Publications by authors named "Eriku Yamada"
Article Synopsis
- Advances in diagnosing carpal tunnel syndrome (CTS) with ultrasonography (US) and artificial intelligence (AI) aim to create a better system than traditional nerve conduction studies, focusing on accurately measuring severity.
- The study involved 75 individuals, recording 132 US videos during finger movements, and creating three datasets to compare the effectiveness of various machine learning algorithms in classifying CTS severity.
- Results indicated that comprehensive video data significantly improved accuracy, with one algorithm achieving a sensitivity of 1.00 and an accuracy of 0.75, highlighting the importance of observing median nerve (MN) movement for accurate diagnosis.
Article Synopsis
- A distal radius fracture (DRF) is common in postmenopausal women and increases the risk of future fractures; this study examines how daily gait changes over time can predict fall risks.
- 16 women with DRF and 28 matched controls were assessed at 4 weeks and 6 months post-fracture using in-shoe inertial measurement units to measure gait and physical strength.
- Results showed initial gait impairments in the fracture group, including lower foot height and variable stride length, which improved over time, but they consistently had lower hand grip strength compared to healthy controls.
Article Synopsis
- Cardiac amyloidosis is a serious heart condition resulting from the buildup of amyloid protein in heart tissue, often leading to severe heart failure, which requires early detection for better outcomes.
- * Recent studies suggest a link between cardiac amyloidosis and orthopedic conditions like carpal tunnel syndrome (CTS) and shoulder diseases, though little has been researched about amyloid presence in shoulder specimens correlated with cardiac issues.
- * In a study of 41 shoulder surgery patients and 33 CTS patients, 7.3% showed amyloid deposition related to rotator cuff tears, but none of these cases had cardiac amyloidosis, indicating that shoulder specimen screening may not effectively predict cardiac amyloidosis.
Background: Distal radius fractures (DRF) commonly occur in early postmenopausal females as the first fragility fracture. Although the incidence of DRF in this set of patients may be related to a lower ability to control their balance and gait, the detailed gait characteristics of DRF patients have not been examined.
Research Question: Is it possible to identify the physical and gait features of DRF patients using in-shoe inertial measurement unit (IMU) sensors at various gait speeds and to develop a machine learning (ML) algorithm to estimate patients with DRF using gait?
Methods: In this cross-sectional case control study, we recruited 28 postmenopausal females with DRF as their first fragility fracture and 32 age-matched females without a history of fragility fractures.
Article Synopsis
- AI, particularly NLP like ChatGPT, is becoming popular in medicine, but its effectiveness in self-diagnosing and recommending medical consultations for orthopedic diseases needs evaluation.
- The study aimed to assess ChatGPT's accuracy in self-diagnosing five common orthopedic conditions and its recommendations for seeking medical advice.
- Results showed high accuracy for carpal tunnel syndrome, but poor for cervical myelopathy, with variability in reproducibility across different conditions and raters, highlighting limitations in ChatGPT's medical consultation advice.
Article Synopsis
- Gait decline in older adults can increase the risk of falls, specifically in postmenopausal women who often experience distal radius fractures (DRF) as a common initial injury that can lead to additional fractures.
- A study involving 27 women with DRF and 28 without utilized in-shoe inertial measurement units (IMUs) to monitor daily gait patterns and assess their link to fall risk.
- Findings indicated that women with DRF exhibited reduced foot movement angles during walking, and a specific angle below 99.0 degrees could signal a higher risk of future fractures, suggesting the need for ongoing research to prevent these injuries through understanding gait characteristics.
Early detection of cervical myelopathy (CM) is important for a favorable outcome, as its prognosis is poor when left untreated. We developed a screening method for CM using machine learning-based analysis of the drawing behavior of 38 patients with CM and 66 healthy volunteers. Using a stylus pen, the participants traced three different shapes displayed on a tablet device.
View Article and Find Full Text PDFArticle Synopsis
- Early detection of degenerative cervical myelopathy (DCM) is crucial, but existing screening methods are complex and costly, prompting this study to explore a simpler 10-second grip-and-release test using machine learning via smartphones.* -
- The study involved 39 participants (22 with DCM and 17 as controls), where videos of the grip test were analyzed to estimate DCM presence using a support vector machine algorithm, yielding high sensitivity (90.9%) and specificity (88.2%).* -
- The proposed screening model shows promise as an effective and accessible tool for identifying DCM, making it useful for non-specialists and the general community.*
Background: Cervical myelopathy (CM) causes several symptoms such as clumsiness of the hands and often requires surgery. Screening and early diagnosis of CM are important because some patients are unaware of their early symptoms and consult a surgeon only after their condition has become severe. The 10-second hand grip and release test is commonly used to check for the presence of CM.
View Article and Find Full Text PDFWhen carpal tunnel syndrome (CTS), an entrapment neuropathy, becomes severe, thumb motion is reduced, which affects manual dexterity, such as causing difficulties in writing; therefore, early detection of CTS by screening is desirable. To develop a screening method for CTS, we developed a tablet app to measure the stylus trajectory and pressure of the stylus tip when drawing a spiral on a tablet screen using a stylus and, subsequently, used these data as training data to predict the classification of participants as non-CTS or CTS patients using a support vector machine. We recruited 33 patients with CTS and 31 healthy volunteers for this study.
View Article and Find Full Text PDF