Can artificial intelligence simplify the screening of muscle mass loss?

Background: Sarcopenia is a risk factor for morbidity and preventable mortality in old age, with consequent high costs for the national health system. Its diagnosis requires costly radiological examinations, such as the DEXA, which complicate screening in medical centers with a high prevalence of sarcopenia. Objectives: Developing a nearly zero-cost screening tool to emulate the performance of DEXA in identifying patients with muscle mass loss. This can crucially help the early diagnosis of sarcopenia at large-scale, contributing to reduce its prevalence and related complications with timely treatments. Methods: We exploit cross-sectional data for about 14,500 patients and 38 non-laboratory variables from successive NHANES over 7 years (1999-2006). Data are analyzed through a state-of-the-art artificial intelligence approach based on decision trees. Results: A reduced number of anthropometric parameters allows to predict the outcome of DEXA with AUC between 0.92 and 0.94. The most complex model derived in this paper exploits 6 variables, related to the circumference of key corporal segments and to the evaluation of body fat. It achieves an optimal trade-off sensitivity of 0.89 and a specificity of 0.82. Restricting exclusively to variables related to lower limb, we obtain an even simpler tool with only slightly lower accuracy (AUC 0.88-0.90). Conclusions: Anthropometric data seem to contain the entire informative content of a more complex set of non-laboratory variables, including anamnestic and/or morbidity factors. Compared to previously published screening tools for muscle mass loss, the newly developed models are less complex and achieve a better accuracy. The new results might suggest a possible inversion of the standard diagnostic algorithm of sarcopenia. We conjecture a new diagnostic scheme, which requires a dedicated clinical validation that goes beyond the scope of the present study.

Artificial intelligence in health data analysis: The Darwinian evolution theory suggests an extremely simple and zero-cost large-scale screening tool for prediabetes and type 2 diabetes.

AIMS: The effective identification of individuals with early dysglycemia status is key to reduce the incidence of type 2 diabetes. We develop and validate a novel zero-cost tool that significantly simplifies the screening of undiagnosed dysglycemia. METHODS: We use NHANES cross-sectional data over 10 years (2007-2016) to derive an equation that links non-laboratory exposure variables to the possible presence of undetected dysglycemia. For the first time, we adopt a novel artificial intelligence approach based on the Darwinian evolutionary theory to analyze health data. We collected data for 47 variables. RESULTS: Age and waist circumference are the only variables required to use the model. To identify undetected dysglycemia, we obtain an area under the curve (AUC) of 75.3%. Sensitivity and specificity are 0.65 and 0.73 by using the optimal threshold value determined from external validation data. CONCLUSIONS: The use of uniquely two variables allows to obtain a zero-cost screening tool of analogous precision than that of more complex tools widely adopted in the literature. The newly developed tool has clinical use as it significantly simplifies the screening of dysglycemia. Furthermore, we suggest that the definition of an age-related waist circumference cut-off might help to improve existing diabetes risk factors.

Clustering in light nuclei and their effects on fusion and pre-equilibrium processes / Agrupamiento de núcleos ligeros y sus efectos en la fusión y procesos de pre-equilibrio

Summary The study of heavy ion nuclear reactionis an important tool to observe and disentangle different and competing mechanisms, which may arise in the different energy regimes. In particular, at relatively low bombarding energy, it is quite interesting the comparison between pre-equilibrium and thermal emission of light charged particles from hot nuclear systems [1-6]. Indeed, the nuclear structure of the interacting partners can be strongly correlated to the dynamics, especially at energies close to the Coulomb barrier, and this effect emerges when some nucleons or clusters of nucleons are either emitted or captured. In particular, a major attention has been devoted, in the last years, to the possible observation of cluster structure effects in the competing nuclear reaction mechanisms, especially when fast processes are involved. At this purpose, the four reactions 16O+30Si at 111 MeV, 16O+30Si at 128 MeV, 18O+28Si at 126 MeV, 19F+27Al at 133 MeV have been measured to study the onset of pre-equilibrium in an energy range where, for central collisions, complete fusion is expected to be the predominant mode. Experimental data were collected using the GARFIELD + RCo array [7], fully equipped with digital electronics at the LegnaroNational Laboratories. The comparison between experimental data and different model predictions have been performed: in particular, both dynamical models based either on Stochastic Mean Field (TWINGO) or Anti-symmetrized Molecular Dynamics and fully statistical models (GEMINI++) have been considered. Simulated events are filtered through a software replica of the apparatus, to take into account all possible distortions of the experimental distributions due to the finite size of the apparatus.

Resumen El estudio de la reacción nuclear iónica pesada es una herramienta importante para observar y esclarecer los diferentes mecanismos que compiten entre sí, que pueden surgir en los diferentes regímenes energéticos. En particular, a una energía de bombardeo relativamente baja, es bastante interesante la comparación entre el preequilibrio y la emisión térmica de partículas ligeras cargadas por sistemas nucleares calientes [1-6]. De hecho, la estructura nuclear del grupo que interactúa puede estar fuertemente correlacionada con la dinámica, especialmente en energías cercanas a la barrera de Coulomb, y este efecto surge cuando se emiten o capturan algunos nucleones o grupos de nucleones. En particular, se ha dedicado una gran atención, en los últimos años, a la posible observación de los efectos de la estructura del agrupamiento en los mecanismos de reacción nuclear competitivos, especialmente cuando se trata de procesos rápidos. Para este propósito, las cuatro reacciones 16O + 30Si a 111 MeV, 16O + 30Si a 128 MeV, 18O + 28Si a 126 MeV, 19F + 27Al a 133 MeV se han medido para estudiar el inicio del preequilibrio en un rango de energía en el cual, para colisiones centrales, se espera que la fusión completa sea el modo predominante. Los datos experimentales se recogieron utilizando la matriz GARFIELD + RCo [7], totalmente equipada con electrónica digital en los Laboratorios Nacionales Legnaro. La comparación entre los datos experimentales y las diferentes predicciones de modelos se han llevado a cabo: en particular, se han considerado los modelos dinámicos basados en el Campo Medio Estocástico (TWINGO) o Dinámica Molecular Antisimétrica y modelos completamente estadísticos (GEMINI ++). Los eventos simulados se filtran a través de una réplica de software del aparato, para tener en cuenta todas las posibles distorsiones de las distribuciones experimentales debido al tamaño finito del aparato.