Technology and Health Care最新文献

BackgroundIn recent years, the importance of chemical experiments has increased, and the frequency of chemical experiments has also increased. As the frequency of chemical experiments increases, the number of chemical experiment-related accidents increases proportionally.ObjectiveAccordingly, we design a remote control biomimetic robotic arm that can safely and actively handle hazardous chemicals on behalf of human to reduce human casualties caused by chemical experiment accidents without compromising the autonomy of experimentation.MethodsThis biomimetic robotic arm can identically mimic the operator arm's movement. The robotic arm moves with 6 degrees of freedom (DOF). The inertial measurement unit (IMU) sensor we designed ourselves is based on micro-electromechanical system (MEMS) technology, and in the IMU sensor the accelerometer-gyroscope sensor and the wireless communication module are integrated. This IMU sensor calculates its own instantaneous angle on a particular axis. The micro controller unit (MCU) controls motor using the angle data of the IMU sensor so that the robotic arm moves in the same movement as the operator arm to which the IMU sensor is attached.ResultsThree IMU sensors were attached to the operator's upper body, upper arm, and lower arm, enabling the robotic arm to accurately replicate the operator's movements. Performance evaluation through comparative experiments confirmed that the robotic arm closely tracked the operator's joint motion and overall trajectory. Although a time delay of approximately 1.4 s was observed due to communication and processing latency, the system maintained stable performance under various motion and load conditions, with joint angle errors remaining below 5.2%.ConclusionThe proposed system enables biomimetic motion of a robotic arm using IMU-based sensing and wireless control, allowing hazardous chemicals to be handled safely during chemical experiments.

BackgroundThe Parkinson's Image Self (PIS) Report app was developed to complement standard clinician-rated assessments, such as the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS), by enabling patients to digitally self-report Parkinson's disease (PD) symptoms, including pain, tremor, rigidity, and emotional states.ObjectiveTo evaluate PIS Report validity and digital health utility by comparing patient-reported outcomes with clinician-rated MDS-UPDRS assessments.MethodsSeventy-eight PD participants completed baseline assessments; 70 provided week-8 follow-up data. PIS outcomes were compared with MDS-UPDRS items using ANOVA, correlation analysis, chi-square tests, and Cohen's kappa statistics.ResultsPIS-derived pain scores differed significantly across MDS-UPDRS pain strata (Item 1.9; F = 4.48, p < 0.01). Head/neck and upper limb pain correlated with perceived OFF periods (r = 0.46-0.48, p < 0.001), while head/neck and lower limb pain correlated negatively with happiness (r = -0.35 to -0.41, p < 0.001). Tremor reports showed fair agreement with clinician ratings (χ² = 18.54, p < 0.001; κ = 0.36), whereas rigidity showed negligible agreement (χ² = 0.00, p = 1.000; κ = 0.01).ConclusionThe PIS Report provides a structured digital tool enhancing patient-clinician communication and remote monitoring by capturing pain, OFF states, and emotional symptoms. Integration with wearables and telemedicine may advance patient-centered PD care.Trial RegistrationCRIS (KCT0006646); ClinicalTrials.gov (NCT05621772).

BackgroundThis study aimed to predict the progression of acute pancreatitis by measuring the maximum cross-sectional area of the psoas major muscle at the level of the L3 vertebra (TPA).ObjectivesThis could enable quick and more proactive clinical interventions to reduce the mortality rates for moderate and severe acute pancreatitis.MethodsData were analyzed from 112 patients with acute pancreatitis who were categorized into mild, moderate, and severe groups based on the 2012 revised Atlanta classification criteria. The TPA values for all patients were measured and the ratios of each patient's TPA to the normal TPA were calculated. The patients were then divided into two groups: Group A (mild acute pancreatitis) and Group B (moderate-to-severe acute pancreatitis). Chi-square tests and receiver operating characteristic (ROC) curve analyses were applied to the TPA ratio data for both groups.ResultsSignificant differences were found between Groups A and B. Using each patient's TPA/normal TPA ratio as a parameter, the ROC curve identified a TPA/normal TPA threshold of 1.056, which achieved a sensitivity and specificity of 62.2% and 80%, respectively, with an area under the curve of 0.761.ConclusionsA smaller TPA significantly increased the risk of progression from acute pancreatitis to moderate or even severe acute pancreatitis.

BackgroundDetermining the type of arrhythmia is crucial for prevention and early diagnosis of cardiovascular diseases.ObjectiveThis aims to address potential information loss caused by preprocessing, improve model performance, and accurately identify multiple types of arrhythmias.MethodsThis study proposes the use of wavelet transform denoising and convolutional neural network (CNN) model to classify and identify six types of arrhythmias. The original electrocardiosignal was transformed into a two-dimensional gray image by construction, and the data were amplified by fixed template clipping. Then, six arrhythmias were identified using an improved two-dimensional CNN model.ResultsThe classification accuracy, sensitivity, and specificity of the proposed method reached 90.50%, 81.70%, and 97.16%, respectively, and six types of arrhythmias were accurately identified.ConclusionsThe results showed that the wavelet transform as a preprocessing method can effectively improve the classification accuracy of the multiple types of arrhythmias. The method proposed in this study can provide a new reference for clinicians in diagnosing arrhythmia.

ObjectiveThis analysis aims to examine studies on artificial intelligence (AI) applications in breast cancer diagnosis through bibliometric methods, focusing on temporal and geographical trends. It contributes to shaping the field's roadmap and helping researchers adapt to technological innovations.MethodA comprehensive search was conducted in the Web of Science (WOS) database. Bibliometric analyses of data from 2013-2024 were performed using VOSviewer and Bibliometrix R programs.ResultsThe analysis included 1537 articles. A significant rise in research activity was observed in 2019. The thematic analysis highlighted topics like histopathology, feature selection, deep learning, and machine learning. India was the most productive country with 405 studies. Keyword analysis showed increased usage of terms like transfer learning, CNN, and radiomics. U.S. was the most cited country with 7511 citations. Concept co-occurrence analysis revealed strong associations between terms such as feature selection, datasets, algorithm performance, and classification methods. Bejnordi's 2017 study was identified as the most influential, with 1909 citations.Discussion and ConclusionThis study identifies key authors, influential works, and trending topics, offering a broad understanding of the field's structure and evolution. It helps outline the advancements and emerging directions in AI applications for breast cancer diagnosis.

IntroductionThe purpose of this study was to examine the content quality and potential shortcomings of arthroplasty training videos on Instagram.Materials and MethodsA search on Instagram was performed from November 1, 2023, to April 30, 2024. The hashtags Replacement, Total knee replacement and Knee arthroplasty were translated into 6 different languages and searched on Instagram by 6 observers who are native speakers of those languages. The videos were scored using the DISCERN score and Global Quality Score (GQS). The extent to which the videos addressed the processes about which patients need to be informed was also examined.ResultA total of 126 videos were analyzed in this study. The median DISCERN and GQS scores were 3.0 [1.0-5.0] and 3.0 [2.0-5.0], respectively. The most frequently mentioned subheading was arthroplasty procedure and prosthesis technology (74%), followed by treatment options (66%). The least mentioned subheading was complications (19%), followed by return to social life (44%).ConclusionsThe main finding of this study was that knee arthroplasty videos posted on Instagram were lacking in data. Video content largely describes surgical techniques but is insufficient to inform patients about postoperative processes. The video content quality was found to be moderately good according to both video quality scores, and these quality scores were moderately correlated with the mention of subheadings.

BackgroundHypertension is one of the most important health-related problems worldwide, and its monitoring is necessary constantly.ObjectiveThe regular methods of blood pressure monitoring have disadvantages; hence, the interest in finding better solutions is stirred.MethodsIn this study, PPG signals from 218 subjects in Guilin People's Hospital were analyzed, where 657 PPG recordings were employed together with demographic and clinical data. CNN-Attention, CNN-GRU, and LSTM, have been conducted with z-score normalization and augmentation in an 80:20 train-test split.ResultsThe highest performance of the CNN-GRU model achieved 75% accuracy, an AUC-ROC of 0.658, and perfect recall for hypertensive cases at 1.00. While the CNN-Attention model reached an accuracy of 61%, the overall poorest performance was given by LSTM.ConclusionThese results prove that accessible cardiovascular monitoring is feasible and valuable in a resource-limited settings.