The purpose of this study is to use the DICOM Radiation Dose Structured Report (RDSR) to compare diagnostic reference levels (DRLs) with the dose values at own facility. We used the JJ1017 Guideline, which are the standards of the Ministry of Health, Labor and Welfare, and focused on comparing doses on a protocol-by-protocol basis. Dose information was extracted from the RDSR, and the number of examinations, CT Dose Index volume, and Dose Length Product for each protocol were obtained and compared using the Target Region and JJ1017 code to identify the imaging region.

　The results revealed that the same code was assigned to multiple device protocols in the Target Region. JJ1017 was able to appropriately represent the protocol contents of DRLs, improving the collection accuracy. The JJ1017 Guideline has proven to be a useful tool in dose management.

　In response to the increasing prominence of malware attacks on HIS systems, we conducted a security assessment of the HIS network. The assessment revealed that firewalls were disabled on most servers and clients. Consequently, we requested each vendor to enable firewalls on their servers and devices. However, only a few vendors were able to respond promptly, exposing a general lack of security awareness among many vendors. Although we had to conduct security assessments and enhancements on the operational systems this time, ideally, clear security measures should be specified and implemented at the time of system installation.

　To address the continuously evolving risks, it is essential for vendors and hospital facilities to collaborate on security measures. Relying solely on vendors is inadequate; hospital facilities must also possess sufficient knowledge about security.

　Epileptic seizures in patients with severe motor and intellectual disabilities (SMID) are difficult to distinguish and may cause respiratory depression; therefore, early detection is crucial. We explored the feasibility of using artificial intelligence technology to detect epileptic seizures early, leveraging facial images and pulse rate data from patients with SMID. The research participant, a patient with SMID diagnosed with Oshima’s classification 1, often exhibited increased pulse rate and decreased transcutaneous oxygen saturation during epileptic seizures. We categorized facial expressions and pulse rate data into three scenarios: days without seizures (A), preseizure (B), and postseizure (C). Using results from previous multiple regression analyses, we performed logistic regression and neural network analyses. The data across the three scenarios were accurately classified as “no seizures,” “possibility of seizures,” and “seizures present” even when using these analyses.