Publications by authors named "Ikusaka M"

Background: Discrepancies existed between the medical knowledge sections of the Model Core Curriculum for Medical Education (MCC) and the Guidelines for the National Examination for Medical Practitioners (GNEMP) in Japan. These discrepancies have been one of the underlying factors hindering the development of learner-centered medical education in the country. The project team responsible for the 'Problem-Solving' section of the MCC aimed to address discrepancies between the disease lists in the MCC and the GNEMP.

View Article and Find Full Text PDF

Background: Creating clinical vignettes requires considerable effort. Recent developments in generative artificial intelligence (AI) for natural language processing have been remarkable and may allow for the easy and immediate creation of diverse clinical vignettes.

Objective: In this study, we evaluated the medical accuracy and grammatical correctness of AI-generated clinical vignettes in Japanese and verified their usefulness.

View Article and Find Full Text PDF

This study tests whether comprehensively gathering information from medical records is useful for developing clinical decision support systems using Bayes' theorem. Using a single-center cross-sectional study, we retrospectively extracted medical records of 270 patients aged ≥16 years who visited the emergency room at the Tokyo Metropolitan Tama Medical Center with a chief complaint of experiencing headaches. The medical records of cases were analyzed in this study.

View Article and Find Full Text PDF

Background: An illness script is a specific script format geared to represent patient-oriented clinical knowledge organized around enabling conditions, faults (i.e., pathophysiological process), and consequences.

View Article and Find Full Text PDF

Background: Medical history contributes approximately 80% to a diagnosis, although physical examinations and laboratory investigations increase a physician's confidence in the medical diagnosis. The concept of artificial intelligence (AI) was first proposed more than 70 years ago. Recently, its role in various fields of medicine has grown remarkably.

View Article and Find Full Text PDF
Article Synopsis
  • - Differentiating psychogenic diseases like conversion disorder and somatic symptom disorder from medical diseases requires a comprehensive biopsychosocial approach due to the complexity of symptoms involved.
  • - Key factors for differentiation include the relationship between symptoms and objective findings, the presence of placebo effects, and identifiable provocative or alleviating factors for the symptoms.
  • - Other distinguishing features involve the progression of symptoms over time, patterns of symptom occurrence (like being intermittent), and changes in symptom severity during rest or sleep.
View Article and Find Full Text PDF

Unlabelled: Kikuchi-Fujimoto disease (KFD), also called histiocytic necrotizing lymphadenitis, is more common in young women and typically presents with small, painful, localized cervical lymphadenopathy that resolves spontaneously within a few weeks. Laboratory findings are variable. As many as 40% of KFD cases are reported to be painless, and up to 22% to be generalized lymphadenopathy.

View Article and Find Full Text PDF

Acute visual loss in an immunocompromised patient may be caused by acute invasive fungal sinusitis (AIFS), even if symptoms include only mild headache and computed tomography (CT) shows only mild sinusitis, especially of the Onodi cell. Herein, we report a case of a 71-year-old man with a medical history of dermatomyositis and type 2 diabetes mellitus who presented with a stepwise progression of acute bilateral visual loss, mild headache, and altered consciousness. Initially, as the plain cranial CT showed only mild fluid retention in the posterior ethmoid sinus without bone destruction, the sinusitis was considered unrelated to the visual loss.

View Article and Find Full Text PDF

Background: The gamification of learning increases student enjoyment, and motivation and engagement in learning tasks. This study investigated the effects of gamification using decision-making cards (DMCs) on diagnostic decision-making and cost using case scenarios.

Method: Thirty medical students in clinical clerkship participated and were randomly assigned to 14 small groups of 2-3 medical students each.

View Article and Find Full Text PDF
Article Synopsis
  • ChatGPT, specifically its latest version GPT-4, has shown improvements in generating accurate and useful responses, particularly in English, though it still faces challenges generating reliable medical information in languages like Chinese and Japanese.
  • The study aimed to assess the accuracy of ChatGPT in providing medical knowledge and diagnoses based on the National Medical Licensing Examination (NMLE) questions from Japan.
  • By analyzing the text-based questions with two general practice physicians verifying the answers, the research seeks to determine the effectiveness of ChatGPT for Japanese healthcare inquiries.
View Article and Find Full Text PDF
Article Synopsis
  • The study investigates whether medical histories related to "infarction" can capture pathophysiological and anatomical insights through word representations from Japanese medical texts using Word2Vec.
  • A morphological analysis was conducted on abstracts sourced from the Ichushi Data Base, which revealed that only 33% of correct medical terminology analogies were achieved, while 52% were correct in new tasks specific to "infarction."
  • Findings suggest that Word2Vec can effectively encapsulate relevant terminology and meanings related to "infarction," indicating that key aspects of its pathophysiology and anatomy are reflected in the representations derived from the text.
View Article and Find Full Text PDF
Article Synopsis
  • A study was conducted to evaluate the effectiveness of a clinical diagnostic support system (CDSS) compared to Google and a control group in aiding medical students with diagnostic accuracy based on patient histories.
  • In the study involving 64 medical students and 13 residents at Chiba University Hospital, students who used the CDSS (mean score of 12.0) and Google (mean score of 11.9) performed better than those in the control group (mean score of 9.5).
  • However, residents who did not use either resource achieved a higher mean score (14.7), indicating that more experienced individuals could still perform better than students using the CDSS or Google.
View Article and Find Full Text PDF
Article Synopsis
  • Angina bullosa haemorrhagica (ABH) is a condition affecting mainly middle-aged adults, characterized by the formation of blood-filled blisters in the throat, especially on the soft palate, which typically heal on their own within a week.
  • A case study described a 50-year-old man who developed a pharyngeal haematoma after an endoscopy, which burst and ultimately led to an ABH diagnosis.
  • Key points to remember: ABH can be triggered by external factors like food or medical procedures, heals without scarring, but may pose a risk for airway obstruction, particularly if located in the pharynx.
View Article and Find Full Text PDF
Article Synopsis
  • This study examined the effectiveness of speech recognition software in providing feedback for medical students' interview skills compared to traditional voice-recording methods.
  • In an observational trial with 79 medical students, those receiving speech recognition feedback showed significantly improved performance in diagnostic accuracy and clinical competence scores.
  • The results indicate that using speech recognition feedback enhances the quality of medical interviews, leading to better outcomes in training future healthcare professionals.
View Article and Find Full Text PDF

We describe a case of pubic osteomyelitis in a 17-year-old Japanese male. The patient presented with acute left groin pain and left lower quadrant pain. He was evaluated at another hospital where pelvic X-ray/computed tomography was normal, and laboratory testing revealed only high C-reactive protein.

View Article and Find Full Text PDF
Article Synopsis
  • The study compares the effectiveness of Hybrid problem-based learning (PBL) and Pure PBL in teaching clinical reasoning skills to 99 medical students at Chiba University Hospital.
  • Results showed no significant differences in students' perceived competence and satisfaction, but the Hybrid PBL group improved significantly in recalling differential diagnoses and practicing clinical reasoning processes.
  • Qualitative analysis identified 13 advantages of Hybrid PBL, highlighting benefits in knowledge acquisition, discussion facilitation, and feedback mechanisms.
View Article and Find Full Text PDF
Article Synopsis
  • * A study used word embedding techniques like Word2Vec, FastText, and GloVe to analyze medical abstracts, focusing on diseases related to the term "infarction" and comparing the findings with ICD-10 codes for accuracy.
  • * Results indicated that while internal validity (measured by cophenetic correlation coefficient or CCC) and external validity (measures like adjusted mutual information or AMI) used different metrics for optimal results, the use of cosine distance was recommended for better similarity evaluations among diseases.
View Article and Find Full Text PDF

Background: Physicians frequently experience patients as difficult. Our study explores whether more empathetic physicians experience fewer patient encounters as difficult.

Objective: To investigate the association between physician empathy and difficult patient encounters (DPEs).

View Article and Find Full Text PDF