Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults.

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately.

Explainable hypoglycemia prediction models through dynamic structured grammatical evolution.

Effective blood glucose management is crucial for people with diabetes to avoid acute complications. Predicting extreme values accurately and in a timely manner is of vital importance to them. People with diabetes are particularly concerned about suffering a hypoglycemia (low value) event and, moreover, that the event will be prolonged in time. It is crucial to predict hyperglycemia (high value) and hypoglycemia events that may cause health damages in the short term and potential permanent damages in the long term. This paper describes our research on predicting hypoglycemia events at 30, 60, 90, and 120 minutes using machine learning methods. We propose using structured Grammatical Evolution and dynamic structured Grammatical Evolution to produce interpretable mathematical expressions that predict a hypoglycemia event. Our proposal generates white-box models induced by a grammar based on if-then-else conditions using blood glucose, heart rate, number of steps, and burned calories as the inputs for the machine learning technique. We apply these techniques to create three types of models: individualized, cluster, and population-based. They all are then compared with the predictions of eleven machine learning techniques. We apply these techniques to a dataset of 24 real patients of the Hospital Universitario Principe de Asturias, Madrid, Spain. The resulting models, presented as if-then-else statements that incorporate numeric, relational, and logical operations between variables and constants, are inherently interpretable. The True Positive Rate and True Negative Rate metrics are above 0.90 for 30-minute predictions, 0.80 for 60 min, and 0.70 for 90 min and 120 min for the three types of models. Individualized models exhibit the best metrics, while cluster and population-based models perform similarly. Structured and dynamic structured grammatical evolution techniques perform similarly for all forecasting horizons. Regarding the comparison of different machine learning techniques, on the shorter forecasting horizons, our proposals have a high probability of winning, a probability that diminishes on the longer time horizons. Structured grammatical evolution provides advanced forecasting models that facilitate model explanation, modification, and retesting, offering flexibility for refining solutions post-creation and a deeper understanding of blood glucose behavior. These models have been integrated into the glUCModel application, designed to serve people with diabetes.

Ten steps to transform ideas into product innovations: An interdisciplinary collaboration between nursing and engineering.

AIMS: To describe the development process of a device from the conception of the idea to the first contact with the commercial environment, and to demonstrate its practical application through an interdisciplinary collaboration between nursing and engineering for the design of a protective device for peripheral venous catheters. BACKGROUND: Nurses are key agents for identifying unresolved needs or problems related to nursing care. To address these needs, creative ideation processes are often triggered among nurses to seek technological answers to these challenges. RESULTS: The ten steps to develop a device are presented: (1) detecting an unsatisfied clinical need; (2) searching for preexisting marketed products; (3) searching for patents; (4) maintaining confidentiality throughout the process; (5) obtaining institutional support; (6) forming a multidisciplinary team; (7) developing the idea; (8) applying for a patent; (9) building the prototype; (10) marketing the device. This methodology was applied to design a protective device for peripheral venous catheters in hospitalized patients. CONCLUSIONS: Nurses can play a key role in the promotion of healthcare innovation in their field to improve procedures, thanks to their direct contact with patients, and by providing their insight on devices that can enhance patient care. The successful interdisciplinary collaboration between nurses and engineers can provide a response to relevant clinical problems such as the manipulation or removal of peripheral venous catheters. IMPLICATIONS FOR NURSING AND/OR HEALTH POLICY: A hospital policy is required to encourage the participation of nurses in innovative actions. Furthermore, it is important to support nurse leaders who can play a pivotal role in incorporating creativity into work environments and empowering other nurses to innovatively address clinical issues. NO PATIENT OR PUBLIC CONTRIBUTION: This article describes the process for developing a health device.

Evaluating the influence of sleep quality and quantity on glycemic control in adults with type 1 diabetes.

Background: Sleep quality disturbances are frequent in adults with type 1 diabetes. However, the possible influence of sleep problems on glycemic variability has yet to be studied in depth. This study aims to assess the influence of sleep quality on glycemic control. Materials and methods: An observational study of 25 adults with type 1 diabetes, with simultaneous recording, for 14 days, of continuous glucose monitoring (Abbott FreeStyle Libre system) and a sleep study by wrist actigraphy (Fitbit Ionic device). The study analyzes, using artificial intelligence techniques, the relationship between the quality and structure of sleep with time in normo-, hypo-, and hyperglycemia ranges and with glycemic variability. The patients were also studied as a group, comparing patients with good and poor sleep quality. Results: A total of 243 days/nights were analyzed, of which 77% (n = 189) were categorized as poor quality and 33% (n = 54) as good quality. Linear regression methods were used to find a correlation (r =0.8) between the variability of sleep efficiency and the variability of mean blood glucose. With clustering techniques, patients were grouped according to their sleep structure (characterizing this structure by the number of transitions between the different sleep phases). These clusters showed a relationship between time in range and sleep structure. Conclusions: This study suggests that poor sleep quality is associated with lower time in range and greater glycemic variability, so improving sleep quality in patients with type 1 diabetes could improve their glycemic control.

Design Engineering in Surgery. How to Design, Test and Market Surgical Devices Made With 3D Printing? / Ingeniería de diseño en Cirugía. ¿Cómo diseñar, probar y comercializar dispositivos quirúrgicos fabricados con impresión 3D?

Industry 4.0 offers new development opportunities for surgeons. Computer-aided design and 3D printing allow for the creation of prototypes and functional end products. Until now, it was difficult for new devices to get to the manufacturing phase. Nowadays, the main limitations are our creativity, available spaces to test our creations and obtaining financing.

Pediatrics Spanish Registry of Percutaneous Melody Pulmonary Valve Implantation in Patients Younger Than 18 Years.

INTRODUCTION AND OBJECTIVES: A decade has passed since the first Spanish percutaneous pulmonary Melody valve implant (PPVI) in March 2007. Our objective was to analyze its results in terms of valvular function and possible mid-term follow-up complications. METHODS: Spanish retrospective descriptive multicenter analysis of Melody PPVI in patients < 18 years from the first implant in March 2007 until January 1, 2016. RESULTS: Nine centers were recruited with a total of 81 PPVI in 77 pediatric patients, whose median age and weight were 13.3 years (interquartile range [IQR], 9.9-15.4) and 46kg (IQR, 27-63). The predominant cardiac malformation was tetralogy of Fallot (n = 27). Most of the valves were implanted on conduits, especially bovine xenografts (n = 31). The incidence of intraprocedure and acute complications was 6% and 8%, respectively (there were no periprocedural deaths). The median follow-up time was 2.4 years (IQR, 1.1-4.9). Infective endocarditis (IE) was diagnosed in 4 patients (5.6%), of which 3 required surgical valve explant. During follow-up, the EI-related mortality rate was 1.3%. At 5 years of follow-up, 80% ± 6.9% and 83% ± 6.1% of the patients were free from reintervention and pulmonary valve replacement. CONCLUSIONS: Melody PPVI was safe and effective in pediatric patients with good short- and mid-term follow-up hemodynamic results. The incidence of IE during follow-up was relatively low but was still the main complication.

Estimación del coste sanitario de las úlceras por presión en pacientes lesionados medulares / Estimation of the Sanitary Cost of Bedsores (Pressure Sores) in Patients with Medullary Lesions / Estimação do custo sanitário das úlceras de pressão em pacientes com lesão medular

Objetivo: conocer el coste total de cada tipo de úlcera por presión, ya que es un tipo de herida crónica que se produce habitualmente en pacientes con poca movilidad. Método: se ha realizado una revisión retrospectiva de las historias clínicas del periodo 2008-2011 correspondiente al registro de actividad de cirugía plástica del Hospital de Parapléjicos. Resultados: la úlcera por presión isquiática es la más frecuentemente tratada (43,27%) así como también la de menor coste total (¬ 57 196,29). El coste más alto de una úlcera por presión por su localización corresponde a la sacra (40,41%, siendo la segunda en frecuencia, y el coste total es de ¬ 112 012,96). Conclusiones: ante estos costes de tratamiento, se imponen campañas de prevención para intentar evitar este alto coste al Sistema Nacional de Salud.

Objective: getting to know the total cost of each type of bedsore (pressure sores), as it is a chronical injury commonly seen in patients with low mobility. Method: We realized a retrospective review of clinical records for the 2008 to 2011 period, corresponding to the plastic surgery activity records of the Paraplegic Hospital. Results: the ischial pressure sore is the most commonly treated (43.27%), and also shows the lowest total cost (¬ 57,196.29). The highest cost of a bedsore due to its location corresponds to sacral pressure sores (40.41%, being the second most frequent type, with a total cost of ¬ 112,012.96). Conclusions: Faced with these treatment costs, prevention campaigns are established in an attempt to prevent these high costs to the National Health System.

Objetivo: conhecer o custo total de cada tipo de úlcera de pressão, ainda que são tipos de ferida crónica que ocorre habitualmente em pacientes com baixa mobilidade. Método: foi realizada uma revisão retrospectiva dos prontuários médicos no período 2008-2011 correspondente ao registro de atividades de cirurgia plástica do Hospital de Paraplégicos. Resultados: as úlceras por pressão isquiáticas são as mais frequentemente tratadas (43,27%) bem como as de menor custo total (¬ 57 196,29). O custo mais alto de uma úlcera de pressão pela sua região corresponde à sacral (40,41 %, sendo a segunda em frequência, e o custo total é de ¬ 112 012,96). Conclusões: perante estes custos de tratamento, impõem-se campanhas de prevenção para tentar evitar este alto custo ao Sistema Nacional de Saúde.

Surgical Treatment of Pressure Ulcers with a Fibrin Sealant in Patients with Spinal Cord Injury: A Cost-Consequence Analysis.

BACKGROUND: A comparative study was performed to evaluate the effectiveness and costs of a fibrin sealant (Tissucol Duo [known as Tisseel in the United States], Baxter International, Deerfield, Illinois) to improve postoperative outcomes in patients with spinal cord injury undergoing surgical treatment for pressure ulcers (PrUs). METHODS: Between January and June 2011, 27 patients underwent surgical treatment for PrUs with the direct application of Tissucol Duo sprayed before closure. The costs and outcomes obtained in this cohort were compared with those obtained in a previous retrospective study where 71 patients underwent conventional surgery. RESULTS: Lower rates of hematoma-seroma were observed in the study group (3.7% vs 33.8%; P < .05). Drain removal occurred earlier (10 vs 15 days; P < .05), and the average drain volume was also lower (155 vs 360 mL; P < .05) for this group. The mean length of hospital stay was significantly lower in the study group and was the main contributing factor to the overall costs. CONCLUSIONS: The application of Tissucol Duo during surgical treatment of PrUs in patients with spinal cord injury has been shown to be effective in reducing postoperative complications and in shortening the duration of the hospital stay with a consequent savings in costs.