Digital twins and artificial intelligence in metabolic disease research.

Digital twin technology is emerging as a transformative paradigm for personalized medicine in the management of chronic conditions. In this article, we explore the concept and key characteristics of a digital twin and its applications in chronic non-communicable metabolic disease management, with a focus on diabetes case studies. We cover various types of digital twin models, including mechanistic models based on ODEs, data-driven ML algorithms, and hybrid modeling strategies that combine the strengths of both approaches. We present successful case studies demonstrating the potential of digital twins in improving glucose outcomes for individuals with T1D and T2D, and discuss the benefits and challenges of translating digital twin research applications to clinical practice.

Variability in Definitions and Criteria of Extrauterine Growth Restriction and Its Association with Neurodevelopmental Outcomes in Preterm Infants: A Narrative Review.

Extrauterine growth restriction (EUGR) has been used in the literature and clinical practice to describe inadequate growth in preterm infants. Significant variability is seen in the criteria for EUGR, with no standard definition reached to date. Moreover, no consensus on the optimal timing for assessment or the ideal growth monitoring tool has been achieved, and an ongoing debate persists on the appropriate terminology to express poor postnatal growth. To ensure an adequate understanding of growth and early intervention in preterm infants at higher risk, it is critical to relate the diagnostic criteria of EUGR to the ability to predict adverse outcomes, such as neurodevelopmental outcomes. This narrative review was conducted to present evidence that evaluates neurodevelopmental outcomes in preterm infants with EUGR, comparing separately the different definitions of this concept by weight (cross-sectional, longitudinal and "true" EUGR). In this article, we highlight the challenges of comparing various published studies on the subject, even when subclassifying by the definition of EUGR, due to the significant variability on the criteria used for each definition and for the evaluation of neurodevelopmental outcomes in different papers. This heterogeneity compromises the obtention of a single firm conclusion on the relation between different definitions of EUGR and adverse neurodevelopmental outcomes.

Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportunities.

OBJECTIVE: Artificial intelligence and machine learning are transforming many fields including medicine. In diabetes, robust biosensing technologies and automated insulin delivery therapies have created a substantial opportunity to improve health. While the number of manuscripts addressing the topic of applying machine learning to diabetes has grown in recent years, there has been a lack of consistency in the methods, metrics, and data used to train and evaluate these algorithms. This manuscript provides consensus guidelines for machine learning practitioners in the field of diabetes, including best practice recommended approaches and warnings about pitfalls to avoid. METHODS: Algorithmic approaches are reviewed and benefits of different algorithms are discussed including importance of clinical accuracy, explainability, interpretability, and personalization. We review the most common features used in machine learning applications in diabetes glucose control and provide an open-source library of functions for calculating features, as well as a framework for specifying data sets using data sheets. A review of current data sets available for training algorithms is provided as well as an online repository of data sources. SIGNIFICANCE: These consensus guidelines are designed to improve performance and translatability of new machine learning algorithms developed in the field of diabetes for engineers and data scientists.

Combining uncertainty-aware predictive modeling and a bedtime Smart Snack intervention to prevent nocturnal hypoglycemia in people with type 1 diabetes on multiple daily injections.

OBJECTIVE: Nocturnal hypoglycemia is a known challenge for people with type 1 diabetes, especially for physically active individuals or those on multiple daily injections. We developed an evidential neural network (ENN) to predict at bedtime the probability and timing of nocturnal hypoglycemia (0-4 vs 4-8 h after bedtime) based on several glucose metrics and physical activity patterns. We utilized these predictions in silico to prescribe bedtime carbohydrates with a Smart Snack intervention specific to the predicted minimum nocturnal glucose and timing of nocturnal hypoglycemia. MATERIALS AND METHODS: We leveraged free-living datasets collected from 366 individuals from the T1DEXI Study and Glooko. Inputs to the ENN used to model nocturnal hypoglycemia were derived from demographic information, continuous glucose monitoring, and physical activity data. We assessed the accuracy of the ENN using area under the receiver operating curve, and the clinical impact of the Smart Snack intervention through simulations. RESULTS: The ENN achieved an area under the receiver operating curve of 0.80 and 0.71 to predict nocturnal hypoglycemic events during 0-4 and 4-8 h after bedtime, respectively, outperforming all evaluated baseline methods. Use of the Smart Snack intervention reduced probability of nocturnal hypoglycemia from 23.9 ± 14.1% to 14.0 ± 13.3% and duration from 7.4 ± 7.0% to 2.4 ± 3.3% in silico. DISCUSSION: Our findings indicate that the ENN-based Smart Snack intervention has the potential to significantly reduce the frequency and duration of nocturnal hypoglycemic events. CONCLUSION: A decision support system that combines prediction of minimum nocturnal glucose and proactive recommendations for bedtime carbohydrate intake might effectively prevent nocturnal hypoglycemia and reduce the burden of glycemic self-management.

Risky movement: Assessing fall risk in people with multiple sclerosis with wearable sensors and beacon-based smart-home monitoring.

BACKGROUND: People with multiple sclerosis (PwMS) fall frequently causing injury, social isolation, and decreased quality of life. Identifying locations and behaviors associated with high fall risk could help direct fall prevention interventions. Here we describe a smart-home system for assessing how mobility metrics relate to real-world fall risk in PwMS. METHODS: We performed a secondary analysis of a dataset of real-world falls collected from PwMS to identify patterns associated with increased fall risk. Thirty-four individuals were tracked over eight weeks with an inertial sensor comprising a triaxial accelerometer and time-of-flight radio transmitter, which communicated with beacons positioned throughout the home. We evaluated associations between locations in the home and movement behaviors prior to a fall compared with time periods when no falls occurred using metrics including gait initiation, time-spent-moving, movement length, and an entropy-based metric that quantifies movement complexity using transitions between rooms in the home. We also explored how fall risk may be related to the percent of times that a participant paused while walking (pauses-while-walking). RESULTS: Seventeen of the participants monitored sustained a total of 105 falls that were recorded. More falls occurred while walking (52%) than when stationary despite participants being largely sedentary, only walking 1.5±3.3% (median ± IQR) of the time that they were in their home. A total of 28% of falls occurred within one second of gait initiation. As the percentage of pauses-while-walking increased from 20 to 60%, the likelihood of a fall increased by nearly 3 times from 0.06 to 0.16%. Movement complexity, which was quantified using the entropy of room transitions, was significantly higher in the 10 min preceding falls compared with other 10-min time segments not preceding falls (1.15 ± 0.47 vs. 0.96 ± 0.24, P = 0.02). Path length was significantly longer (151.3 ± 156.1 m vs. 95.0 ± 157.2 m, P = 0.003) in the ten minutes preceding a fall compared with non-fall periods. Fall risk also varied among rooms but not consistently across participants. CONCLUSIONS: Movement metrics derived from wearable sensors and smart-home tracking systems are associated with fall risk in PwMS. More pauses-while-walking, and more complex, longer movement trajectories are associated with increased fall risk. FUNDING: Department of Veterans Affairs (RX001831-01A1). National Science Foundation (#2030859).

Integrating metabolic expenditure information from wearable fitness sensors into an AI-augmented automated insulin delivery system: a randomised clinical trial.

BACKGROUND: Exercise can rapidly drop glucose in people with type 1 diabetes. Ubiquitous wearable fitness sensors are not integrated into automated insulin delivery (AID) systems. We hypothesised that an AID can automate insulin adjustments using real-time wearable fitness data to reduce hypoglycaemia during exercise and free-living conditions compared with an AID not automating use of fitness data. METHODS: Our study population comprised of individuals (aged 21-50 years) with type 1 diabetes from from the Harold Schnitzer Diabetes Health Center clinic at Oregon Health and Science University, OR, USA, who were enrolled into a 76 h single-centre, two-arm randomised (4-block randomisation), non-blinded crossover study to use (1) an AID that detects exercise, prompts the user, and shuts off insulin during exercise using an exercise-aware adaptive proportional derivative (exAPD) algorithm or (2) an AID that automates insulin adjustments using fitness data in real-time through an exercise-aware model predictive control (exMPC) algorithm. Both algorithms ran on iPancreas comprising commercial glucose sensors, insulin pumps, and smartwatches. Participants executed 1 week run-in on usual therapy followed by exAPD or exMPC for one 12 h primary in-clinic session involving meals, exercise, and activities of daily living, and 2 free-living out-patient days. Primary outcome was time below range (<3·9 mmol/L) during the primary in-clinic session. Secondary outcome measures included mean glucose and time in range (3·9-10 mmol/L). This trial is registered with ClinicalTrials.gov, NCT04771403. FINDINGS: Between April 13, 2021, and Oct 3, 2022, 27 participants (18 females) were enrolled into the study. There was no significant difference between exMPC (n=24) versus exAPD (n=22) in time below range (mean [SD] 1·3% [2·9] vs 2·5% [7·0]) or time in range (63·2% [23·9] vs 59·4% [23·1]) during the primary in-clinic session. In the 2 h period after start of in-clinic exercise, exMPC had significantly lower mean glucose (7·3 [1·6] vs 8·0 [1·7] mmol/L, p=0·023) and comparable time below range (1·4% [4·2] vs 4·9% [14·4]). Across the 76 h study, both algorithms achieved clinical time in range targets (71·2% [16] and 75·5% [11]) and time below range (1·0% [1·2] and 1·3% [2·2]), significantly lower than run-in period (2·4% [2·4], p=0·0004 vs exMPC; p=0·012 vs exAPD). No adverse events occurred. INTERPRETATION: AIDs can integrate exercise data from smartwatches to inform insulin dosing and limit hypoglycaemia while improving glucose outcomes. Future AID systems that integrate exercise metrics from wearable fitness sensors may help people living with type 1 diabetes exercise safely by limiting hypoglycaemia. FUNDING: JDRF Foundation and the Leona M and Harry B Helmsley Charitable Trust, National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases.

Predicting labor onset relative to the estimated date of delivery using smart ring physiological data.

The transition from pregnancy into parturition is physiologically directed by maternal, fetal and placental tissues. We hypothesize that these processes may be reflected in maternal physiological metrics. We enrolled pregnant participants in the third-trimester (n = 118) to study continuously worn smart ring devices monitoring heart rate, heart rate variability, skin temperature, sleep and physical activity from negative temperature coefficient, 3-D accelerometer and infrared photoplethysmography sensors. Weekly surveys assessed labor symptoms, pain, fatigue and mood. We estimated the association between each metric, gestational age, and the likelihood of a participant's labor beginning prior to (versus after) the clinical estimated delivery date (EDD) of 40.0 weeks with mixed effects regression. A boosted random forest was trained on the physiological metrics to predict pregnancies that naturally passed the EDD versus undergoing onset of labor prior to the EDD. Here we report that many raw sleep, activity, pain, fatigue and labor symptom metrics are correlated with gestational age. As gestational age advances, pregnant individuals have lower resting heart rate 0.357 beats/minute/week, 0.84 higher heart rate variability (milliseconds) and shorter durations of physical activity and sleep. Further, random forest predictions determine pregnancies that would pass the EDD with accuracy of 0.71 (area under the receiver operating curve). Self-reported symptoms of labor correlate with increased gestational age and not with the timing of labor (relative to EDD) or onset of spontaneous labor. The use of maternal smart ring-derived physiological data in the third-trimester may improve prediction of the natural duration of pregnancy relative to the EDD.

Dexmedetomidine: An Alternative to Pain Treatment in Neonatology.

Infants might be exposed to pain during their admissions in the neonatal intensive care unit [NICU], both from their underlying conditions and several invasive procedures required during their stay. Considering the particularities of this population, recognition and adequate management of pain continues to be a challenge for neonatologists and investigators. Diverse therapies are available for treatment, including non-pharmacological pain management measures and pharmacological agents (sucrose, opioids, midazolam, acetaminophen, topical agents…) and research continues. In recent years one of the most promising drugs for analgesia has been dexmedetomidine, an alpha-2 adrenergic receptor agonist. It has shown a promising efficacy and safety profile as it produces anxiolysis, sedation and analgesia without respiratory depression. Moreover, studies have shown a neuroprotective role in animal models which could be beneficial to neonatal population, especially in preterm newborns. Side effects of this therapy are mainly cardiovascular, but in most studies published, those were not severe and did not require specific therapeutic measures for their resolution. The main objective of this article is to summarize the existing literature on neonatal pain management strategies available and review the efficacy of dexmedetomidine as a new therapy with increasing use in the NICU.

Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence.

We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9 minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose >180 mg/dL) by 10.8% (P = 0.04) and trends toward increasing time in range (70-180 mg/dL) by 9.1% compared with MPC. Time below range (glucose <70 mg/dL) is not significantly different between RAP and MPC.

Modeling risk of hypoglycemia during and following physical activity in people with type 1 diabetes using explainable mixed-effects machine learning.

BACKGROUND: Physical activity (PA) can cause increased hypoglycemia (glucose <70 mg/dL) risk in people with type 1 diabetes (T1D). We modeled the probability of hypoglycemia during and up to 24 h following PA and identified key factors associated with hypoglycemia risk. METHODS: We leveraged a free-living dataset from Tidepool comprised of glucose measurements, insulin doses, and PA data from 50 individuals with T1D (6448 sessions) for training and validating machine learning models. We also used data from the T1Dexi pilot study that contains glucose management and PA data from 20 individuals with T1D (139 session) for assessing the accuracy of the best performing model on an independent test dataset. We used mixed-effects logistic regression (MELR) and mixed-effects random forest (MERF) to model hypoglycemia risk around PA. We identified risk factors associated with hypoglycemia using odds ratio and partial dependence analysis for the MELR and MERF models, respectively. Prediction accuracy was measured using the area under the receiver operating characteristic curve (AUROC). RESULTS: The analysis identified risk factors significantly associated with hypoglycemia during and following PA in both MELR and MERF models including glucose and body exposure to insulin at the start of PA, low blood glucose index 24 h prior to PA, and PA intensity and timing. Both models showed overall hypoglycemia risk peaking 1 h after PA and again 5-10 h after PA, which is consistent with the hypoglycemia risk pattern observed in the training dataset. Time following PA impacted hypoglycemia risk differently across different PA types. Accuracy of hypoglycemia prediction using the fixed effects of the MERF model was highest when predicting hypoglycemia during the first hour following the start of PA (AUROCVALIDATION = 0.83 and AUROCTESTING = 0.86) and decreased when predicting hypoglycemia in the 24 h after PA (AUROCVALIDATION = 0.66 and AUROCTESTING = 0.68). CONCLUSION: Hypoglycemia risk after the start of PA can be modeled using mixed-effects machine learning to identify key risk factors that may be used within decision support and insulin delivery systems. We published the population-level MERF model online for others to use.

Intrinsic values of procalcitonin in bacterial bloodstream infections in people aged 75 years and over: a retrospective study.

OBJECTIVE: To evaluate PCT measurement in the diagnosis of bloodstream infection (BSI) in hospitalized patients aged 75+. METHOD: Descriptive, retrospective, monocentric study conducted in France, in patients with at least one blood culture and PCT and CRP measurements within the 24 hours before or after blood culture. RESULTS: The mean PCT and CRP values for the 118 (15.2%) positive blood cultures were 18.90 ng/ml [95%CI: 0.007-334.7] and 153.93 mg/l [1-557], respectively. With a threshold of 0.3 ng/ml, PCT measurement had a sensitivity of 84%, a specificity of 53%, a PPV of 24%, and an NPV of 95%, making it possible to rule out BSI in 350 (45.1%) patients (α-risk=5%). CONCLUSION: PCT measurement may eliminate BSI diagnosis more quickly than does blood culture reducing the inadequate and detrimental use of antibiotic therapy. A prospective study is required to validate its usefulness and confirm the cut-off value in geriatric populations.

Vickybot, a Chatbot for Anxiety-Depressive Symptoms and Work-Related Burnout in Primary Care and Health Care Professionals: Development, Feasibility, and Potential Effectiveness Studies.

BACKGROUND: Many people attending primary care (PC) have anxiety-depressive symptoms and work-related burnout compounded by a lack of resources to meet their needs. The COVID-19 pandemic has exacerbated this problem, and digital tools have been proposed as a solution. OBJECTIVE: We aimed to present the development, feasibility, and potential effectiveness of Vickybot, a chatbot aimed at screening, monitoring, and reducing anxiety-depressive symptoms and work-related burnout, and detecting suicide risk in patients from PC and health care workers. METHODS: Healthy controls (HCs) tested Vickybot for reliability. For the simulation study, HCs used Vickybot for 2 weeks to simulate different clinical situations. For feasibility and effectiveness study, people consulting PC or health care workers with mental health problems used Vickybot for 1 month. Self-assessments for anxiety (Generalized Anxiety Disorder 7-item) and depression (Patient Health Questionnaire-9) symptoms and work-related burnout (based on the Maslach Burnout Inventory) were administered at baseline and every 2 weeks. Feasibility was determined from both subjective and objective user-engagement indicators (UEIs). Potential effectiveness was measured using paired 2-tailed t tests or Wilcoxon signed-rank test for changes in self-assessment scores. RESULTS: Overall, 40 HCs tested Vickybot simultaneously, and the data were reliably transmitted and registered. For simulation, 17 HCs (n=13, 76% female; mean age 36.5, SD 9.7 years) received 98.8% of the expected modules. Suicidal alerts were received correctly. For the feasibility and potential effectiveness study, 34 patients (15 from PC and 19 health care workers; 76% [26/34] female; mean age 35.3, SD 10.1 years) completed the first self-assessments, with 100% (34/34) presenting anxiety symptoms, 94% (32/34) depressive symptoms, and 65% (22/34) work-related burnout. In addition, 27% (9/34) of patients completed the second self-assessment after 2 weeks of use. No significant differences were found between the first and second self-assessments for anxiety (t8=1.000; P=.34) or depressive (t8=0.40; P=.70) symptoms. However, work-related burnout scores were moderately reduced (z=-2.07, P=.04, r=0.32). There was a nonsignificant trend toward a greater reduction in anxiety-depressive symptoms and work-related burnout with greater use of the chatbot. Furthermore, 9% (3/34) of patients activated the suicide alert, and the research team promptly intervened with successful outcomes. Vickybot showed high subjective UEI (acceptability, usability, and satisfaction), but low objective UEI (completion, adherence, compliance, and engagement). Vickybot was moderately feasible. CONCLUSIONS: The chatbot was useful in screening for the presence and severity of anxiety and depressive symptoms, and for detecting suicidal risk. Potential effectiveness was shown to reduce work-related burnout but not anxiety or depressive symptoms. Subjective perceptions of use contrasted with low objective-use metrics. Our results are promising but suggest the need to adapt and enhance the smartphone-based solution to improve engagement. A consensus on how to report UEIs and validate digital solutions, particularly for chatbots, is required.

Empirical evidence of predictive adaptive response in humans: systematic review and meta-analysis of migrant populations.

Meta-analysis is used to test a variant of a Developmental Origins of Adult Health and Disease (DOHaD)'s conjecture known as predictive adaptive response (PAR). According to it, individuals who are exposed to mismatches between adverse or constrained in utero conditions, on the one hand, and postnatal obesogenic environments, on the other, are at higher risk of developing adult chronic conditions, including obesity, type 2 diabetes (T2D), hypertension and cardiovascular disease. We argue that migrant populations from low and middle to high-income countries offer a unique opportunity to test the conjecture. A database was constructed from an exhaustive literature search of peer-reviewed papers published prior to May 2021 contained in PUBMED and SCOPUS using keywords related to migrants, DOHaD, and associated health outcomes. Random effects meta-regression models were estimated to assess the magnitude of effects associated with migrant groups on the prevalence rate of T2D and hypertension in adults and overweight/obesity in adults and children. Overall, we used 38 distinct studies and 78 estimates of diabetes, 59 estimates of hypertension, 102 estimates of overweight/obesity in adults, and 23 estimates of overweight/obesity in children. Our results show that adult migrants experience higher prevalence of T2D than populations at destination (PR 1.48; 95% CI 1.35-1.65) and origin (PR 1.80; 95% CI 1.40-2.34). Similarly, there is a significant excess of obesity prevalence in children migrants (PR 1.22; 95% CI 1.04-1.43) but not among adult migrants (PR 0.89; 95% CI 0.80-1.01). Although the total effect of migrant status on prevalence of hypertension is centered on zero, some migrant groups show increased risks. Finally, the size of estimated effects varies significantly by migrant groups according to place of destination. Despite limitations inherent to all meta-analyses and admitting that some of our findings may be accounted for alternative explanations, the present study shows empirical evidence consistent with selected PAR-like conjectures.

Postnatal Growth Faltering: Growth and Height Improvement at Two Years in Children with Very Low Birth Weight between 2002-2017.

The prevalence of postnatal growth faltering (PGF) in preterm infants with very low birth weight (VLBW) (<1500 g) is a universal problem. Growth improvement is expected as neonatal care is optimized. Objectives: To determine if there has been a decrease in the prevalence of PGF and an improvement in height at 2 years in appropriate for gestational age VLBW children in the last two decades. Methods: Clinical descriptive retrospective analysis of neonatal somatometry at birth and at two-year corrected age in VLBW preterm infants. Small for gestational age were excluded. Two cohorts (2002−2006, n = 112; and 2013−2017, n = 92) were compared. Results. In the second five-year period, a decrease in prevalence of PGF was observed (36.6% vs. 22.8%, p = 0.033), an increase in growth rate in the first 28 days (5.22 (4.35−6.09) g/kg/day vs. 11.38 (10.61−12.15) g/kg/day, p < 0.0001) and an increase in height standard deviation (SD) at 2 years (−1.12 (−1.35−−0.91) vs. −0.74 (−0.99−−0.49) p = 0.023). Probability of short stature at 2 years was directly related to daily weight gain in the first 28 days. Conclusions: when comparing two five-year periods in the last two decades, growth in VLBW preterm infants has improved, both during neonatal period and at two years of age.

Assessment of a Decision Support System for Adults with Type 1 Diabetes on Multiple Daily Insulin Injections.

Introduction: DailyDose is a decision support system designed to provide real-time dosing advice and weekly insulin dose adjustments for adults living with type 1 diabetes using multiple daily insulin injections. Materials and Methods: Twenty-five adults were enrolled in this single-arm study. All participants used Dexcom G6 for continuous glucose monitoring, InPen for short-acting insulin doses, and Clipsulin to track long-acting insulin doses. Participants used DailyDose on an iPhone for 8 weeks. The primary endpoint was % time in range (TIR) comparing the 2-week baseline to the final 2-week period of DailyDose use. Results: There were no significant differences between TIR or other glycemic metrics between the baseline period compared to final 2-week period of DailyDose use. TIR significantly improved by 6.3% when more than half of recommendations were accepted and followed compared with 50% or fewer recommendations (95% CI 2.5%-10.1%, P = 0.001). Conclusions: Use of DailyDose did not improve glycemic outcomes compared to the baseline period. In a post hoc analysis, accepting and following recommendations from DailyDose was associated with improved TIR. Clinical Trial Registration Number: NCT04428645.

Multifocal Abdominal Pyomyositis From Subcutaneous Dissemination in an Immunocompetent Patient.

A 61-year-old woman presented to the emergency ward complaining of low back pain for a month. She had undergone several spinal surgeries and a right radical nephrectomy 30 years before. A few days earlier she was injected with an intramuscular painkiller in her right buttock. An abdominal CT scan revealed multiple abscesses in the psoas muscle and the right posterior abdominal wall, including cellulitis in the adjacent subcutaneous tissue and the injection site. A diagnosis of pyomyositis from subcutaneous dissemination was made, and intravenous cefazolin was initiated. After five days of favorable progress, treatment was switched to oral cefadroxil to complete four weeks, leading to full recovery.

Quantifying the impact of physical activity on future glucose trends using machine learning.

Prevention of hypoglycemia (glucose <70 mg/dL) during aerobic exercise is a major challenge in type 1 diabetes. Providing predictions of glycemic changes during and following exercise can help people with type 1 diabetes avoid hypoglycemia. A unique dataset representing 320 days and 50,000 + time points of glycemic measurements was collected in adults with type 1 diabetes who participated in a 4-arm crossover study evaluating insulin-pump therapies, whereby each participant performed eight identically designed in-clinic exercise studies. We demonstrate that even under highly controlled conditions, there is considerable intra-participant and inter-participant variability in glucose outcomes during and following exercise. Participants with higher aerobic fitness exhibited significantly lower minimum glucose and steeper glucose declines during exercise. Adaptive, personalized machine learning (ML) algorithms were designed to predict exercise-related glucose changes. These algorithms achieved high accuracy in predicting the minimum glucose and hypoglycemia during and following exercise sessions, for all fitness levels.

Tumor miofibroblástico de lengua / Myofibroblastic tongue tumour

El tumor miofibroblástico inflamatorio (TMI) es un tumor del estroma submucoso raro cuya presentación más frecuente es en el pulmón. Se trata de un tumor heterogéneo, formado por células fusiformes, inflamatorias y miofibroblastos, que por lo general es benigno, pero puede producir invasión local, recidiva y transformación maligna. Presentamos un paciente joven con una neoplasia en la lengua de aspecto invasivo e infiltrante que resultó ser un tumor miofibroblástico, pero que causó gran preocupación por su rápido crecimiento.(AU)

An inflammatory myofibroblastic tumour is a rare submucosal stromal tumour whose most common presentation is in the lung. This is a heterogeneous tumour, comprised of spindle cells, inflammatory cells and myofibroblasts, which is generally benign. However, it can cause local invasion, recurrence and malignant transformation. We report a young patient with an invasive and infiltrating tumour on the tongue that turned out to be a myofibroblastic tumour but caused major concern due to its rapid growth.(AU)

Incorporating Glucose Variability into Glucose Forecasting Accuracy Assessment Using the New Glucose Variability Impact Index and the Prediction Consistency Index: An LSTM Case Example.

BACKGROUND: In this work, we developed glucose forecasting algorithms trained and evaluated on a large dataset of free-living people with type 1 diabetes (T1D) using closed-loop (CL) and sensor-augmented pump (SAP) therapies; and we demonstrate how glucose variability impacts accuracy. We introduce the glucose variability impact index (GVII) and the glucose prediction consistency index (GPCI) to assess the accuracy of prediction algorithms. METHODS: A long-short-term-memory (LSTM) neural network was designed to predict glucose up to 60 minutes in the future using continuous glucose measurements and insulin data collected from 175 people with T1D (41,318 days) and evaluated on 75 people (11,333 days) from the Tidepool Big Data Donation Dataset. LSTM was compared with two naïve forecasting algorithms as well as Ridge linear regression and a random forest using root-mean-square error (RMSE). Parkes error grid quantified clinical accuracy. Regression analysis was used to derive the GVII and GPCI. RESULTS: The LSTM had highest accuracy and best GVII and GPCI. RMSE for CL was 19.8 ± 3.2 and 33.2 ± 5.4 mg/dL for 30- and 60-minute prediction horizons, respectively. RMSE for SAP was 19.6 ± 3.8 and 33.1 ± 7.3 mg/dL for 30- and 60-minute prediction horizons, respectively; 99.6% and 97.6% of predictions were within zones A+B of the Parkes error grid at 30- and 60-minute prediction horizons, respectively. Glucose variability was strongly correlated with RMSE (R≥0.64, P < 0.001); GVII and GPCI demonstrated a means to compare algorithms across datasets with different glucose variability. CONCLUSIONS: The LSTM model was accurate on a large real-world free-living dataset. Glucose variability should be considered when assessing prediction accuracy using indices such as GVII and GPCI.

Neuropsychological Development and New Criteria for Extrauterine Growth Restriction in Very Low-Birth-Weight Children.

BACKGROUND: Controversy between short-term neonatal growth of very low birth-weight preterm (VLBW) and neurodevelopment may be affected by criteria changes of extrauterine growth restriction (EUGR). OBJECTIVE: to determine if new EUGR criteria imply modifications in the relationship between old criteria and results of neuropsychological tests in preterm children. PATIENTS AND METHODS: 87 VLBW at 5-7 years of age were studied. Neuropsychological assessment included RIST test (Reynolds Intellectual Sctreening Test) and NEPSY-II (NE neuro, PSY psycolgy assessment) tests. The relationships between these tests and the different growth parameters were analyzed. RESULTS: RIST index was correlated with z-score Fenton's weight (p = 0.004) and length (p = 0.003) and with z-score IGW-21's (INTERGRWTH-21 Project) weight (p = 0.004) and length (p = 0.003) at neonatal discharge, but not with z-score difference between birth and neonatal discharge in weight, length, and HC for both. We did not find a statistically significant correlation between Fenton or IGW-21 z-scores and scalar data of NEPSY-II subtasks. CONCLUSION: In our series, neonatal growth influence on neuropsychological tests at the beginning of primary school does not seem robust, except for RIST test. New EUGR criteria do not improve the predictive ability of the old ones.