This study analyzed the capability of GPT-4o to properly identify knee osteoarthritis and found that the model had good sensitivity but poor specificity in identifying knee osteoarthritis; patients and clinicians should practice caution when using GPT-4o for image analysis in knee osteoarthritis.
Background: Cardiovascular diseases (CVDs) are the leading cause of death globally, and almost one-half of all adults in the United States have at least one form of heart disease. This review focused on advanced technologies, genetic variables in CVD, and biomaterials used for organ-independent cardiovascular repair systems.
Objective: A variety of implantable and wearable devices, including biosensor-equipped cardiovascular stents and biocompatible cardiac patches, have been developed and evaluated. The incorporation of those strategies will hold a bright future in the management of CVD in advanced clinical practice.
Methods: This study employed widely used academic search systems, such as Google Scholar, PubMed, and Web of Science. Recent progress in diagnostic and treatment methods against CVD, as described in the content, are extensively examined. The innovative bioengineering, gene delivery, cell biology, and artificial intelligence-based technologies that will continuously revolutionize biomedical devices for cardiovascular repair and regeneration are also discussed. The novel, balanced, contemporary, query-based method adapted in this manuscript defined the extent to which an updated literature review could efficiently provide research on the evidence-based, comprehensive applicability of cardiovascular devices for clinical treatment against CVD.
Results: Advanced technologies along with artificial intelligence-based telehealth will be essential to create efficient implantable biomedical devices, including cardiovascular stents. The proper statistical approaches along with results from clinical studies including model-based risk probability prediction from genetic and physiological variables are integral for monitoring and treatment of CVD risk.
Conclusions: To overcome the current obstacles in cardiac repair and regeneration and achieve successful therapeutic applications, future interdisciplinary collaborative work is essential. Novel cardiovascular devices and their targeted treatments will accomplish enhanced health care delivery and improved therapeutic efficacy against CVD. As the review articles contain comprehensive sources for state-of-the-art evidence for clinicians, these high-quality reviews will serve as a first outline of the updated progress on cardiovascular devices before undertaking clinical studies.
Background: Exercise is essential for physical rehabilitation, helping to improve functional performance and manage chronic conditions. Telerehabilitation offers an innovative way to deliver personalized exercise programs remotely, enhancing patient adherence and clinical outcomes. The Home Automated Telemanagement (HAT) System, integrated with the interactive bike (iBikE) system, was designed to support home-based rehabilitation by providing patients with individualized exercise programs that can be monitored remotely by a clinical rehabilitation team.
Objective: This study aims to evaluate the design, usability, and efficacy of the iBikE system within the HAT platform. We assessed the system's ability to enhance patient adherence to prescribed exercise regimens while minimizing patient and clinician burden in carrying out the rehabilitation program.
Methods: We conducted a quasi-experimental study with 5 participants using a pre- and posttest design. Usability testing included 2 primary tasks that participants performed with the iBikE system. Task completion times, adherence to exercise protocols, and user satisfaction were measured. A System Usability Scale (SUS) was also used to evaluate participants' overall experience. After an initial introduction, users performed the tasks independently following a 1-week break to assess retention of the system's operation skills and its functionality.
Results: Task completion times improved substantially from the pretest to the posttest: execution time for task 1 reduced from a mean of 8.6 (SD 4.7) seconds to a mean of 1.8 (SD 0.8) seconds, and the time for task 2 decreased from a mean of 315 (SD 6.9) seconds to a mean of 303.4 (SD 1.1) seconds. Adherence to the prescribed cycling speed also improved, with deviations from the prescribed speed reduced from a mean of 6.26 (SD 1.00) rpm (revolutions per minute) to a mean of 4.02 (SD 0.82) rpm (t=3.305, n=5, P=.03). SUS scores increased from a mean of 92 (SD 8.6) to a mean of 97 (SD 3.3), indicating high user satisfaction and confidence in system usability. All participants successfully completed both tasks without any additional assistance during the posttest phase, demonstrating the system's ease of use and effectiveness in supporting independent exercise.
Conclusions: The iBikE system, integrated into the HAT platform, effectively supports home-based telerehabilitation by enabling patients to follow personalized exercise prescriptions with minimal need for further training or supervision. The significant improvements in task performance and exercise adherence suggest that the system is well-suited for use in home-based rehabilitation programs, promoting sustained patient engagement and adherence to exercise regimens. Further studies with larger sample sizes are recommended to validate these findings and explore the long-term benefits of the syst
Background: Numerous studies have explored image processing techniques aimed at enhancing ultrasound images to narrow the performance gap between low-quality portable devices and high-end ultrasound equipment. These investigations often use registered image pairs created by modifying the same image through methods like down sampling or adding noise, rather than using separate images from different machines. Additionally, they rely on organ-specific features, limiting the models' generalizability across various imaging conditions and devices. The challenge remains to develop a universal framework capable of improving image quality across different devices and conditions, independent of registration or specific organ characteristics.
Objective: This study aims to develop a robust framework that enhances the quality of ultrasound images, particularly those captured with compact, portable devices, which are often constrained by low quality due to hardware limitations. The framework is designed to effectively process nonregistered ultrasound image pairs, a common challenge in medical imaging, across various clinical settings and device types. By addressing these challenges, the research seeks to provide a more generalized and adaptable solution that can be widely applied across diverse medical scenarios, improving the accessibility and quality of diagnostic imaging.
Methods: A retrospective analysis was conducted by using a cycle-consistent generative adversarial network (CycleGAN) framework enhanced with perceptual loss to improve the quality of ultrasound images, focusing on nonregistered image pairs from various organ systems. The perceptual loss was integrated to preserve anatomical integrity by comparing deep features extracted from pretrained neural networks. The model's performance was evaluated against corresponding high-resolution images, ensuring that the enhanced outputs closely mimic those from high-end ultrasound devices. The model was trained and validated using a publicly available, diverse dataset to ensure robustness and generalizability across different imaging scenarios.
Results: The advanced CycleGAN framework, enhanced with perceptual loss, significantly outperformed the previous state-of-the-art, stable CycleGAN, in multiple evaluation metrics. Specifically, our method achieved a structural similarity index of 0.2889 versus 0.2502 (P<.001), a peak signal-to-noise ratio of 15.8935 versus 14.9430 (P<.001), and a learned perceptual image patch similarity score of 0.4490 versus 0.5005 (P<.001). These results demonstrate the model's superior ability to enhance image quality while preserving critical anatomical details, thereby improving diagnostic usefulness.
Conclusions: This study presents a significant advancement in ultrasound imaging by leveraging a CycleGAN model enhanced with perceptual loss to bridge the quality gap
Background: Wearable sensors are rapidly evolving, particularly in health care, due to their ability to facilitate continuous or on-demand physiological monitoring.
Objective: This study aimed to design and validate a wearable sensor prototype incorporating photoplethysmography (PPG) and long-range wide area network technology for heart rate (HR) measurement during a functional test.
Methods: We conducted a transversal exploratory study involving 20 healthy participants aged between 20 and 30 years without contraindications for physical exercise. Initially, our laboratory developed a pulse wearable sensor prototype for HR monitoring. Following this, the participants were instructed to perform the Incremental Shuttle Walk Test while wearing the Polar H10 HR chest strap sensor (the reference for HR measurement) and the wearable sensor. This test allowed for real-time comparison of HR responses between the 2 devices. Agreement between these measurements was determined using the intraclass correlation coefficient (ICC3.1) and Lin concordance correlation coefficient. The mean absolute percentage error was calculated to evaluate reliability or validity. Cohen d was used to calculate the agreement's effect size.
Results: The mean differences between the Polar H10 and the wearable sensor during the test were -2.6 (95% CI -3.5 to -1.8) for rest HR, -4.1 (95% CI -5.3 to -3) for maximum HR, -2.4 (95% CI -3.5 to -1.4) for mean test HR, and -2.5 (95% CI -3.6 to -1.5) for mean recovery HR. The mean absolute percentage errors were -3% for rest HR, -2.2% for maximum HR, -1.8% for mean test HR, and -1.6% for recovery HR. Excellent agreement was observed between the Polar H10 and the wearable sensor for rest HR (ICC3.1=0.96), mean test HR (ICC3.1=0.92), and mean recovery HR (ICC3.1=0.96). The agreement for maximum HR (ICC3.1=0.78) was considered good. By the Lin concordance correlation coefficient, the agreement was found to be substantial for rest HR (rc=0.96) and recovery HR (rc=0.96), moderate for mean test HR (rc=0.92), and poor for maximum HR (rc=0.78). The power of agreement between the Polar H10 and the wearable sensor prototype was large for baseline HR (Cohen d=0.97), maximum HR (Cohen d=1.18), and mean recovery HR (Cohen d=0.8) and medium for mean test HR (Cohen d= 0.76).
Conclusions: The pulse-wearable sensor prototype tested in this study proves to be a valid tool for monitoring HR at rest, during functional tests, and during recovery compared with the Polar H10 reference device used in the laboratory setting.
Background: Long-term unobtrusive monitoring of breathing patterns can potentially give a more realistic insight into the respiratory health of people with asthma or chronic obstructive pulmonary disease than brief tests performed in medical environments. However, it is uncertain whether users would be willing to wear these sensor garments long term.
Objective: Our objective was to explore whether users would wear ordinary looking knitted garments with unobtrusive knitted-in breathing sensors long term to monitor their lung health and under what conditions.
Methods: Multiple knitted breathing sensor garments, developed and fabricated by the research team, were presented during a demonstration. Participants were encouraged to touch and feel the garments and ask questions. This was followed by two semistructured, independently led focus groups with a total of 16 adults, of whom 4 had asthma. The focus group conversations were recorded and transcribed. Thematic analysis was carried out by three independent researchers in 3 phases consisting of familiarization with the data, independent coding, and overarching theme definition. Participants also completed a web-based questionnaire to probe opinion about wearability and functionality of the garments. Quantitative analysis of the sensors' performance was mapped to participants' garment preference to support the feasibility of the technology for long-term wear.
Results: Key points extracted from the qualitative data were (1) garments are more likely to be worn if medically prescribed, (2) a cotton vest worn as underwear was preferred, and (3) a breathing crisis warning system was seen as a promising application. The qualitative analysis showed a preference for a loose-fitting garment style with short sleeves (13/16 participants), 11 out of 16 would also wear snug fitting garments and none of the participants would wear tight-fitting garments over a long period of time. In total, 10 out of 16 participants would wear the snug fitting knitted garment for the whole day and 13 out of 16 would be happy to wear it only during the night if not too hot. The sensitivity demands on the knitted wearable sensors can be aligned with most users' garment preferences (snug fit).
Conclusions: There is an overall positive opinion about wearing a knitted sensor garment over a long period of time for monitoring respiratory health. The knit cannot be tight but a snugly fitted vest as underwear in a breathable material is acceptable for most participants. These requirements can be fulfilled with the proposed garments. Participants with asthma supported using it as a sensor garment connected to an asthma attack alert system.
Background: Stroke therapy is essential to reduce impairments and improve motor movements by engaging autogenous neuroplasticity. Traditionally, stroke rehabilitation occurs in inpatient and outpatient rehabilitation facilities. However, recent literature increasingly explores moving the recovery process into the home and integrating technology-based interventions. This study advances this goal by promoting in-home, autonomous recovery for patients who experienced a stroke through robotics-assisted rehabilitation and classifying stroke residual severity using machine learning methods.
Objective: Our main objective is to use kinematics data collected during in-home, self-guided therapy sessions to develop supervised machine learning methods, to address a clinician's autonomous classification of stroke residual severity-labeled data toward improving in-home, robotics-assisted stroke rehabilitation.
Methods: In total, 33 patients who experienced a stroke participated in in-home therapy sessions using Motus Nova robotics rehabilitation technology to capture upper and lower body motion. During each therapy session, the Motus Hand and Motus Foot devices collected movement data, assistance data, and activity-specific data. We then synthesized, processed, and summarized these data. Next, the therapy session data were paired with clinician-informed, discrete stroke residual severity labels: "no range of motion (ROM)," "low ROM," and "high ROM." Afterward, an 80%:20% split was performed to divide the dataset into a training set and a holdout test set. We used 4 machine learning algorithms to classify stroke residual severity: light gradient boosting (LGB), extra trees classifier, deep feed-forward neural network, and classical logistic regression. We selected models based on 10-fold cross-validation and measured their performance on a holdout test dataset using F1-score to identify which model maximizes stroke residual severity classification accuracy.
Results: We demonstrated that the LGB method provides the most reliable autonomous detection of stroke severity. The trained model is a consensus model that consists of 139 decision trees with up to 115 leaves each. This LGB model boasts a 96.70% F1-score compared to logistic regression (55.82%), extra trees classifier (94.81%), and deep feed-forward neural network (70.11%).
Conclusions: We showed how objectively measured rehabilitation training paired with machine learning methods can be used to identify the residual stroke severity class, with efforts to enhance in-home self-guided, individualized stroke rehabilitation. The model we trained relies only on session summary statistics, meaning it can potentially be integrated into similar settings for real-time classification, such as outpatient rehabilitation facilities.
Background: Determining maximum oxygen uptake (VO2max) is essential for evaluating cardiorespiratory fitness. While laboratory-based testing is considered the gold standard, sports watches or fitness trackers offer a convenient alternative. However, despite the high number of wrist-worn devices, there is a lack of scientific validation for VO2max estimation outside the laboratory setting.
Objective: This study aims to compare the Apple Watch Series 7's performance against the gold standard in VO2max estimation and Apple's validation findings.
Methods: A total of 19 participants (7 female and 12 male), aged 18 to 63 (mean 28.42, SD 11.43) years were included in the validation study. VO2max for all participants was determined in a controlled laboratory environment using a metabolic gas analyzer. Thereby, they completed a graded exercise test on a cycle ergometer until reaching subjective exhaustion. This value was then compared with the estimated VO2max value from the Apple Watch, which was calculated after wearing the watch for at least 2 consecutive days and measured directly after an outdoor running test.
Results: The measured VO2max (mean 45.88, SD 9.42 mL/kg/minute) in the laboratory setting was significantly higher than the predicted VO2max (mean 41.37, SD 6.5 mL/kg/minute) from the Apple Watch (t18=2.51; P=.01) with a medium effect size (Hedges g=0.53). The Bland-Altman analysis revealed a good overall agreement between both measurements. However, the intraclass correlation coefficient ICC(2,1)=0.47 (95% CI 0.06-0.75) indicated poor reliability. The mean absolute percentage error between the predicted and the actual VO2max was 15.79%, while the root mean square error was 8.85 mL/kg/minute. The analysis further revealed higher accuracy when focusing on participants with good fitness levels (mean absolute percentage error=14.59%; root-mean-square error=7.22 ml/kg/minute; ICC(2,1)=0.60 95% CI 0.09-0.87).
Conclusions: Similar to other smartwatches, the Apple Watch also overestimates or underestimates the VO2max in individuals with poor or excellent fitness levels, respectively. Assessing the accuracy and reliability of the Apple Watch's VO2max estimation is crucial for determining its suitability as an alternative to laboratory testing. The findings of this study will apprise researchers, physical training professionals, and end users of wearable technology, thereby enhancing the knowledge base and practical application of such devices in assessing cardiorespiratory fitness parameters.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：