Background: Primary headaches are widespread and costly public health problems. However, there are insufficient medical resources for their treatment in Japan due to two reasons. First, the numbers of headache specialists and clinics remain insufficient. Second, neurologists and neurosurgeons mainly treat headaches in Japan. However, they mainly work as general stroke neurologists, so they cannot focus on primary headache treatment. To solve these problems, we preliminarily developed a deep learning (DL)-based automated diagnosis model from patients’ Japanese unstructured sentences in the medical questionnaire using a DL framework. We hypothesized that the model would reduce the time and burden on both doctors and patients and improve their quality of life. Methods: We retrospectively investigated our primary headache database and developed a diagnosis model using the DL framework (Prediction One, Sony Network Communications Inc., Japan). We used age, sex, date, and embedding layer made by the medical questionnaire’s natural language processing (NLP). Results: Eight hundred and forty-eight primary headache patients (495 women and 353 men) are included. The median (interquartile range) age was 59 (40–74). Migraine accounted for 46%, tension-type headache for 47%, trigeminal autonomic cephalalgias for 5%, and other primary headache disorders for 2%. The accuracy, mean precision, mean recall, and mean F value of the developed diagnosis model were 0.7759, 0.8537, 0.6086, and 0.6353, which were satisfactory. Conclusion: The DL-based diagnosis model for primary headaches using the raw medical questionnaire’s Japanese NLP would be useful in performing efficient medical practice after ruling out the secondary headaches.

Background: Skeletal muscle mass is an important factor for various diseases’ outcomes. The psoas muscle cross-sectional area on the abdominal computed tomography (CT), gait speed, and handgrip strength is used to measure it. However, it is difficult to measure the neurological patients’ muscle mass or function because (1) we do not perform abdominal CT. (2) Such patients have impaired consciousness, gait disturbance, paresis, and need of rest. Temporal muscle thickness (TMT) on magnetic resonance imaging (MRI) is now attractive for skeletal muscle volume indicator, but the reference values are not established. We herein investigated the standard value of the Japanese TMT using the brain check-up database by MRI. Methods: We retrospectively investigated 360 Japanese individuals from two institutions between 2017 and 2019. We measured TMT on the T1-weighted images in the previously reported way. The associations between TMT and other variables were analyzed. Results: TMT of 214 women and 146 men, ranging from 35 to 84 years old, was investigated. TMT ranged from 3.69 to 16.90 mm. Mean TMT values were significantly higher in men compared to women except for the over 70-year-old cohort. TMT was correlated to weight and body mass index in both sexes. Conclusion: This is the first retrospective study on the standard TMT values from the Japanese brain check-up database. Our results were just reference values, but these would be useful for further investigation in other neurosurgical and neurological diseases regarding muscle volume or sarcopenia.

It is important to assess the cerebral arteries near the clip after cerebral aneurysm clipping. Contrast-enhanced computed tomography angiography has side effects of contrast medium and radiation exposure. Time-of-flight magnetic resonance angiography (TOF-MRA) is a fast and non-invasive method, but clip-induced artifact limits the assessment around the clip. Recently, 3 tesla MRA with ultrashort echo time called SILENT MRA (GE Healthcare Life Sciences, UK) has been reported to have the potential to overcome these disadvantages. We herein present consecutive 19 cerebral aneurysm patients treated by clipping and evaluated using SILENT MRA. The 19 patients (15 women and 4 men) underwent TOF-MRA and SILENT MRA during the same scan session. Two neurosurgeons independently assessed the visibility of the mother vessel at the clipping site in TOF-MRA and SILENT MRA. We also investigated the factors related to visibility in SILENT MRA. All patients' mother vessels were not described in TOF-MRA, and that of 16 patients (84%) were described in SILENT MRA. Overall agreement was 100% in the two neurosurgeons, and the fixed marginal kappa = 1.00 (95% CI: 0.36–1.00). Univariate analysis revealed that larger aneurysm dome and long clip blade length contributed to the visibility of the mother vessel in SILENT MRA. (p = 0.023, 0.007, each). In conclusion, SILENT MRA can be applied for the assessment of the arteries and aneurysm neck remnants near the clip. Using clips with long blade and ligation with its tip would be related to the visibility of the mother vessels in SILENT MRA.

Gefitinib is an epidermal growth factor receptor tyrosine kinase inhibitor. Clinical trials have reported its effectiveness in the treatment of brain metastases from non-small cell lung cancer by overcoming the blood–brain barrier. Gefitinib is generally regarded as a relatively safe agent, and several reports have described its efficacy in patients with epidermal growth factor receptor mutation-positive non-small cell lung cancer and a poor performance status. We herein described two patients with brain metastasis from non-small cell lung cancer who achieved the total regression of metastasis with the administration of gefitinib. A 70-year-old Japanese woman was referred to our hospital with a severe cough. Brain magnetic resonance imaging revealed a metastatic lesion in the left temporal lobe. The tumor was positive for an epidermal growth factor receptor L858R mutation in exon 21 using the peptide nucleic acid-locked nucleic acid polymerase chain reaction clamp method. She was treated with 250 mg gefitinib per day, and, 1 month later, the primary lesion and brain metastasis had totally resolved. A 58-year-old Japanese woman was referred to our hospital with nausea and headache. Brain magnetic resonance imaging revealed a metastatic lesion in the left cerebellar hemisphere and meningeal dissemination. The tumor was positive for the epidermal growth factor receptor L858R mutation in exon 21. She was treated with 250 mg gefitinib per day, and, 3 weeks later, the primary lesion, brain metastasis, and meningeal dissemination had completely resolved. We successfully treated two lung cancer patients with brain metastasis using gefitinib. Gefitinib therapy may be a suitable treatment for brain metastasis in lung cancer with an epidermal growth factor receptor mutation, particularly in elderly patients with a poor performance status.

Cancerous cells are known to metastasize to different ocular structures. This happens especially to the choroid in males with lung cancer and females with breast cancer. However, we observed two cases of cancerous metastasis to the optic canal region. Both cases showed only a progressive decrease in vision without any other remarkable ophthalmological symptoms or abnormalities in the affected eye. Two females, a 60-year-old and a 73-year-old, came to our hospital because of progressive loss of vision. These patients showed no remarkable symptoms or signs in their eyes except visual acuity loss. Several ophthalmoscopic examinations, such as slit lamp microscopy and fundoscopy, showed no abnormal changes in their affected eye but magnetic resonance imaging indicated a massive legion around the optic nerve. It is possible for cancer to metastasize to the optic canal region and the existence of primary tumors should be considered.

Background: Chronologically meteorological and calendar factors were risks of stroke occurrence. However, the prediction of stroke occurrences is difficult depending on only meteorological and calendar factors. We tried to make prediction models for stroke occurrences using deep learning (DL) software, Prediction One (Sony Network Communications Inc., Tokyo, Japan), with those variables.Methods: We retrospectively investigated the daily stroke occurrences between 2017 and 2019. We used Prediction One software to make the prediction models for daily stroke occurrences (present or absent) using 221 chronologically meteorological and calendar factors. We made a prediction models from the 3-year dataset and evaluated their accuracies using the internal cross-validation. Areas under the curves (AUCs) of receiver operating characteristic curves were used as accuracies.Results: The 371 cerebral infarction (CI), 184 intracerebral hemorrhage (ICH), and 53 subarachnoid hemorrhage patients were included in the study. The AUCs of the several DL-based prediction models for all stroke occurrences were 0.532–0.757. Those for CI were 0.600–0.782. Those for ICH were 0.714–0.988.Conclusion: Our preliminary results suggested a probability of the DL-based prediction models for stroke occurrence only by meteorological and calendar factors. In the future, by synchronizing a variety of medical information among the electronic medical records and personal smartphones as well as integrating the physical activities or meteorological conditions in real time, the prediction of stroke occurrence could be performed with high accuracy, to save medical resources, to have patients care for themselves, and to perform efficient medicine.