starting hypothesis, which we have validated in a very demanding simulator. In this paper, we propose an intermittent closed-loop control system specifically intended for multiple daily injection therapy to bring the benefits of artificial pancreas to the application of multiple daily injections. METHODS: The proposed control algorithm is based on model predictive control and integrates two patient-driven control actions. Correction insulin boluses are automatically computed and recommended to the patient to minimize the duration of hyperglycemia. Rescue carbohydrates are also triggered to avoid hypoglycemia episodes. The algorithm can adapt to different patient lifestyles with customizable triggering conditions, closing the gap between practicality and performance. The proposed algorithm is compared with conventional open-loop therapy, and its superiority is demonstrated through extensive in silico evaluations using realistic cohorts and scenarios. The evaluations were conducted in a cohort of 47 virtual patients. We also provide detailed explanations of the implementation, imposed constraints, triggering conditions, cost functions, and penalties for the algorithm. RESULTS: The in-silico outcomes combining the proposed closed-loop strategy with slow-acting insulin analog injections at 09:00 h resulted in percentages of time in range (TIR) (70-180 mg/dL) of 69.5%, 70.6%, and 70.4% for glargine-100, glargine-300, and degludec-100, respectively, and injections at 20:00 h resulted in percentages of TIR of 70.5%, 70.3%, and 71.6%, respectively. In all the cases, the percentages of TIR were considerably higher than those obtained from the open-loop strategy, being only 50.7%, 53.9%, and 52.2% for daytime injection and 55.5%, 54.1%, and 56.9% for nighttime injection. Overall, the occurrence of hypoglycemia and hyperglycemia was notably reduced using our approach. CONCLUSIONS: Event-triggering model predictive control in the proposed algorithm is feasible and may meet clinical targets for people with type 1 diabetes.

Bolus Insulin calculation without meal information. A reinforcement learning approach.

In continuous subcutaneous insulin infusion and multiple daily injections, insulin boluses are usually calculated based on patient-specific parameters, such as carbohydrates-to-insulin ratio (CR), insulin sensitivity-based correction factor (CF), and the estimation of the carbohydrates (CHO) to be ingested. This study aimed to calculate insulin boluses without CR, CF, and CHO content, thereby eliminating the errors caused by misestimating CHO and alleviating the management burden on the patient. A Q-learning-based reinforcement learning algorithm (RL) was developed to optimise bolus insulin doses for in-silico type 1 diabetic patients. A realistic virtual cohort of 68 patients with type 1 diabetes that was previously developed by our research group, was considered for the in-silico trials. The results were compared to those of the standard bolus calculator (SBC) with and without CHO misestimation using open-loop basal insulin therapy. The percentage of the overall duration spent in the target range of 70-180 mg/dL was 73.4% and 72.37%, <70 mg/dL was 1.96 and 0.70%, and >180 mg/dL was 23.40 and 24.63%, respectively, for RL and SBC without CHO misestimation. The results revealed that RL outperformed SBC in the presence of CHO misestimation, and despite not knowing the CHO content of meals, the performance of RL was similar to that of SBC in perfect conditions. This algorithm can be incorporated into artificial pancreas and automatic insulin delivery systems in the future.

Generation of Individualized Synthetic Data for Augmentation of the Type 1 Diabetes Data Sets Using Deep Learning Models.

In this paper, we present a methodology based on generative adversarial network architecture to generate synthetic data sets with the intention of augmenting continuous glucose monitor data from individual patients. We use these synthetic data with the aim of improving the overall performance of prediction models based on machine learning techniques. Experiments were performed on two cohorts of patients suffering from type 1 diabetes mellitus with significant differences in their clinical outcomes. In the first contribution, we have demonstrated that the chosen methodology is able to replicate the intrinsic characteristics of individual patients following the statistical distributions of the original data. Next, a second contribution demonstrates the potential of synthetic data to improve the performance of machine learning approaches by testing and comparing different prediction models for the problem of predicting nocturnal hypoglycemic events in type 1 diabetic patients. The results obtained for both generative and predictive models are quite encouraging and set a precedent in the use of generative techniques to train new machine learning models.

A Machine Learning Approach to Minimize Nocturnal Hypoglycemic Events in Type 1 Diabetic Patients under Multiple Doses of Insulin.

Nocturnal hypoglycemia (NH) is one of the most challenging events for multiple dose insulin therapy (MDI) in people with type 1 diabetes (T1D). The goal of this study is to design a method to reduce the incidence of NH in people with T1D under MDI therapy, providing a decision-support system and improving confidence toward self-management of the disease considering the dataset used by Bertachi et al. Different machine learning (ML) algorithms, data sources, optimization metrics and mitigation measures to predict and avoid NH events have been studied. In addition, we have designed population and personalized models and studied the generalizability of the models and the influence of physical activity (PA) on them. Obtaining 30 g of rescue carbohydrates (CHO) is the optimal value for preventing NH, so it can be asserted that this is the value with which the time under 70 mg/dL decreases the most, with almost a 35% reduction, while increasing the time in the target range by 1.3%. This study supports the feasibility of using ML techniques to address the prediction of NH in patients with T1D under MDI therapy, using continuous glucose monitoring (CGM) and a PA tracker. The results obtained prove that BG predictions can not only be critical in achieving safer diabetes management, but also assist physicians and patients to make better and safer decisions regarding insulin therapy and their day-to-day lives.

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges.

(1) Background: the use of machine learning techniques for the purpose of anticipating hypoglycemia has increased considerably in the past few years. Hypoglycemia is the drop in blood glucose below critical levels in diabetic patients. This may cause loss of cognitive ability, seizures, and in extreme cases, death. In almost half of all the severe cases, hypoglycemia arrives unannounced and is essentially asymptomatic. The inability of a diabetic patient to anticipate and intervene the occurrence of a hypoglycemic event often results in crisis. Hence, the prediction of hypoglycemia is a vital step in improving the life quality of a diabetic patient. The objective of this paper is to review work performed in the domain of hypoglycemia prediction by using machine learning and also to explore the latest trends and challenges that the researchers face in this area; (2) Methods: literature obtained from PubMed and Google Scholar was reviewed. Manuscripts from the last five years were searched for this purpose. A total of 903 papers were initially selected of which 57 papers were eventually shortlisted for detailed review; (3) Results: a thorough dissection of the shortlisted manuscripts provided an interesting split between the works based on two categories: hypoglycemia prediction and hypoglycemia detection. The entire review was carried out keeping this categorical distinction in perspective while providing a thorough overview of the machine learning approaches used to anticipate hypoglycemia, the type of training data, and the prediction horizon.

Prediction of Nocturnal Hypoglycemia in Adults with Type 1 Diabetes under Multiple Daily Injections Using Continuous Glucose Monitoring and Physical Activity Monitor.

(1) Background: nocturnal hypoglycemia (NH) is one of the most challenging side effects of multiple doses of insulin (MDI) therapy in type 1 diabetes (T1D). This work aimed to investigate the feasibility of a machine-learning-based prediction model to anticipate NH in T1D patients on MDI. (2) Methods: ten T1D adults were studied during 12 weeks. Information regarding T1D management, continuous glucose monitoring (CGM), and from a physical activity tracker were obtained under free-living conditions at home. Supervised machine-learning algorithms were applied to the data, and prediction models were created to forecast the occurrence of NH. Individualized prediction models were generated using multilayer perceptron (MLP) and a support vector machine (SVM). (3) Results: population outcomes indicated that more than 70% of the NH may be avoided with the proposed methodology. The predictions performed by the SVM achieved the best population outcomes, with a sensitivity and specificity of 78.75% and 82.15%, respectively. (4) Conclusions: our study supports the feasibility of using ML techniques to address the prediction of nocturnal hypoglycemia in the daily life of patients with T1D on MDI, using CGM and a physical activity tracker.

Prediction and prevention of hypoglycaemic events in type-1 diabetic patients using machine learning.

Tight blood glucose control reduces the risk of microvascular and macrovascular complications in patients with type 1 diabetes. However, this is very difficult due to the large intra-individual variability and other factors that affect glycaemic control. The main limiting factor to achieve strict control of glucose levels in patients on intensive insulin therapy is the risk of severe hypoglycaemia. Therefore, hypoglycaemia is the main safety problem in the treatment of type 1 diabetes, negatively affecting the quality of life of patients suffering from this disease. Decision support tools based on machine learning methods have become a viable way to enhance patient safety by anticipating adverse glycaemic events. This study proposes the application of four machine learning algorithms to tackle the problem of safety in diabetes management: (1) grammatical evolution for the mid-term continuous prediction of blood glucose levels, (2) support vector machines to predict hypoglycaemic events during postprandial periods, (3) artificial neural networks to predict hypoglycaemic episodes overnight, and (4) data mining to profile diabetes management scenarios. The proposal consists of the combination of prediction and classification capabilities of the implemented approaches. The resulting system significantly reduces the number of episodes of hypoglycaemia, improving safety and providing patients with greater confidence in decision-making.

Minimizing postprandial hypoglycemia in Type 1 diabetes patients using multiple insulin injections and capillary blood glucose self-monitoring with machine learning techniques.

BACKGROUND: Diabetic patients treated with intensive insulin therapies require a tight glycemic control and may benefit from advanced tools to predict blood glucose (BG) concentration levels and hypo/hyperglycemia events. Prediction systems using machine learning techniques have mainly focused on applications for sensor augmented pump (SAP) therapy. In contrast, insulin bolus calculators that rely on BG prediction for multiple daily insulin (MDI) injections for patients under self-monitoring blood glucose (SMBG) are scarce because of insufficient data sources and limited prediction capability of forecasting models. METHODS: We trained individualized models that can predict postprandial hypoglycemia via different machine learning algorithms using retrospective data from 10 real patients. In addition, we designed and tested a hypoglycemia reduction strategy for a similar in silico population. The system generates a bolus reduction suggestion as the scaled weighted sum of the predictions. We evaluated the general and postprandial glycemic outcomes of the in silico population to assess the systems capability of avoiding hypoglycemias. RESULTS: The median [IQR] sensitivity and specificity for hypoglycemia cases where the BG level was below 70 mg/dL were 0.49 [0.2-0.5] and 0.74 [0.7-0.9], respectively. For hypoglycemia cases where the BG level was below 54 mg/dL, the median [IQR] sensitivity and specificity were 0.51 [0.4-0.6] and 0.74 [0.7-0.8], respectively. CONCLUSIONS: The results indicated a decrease of 37% in the median number of postprandial hypoglycemias median decrease of 44% for hypoglycemias of 70 mg/dL and 54 mg/dL, respectively. This dramatic reduction makes this method a good candidate to be integrated into any Decision Support System for diabetes management.

Risk-based postprandial hypoglycemia forecasting using supervised learning.

BACKGROUND: Predicting insulin-induced postprandial hypoglycemic events is critical for the safety of type 1 diabetes patients because an early warning of hypoglycemia facilitates correction of the insulin bolus before its administration. The postprandial hypoglycemic event counts can be lowered by reducing the size of the bolus based on a reliable prediction but at the cost of increasing the average blood glucose. METHODS: We developed a method for predicting postprandial hypoglycemia using machine learning techniques personalized to each patient. The proposed system enables on-line therapeutic decision making for patients using a sensor augmented pump therapy. Two risk-based approaches were developed for a window of 240 min after the meal/bolus, and they were tested based on real retrospective data from 10 patients using 70 mg/dL and 54 mg/dL as thresholds according to the consensus for Level 1 and Level 2 hypoglycemia, respectively. Due to the small size of the patient cohort, we trained personalized models for each patient. RESULTS: The median specificity and sensitivity were 79% and 71% for Level 1 hypoglycemia, respectively, and 81% and 77% for Level 2. CONCLUSIONS: The results demonstrated that it is feasible to anticipate hypoglycemic events with a reasonable false-positive rate. The accuracy of the results and the trade-off between performance metrics allow its use in decision support systems for patients who wear insulin pumps.

Impact of Use Frequency of a Mobile Diabetes Management App on Blood Glucose Control: Evaluation Study.

BACKGROUND: Technology has long been used to carry out self-management as well as to improve adherence to treatment in people with diabetes. However, most technology-based apps do not meet the basic requirements for engaging patients. OBJECTIVE: This study aimed to evaluate the effect of use frequency of a diabetes management app on glycemic control. METHODS: Overall, 2 analyses were performed. The first consisted of an examination of the reduction of blood glucose (BG) mean, using a randomly selected group of 211 users of the SocialDiabetes app (SDA). BG levels at baseline, month 3, and month 6 were calculated using the intercept of a regression model based on data from months 1, 4, and 7, respectively. In the second analysis, the impact of low and high BG risk was examined. A total of 2692 users logging SDA ≥5 days/month for ≥6 months were analyzed. The highest quartile regarding low blood glucose index (LBGI) and high blood glucose index (HBGI) at baseline (t1) was selected (n=74 for group A; n=440 for group B). Changes in HBGI and LBGI at month 6 (t2) were analyzed. RESULTS: For analysis 1, baseline BG results for type 1 diabetes mellitus (T1DM) groups A and B were 213.61 (SD 31.57) mg/dL and 206.43 (SD 18.65) mg/dL, respectively, which decreased at month 6 to 175.15 (SD 37.88) mg/dL and 180.6 (SD 40.47) mg/dL, respectively. For type 2 diabetes mellitus (T2DM), baseline BG was 218.77 (SD 40.18) mg/dL and 232.55 (SD 46.78) mg/dL, respectively, which decreased at month 6 to 160.51 (SD 39.32) mg/dL and 173.14 (SD 52.81) mg/dL for groups A and B, respectively. This represents a reduction of estimated A1c (eA1c) of approximately 1.3% (P<.001) and 0.9% (P=.001) for T1DM groups A and B, respectively, and 2% (P<.001) for both A and B T2DM groups, respectively. For analysis 2, T1DM baseline LBGI values for groups A and B were 5.2 (SD 3.9) and 4.4 (SD 2.3), respectively, which decreased at t2 to 3.4 (SD 3.3) and 3.4 (SD 1.9), respectively; this was a reduction of 34.6% (P=.005) and 22.7% (P=.02), respectively. Baseline HBGI values for groups A and B were 12.6 (SD 4.3) and 10.6 (SD 4.03), respectively, which decreased at t2 to 9.0 (SD 6.5) and 8.6 (SD 4.7), respectively; this was a reduction of 30% (P=.001) and 22% (P=.003), respectively. CONCLUSIONS: A significant reduction in BG was found in all groups, independent of the use frequency of the app. Better outcomes were found for T2DM patients. A significant reduction in LBGI and HBGI was found in all groups, regardless of the use frequency of the app. LBGI and HBGI indices of both groups tend to have similar values after 6 months of app use.

Artificial Intelligence for Diabetes Management and Decision Support: Literature Review.

BACKGROUND: Artificial intelligence methods in combination with the latest technologies, including medical devices, mobile computing, and sensor technologies, have the potential to enable the creation and delivery of better management services to deal with chronic diseases. One of the most lethal and prevalent chronic diseases is diabetes mellitus, which is characterized by dysfunction of glucose homeostasis. OBJECTIVE: The objective of this paper is to review recent efforts to use artificial intelligence techniques to assist in the management of diabetes, along with the associated challenges. METHODS: A review of the literature was conducted using PubMed and related bibliographic resources. Analyses of the literature from 2010 to 2018 yielded 1849 pertinent articles, of which we selected 141 for detailed review. RESULTS: We propose a functional taxonomy for diabetes management and artificial intelligence. Additionally, a detailed analysis of each subject category was performed using related key outcomes. This approach revealed that the experiments and studies reviewed yielded encouraging results. CONCLUSIONS: We obtained evidence of an acceleration of research activity aimed at developing artificial intelligence-powered tools for prediction and prevention of complications associated with diabetes. Our results indicate that artificial intelligence methods are being progressively established as suitable for use in clinical daily practice, as well as for the self-management of diabetes. Consequently, these methods provide powerful tools for improving patients' quality of life.

Personalized blood glucose prediction: A hybrid approach using grammatical evolution and physiological models.

The large patient variability in human physiology and the effects of variables such as exercise or meals challenge current prediction modeling techniques. Physiological models are very precise but they are typically complex and specific physiological knowledge is required. In contrast, data-based models allow the incorporation of additional inputs and accurately capture the relationship between these inputs and the outcome, but at the cost of losing the physiological meaning of the model. In this work, we designed a hybrid approach comprising physiological models for insulin and grammatical evolution, taking into account the clinical harm caused by deviations from the target blood glucose by using a penalizing fitness function based on the Clarke error grid. The prediction models were built using data obtained over 14 days for 100 virtual patients generated by the UVA/Padova T1D simulator. Midterm blood glucose was predicted for the 100 virtual patients using personalized models and different scenarios. The results obtained were promising; an average of 98.31% of the predictions fell in zones A and B of the Clarke error grid. Midterm predictions using personalized models are feasible when the configuration of grammatical evolution explored in this study is used. The study of new alternative models is important to move forward in the development of alarm-and-control applications for the management of type 1 diabetes and the customization of the patient's treatments. The hybrid approach can be adapted to predict short-term blood glucose values to detect continuous glucose-monitoring sensor errors and to estimate blood glucose values when the continuous glucose-monitoring system fails to provide them.

Adaptive Workflows for Diabetes Management: Self-Management Assistant and Remote Treatment for Diabetes.

Diabetes self-management is a crucial element for all people with diabetes and those at risk for developing the disease. Diabetic patients should be empowered to increase their self-management skills in order to prevent or delay the complications of diabetes. This work presents the proposal and first development stages of a smartphone application focused on the empowerment of the patients with diabetes. The concept of this interventional tool is based on the personalization of the user experience from an adaptive and dynamic perspective. The segmentation of the population and the dynamical treatment of user profiles among the different experience levels is the main challenge of the implementation. The self-management assistant and remote treatment for diabetes aims to develop a platform to integrate a series of innovative models and tools rigorously tested and supported by the research literature in diabetes together the use of a proved engine to manage workflows for healthcare.

Profiling intra-patient type I diabetes behaviors.

BACKGROUND: The large intra-patient variability in type 1 diabetic patients dramatically reduces the ability to achieve adequate blood glucose control. A novel methodology to identify different blood glucose dynamics profiles will allow therapies to be more accurate and tailored according to patient's conditions and to the situations faced by patients (exercise, week-ends, holidays, menstruation, etc). MATERIALS AND METHODS: A clustering methodology based on the normalized compression distance is applied to identify different profiles for diabetic patients. First, the methodology is validated using "in silico" data from 10 patients in 3 different scenarios: days without exercise, poor controlled exercise days and days with well-controlled exercise. Second, we perform a series of in vivo experiments using data from 10 patients assessing the ability of the proposed methodology in real scenarios. RESULTS: In silico experiments show that the methodology is able to identify poor and well-controlled days in theoretical scenarios. In vivo experiments present meaningful profiles for working days, bank days and other situations, where different insulin requirements were detected. CONCLUSIONS: A tool for profiling blood glucose dynamics of patients can be implemented in a short term to enhance existing analysis platforms using combined CGM-CSII systems. Besides coping with the information overload, the tool will assist physicians to adjust and improve insulin therapy and patients in the self-management of the disease.

Tratamiento de la leucemia mieloide crónica con mesilato de imatinib en pacientes resistentes o intolerantes al interferón alfa recombinante. Resultados preliminares / Chronic myeloid leukemia treated with Imatinib Mesilate in patients resistant to or intolerant to recombinant alpha Interferon. Preliminary studies

Se evaluaron 43 pacientes adultos con leucemia mieloide crónica, Philadelphia positivo, que recibieron tratamiento con mesilato de imatinib como droga de segunda línea por resistencia o intolerancia al interferón alfa recombinante. La manifestación más frecuente al inicio de la enfermedad fue la esplenomegalia. El tratamiento con mesilato de imatinib se inició por resistencia (33; 76,7 por ciento) o intolerancia grado 3 o 4 (10; 23,3 por ciento). El mayor porcentaje de respuesta citogenética mayor (22; 91,7 por ciento) y completa (11; 61,1 por ciento) se alcanzó a los 18 y 24 meses de evolución. El 74,3 por ciento no mostró respuesta molecular y el 5,1 por ciento ya presentaba respuesta molecular antes del tratamiento; 9 (26,5 por ciento) mostraron pérdida de la remisión hematológica completa, de ellos, 7 fallecieron por progresión de la enfermedad. La sobrevida global fue de 90,7 por ciento, 83,3 por ciento, 82,6 por ciento y 78,9 por ciento a los 5, 6, 7 y 8 años de evolución, respectivamente. La sobrevida global y libre de eventos a los 3 años de iniciado el mesilato de imatinib fue de 92,3 por ciento y 81,8 por ciento, respectivamente. Se encontró diferencia significativa entre la sobrevida libre de eventos y el índice pronóstico de Sokal. Las reacciones clínicas secundarias más frecuentes fueron dolores óseos, musculares o ambos; y las hematológicas: anemia hemolítica autoinmune y trombocitopenia

Forty three patients presenting with chronic positive-Philadelphia myeloid leukemia were assessed treated with Imatinib Mesilate as a second line drug by resistance or intolerance to recombinant alpha Interferon. At onset, the more frequent manifestation of this condition was the splenomegalia. Imatinib Mesilate treatment was started by resistance (33; 7.6 percent) or 3 or 4 degree intolerance (10; 23.3 percent). The greater percentage of cytogenetic response (22; 91.7 percent) and complete (11; 61.1 percent) was achieved at 18 and 24 course months. The 74,3 percent hadn't ,molecular response and the 5,1 percent yet had it before treatment; 9 (26.5 percent) showed a loss of complete hematologic remission, from them, 7 deceased from disease progression. Global survival was of 90.7 percent, 83,3 percent

Ischemic preconditioning and spinal cord function monitoring in the descending thoracic aorta approach.

OBJECTIVES: To evaluate the effectiveness of acute ischemic preconditioning (IP), based on somatosensory evoked potentials (SSEP) monitoring, as a method of spinal cord protection and to asses SSEP importance in spinal cord neuromonitoring. METHODS: Twenty-eight dogs were submitted to spinal cord ischemic injury attained by descending thoracic aorta cross-clamping. In the C45 group, the aortic cross-clamping time was 45 min (n=7); in the IP45 group, the dogs were submitted to IP before the aortic cross-clamping for 45 min (n=7). In the C60 group, the dogs were submitted to 60 min of aortic cross-clamping (n=7), as in the IP60 group that was previously submitted to IP. The IP cycles were determined based on SSEP changes. RESULTS: Tarlov scores of the IP groups were significantly better than those of the controls (p = 0.005). Paraplegia was observed in 3 dogs from C45 and in 6 from C60 group, although all dogs from IP45 group were neurologically normal, as 4 dogs from IP60. There was a significant correlation between SSEP recovery time until one hour of aortic reperfusion and the neurological status (p = 0.011), showing sensitivity of 75% and specificity of 83%. CONCLUSION: Repetitive acute IP based on SSEP is a protection factor during spinal cord ischemia, decreasing paraplegia incidence. SSEP monitoring seems to be a good neurological injury assessment method during surgical procedures that involve spinal cord ischemia.