Dataset Information

FACE: the barefaced facts of AI potency.

ABSTRACT: The use of third-generation aromatase inhibitors (AIs), such as anastrozole and letrozole, as initial adjuvant hormonal therapy in postmenopausal women (PMW) with hormone receptor-positive (HR+) breast cancer offers a significant benefit over tamoxifen for reducing recurrence risk. Clinical studies, including the Arimidex Tamoxifen Alone or in Combination (ATAC) and the Breast International Group (BIG) 1-98 trials, have proven that both anastrozole and letrozole are, respectively, superior to tamoxifen in improving disease-free survival. Although differing in design, objectives, and follow-up time, these trials offer some insight into the comparative clinical efficacy of these two nonsteroidal AIs. In particular, results from BIG 1-98 show that letrozole significantly reduces early distant metastatic (DM) events, which constitute the majority of early recurrence events. Subsequently, there is a beneficial overall survival effect emerging in the trial, whereas survival is unchanged with anastrozole after 100 months of follow-up in ATAC. Significant differences in the potency of these two drugs, vis-à-vis their degree of aromatase inhibition, have been observed in comparative trials and show that letrozole causes a more complete suppression of estrogen levels than does anastrozole. Whether this difference in potency is relevant to reductions in DM events during adjuvant therapy remains unclear. The Femara Anastrozole Clinical Evaluation trial is addressing this issue in a more unequivocal manner by comparing initial adjuvant treatment with anastrozole or letrozole in a population of breast cancer patients at high risk of recurrence: PMW with HR+ disease and axillary lymph node involvement.

SUBMITTER: Monnier A

PROVIDER: S-EPMC3004571 | biostudies-other | 2010 Oct

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

FACE: the barefaced facts of AI potency.

Monnier Alain A

Cancer management and research 20101027

The use of third-generation aromatase inhibitors (AIs), such as anastrozole and letrozole, as initial adjuvant hormonal therapy in postmenopausal women (PMW) with hormone receptor-positive (HR+) breast cancer offers a significant benefit over tamoxifen for reducing recurrence risk. Clinical studies, including the Arimidex Tamoxifen Alone or in Combination (ATAC) and the Breast International Group (BIG) 1-98 trials, have proven that both anastrozole and letrozole are, respectively, superior to ta ...[more]

PMID: 21188118

Similar Datasets

Project description:Today's children have more opportunities than ever before to learn from interactive technology, yet experimental research assessing the efficacy of children's learning from interactive media in comparison to traditional learning approaches is still quite scarce. Moreover, little work has examined the efficacy of using touch-screen devices for research purposes. The current study compared children's rate of learning factual information about animals during a face-to-face instruction from an adult female researcher versus an analogous instruction from an interactive device. Eighty-six children ages 4 through 8 years (64% male) completed the learning task in either the Face-to-Face condition (n = 43) or the Interactive Media condition (n = 43). In the Learning Phase of the experiment, which was presented as a game, children were taught novel facts about animals without being told that their memory of the facts would be tested. The facts were taught to the children either by an adult female researcher (Face-to-Face condition) or from a pre-recorded female voice represented by a cartoon Llama (Interactive Media condition). In the Testing Phase of the experiment that immediately followed, children's memory for the taught facts was tested using a 4-option forced-choice paradigm. Children's rate of learning was significantly above chance in both conditions and a comparison of the rates of learning across the two conditions revealed no significant differences. Learning significantly improved from age 4 to age 8, however, even the preschool-aged children performed significantly above chance, and their performance did not differ between conditions. These results suggest that, interactive media can be equally as effective as one-on-one instruction, at least under certain conditions. Moreover, these results offer support for the validity of using interactive technology to collect data for research purposes. We discuss the implications of these results for children's learning from interactive media, parental attitudes about interactive technology, and research methods.

Project description:The increasingly popular application of AI runs the risk of amplifying social bias, such as classifying non-white faces as animals. Recent research has largely attributed this bias to the training data implemented. However, the underlying mechanism is poorly understood; therefore, strategies to rectify the bias are unresolved. Here, we examined a typical deep convolutional neural network (DCNN), VGG-Face, which was trained with a face dataset consisting of more white faces than black and Asian faces. The transfer learning result showed significantly better performance in identifying white faces, similar to the well-known social bias in humans, the other-race effect (ORE). To test whether the effect resulted from the imbalance of face images, we retrained the VGG-Face with a dataset containing more Asian faces, and found a reverse ORE that the newly-trained VGG-Face preferred Asian faces over white faces in identification accuracy. Additionally, when the number of Asian faces and white faces were matched in the dataset, the DCNN did not show any bias. To further examine how imbalanced image input led to the ORE, we performed a representational similarity analysis on VGG-Face's activation. We found that when the dataset contained more white faces, the representation of white faces was more distinct, indexed by smaller in-group similarity and larger representational Euclidean distance. That is, white faces were scattered more sparsely in the representational face space of the VGG-Face than the other faces. Importantly, the distinctiveness of faces was positively correlated with identification accuracy, which explained the ORE observed in the VGG-Face. In summary, our study revealed the mechanism underlying the ORE in DCNNs, which provides a novel approach to studying AI ethics. In addition, the face multidimensional representation theory discovered in humans was also applicable to DCNNs, advocating for future studies to apply more cognitive theories to understand DCNNs' behavior.

Project description:This paper presents a new approach for evaluating and controlling expressive humanoid robotic faces using open-source computer vision and machine learning methods. Existing research in Human-Robot Interaction lacks flexible and simple tools that are scalable for evaluating and controlling various robotic faces; thus, our goal is to demonstrate the use of readily available AI-based solutions to support the process. We use a newly developed humanoid robot prototype intended for medical training applications as a case example. The approach automatically captures the robot's facial action units through a webcam during random motion, which are components traditionally used to describe facial muscle movements in humans. Instead of manipulating the actuators individually or training the robot to express specific emotions, we propose using action units as a means for controlling the robotic face, which enables a multitude of ways to generate dynamic motion, expressions, and behavior. The range of action units achieved by the robot is thus analyzed to discover its expressive capabilities and limitations and to develop a control model by correlating action units to actuation parameters. Because the approach is not dependent on specific facial attributes or actuation capabilities, it can be used for different designs and continuously inform the development process. In healthcare training applications, our goal is to establish a prerequisite of expressive capabilities of humanoid robots bounded by industrial and medical design constraints. Furthermore, to mediate human interpretation and thus enable decision-making based on observed cognitive, emotional, and expressive cues, our approach aims to find the minimum viable expressive capabilities of the robot without having to optimize for realism. The results from our case example demonstrate the flexibility and efficiency of the presented AI-based solutions to support the development of humanoid facial robots.

Dataset Information

FACE: the barefaced facts of AI potency.

Publications

FACE: the barefaced facts of AI potency.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets