Automatic Sleep Stage Classification Using Nasal Pressure Decoding Based on a Multi-Kernel Convolutional BiLSTM Network.

Sleep quality is an essential parameter of a healthy human life, while sleep disorders such as sleep apnea are abundant. In the investigation of sleep and its malfunction, the gold-standard is polysomnography, which utilizes an extensive range of variables for sleep stage classification. However, undergoing full polysomnography, which requires many sensors that are directly connected to the heaviness of the setup and the discomfort of sleep, brings a significant burden. In this study, sleep stage classification was performed using the single dimension of nasal pressure, dramatically decreasing the complexity of the process. In turn, such improvements could increase the much needed clinical applicability. Specifically, we propose a deep learning structure consisting of multi-kernel convolutional neural networks and bidirectional long short-term memory for sleep stage classification. Sleep stages of 25 healthy subjects were classified into 3-class (wake, rapid eye movement (REM), and non-REM) and 4-class (wake, REM, light, and deep sleep) based on nasal pressure. Following a leave-one-subject-out cross-validation, in the 3-class the accuracy was 0.704, the F1-score was 0.490, and the kappa value was 0.283 for the overall metrics. In the 4-class, the accuracy was 0.604, the F1-score was 0.349, and the kappa value was 0.217 for the overall metrics. This was higher than the four comparative models, including the class-wise F1-score. This result demonstrates the possibility of a sleep stage classification model only using easily applicable and highly practical nasal pressure recordings. This is also likely to be used with interventions that could help treat sleep-related diseases.

Palbociclib in adults aged 70 years and older with advanced breast cancer: A phase 2 multicenter trial (Alliance A171601).

INTRODUCTION: Palbociclib is a widely used treatment for advanced breast cancer in older adults. However, the existing evidence regarding its safety and tolerability in this age group is inconsistent and limited to retrospective subgroup or pooled analyses. MATERIALS AND METHODS: We conducted a prospective single-arm multicenter phase 2 study to evaluate the safety and tolerability of palbociclib in participants aged 70 years or older with advanced hormone receptor-positive breast cancer. Participants were given palbociclib in combination with their physician's choice of endocrine therapy (letrozole or fulvestrant). The primary endpoint was the incidence of grade 3+ adverse events (AEs) by six months. Secondary endpoints included AE-related dose delays, dose reductions, early discontinuations, and hospitalizations. Additionally, we compared these endpoints by age groups (70-74 and ≥ 75 years). RESULTS: Of the 90 participants (median age 74 years [70-87]) enrolled, 75.6% (95% confidence interval [CI], 65.4-84.0) had grade 3+ AEs by six months. The most frequent grade 3+ AEs were neutropenia (61%), fatigue (4%), and nausea (3%). Febrile neutropenia was uncommon (1.1%). Due to AEs, 36% had dose delays, 34% had dose reductions, 10% had early discontinuations, and 10% had hospitalizations. Compared to those aged 70-74 years, participants aged ≥75 years had higher rates of early discontinuations (5.9% vs 15.9%, a difference of 9.5% [95% CI 3.5%-22.5%]). DISCUSSION: Palbociclib has an overall favorable safety profile in adults aged ≥70 with advanced breast cancer. However, adults ≥75 years had a trend toward higher rates of AE-related early discontinuations compared to those 70-74 years. Further research is needed to evaluate tolerability and improve the delivery of palbociclib in older adults. CLINICALTRIALS: gov:NCT03633331.

Optimization of alert notifications in electronic patient-reported outcome (ePRO) remote symptom monitoring systems (AFT-39).

PURPOSE: Clinical benefits result from electronic patient-reported outcome (ePRO) systems that enable remote symptom monitoring. Although clinically useful, real-time alert notifications for severe or worsening symptoms can overburden nurses. Thus, we aimed to algorithmically identify likely non-urgent alerts that could be suppressed. METHODS: We evaluated alerts from the PRO-TECT trial (Alliance AFT-39) in which oncology practices implemented remote symptom monitoring. Patients completed weekly at-home ePRO symptom surveys, and nurses received real-time alert notifications for severe or worsening symptoms. During parts of the trial, patients and nurses each indicated whether alerts were urgent or could wait until the next visit. We developed an algorithm for suppressing alerts based on patient assessment of urgency and model-based predictions of nurse assessment of urgency. RESULTS: 593 patients participated (median age = 64 years, 61% female, 80% white, 10% reported never using computers/tablets/smartphones). Patients completed 91% of expected weekly surveys. 34% of surveys generated an alert, and 59% of alerts prompted immediate nurse actions. Patients considered 10% of alerts urgent. Of the remaining cases, nurses considered alerts urgent more often when patients reported any worsening symptom compared to the prior week (33% of alerts with versus 26% without any worsening symptom, p = 0.009). The algorithm identified 38% of alerts as likely non-urgent that could be suppressed with acceptable discrimination (sensitivity = 80%, 95% CI [76%, 84%]; specificity = 52%, 95% CI [49%, 55%]). CONCLUSION: An algorithm can identify remote symptom monitoring alerts likely to be considered non-urgent by nurses, and may assist in fostering nurse acceptance and implementation feasibility of ePRO systems.

IL-7-primed bystander CD8 tumor-infiltrating lymphocytes optimize the antitumor efficacy of T cell engager immunotherapy.

Bispecific T cell engagers (TCEs) show promising clinical efficacy in blood tumors, but their application to solid tumors remains challenging. Here, we show that Fc-fused IL-7 (rhIL-7-hyFc) changes the intratumoral CD8 T cell landscape, enhancing the efficacy of TCE immunotherapy. rhIL-7-hyFc induces a dramatic increase in CD8 tumor-infiltrating lymphocytes (TILs) in various solid tumors, but the majority of these cells are PD-1-negative tumor non-responsive bystander T cells. However, they are non-exhausted and central memory-phenotype CD8 T cells with high T cell receptor (TCR)-recall capacity that can be triggered by tumor antigen-specific TCEs to acquire tumoricidal activity. Single-cell transcriptome analysis reveals that rhIL-7-hyFc-induced bystander CD8 TILs transform into cycling transitional T cells by TCE redirection with decreased memory markers and increased cytotoxic molecules. Notably, TCE treatment has no major effect on tumor-reactive CD8 TILs. Our results suggest that rhIL-7-hyFc treatment promotes the antitumor efficacy of TCE immunotherapy by increasing TCE-sensitive bystander CD8 TILs in solid tumors.

Genomic Analysis of Monkeypox Virus During the 2023 Epidemic in Korea.

We aimed to characterize the genomes of monkeypox virus isolates from the Far East, providing insights into viral transmission and evolution. Genomic analysis was conducted on 8 isolates obtained from patients with monkeypox virus disease in the Republic of Korea between May 2022 and early 2023. These isolates were classified into Clade IIb. Distinct lineages, including B.1.1, A.2.1, and B.1.3, were observed in 2022 and 2023 isolates, with only the B.1.3 lineage detected in six isolates of 2023. These genetic features were specific to Far East isolates (the Republic of Korea, Japan, and Taiwan), distinguishing them from the diverse lineages found in the Americas, Europe, Africa, and Oceania. In early 2023, the prevalence of the B.1.3 lineage of monkeypox virus identified in six patients with no overseas travel history is considered as an indicator of the potential initiation of local transmission in the Republic of Korea.

Digital wearable insole-based identification of knee arthropathies and gait signatures using machine learning.

Gait is impaired in musculoskeletal conditions, such as knee arthropathy. Gait analysis is used in clinical practice to inform diagnosis and monitor disease progression or intervention response. However, clinical gait analysis relies on subjective visual observation of walking as objective gait analysis has not been possible within clinical settings due to the expensive equipment, large-scale facilities, and highly trained staff required. Relatively low-cost wearable digital insoles may offer a solution to these challenges. In this work, we demonstrate how a digital insole measuring osteoarthritis-specific gait signatures yields similar results to the clinical gait-lab standard. To achieve this, we constructed a machine learning model, trained on force plate data collected in participants with knee arthropathy and controls. This model was highly predictive of force plate data from a validation set (area under the receiver operating characteristics curve [auROC] = 0.86; area under the precision-recall curve [auPR] = 0.90) and of a separate, independent digital insole dataset containing control and knee osteoarthritis subjects (auROC = 0.83; auPR = 0.86). After showing that digital insole-derived gait characteristics are comparable to traditional gait measurements, we next showed that a single stride of raw sensor time-series data could be accurately assigned to each subject, highlighting that individuals using digital insoles can be identified by their gait characteristics. This work provides a framework for a promising alternative to traditional clinical gait analysis methods, adds to the growing body of knowledge regarding wearable technology analytical pipelines, and supports clinical development of at-home gait assessments, with the potential to improve the ease, frequency, and depth of patient monitoring.

The way we walk ­ our 'gait' ­ is a key indicator of health. Gait irregularities like limping, shuffling or a slow pace can be signs of muscle or joint problems. Assessing a patient's gait is therefore an important element in diagnosing these conditions, and in evaluating whether treatments are working. Gait is often assessed via a simple visual inspection, with patients being asked to walk back and forth in a doctor's office. While quick and easy, this approach is highly subjective and therefore imprecise. 'Objective gait analysis' is a more accurate alternative, but it relies on tests being conducted in specialised laboratories with large-scale, expensive equipment operated by highly trained staff. Unfortunately, this means that gait laboratories are not accessible for everyday clinical use. In response, Wipperman et al. aimed to develop a low-cost alternative to the complex equipment used in gait laboratories. To do this, they harnessed wearable sensor technologies ­ devices that can directly measure physiological data while embedded in clothing or attached to the user. Wearable sensors have the advantage of being cheap, easy to use, and able to provide clinically useful information without specially trained staff. Wipperman et al. analysed data from classic gait laboratory devices, as well as 'digital insoles' equipped with sensors that captured foot movements and pressure as participants walked. The analysis first 'trained' on data from gait laboratories (called force plates) and then applied the method to gait measurements obtained from digital insoles worn by either healthy participants or patients with knee problems. Analysis of the pressure data from the insoles confirmed that they could accurately predict which measurements were from healthy individuals, and which were from patients. The gait characteristics detected by the insoles were also comparable to lab-based measurements ­ in other words, the insoles provided similar type and quality of data as a gait laboratory. Further analysis revealed that information from just a single step could reveal additional information about the subject's walking. These results support the use of wearable devices as a simple and relatively inexpensive way to measure gait in everyday clinical practice, without the need for specialised laboratories and visits to the doctor's office. Although the digital insoles will require further analytical and clinical study before they can be widely used, Wipperman et al. hope they will eventually make monitoring muscle and joint conditions easier and more affordable.

Multi-Task Heterogeneous Ensemble Learning-Based Cross-Subject EEG Classification Under Stroke Patients.

Robot-assisted motor training is applied for neurorehabilitation in stroke patients, using motor imagery (MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing movement challenges. However, the effectiveness of training with MI may vary depending on the location of the stroke lesion, which should be considered. This paper introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature extraction, and the features according to stroke lesions are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used as classifiers. Nine patients with chronic ischemic stroke participated, engaging in MI and motor execution (ME) paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways, taking into account the characteristics of stroke patients. In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270) in ME. The second task focused on motor assessment for lesion location, resulting in a performance of 0.7457 (±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing the specific-subject session, except for ME on the motor assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore, classification performance was similar to or statistically higher in cross-subject sessions compared to baseline models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings and facilitating the detection of lesions.

PRO-Angoff method for remote standard setting: establishing clinical thresholds for the upper digestive disease tool.

BACKGROUND: The Upper Digestive Disease (UDD) Tool™ is used to monitor symptom frequency, intensity, and interference across nine symptom domains and includes two Patient-Reported Outcome Measurement Information System (PROMIS) domains assessing physical and mental health. This study aimed to establish cut scores for updated symptom domains through standard setting exercises and evaluate the effectiveness and acceptability of virtual standard setting. METHODS: The extended Angoff method was employed to determine cut scores. Subject matter experts refined performance descriptions for symptom control categories and achieved consensus. Domains were categorized into good, moderate, and poor symptom control. Two cut scores were established, differentiating good vs. moderate and moderate vs. poor. Panelists estimated average scores for 100 borderline patients per item. Cut scores were computed based on the sum of the average ratings for individual questions, converted to 0-100 scale. RESULTS: Performance descriptions were refined. Panelists discussed that interpretation of the scores should take into account the timing of symptoms after surgery and patient populations, and the importance of items asking symptom frequency, severity, and interference with daily life. The good/moderate cut scores ranged from 21.3 to 35.0 (mean 28.6, SD 3.6) across domains, and moderate/poor ranged from 47.5 to 71.3 (mean 54.5, SD 7.0). CONCLUSIONS: Panelists were confident in the virtual standard setting process, expecting valid cut scores. Future studies can further validate the cut scores using patient perspectives and collect patient and physician preferences for displaying contextual items on patient- and physician-facing dashboard.

rhIL-7-hyFc and hIL-2/TCB2c combination promotes an immune-stimulatory tumor microenvironment that improves antitumor efficacy of checkpoint inhibitors.

BACKGROUND: Recombinant human interleukin (rhIL)-7-hyFc (efineptakin alfa; NT-I7) is a potent T-cell amplifier, with two IL-7 molecules fused to IgD/IgG4 elements. rhIL-7-hyFc promotes extensive infiltration of CD8+ T cells into the tumor, concurrently increasing the numbers of intratumoral PD-1+CD8+ T cells. The hIL-2/TCB2 complex (SLC-3010) inhibits tumor growth by preferential activation of CD122 (IL-2Rß)high CD8+ T cells and natural killer cells, over regulatory T cells (Tregs). We investigated the underlying mechanisms of rhIL-7-hyFc and hIL-2/TCB2c antitumor activity and the potential synergistic efficacy, specifically focusing on tumor-specific CD8+ cells within the tumor and the tumor-draining lymph nodes (tdLN). METHODS: MC38 and CT26 tumor-bearing mice were administered with 10 mg/kg rhIL-7-hyFc intramuscularly and 0.9 mg/kg hIL-2/TCB2c intravenously. Anti-PD-1 monoclonal antibody was administered intraperitoneally three times at 3-day intervals at a dose of 5 mg/kg. Tumor volume was measured to assess efficacy. To compare the composition of immune cells between each monotherapy and the combination therapy, we analyzed tumors and tdLNs by flow cytometry. RESULTS: Our data demonstrate that the combination of rhIL-7-hyFc and hIL-2/TCB2c increases efficacy and generates an immune-stimulatory tumor microenvironment (TME). The TME is characterized by an increased infiltration of tumor-specific CD8+ T cells, and a decreased frequency of CD39highTIM-3+ Treg cells. Most importantly, rhIL-7-hyFc increases infiltration of a CD62L+Ly108+ early progenitor population of exhausted CD8+ T cells (TPEX), which may retain long-term proliferation capacity and replenish functional effector CD8+ T cells. hIL-2/TCB2c induces differentiation of CD62L+Ly108+ TPEX rapidly into CD101+ terminally differentiated subsets (terminally exhausted T cell (TEX term)). Our study also demonstrates that rhIL-7-hyFc significantly enhances the proliferation rate of TPEX in the tdLNs, positively correlating with their abundance within the tumor. Moreover, rhIL-7-hyFc and hIL-2/TCB2c can overcome the limited therapeutic effectiveness of PD-1 blockade, culminating in the complete regression of tumors. CONCLUSIONS: rhIL-7-hyFc can expand and maintain the progenitor pool of exhausted CD8+ T cells, whereas hIL-2/TCB2c promotes their differentiation into TEX term. Together, this induces an immune-stimulatory TME that improves the efficacy of checkpoint blockade.

Extending venous thromboembolism secondary prevention with apixaban in cancer patients. The EVE trial.

BACKGROUND: Cancer-associated venous thromboembolism (VTE) management guideline recommendations include continued therapeutic anticoagulation while active cancer persists. The Federal Drug Administration label for apixaban for secondary VTE prevention includes a dose reduction to 2.5 mg twice daily after 6 months of treatment. OBJECTIVES: The study's purpose was to determine whether this dose reduction is advisable for cancer-associated VTE. METHODS: A randomized, double-blind trial compared apixaban 2.5 mg with 5 mg twice daily for 12 months among cancer patients with VTE who had completed 6 to 12 months of anticoagulation therapy. The primary outcome was combined major bleeding plus clinically relevant nonmajor bleeding. RESULTS: Of 370 patients recruited, 360 were included in the intention-to-treat analyses. Major plus clinically relevant nonmajor bleeding occurred in 16 of 179 patients (8.9%) in the apixaban 2.5 mg group compared with 22 of 181 patients (12.2%) in the 5 mg group (hazard ratio [HR], 0.72; 95% CI, 0.38-1.37; P = .39). Major bleeding occurred in 2.8% of the apixaban 2.5 mg group and in 2.2% of the 5 mg group (HR, 1.26; 95% CI, 0.34-4.66; P = .73). Recurrent VTE or arterial thrombosis occurred in 9 of 179 patients (5.0%) in the apixaban 2.5 mg group and 9 of 181 patients (5.0%) in the 5 mg group (HR, 1.0; 95% CI, 0.40-2.53; P = 1.00). All-cause mortality rates were similar between groups, 13% vs 12% (HR, 1.14; 95% CI, 0.63-2.04; P = .67). CONCLUSION: For secondary prevention of cancer-associated VTE, apixaban 2.5 mg compared with 5 mg twice daily did not lower combined bleeding events (EVE trial NCT03080883).

Minimal effect of long-term clonazepam on cognitive function in patients with isolated rapid eye movement sleep behavior disorder.

STUDY OBJECTIVES: Despite its widespread use in patients with isolated rapid eye movement sleep behavior disorder (iRBD), the cognitive effect of clonazepam is uncertain. This study aimed to investigate the effect of cumulative clonazepam on cognitive function in patients with iRBD. METHODS: Demographic characteristics, baseline cognitive test, and most recent cognitive test information were collected retrospectively. Based on cumulative clonazepam doses, patients were classified into 4 subgroups: group 1, < 365 mg (1 mg × 1 year); group 2, 365 mg to < 1,095 mg (1 mg × 3 years); group 3, 1,095 mg to < 2,190 mg (1 mg × 6 years); and group 4, 2,190 mg or more. Cognitive test scores were calculated as z scores adjusted for age, education, and sex. RESULTS: This study included 101 patients with iRBD (63 males). Groups 1, 2, 3, and 4 had 14, 20, 32, and 35 patients, respectively. In within-group comparisons, follow-up Digit Span Backward test and the Trail Making Test A scores decreased in group 3, and follow-up Trail Making Test A and the Trail Making Test B scores decreased significantly in group 4. In the multiple regression analysis to determine influential factors on cognitive decline, cumulative clonazepam dose did not show a significant correlation with any cognitive domain. Follow-up cognitive function showed significant correlation only with baseline cognitive function. CONCLUSIONS: Memory and executive functions tended to decline in patients with iRBD. However, there was no significant effect of cumulative clonazepam. There was no evidence that long-term use of clonazepam was related to cognitive decline in patients with iRBD. CITATION: Lee M, Kim TK, Hong JK, Yoon I-Y. Minimal effect of long-term clonazepam on cognitive function in patients with isolated rapid eye movement sleep behavior disorder. J Clin Sleep Med. 2024;20(7):1173-1182.

Prolonged viral shedding in an immunocompromised Korean patient infected with hMPXV, sub-lineage B.1.3, with acquired drug resistant mutations during tecovirimat treatment.

Following the worldwide surge in mpox (monkeypox) in 2022, cases have persisted in Asia, including South Korea, and sexual contact is presumed as the predominant mode of transmission, with a discernible surge in prevalence among immunocompromised patients. Drugs such as tecovirimat can result in drug-resistant mutations, presenting obstacles to treatment. This study aimed to ascertain the presence of tecovirimat-related resistant mutations through genomic analysis of the monkeypox virus isolated from a reported case involving prolonged viral shedding in South Korea. Here, tecovirimat-resistant mutations, previously identified in the B.1 clade, were observed in the B.1.3 clade, predominant in South Korea. These mutations exhibited diverse patterns across different samples from the same patient and reflected the varied distribution of viral subpopulations in different anatomical regions. The A290V and A288P mutant strains we isolated hold promise for elucidating these mechanisms, enabling a comprehensive analysis of viral pathogenesis, replication strategies, and host interactions. Our findings imply that acquired drug-resistant mutations, may present a challenge to individual patient treatment. Moreover, they have the potential to give rise to transmitted drug-resistant mutations, thereby imposing a burden on the public health system. Consequently, the meticulous genomic surveillance among immunocompromised patients, conducted in this research, assumes paramount importance.

Heterogeneous osteoimmune profiles via single-cell transcriptomics in osteoporotic patients who fail bisphosphonate treatment.

Postmenopausal osteoporosis arises from imbalanced osteoclast and osteoblast activity, and mounting evidence suggests a role for the osteoimmune system in bone homeostasis. Bisphosphonate (BP) is an antiresorptive agent, but its treatment failure rate can be as high as 40%. Here, we performed single-cell RNA sequencing on peripheral immune cells from carefully selected postmenopausal women: non-osteoporotic, osteoporosis improved after BP treatment, and BP-failed cases. We found an increase in myeloid cells in patients with osteoporosis (specifically, T cell receptor+ macrophages). Furthermore, lymphoid lineage cells varied significantly, notably elevated natural killer cells (NKs) in the BP-failed group. Moreover, we provide fruitful lists of biomarkers within the immune cells that exhibit condition-dependent differences. The existence of osteoporotic- and BP-failure-specific cellular information flows was revealed by cell-cell interaction analysis. These findings deepen our insight of the osteoporosis pathology enhancing comprehension of the role of immune heterogeneity in postmenopausal osteoporosis and BP treatment failure.

Toxic dinoflagellate Centrodinium punctatum (Cleve) F.J.R. Taylor: An examination on the responses in growth and toxin contents to drastic changes of temperature and salinity.

To understand environmental effects affecting paralytic shellfish toxin production of Centrodinium punctatum, this study examined the growth responses, and toxin contents and profiles of a C. punctatum culture exposed to drastic changes of temperature (5-30 °C) and salinity (15-40). C. punctatum grew over a temperature range of 15-25 °C, with an optimum of 20 °C., and over a salinity range of 25-40, with optimum salinities of 30-35. This suggests that C. punctatum prefers relatively warm waters and an oceanic habitat for its growth and can adapt to significant changes of salinity levels. When C. punctatum was cultivated at different temperature and salinity levels, the PST profile included four major analogs (STX, neoSTX, GTX1 and GTX4, constituted >80 % of the profile), while low amounts of doSTX and traces of dc-STX and dc-GTX2 were also observed. Interestingly, though overall toxin contents did not change significantly with temperature, increases in the proportion of STX, and decreases in proportions in GTX1 and GTX4 were observed with higher temperatures. Salinity did not affect either toxin contents or profile from 25 to 35. However, the total toxin content dropped to approximately half at salinity 40, suggesting this salinity may induce metabolic changes in C. punctatum.

Molecular Detection and Phylogenetic Analysis of Tick-Borne Encephalitis Virus from Ticks Collected from Cattle in Kyrgyzstan, 2023.

Ticks are important vectors of the tick-borne encephalitis virus (TBEV). In Kyrgyzstan, the livestock farming trade and nomadic lifestyle enable tick-borne diseases to be imported from neighboring countries, but there are few relevant studies. In this study, we collected 40 ticks from cattle in Kyrgyzstan. Molecular marker analysis identified the ticks as Ixodes persulcatus (97.5%; n = 39) and Haemaphysalis punctata (2.5%; n = 1). Real-time PCR screening revealed two ticks to be positive for TBEV, but only one tick was amplified using nested PCR targeting the TBEV envelope (E) and non-structure 5 (NS5) gene. The obtained sequences belonged to the TBEV Siberian subtype and phylogenetic tree analysis results confirmed that the virus was related to the Bosnia strain. We also performed next-generation sequencing, which confirmed the TBEV Siberian subtype. Continuous research and surveillance of TBEV in Kyrgyzstan are required to provide further information on tick-borne diseases.

Evaluation of the Predictive Value of Routinely Collected Health-Related Social Needs Measures.

The objective was to assess the value of routinely collected patient-reported health-related social needs (HRSNs) measures for predicting utilization and health outcomes. The authors identified Mayo Clinic patients with cancer, diabetes, or heart failure. The HRSN measures were collected as part of patient-reported screenings from June to December 2019 and outcomes (hospitalization, 30-day readmission, and death) were ascertained in 2020. For each outcome and disease combination, 4 models were used: gradient boosting machine (GBM), random forest (RF), generalized linear model (GLM), and elastic net (EN). Other predictors included clinical factors, demographics, and area-based HRSN measures-area deprivation index (ADI) and rurality. Predictive performance for models was evaluated with and without the routinely collected HRSN measures as change in area under the curve (AUC). Variable importance was also assessed. The differences in AUC were mixed. Significant improvements existed in 3 models of death for cancer (GBM: 0.0421, RF: 0.0496, EN: 0.0428), 3 models of hospitalization (GBM: 0.0372, RF: 0.0640, EN: 0.0441), and 1 of death (RF: 0.0754) for diabetes, and 1 model of readmissions (GBM: 0.1817), and 3 models of death (GBM: 0.0333, RF: 0.0519, GLM: 0.0489) for heart failure. Age, ADI, and the Charlson comorbidity index were the top 3 in variable importance and were consistently more important than routinely collected HRSN measures. The addition of routinely collected HRSN measures resulted in mixed improvement in the predictive performance of the models. These findings suggest that existing factors and the ADI are more important for prediction in these contexts. More work is needed to identify predictors that consistently improve model performance.

Explainable Artificial Intelligence Warning Model Using an Ensemble Approach for In-Hospital Cardiac Arrest Prediction: Retrospective Cohort Study.

BACKGROUND: Cardiac arrest (CA) is the leading cause of death in critically ill patients. Clinical research has shown that early identification of CA reduces mortality. Algorithms capable of predicting CA with high sensitivity have been developed using multivariate time series data. However, these algorithms suffer from a high rate of false alarms, and their results are not clinically interpretable. OBJECTIVE: We propose an ensemble approach using multiresolution statistical features and cosine similarity-based features for the timely prediction of CA. Furthermore, this approach provides clinically interpretable results that can be adopted by clinicians. METHODS: Patients were retrospectively analyzed using data from the Medical Information Mart for Intensive Care-IV database and the eICU Collaborative Research Database. Based on the multivariate vital signs of a 24-hour time window for adults diagnosed with heart failure, we extracted multiresolution statistical and cosine similarity-based features. These features were used to construct and develop gradient boosting decision trees. Therefore, we adopted cost-sensitive learning as a solution. Then, 10-fold cross-validation was performed to check the consistency of the model performance, and the Shapley additive explanation algorithm was used to capture the overall interpretability of the proposed model. Next, external validation using the eICU Collaborative Research Database was performed to check the generalization ability. RESULTS: The proposed method yielded an overall area under the receiver operating characteristic curve (AUROC) of 0.86 and area under the precision-recall curve (AUPRC) of 0.58. In terms of the timely prediction of CA, the proposed model achieved an AUROC above 0.80 for predicting CA events up to 6 hours in advance. The proposed method simultaneously improved precision and sensitivity to increase the AUPRC, which reduced the number of false alarms while maintaining high sensitivity. This result indicates that the predictive performance of the proposed model is superior to the performances of the models reported in previous studies. Next, we demonstrated the effect of feature importance on the clinical interpretability of the proposed method and inferred the effect between the non-CA and CA groups. Finally, external validation was performed using the eICU Collaborative Research Database, and an AUROC of 0.74 and AUPRC of 0.44 were obtained in a general intensive care unit population. CONCLUSIONS: The proposed framework can provide clinicians with more accurate CA prediction results and reduce false alarm rates through internal and external validation. In addition, clinically interpretable prediction results can facilitate clinician understanding. Furthermore, the similarity of vital sign changes can provide insights into temporal pattern changes in CA prediction in patients with heart failure-related diagnoses. Therefore, our system is sufficiently feasible for routine clinical use. In addition, regarding the proposed CA prediction system, a clinically mature application has been developed and verified in the future digital health field.

Oxidative Stress and DNA Damage in Pagrus major by the Dinoflagellate Karenia mikimotoi.

Karenia mikimotoi is a common species of red tide dinoflagellate that causes the mass mortality of marine fauna in coastal waters of Republic of Korea. Despite continuous studies on the ecophysiology and toxicity of K. mikimotoi, the underlying molecular mechanisms remain poorly understood. Red sea bream, Pagrus major, is a high-value aquaculture fish species, and the coastal aquaculture industry of red sea bream has been increasingly affected by red tides. To investigate the potential oxidative effects of K. mikimotoi on P. major and the molecular mechanisms involved, we exposed the fish to varying concentrations of K. mikimotoi and evaluated its toxicity. Our results showed that exposure to K. mikimotoi led to an accumulation of reactive oxygen species (ROS) and oxidative DNA damage in the gill tissue of P. major. Furthermore, we found that K. mikimotoi induced the activation of antioxidant enzymes, such as superoxide dismutase, catalase, glutathione peroxidase, and glutathione reductase, in the gill tissue of P. major, with a significant increase in activity at concentrations above 5000 cells/mL. However, the activity of glutathione S-transferase did not significantly increase at the equivalent concentration. Our study confirms that oxidative stress and DNA damage is induced by acute exposure to K. mikimotoi, as it produces ROS and hypoxic conditions in P. major. In addition, it was confirmed that gill and blood samples can be used as biomarkers to detect the degree of oxidative stress in fish. These findings have important implications for the aquaculture of red sea bream, particularly in the face of red tide disasters.

SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring.

Introduction: We propose an automatic sleep stage scoring model, referred to as SeriesSleepNet, based on convolutional neural network (CNN) and bidirectional long short-term memory (bi-LSTM) with partial data augmentation. We used single-channel raw electroencephalography signals for automatic sleep stage scoring. Methods: Our framework was focused on time series information, so we applied partial data augmentation to learn the connected time information in small series. In specific, the CNN module learns the time information of one epoch (intra-epoch) whereas the bi-LSTM trains the sequential information between the adjacent epochs (inter-epoch). Note that the input of the bi-LSTM is the augmented CNN output. Moreover, the proposed loss function was used to fine-tune the model by providing additional weights. To validate the proposed framework, we conducted two experiments using the Sleep-EDF and SHHS datasets. Results and Discussion: The results achieved an overall accuracy of 0.87 and 0.84 and overall F1-score of 0.80 and 0.78 and kappa value of 0.81 and 0.78 for five-class classification, respectively. We showed that the SeriesSleepNet was superior to the baselines based on each component in the proposed framework. Our architecture also outperformed the state-of-the-art methods with overall F1-score, accuracy, and kappa value. Our framework could provide information on sleep disorders or quality of sleep to automatically classify sleep stages with high performance.