Reverse Encoding Distortion Correction for Clinical Head Echo-Planar Diffusion-Weighted MRI: Initial Experience.

OBJECTIVE: This study aimed to evaluate the feasibility of the recently commercialized reverse encoding distortion correction (RDC) method for echo-planar imaging (EPI) diffusion-weighted imaging (DWI) by applying clinical head MRI. METHODS: This study included 50 consecutive patients who underwent head MRI, including single-shot (SS) EPI DWI and RDC-EPI DWI. For evaluation of normal structures, qualitative scores for image distortion, Dice similarity coefficient (DSC) values, distortion ratios, and mean apparent diffusion coefficient (ADC) values were assessed in the pons, temporal lobe at the skull base, and frontal lobe at the level of the lateral ventricles in 30 patients. To evaluate pathologies, qualitative scores for image distortion were assessed for 25 intracranial and 21 extracranial pathologies identified in 32 patients. RESULTS: Qualitative scores for image distortion, DSC values, distortion ratios, and mean ADC values of the pons and temporal lobe were significantly different between SS-EPI DWI and RDC-EPI DWI, whereas those of the frontal lobe at the level of the lateral ventricles were not significantly different between the 2 DWIs. The qualitative scores for image distortion and mean ADC values of extracranial pathologies were significantly different between the DWIs, whereas those of intracranial pathologies were not significantly different. CONCLUSIONS: RDC-EPI DWI significantly reduced image distortion and showed higher mean ADC values of the brain parenchyma in the skull base and extracranial pathologies.

Comparison of natural language processing algorithms in assessing the importance of head computed tomography reports written in Japanese.

PURPOSE: To propose a five-point scale for radiology report importance called Report Importance Category (RIC) and to compare the performance of natural language processing (NLP) algorithms in assessing RIC using head computed tomography (CT) reports written in Japanese. MATERIALS AND METHODS: 3728 Japanese head CT reports performed at Osaka University Hospital in 2020 were included. RIC (category 0: no findings, category 1: minor findings, category 2: routine follow-up, category 3: careful follow-up, and category 4: examination or therapy) was established based not only on patient severity but also on the novelty of the information. The manual assessment of RIC for the reports was performed under the consensus of two out of four neuroradiologists. The performance of four NLP models for classifying RIC was compared using fivefold cross-validation: logistic regression, bidirectional long-short-term memory (BiLSTM), general bidirectional encoder representations of transformers (general BERT), and domain-specific BERT (BERT for medical domain). RESULTS: The proportion of each RIC in the whole data set was 15.0%, 26.7%, 44.2%, 7.7%, and 6.4%, respectively. Domain-specific BERT showed the highest accuracy (0.8434 ± 0.0063) in assessing RIC and significantly higher AUC in categories 1 (0.9813 ± 0.0011), 2 (0.9492 ± 0.0045), 3 (0.9637 ± 0.0050), and 4 (0.9548 ± 0.0074) than the other models (p < .05). Analysis using layer-integrated gradients showed that the domain-specific BERT model could detect important words, such as disease names in reports. CONCLUSIONS: Domain-specific BERT has superiority over the other models in assessing our newly proposed criteria called RIC of head CT radiology reports. The accumulation of similar and further studies of has a potential to contribute to medical safety by preventing missed important findings by clinicians.

Nurse-Led Collaborative Management Using Telemonitoring Improves Quality of Life and Prevention of Rehospitalization in Patients with Heart Failure.

The effects of disease management using telemonitoring for patients with heart failure (HF) remain controversial. Hence, we embedded care coordination and enhanced collaborative self-management through interactive communication via a telemonitoring system (collaborative management; CM). This study evaluated whether CM improved psychosocial status and prevented rehospitalization in patients with HF in comparison with self-management education (SM), and usual care (UC).We randomly allocated 59 patients into 3 groups; UC (n = 19), SM (n = 20), and CM (n = 20). The UC group received one patient education session, and the SM and CM groups participated in disease management programs for 12 months. The CM group received telemonitoring concurrently. All groups were followed up for another 12 months. Data were collected at baseline and at 6, 12, 18, and 24 months.The primary endpoint was quality of life (QOL). Secondary endpoints included self-efficacy, self-care, and incidence of rehospitalization. The QOL score improved in CM compared to UC at 18 and 24 months (P < 0.05). There were no significant differences among the 3 groups in self-efficacy and self-care. However, compared within each group, only the CM had significant changes in self-efficacy and in self-care (P < 0.01). Rehospitalization rates were high in the UC (11/19; 57.9%) compared with the SM (5/20; 27.8%) and CM groups (4/20; 20.0%). The readmission-free survival rate differed significantly between the CM and UC groups (P = 0.020).We conclude that CM has the potential to improve psychosocial status in patients with HF and prevent rehospitalization due to HF.

Roles of Nurses in Home Medical Care.

Some patients of advanced age with heart failure (HF) require repeated hospital care. In an aging society, the importance of medical and social care support systems for patients with HF further increases. In Onomichi-city, a comprehensive community care system has been in place since its introduction in 1997. The system is called "Onomichi Type". This is an interprofessional care system in which a variety of healthcare professionals, with common basic knowledge of disease prevention, treatment and welfare, collaborate with other care professionals. These professionals gain shared knowledge in regard to care management, and fulfill their respective roles at Care Conferences held during a patient's hospital stay. Elderly patients also often have multiple comorbidities and take a lot of medicines. Some patients might forget to take their medicine, whereas others might take an overdose. Thus, sharing a patient's complete medical information with pharmacists is also necessary. We began to collaborate with pharmacists in hospitals and at pharmacies in 2014. The pharmacist plays a great role in providing comprehensive community medical care.