Virtual clinical trial based on outcome modeling with iteratively redistributed extrapolation data.

Virtual clinical trials (VCTs) can potentially simulate clinical trials on a computer, but their application with a limited number of past clinical cases is challenging due to the biased estimation of the statistical population. In this study, we developed ExMixup, a novel training technique based on machine learning, using iteratively redistributed extrapolated data. Information obtained from 100 patients with prostate cancer and 385 patients with oropharyngeal cancer was used to predict the recurrence after radiotherapy. Model performance was evaluated by developing outcome prediction models based on three types of training methods: training with original data (baseline), interpolation data (Mixup), and interpolation + extrapolation data (ExMixup). Two types of VCTs were conducted to predict the treatment response of patients with distinct characteristics compared to the training data obtained from patient cohorts categorized under risk classification or cancer stage. The prediction models developed with ExMixup yielded concordance indices (95% confidence intervals) of 0.751 (0.719-0.818) and 0.752 (0.734-0.785) for VCTs on the prostate and oropharyngeal cancer datasets, respectively, which significantly outperformed the baseline and Mixup models (P < 0.01). The proposed approach could enhance the ability of VCTs to predict treatment results in patients excluded from past clinical trials.

Identification of Aquatic Organisms Using a Magneto-Optical Element.

In recent advanced information society, it is important to individually identify products or living organisms automatically and quickly. However, with the current identifying technology such as RFID tag or biometrics, it is difficult to apply to amphibians such as frogs or newts because of its size, stability, weakness under a wet environment and so on. Thus, this research aims to establish a system that can trace small amphibians easily even in a wet environment and keep stable sensing for a long time. The magnetism was employed for identification because it was less influenced by water for a long time. Here, a novel magnetization-free micro-magnetic tag is proposed and fabricated with low cost for installation to a living target sensed by Magneto-Optical sensor for high throughput sensing. The sensing ability of the proposed method, which was evaluated by image analysis, indicated that it was less than half of the target value (1 mm) both in the water and air. The FEM analysis showed that it is approximately twice the actual identification ability under ideal conditions, which suggests that the actual sensing ability can be extended by further improvement of the sensing system. The developed magnetization-free micro-magnetic tag can contribute to keep up the increasing demand to identify a number of samples under a wet environment especially with the development of gene technology.