Artificial neural network models for predicting 1-year mortality in elderly patients with intertrochanteric fractures in China

The mortality rate of older patients with intertrochanteric fractures has been increasing with the aging of populations in China. The purpose of this study was: 1) to develop an artificial neural network (ANN) using clinical information to predict the 1-year mortality of elderly patients with intertrochanteric fractures, and 2) to compare the ANN's predictive ability with that of logistic regression models. The ANN model was tested against actual outcomes of an intertrochanteric femoral fracture database in China. The ANN model was generated with eight clinical inputs and a single output. ANN's performance was compared with a logistic regression model created with the same inputs in terms of accuracy, sensitivity, specificity, and discriminability. The study population was composed of 2150 patients (679 males and 1471 females): 1432 in the training group and 718 new patients in the testing group. The ANN model that had eight neurons in the hidden layer had the highest accuracies among the four ANN models: 92.46 and 85.79% in both training and testing datasets, respectively. The areas under the receiver operating characteristic curves of the automatically selected ANN model for both datasets were 0.901 (95%CI=0.814-0.988) and 0.869 (95%CI=0.748-0.990), higher than the 0.745 (95%CI=0.612-0.879) and 0.728 (95%CI=0.595-0.862) of the logistic regression model. The ANN model can be used for predicting 1-year mortality in elderly patients with intertrochanteric fractures. It outperformed a logistic regression on multiple performance measures when given the same variables.

The use of artificial intelligence algorithms to guide surgical treatment of adolescent idiopathic scoliosis

La scoliose idiopathique de l’adolescent (SIA) est une déformation tri-dimensionelle du rachis. Son traitement comprend l’observation, l’utilisation de corsets pour limiter sa progression ou la chirurgie pour corriger la déformation squelettique et cesser sa progression. Le traitement chirurgical reste controversé au niveau des indications, mais aussi de la chirurgie à entreprendre. Malgré la présence de classifications pour guider le traitement de la SIA, une variabilité dans la stratégie opératoire intra et inter-observateur a été décrite dans la littérature. Cette variabilité s’accentue d’autant plus avec l’évolution des techniques chirurgicales et de l’instrumentation disponible. L’avancement de la technologie et son intégration dans le milieu médical a mené à l’utilisation d’algorithmes d’intelligence artificielle informatiques pour aider la classification et l’évaluation tridimensionnelle de la scoliose. Certains algorithmes ont démontré être efficace pour diminuer la variabilité dans la classification de la scoliose et pour guider le traitement. L’objectif général de cette thèse est de développer une application utilisant des outils d’intelligence artificielle pour intégrer les données d’un nouveau patient et les évidences disponibles dans la littérature pour guider le traitement chirurgical de la SIA. Pour cela une revue de la littérature sur les applications existantes dans l’évaluation de la SIA fut entreprise pour rassembler les éléments qui permettraient la mise en place d’une application efficace et acceptée dans le milieu clinique. Cette revue de la littérature nous a permis de réaliser que l’existence de “black box” dans les applications développées est une limitation pour l’intégration clinique ou la justification basée sur les évidence est essentielle. Dans une première étude nous avons développé un arbre décisionnel de classification de la scoliose idiopathique basé sur la classification de Lenke qui est la plus communément utilisée de nos jours mais a été critiquée pour sa complexité et la variabilité inter et intra-observateur. Cet arbre décisionnel a démontré qu’il permet d’augmenter la précision de classification proportionnellement au temps passé à classifier et ce indépendamment du niveau de connaissance sur la SIA. Dans une deuxième étude, un algorithme de stratégies chirurgicales basé sur des règles extraites de la littérature a été développé pour guider les chirurgiens dans la sélection de l’approche et les niveaux de fusion pour la SIA. Lorsque cet algorithme est appliqué à une large base de donnée de 1556 cas de SIA, il est capable de proposer une stratégie opératoire similaire à celle d’un chirurgien expert dans prêt de 70% des cas. Cette étude a confirmé la possibilité d’extraire des stratégies opératoires valides à l’aide d’un arbre décisionnel utilisant des règles extraites de la littérature. Dans une troisième étude, la classification de 1776 patients avec la SIA à l’aide d’une carte de Kohonen, un type de réseaux de neurone a permis de démontrer qu’il existe des scoliose typiques (scoliose à courbes uniques ou double thoracique) pour lesquelles la variabilité dans le traitement chirurgical varie peu des recommandations par la classification de Lenke tandis que les scolioses a courbes multiples ou tangentielles à deux groupes de courbes typiques étaient celles avec le plus de variation dans la stratégie opératoire. Finalement, une plateforme logicielle a été développée intégrant chacune des études ci-dessus. Cette interface logicielle permet l’entrée de données radiologiques pour un patient scoliotique, classifie la SIA à l’aide de l’arbre décisionnel de classification et suggère une approche chirurgicale basée sur l’arbre décisionnel de stratégies opératoires. Une analyse de la correction post-opératoire obtenue démontre une tendance, bien que non-statistiquement significative, à une meilleure balance chez les patients opérés suivant la stratégie recommandée par la plateforme logicielle que ceux aillant un traitement différent. Les études exposées dans cette thèse soulignent que l’utilisation d’algorithmes d’intelligence artificielle dans la classification et l’élaboration de stratégies opératoires de la SIA peuvent être intégrées dans une plateforme logicielle et pourraient assister les chirurgiens dans leur planification préopératoire.

Visual Recognition and Categorization on the Basis of Similarities to Multiple Class Prototypes

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character both of natural kinds and of artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.

Multiple camera people detection and tracking using support integration

This paper proposes a method to locate and track people by combining evidence from multiple cameras using the homography constraint. The proposed method use foreground pixels from simple background subtraction to compute evidence of the location of people on a reference ground plane. The algorithm computes the amount of support that basically corresponds to the ""foreground mass"" above each pixel. Therefore, pixels that correspond to ground points have more support. The support is normalized to compensate for perspective effects and accumulated on the reference plane for all camera views. The detection of people on the reference plane becomes a search for regions of local maxima in the accumulator. Many false positives are filtered by checking the visibility consistency of the detected candidates against all camera views. The remaining candidates are tracked using Kalman filters and appearance models. Experimental results using challenging data from PETS`06 show good performance of the method in the presence of severe occlusion. Ground truth data also confirms the robustness of the method. (C) 2010 Elsevier B.V. All rights reserved.

Fixed-time artificial insemination with estradiol and progesterone for Bos indicus cows II: Strategies and factors affecting fertility

In Experiments 1, 2, and 3, we evaluated the effects of temporary weaning (TW), equine chorionic gonadotropin (eCG), and follicle-stimulating hormone (FSH) treatments on results of it fixed-time artificial insemination (TAI) protocol in postpartum Bos indicus cows. In Experiment 1, treatment with 400 IU eCG or with TW for 48 h consistently improved pregnancy rates (PRs) at TAI, but, in Experiment 2, FSH treatment was less effective than eCG or TW. In Experiment 3, the inclusion of eCG treatment in cows subjected to TW did not improve PRs. We concluded that TW or 400 IU eCG should be included in the TAI protocol in postpartum Bos indicus cows to enhance fertility. In Experiment 4, we used records front heifers and cows treated with the proposed protocol during the 2006-2007 (n = 27,195) and 2007-2008 (n = 36,838) breeding seasons from multiple locations in Brazil to evaluate factors potentially affecting PRs. Overall PR at TAI was 49.6% (31,786 of 64,033). Pregnancy rate differed (P < 0.01) among farm within location (results ranging between 26.8% and 68.0%; P < 0.01), cow group within farm, by breed (Bos indicus, 48.3% [26,123 of 54,145]; Bos taurus, 61.7% [3652 of 5922]; and crossbred Bos indicus x Bos taurus, 50.7% [2011 of 3966]), category (nulliparous, 39.6% [2095 of 52901] suckled primiparous, 45.2% [3924 of 8677]; suckled multiparous, 51.8% [24,245 of 46,767]; and nonsuckled multiparous, 46.1% [1522 of 3299]), body condition score at TAI (<= 2.5 43.0% [3409 of 7923]; 3.0, 49.6% [18,958 of 38,229]; and >3.5, 52.7% [9419 of 17,881]). Days postpartum at beginning, of protocol did not affect PR (30 to 60 d, 47.6% [4228 of 8881]; 61 to 90 d, 51.7% 116,325 to 31,5721; and 91 to 150 d, 50.8% [7616 to 14,991]; P > 0.1). Pregnancy rate was also consistently affected (P < 0.01) by sire (results ranging from 7.2% to 77.3%) and artificial insemination technician (results ranging from 15.1% to 81.8%). (C) 2009 Elsevier B.V. All rights reserved.

Artificial neural networks: A novel approach to analysing the nutritional ecology of a blowfly species, Chrysomya megacephala

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The use of artificial neural networks in analysing the nutritional ecology of Chrysomya megacephala (F.) (Diptera: Calliphoridae), compared with a statistical model

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Weather-based prediction of anthracnose severity using artificial neural network models

Data were collected and analysed from seven field sites in Australia, Brazil and Colombia on weather conditions and the severity of anthracnose disease of the tropical pasture legume Stylosanthes scabra caused by Colletotrichum gloeosporioides. Disease severity and weather data were analysed using artificial neural network (ANN) models developed using data from some or all field sites in Australia and/or South America to predict severity at other sites. Three series of models were developed using different weather summaries. of these, ANN models with weather for the day of disease assessment and the previous 24 h period had the highest prediction success, and models trained on data from all sites within one continent correctly predicted disease severity in the other continent on more than 75% of days; the overall prediction error was 21.9% for the Australian and 22.1% for the South American model. of the six cross-continent ANN models trained on pooled data for five sites from two continents to predict severity for the remaining sixth site, the model developed without data from Planaltina in Brazil was the most accurate, with >85% prediction success, and the model without Carimagua in Colombia was the least accurate, with only 54% success. In common with multiple regression models, moisture-related variables such as rain, leaf surface wetness and variables that influence moisture availability such as radiation and wind on the day of disease severity assessment or the day before assessment were the most important weather variables in all ANN models. A set of weights from the ANN models was used to calculate the overall risk of anthracnose for the various sites. Sites with high and low anthracnose risk are present in both continents, and weather conditions at centres of diversity in Brazil and Colombia do not appear to be more conducive than conditions in Australia to serious anthracnose development.

Combining artificial intelligence and human problem solving: Proposing a new architecture for ITS's

This paper shows a comparative study between the Artificial Intelligence Problem Solving and the Human Problem Solving. The study is based on the solution by many ways of problems proposed via multiple-choice questions. General techniques used by humans to solve this kind of problems are grouped in blocks and each block is divided in steps. A new architecture for ITS - Intelligent Tutoring System is proposed to support experts' knowledge representation and novices' activities. Problems are represented by a text and feasible answers with particular meaning and form, to be rigorously analyzed by the solver to find the right one. Paths through a conceptual space of states represent each right solution.

Impedance-based structural health monitoring with artificial neural networks

This paper presents a non-model based technique to detect, locate, and characterize structural damage by combining the impedance-based structural health monitoring technique with an artificial neural network. The impedance-based structural health monitoring technique, which utilizes the electromechanical coupling property of piezoelectric materials, has shown engineering feasibility in a variety of practical field applications. Relying on high frequency structural excitations (typically >30 kHz), this technique is very sensitive to minor structural changes in the near field of the piezoelectric sensors. In order to quantitatively assess the state of structures, multiple sets of artificial neural networks, which utilize measured electrical impedance signals for input patterns, were developed. By employing high frequency ranges and by incorporating neural network features, this technique is able to detect the damage in its early stage and to estimate the nature of damage without prior knowledge of the model of structures. The paper concludes with experimental examples, investigations on a massive quarter scale model of a steel bridge section and a space truss structure, in order to verify the performance of this proposed methodology.

Surface electromyography of facial muscles during natural and artificial feeding of infants

Objective: To measure and compare the activity of the masseter, temporalis and buccinator muscles in different infant feeding methods. Method: Cross-sectional study of 60 full-term infants with no intercurrent diseases, aged between two and three months, classified into the following groups: 1) exclusive breastfeeding; 2) breastfeeding plus bottle-feeding; and 3) exclusive breastfeeding plus cup feeding. Surface electromyography was performed during infant feeding. The Krushal-Wallis test was used, complemented by multiple paired comparisons of the groups. A 5% significance level was chosen for the tests. Results: Statistically higher results were verified in the breastfeeding group in relation to the bottle-feeding one, both in the range of movement and the mean contraction of the masseter. With regard to the temporalis muscle, statistically higher results were found in the breastfeeding group comparatively to the bottle-feeding one. As to the buccinator muscle, statistically higher results were observed in the breastfeeding group in relation to the bottle-feeding one, although in this case, the difference concerned only the range of contraction. Conclusion: The similarities between the muscle activity in the breastfeeding and in the cup-feeding groups suggests that cup-feeding can be used as an alternative infant feeding method, being better than bottle-feeding, due to the hyperactivity of the buccinator muscle, which could result in changes to the structural growth and development of the stomatognathic system functions. Copyright © 2006 by Sociedade Brasileira de Pediatria.

Avaliação eletromiográfica dos músculos masseter, temporal e bucinador de lactentes em situação de aleitamento natural e artificial

Pós-graduação em Pediatria - FMB

Efeito do flushing sobre o desempenho reprodutivo de ovelhas Morada Nova e Santa Inês submetidas à inseminação artificial em tempo fixo

The aim of this study was to analyze the effect of flushing on the reproductive performance of Morada Nova (MN) and Santa Inês (SI) ewes submitted to fixed time artificial insemination (TAI). Twenty seven SI and 24 MN supplemented with concentrate (1% of live weight, on average), for 75 days during the breeding season. After 30 days of supplementation, ewes were synchronized with the aid of a hormonal protocol (HP) based on progesterone, eCG and cloprostenol. The estrus observation was conducted at 12, 24, 36 and 48 h after the end of HP with the aid of two ruffians. TAI was done 55 h after the end of HP. From 20 to 45 days after the beginning of the HP ewes were exposed to rams (natural breeding). The pregnancy diagnosis was evaluated 70 days after TAI. We analyzed the weight, body condition score, estrus rate, pregnancy rate and prolificacy testing the effects of race, week of supplementation and body condition score class. The weight and body conditions of ewes varied according to the week of supplementation, with higher values in the first two weeks following TAI. The estrus rate was 88.2% and 43.2% of the ewes showed estrus up to 24 hours of the end of the HP. The pregnancy rate per TAI was 31.3% and the pregnancy rate after natural breeding was 50.0%. It was observed that body condition score classes interfered in pregnancy rates. There was a higher percentage of multiple births by pregnancy by TAI than by natural breeding. It was concluded that the flushing resulted in weight gain and better body conditions ensuring the standardization of the herd for breeding season, which therefore improved reproductive performance. The HP used advanced the onset of estrus and increased prolificacy, but was inefficient in the synchronization of woolless sheep.

Control of Buffalo Follicular Dynamics for Artificial Insemination, Superovulation and In Vitro Embryo Production

Currently, timed ovulation induction and timed artificial insemination (TAI) can be performed in buffalo using GnRH or estradiol plus progesterone/progestin (P4)-releasing devices and prostaglandin F-2 alpha (PGF(2 alpha)). The control of the emergence of follicular waves and of ovulation at predetermined times, without the need for estrus detection, has facilitated the management and improved the efficiency of AI programs in buffalo during the breeding and nonbreeding season. Multiple ovulations, embryo transfer, ovum collection and in vitro embryo production have been shown to be feasible in buffalo, although low efficiency and limited commercial application of these techniques have been documented as well. These results could be associated with low ovarian follicular pools, high levels of follicular atresia and failures of the oocyte to enter the oviduct after superstimulation of follicular growth. This review discusses a number of key points related to the manipulation of ovarian follicular growth to improve pregnancy rates following TAI and embryo transfer of in vivo- and in vitro-derived embryos in buffalo.