Yun Kwan Kim

Cancer remains a leading cause of mortality worldwide. Chemotherapy is effective but can cause febrile neutropenia, deplete neutrophils, and increase infection risk. Although timely fever detection is critical to prevent complications, periodic temperature monitoring has inherent limitations. Wearable devices (WDs) for real-time body temperature (RBT) monitoring are emerging as tools for early fever detection, though their clinical feasibility and usability remain unverified. This study assessed the clinical feasibility of a novel WD by comparing its temperature concordance and fever detection capability against a standard reference in patients with cancer. The RBT system’s clinical maturity, including its capacity for early fever detection and monitoring treatment-related changes, was evaluated. Furthermore, satisfaction among clinicians and patients was analyzed in a hospital setting. In this prospective study, patients with hematologic malignancies at high infection risk admitted to the Chonnam National University in Hwasun Hospital, South Korea, were enrolled. Data from 47 patients were analyzed to compare MT100D as WD (SEERS Technology Co., Ltd., South Korea) readings with axillary thermometers. Temperature concordance was evaluated using the intraclass correlation coefficient (ICC), and diagnostic performance was compared with the reference thermometer. The early fever detection performance of the MT100D was analyzed to evaluate the clinical effectiveness of the early response system. Usability was evaluated through a five-point Likert scale survey completed by clinical nurses. The MT100D demonstrated good agreement with the reference thermometer (mean difference: −0.19 ± 0.35 °C; ICC: 0.78). The RBT system achieved sensitivity, specificity, and area under the receiver operating characteristic curve values of 81.50%, 96.32%, and 96.60%, respectively. The early fever detection rate was 77.1%, with the RBT system detecting fever an average of 1.13 ± 1.28 h earlier than the reference. Usability and satisfaction assessments showed high patient satisfaction (mean 4.69 ± 0.5; range 4.57–4.80) and moderate clinician satisfaction (mean 3.63 ± 0.75; range 2.89–4.11). Among patients with cancer, including those at risk of febrile neutropenia, the MT100D demonstrated strong concordance with standard thermometry, enabling early fever detection. The RBT system shows promise for the early identification of neutropenic risk during chemotherapy.

Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms. However, forming a CDSS for the arrhythmia classification task is challenging due to the varying lengths of arrhythmias. Although the onset time of arrhythmia varies, previously developed methods have not considered such conditions. Thus, we propose a framework that consists of 1) local and global extraction and 2) local-global information fusion with attention to enable arrhythmia detection and classification within a constrained input length. The framework’s performance was evaluated in terms of 10-class and 4-class arrhythmia detection, focusing on identifying the onset and ending point of arrhythmia episodes and their duration using the MIT-BIH arrhythmia database (MITDB) and the MIT-BIH atrial fibrillation database (AFDB). Duration, episode, and Dice score performances resulted in overall F1-scores of 96.45%, 82.05%, and 96.31% on the MITDB and 97.57%, 98.31%, and 97.45% on the AFDB, respectively. The results demonstrated statistically superior performance compared to those of the benchmark models. To assess the generalization capability of the proposed method, an MITDB-trained model and MIT-BIH malignant ventricular arrhythmia database-trained model were tested AFDB and MITDB, respectively. Superior performance was attained compared with that of a state-of-the-art model. The proposed method effectively captures both local and global information and dynamics without significant information loss. Consequently, arrhythmias can be detected with greater accuracy, and their occurrence times can be precisely determined, enabling the clinical field to develop more accurate treatment plans based on the proposed method.

Continuous and noninvasive blood pressure (BP) monitoring is essential for the early detection and management of hypertension. Cuffless BP estimation using photoplethysmography (PPG) has emerged as a promising alternative to traditional methods. However, most calibration-based approaches underestimate the physiological link between PPG signals and BP values. In this study, we propose a lightweight and efficient framework using affine-transformed triple PPG signals and self-attention. The proposed framework predicts BP by leveraging both calibration BP values and multiple forms of PPG signals, including its first and second derivatives. The proposed model consists of a CNN-based feature extractor for encoding the input signals, an attention mechanism using a residual block with squeeze-and-excitation to enhance channel-wise representations, and a regression module for estimating systolic and diastolic BP. A key novelty lies in the use of an affine transformation that integrates calibration BP values into the signal features without relying on additional neural networks. The proposed framework is evaluated on two public datasets, VitalDB and BP-UCI, comprising over 4,900 independent cases. It satisfies both the Association for the Advancement of Medical Instrumentation standard and the British Hypertension Society Grade A criteria. Comparative and ablation studies demonstrate that our proposed model consistently outperforms state-of-the-art machine learning and deep learning models in both accuracy and clinical reliability. The results confirms that it provides a generalizable, low-cost solution for cuffless BP estimation, with strong potential for real-time deployment in wearable healthcare systems.

Stroke is a significant impediment on a global scale, with the prognosis for motor ability contingent on initial rehabilitation and the severity of the injury. Consequently, the predictability of early recovery potential for personalized rehabilitation is crucial. However, studies predicting the prognosis of motor ability are still limited in performance. In this study, we propose a novel framework, called dual-stream dynamic convolution network (DualDyConvNet), to predict motor recovery for two months using resting-state electroencephalogram data in the subacute phase. Specifically, the channel-stream emphasizes distinct characteristics within each frequency band, while the spatial-stream integrates information across frequency bands to capture spatial patterns. We utilized the SMC and KIST datasets consisting of subacute stroke patients, and recovery potential was quantified using Fugl-Meyer Assessment of upper limb. As a result, we achieved average root mean squared error (RMSE) of 0.070 ± 0.045 and 0.223 ± 0.148 on the two datasets, respectively. This outperformed existing models, confirming the efficacy of our framework. Moreover, external (cross-dataset) validation was conducted under two conditions of with and without Euclidean-space alignment (EA) application, and DualDyConvNet outperformed comparative models, demonstrating strong generalization: pre-trained on SMC, it achieved mean RMSEs of 0.218 ± 0.172 (w/o EA) and 0.215 ± 0.201 (w/ EA); pre-trained on KIST, 0.160 ± 0.087 (w/o EA) and 0.135 ± 0.087 (w/ EA). The proposed framework holds significant potential in facilitating early rehabilitation planning by predicting motor function prognosis in stroke patients. Furthermore, it can contribute to enhancing the quality of life by providing patients with prognostication.

BACKGROUND Sleep plays a crucial role in the immune system, memory, and emotional control, which in turn affects overall quality of life. Although several studies have used wearable devices to measure sleep efficiency, these tools primarily monitor sleep patterns without offering strategies to improve sleep efficiency. OBJECTIVE In response, our study introduced a framework that not only measures sleep efficiency using wearable technology but also suggests lifestyle changes to enhance sleep quality, using explainable artificial intelligence. METHODS Lifelog data was measured using a smartwatch and only features that can be controlled by the user, such as the number of steps, were extracted from the lifelog data. A light gradient-boosted machine was utilized as a classifier to predict whether sleep efficiency was low or high. Using Shapley additive explanation, important features related to sleep efficiency, such as walking speed were identified and lifestyles were recommended to improve sleep efficiency. We also investigated the relationship between sleep efficiency and sleep stages, which were excluded from the features extracted as uncontrolled factors from wearable devices. RESULTS Results show that, following a 10-fold leave-one-subject-out cross-validation evaluation, an accuracy rate of 80% was achieved in measuring sleep efficiency. In a scenario where lifestyle was adjusted according to the feature importance derived from the model output, an improvement from bad to good sleep efficiency was observed. In addition, the sleep stage variables were found to be statistically higher for the cases exhibiting good sleep efficiency. CONCLUSIONS This framework provides insights into developing technologies that suggest lifestyle changes to enhance sleep efficiency, potentially leading to better health outcomes through improved sleep quality.

BACKGROUND Cancer is among the leading causes of mortality worldwide. Chemotherapy is an effective treatment for patients with cancer; however, febrile neutropenia after chemotherapy may result in decreased neutrophils, increasing infection risk. Although early fever detection is crucial for infection prevention, periodic temperature measurements have inherent limitations. Wearable devices (WD) that use real-time body temperature (RBT) measurements are currently being developed to detect fever. However, their clinical maturity and usability remain unverified. OBJECTIVE We evaluated the clinical feasibility of a novel WD by comparing temperature agreement and early fever detection between the WD and a reference in patients with cancer. We also verified the clinical maturity of the RBT monitoring system, including its capacity for early fever detection and monitoring cancer treatment and post-treatment changes. Finally, satisfaction and convenience of use for clinicians and patients were analyzed when the WD-based RBT monitoring system was applied in a hospital setting. METHODS This prospective study included patients with hematologic diseases and high-risk infections in the cancer ward of Chonnam National University in Hwasun. We used data from 47 patients to establish the inclusion and exclusion criteria for early fever detection and temperature comparison between the reference and WD groups. We assessed the body temperature agreement between the MT100D (SEERS Technology Co., Ltd.) as the WD and an auxiliary thermometer as a reference. We further evaluated the MT100D’s early fever detection rate and the early response system’s clinical efficiency based on fever detection. Finally, we performed a usability test to check the satisfaction and convenience of users and clinicians using the RBT monitoring system. RESULTS A comparison of the MT100D and the reference revealed an average difference of -0.19 ± 0.35°C and an inter-class correlation coefficient of 0.78, indicating good agreement. Subsequently, the fever detection performance of the RBT monitoring system achieved sensitivity, specificity, and an area under the receiver operating characteristic curve of 81.50%, 96.32%, and 96.60%, respectively. The early fever detection rate was 75.0%, and our RBT system detected fever 1.24 hours earlier than the reference. In a survey, the MT100D and RBT monitoring systems received high ratings of 4.81 and 3.81 out of 5 points, respectively. CONCLUSIONS Among patients with cancer, including those at a high risk of fever, the MT100D demonstrated a good degree of agreement with the reference. This demonstrates the RBT monitoring system’s high early fever detection rate. Consequently, the RBT monitoring system utilizing MT100D can be employed as a reliable system for early detection of neutropenia risk in patients undergoing chemotherapy. CLINICALTRIAL KCT0008874