A new law was established in Japan to promote utilization of EHRs for research and developments, while de-identification is required to use EHRs. However, studies of automatic de-identification in the healthcare domain is not active for Japanese language, no de-identification tool available in practical performance for Japanese medical domains, as far as we know. Previous work shows that rule-based methods are still effective, while deep learning methods are reported to be better recently. In order to implement and evaluate a de-identification tool in a practical level, we implemented three methods, rule-based, CRF, and LSTM. We prepared three datasets of pseudo EHRs with de-identification tags manually annotated. These datasets are derived from shared task data to compare with previous work, and our new data to increase training data. Our result shows that our LSTMbased method is better and robust, which leads to our future work that plans to apply our system to actual de-identification tasks in hospitals.

In this paper, we propose a coaxial-fed circular dipole array in a borehole (CFCAB) for directional borehole radar and present a design method for the CFCAB. In the CFCAB, a circular dipole array is arranged around a conducting cylinder. When a wave is incident on the antenna, we may divide the signals received at the antenna into two components. One is caused by the waves arriving at the antenna directly, and the other is due to the waves scattered at the conducting cylinder. We proposed a criterion to quantify the influence of the conducting cylinder on the radar measurement. We show results of experiments in air and in granite to examine the validity of the criterion. Making use of the criterion, we designed and built the directional borehole radar system with the CFCAB working at around 200 MHz. Conducting the field experiments in granite, we confirmed that the CFCAB can estimate the directions of arrival waves on the time-frequency plane, as we expected with the criterion.Index Terms-Circular array, coaxial cable, dipole antenna, directional borehole radar, Method of Moments (MoM).

Automated summarization of clinical texts can reduce the burden of medical professionals. "Discharge summaries" are one promising application of the summarization, because they can be generated from daily inpatient records. Our preliminary experiment suggests that 20-31% of the descriptions in discharge summaries overlap with the content of the inpatient records. However, it remains unclear how the summaries should be generated from the unstructured source. To decompose the physician's summarization process, this study aimed to identify the optimal granularity in summarization. We first defined three types of summarization units with different granularities to compare the performance of the discharge summary generation: whole sentences, clinical segments, and clauses. We defined clinical segments in this study, aiming to express the smallest medically meaningful concepts. To obtain the clinical segments, it was necessary to automatically split the texts in the first stage of the pipeline. Accordingly, we compared rule-based methods and a machine learning method, and the latter outperformed the formers with an F1 score of 0.846 in the splitting task. Next, we experimentally measured the accuracy of extractive summarization using the three types of units, based on the ROUGE-1 metric, on a multi-institutional national archive of health records in Japan. The measured accuracies of extractive summarization using whole sentences, clinical segments, and clauses were 31.91, 36.15, and 25.18, respectively. We found that the clinical segments yielded higher accuracy than sentences and clauses. This result indicates that summarization of inpatient records demands finer granularity than sentence-oriented processing. Although we used only Japanese health records, it can be interpreted as follows: physicians extract "concepts of medical significance" from patient records and recombine them in new contexts when summarizing chronological clinical records, rather than simply copying and pasting topic sentences. This observation suggests that a discharge summary is created by higher-order information processing over concepts on sub-sentence level, which may guide future research in this field.

To effectively mitigate the COVID-19 pandemic, various methods have been proposed to control the infection risk using mobile phone technologies. In this respect, short-range Bluetooth in mobile phones has been mostly used to detect contacts with other devices that approach within a certain range for a specific duration and to notify residents regarding potential contact with infected patients. However, the technology can only detect direct contacts and neglects various modalities of infection, which might have contributed to the pandemic worldwide. In this article, we proposed an approach that evaluates the infection risk for residents, using the locational information of their mobile phones and confidential information of infected patients. The article first outlines the proposed method, the Computation of Infection Risks via Confidential Locational Entries method. Moreover, a comparative evaluation is qualitatively and quantitatively performed against the Bluetooth method. Results highlight the advantages of the proposed method and suggest that it could work in a complementary manner with the Bluetooth method toward effective mitigation of infection risks, while protecting privacy.