A feasibility study of a psychoeducational intervention program for gynecological cancer patients.

PURPOSE OF THE RESEARCH: This study aimed to test the feasibility of implementing a psychoeducational intervention program for gynecological cancer patients. METHODS AND SAMPLE: A single-blinded randomized controlled trial and mixed-method design were used. Study subjects were newly diagnosed gynecological cancer patients with surgery as the first-line treatment. They were randomly assigned to the intervention group, in which a psychoeducational intervention program based on a thematic counseling model was offered, or to the attention control group. Quantitative data on sexual functioning, quality of life, uncertainty, anxiety, depression and social support were collected at recruitment, post-operative and during the in-hospital period, and eight weeks after the operation. Participants in the intervention group and three nurses working in the clinical setting were invited to have semi-structured interviews. KEY RESULTS: Of the 30 eligible subjects, 26 were successfully recruited into the study. Following the psychoeducational intervention program, there was significant improvement in the level of inconsistent information about the illness within the category of uncertainty among participants in the intervention group. In addition, trends towards improvement were demonstrated in quality of life, uncertainty, depression and perceived social support with the provision of the interventions. Qualitative data indicated the interventions were desired and appreciated by the participants, as well as being feasible and practical to implement in Hong Kong clinical settings. CONCLUSIONS: The findings suggest that it is feasible to deliver the psychoeducational intervention program and it may have beneficial effects in gynecological cancer patients. A full-scale study is warranted to confirm the results.

Classification of linearly nonseparable patterns by linear threshold elements.

Learning and convergence properties of linear threshold elements or perceptrons are well understood for the case where the input vectors (or the training sets) to the perceptron are linearly separable. Little is known, however, about the behavior of the perceptron learning algorithm when the training sets are linearly nonseparable. We present the first known results on the structure of linearly nonseparable training sets and on the behavior of perceptrons when the set of input vectors is linearly nonseparable. More precisely, we show that using the well known perceptron learning algorithm, a linear threshold element can learn the input vectors that are provably learnable, and identify those vectors that cannot be learned without committing errors. We also show how a linear threshold element can be used to learn large linearly separable subsets of any given nonseparable training set. In order to develop our results, we first establish formal characterizations of linearly nonseparable training sets and define learnable structures for such patterns. We also prove computational complexity results for the related learning problems. Next, based on such characterizations, we show that a perceptron does the best one can expect for linearly nonseparable sets of input vectors and learns as much as is theoretically possible.