Machine learning and statistical prediction of patient quality-of-life after prostate radiation therapy.

Thanks to advancements in diagnosis and treatment, prostate cancer patients have high long-term survival rates. Currently, an important goal is to preserve quality of life during and after treatment. The relationship between the radiation a patient receives and the subsequent side effects he experiences is complex and difficult to model or predict. Here, we use machine learning algorithms and statistical models to explore the connection between radiation treatment and post-treatment gastro-urinary function. Since only a limited number of patient datasets are currently available, we used image flipping and curvature-based interpolation methods to generate more data to leverage transfer learning. Using interpolated and augmented data, we trained a convolutional autoencoder network to obtain near-optimal starting points for the weights. A convolutional neural network then analyzed the relationship between patient-reported quality-of-life and radiation doses to the bladder and rectum. We also used analysis of variance and logistic regression to explore organ sensitivity to radiation and to develop dosage thresholds for each organ region. Our findings show no statistically significant association between the bladder and quality-of-life scores. However, we found a statistically significant association between the radiation applied to posterior and anterior rectal regions and changes in quality of life. Finally, we estimated radiation therapy dose thresholds for each organ. Our analysis connects machine learning methods with organ sensitivity, thus providing a framework for informing cancer patient care using patient reported quality-of-life metrics.

Impact of aluminosilicates on productivity, carcass traits, meat quality, and jejunum morphology of broiler chickens.

The aim of the study was to compare production results and quality of meat, as well as histological features of the jejunum in broiler chickens administered feed with 1% addition of zeolite or halloysite, with the addition of aluminosilicates to litter (4.50 kg/m2) throughout the rearing. In the experiment, 300 male broilers were used for 6 wk. They were divided into 3 groups, each of 10 repetitions (10 birds each). Group 1 was a control, halloysite was added to feed and litter in group 2, while zeolite was applied instead of halloysite in group 3. After rearing, 10 selected birds from each group were slaughtered. Selected production properties and degree of footpad dermatitis were examined, and histomorphometric examination of the jejunum was performed. The lowest yield and the highest proportion of neck with skin in the carcass were demonstrated in group 2 (P < 0.05). The lowest percentage of skin with subcutaneous fat was found in group 3 (P < 0.05). A decrease in lightness (L∗) and yellowness (b∗) was demonstrated in group 2, while redness (a∗) was the lowest in group 3 (P < 0.05). Group 2 was characterized by the lowest water-holding capacity in breast muscles, and in group 3, in leg muscles (P < 0.05). In group 3, the highest fat content and the lowest water content in the breast muscles (P < 0.05) were found. The leg muscles in groups 2 and 3 were characterized by the highest a∗, and in group 2, by b∗. The control group had the lowest protein and the highest fat content in leg muscles. In the intestine from group 2, a higher height (P < 0.05) and surface area (P < 0.01) of intestinal villi were found, in comparison to group 3. The width of intestinal villi was higher in groups 2 and 1 than in group 3 (P < 0.05), similarly the depth of intestinal crypts. The addition of zeolite could be proposed because of the obtained production results, while the halloysite had a positive effect on the histomorphometric features of the jejunum.

Gadolinium doped europium sulfide.

We have prepared gadolinium doped europium sulfides, Eu(1-x)Gd(x)S for a doping range of 0 ≤ x ≤ 0.1 by thermal decomposition of the precursors Eu(S(2)CNEt(2))(3)Phen/Gd(S(2)CNEt(2))(3)Phen with respective ratios. Electron doping provides indirect evidence for the magnetic coupling through carrier electrons in magnetic semiconductors. Based on the magnetic properties, we determined that the paramagnetic Curie temperature, Θp, varies with doping level, in a similar way to Eu(1-x)Gd(x)O exhibiting a significant increase at low doping levels. All materials have been characterized by X-ray powder diffraction, magnetic measurements, ICP-MS, and TEM.