Plasmonic Annular Nanotrenches with 1 nm Nanogaps for Detection of SARS-CoV-2 Using SERS-Based Immunoassay.

This study represents the synthesis of a novel class of nanoparticles denoted as annular Au nanotrenches (AANTs). AANTs are engineered to possess embedded, narrow circular nanogaps with dimensions of approximately 1 nm, facilitating near-field focusing for detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) via a surface-enhanced Raman scattering (SERS)-based immunoassay. Notably, AANTs exhibited an exceedingly low limit of detection (LOD) of 1 fg/mL for SARS-CoV-2 spike glycoproteins, surpassing the commercially available enzyme-linked immunosorbent assay (ELISA) by 6 orders of magnitude (1 ng/mL from ELISA). To assess the real-world applicability, a study was conducted on 50 clinical samples using an SERS-based immunoassay with AANTs. The results revealed a sensitivity of 96% and a selectivity of 100%, demonstrating the significantly enhanced sensing capabilities of the proposed approach in comparison to ELISA and commercial lateral flow assay kits.

Development of an Interoperable and Easily Transferable Clinical Decision Support System Deployment Platform: System Design and Development Study.

BACKGROUND: A clinical decision support system (CDSS) is recognized as a technology that enhances clinical efficacy and safety. However, its full potential has not been realized, mainly due to clinical data standards and noninteroperable platforms. OBJECTIVE: In this paper, we introduce the common data model-based intelligent algorithm network environment (CANE) platform that supports the implementation and deployment of a CDSS. METHODS: CDSS reasoning engines, usually represented as R or Python objects, are deployed into the CANE platform and converted into C# objects. When a clinician requests CANE-based decision support in the electronic health record (EHR) system, patients' information is transformed into Health Level 7 Fast Healthcare Interoperability Resources (FHIR) format and transmitted to the CANE server inside the hospital firewall. Upon receiving the necessary data, the CANE system's modules perform the following tasks: (1) the preprocessing module converts the FHIRs into the input data required by the specific reasoning engine, (2) the reasoning engine module operates the target algorithms, (3) the integration module communicates with the other institutions' CANE systems to request and transmit a summary report to aid in decision support, and (4) creates a user interface by integrating the summary report and the results calculated by the reasoning engine. RESULTS: We developed a CANE system such that any algorithm implemented in the system can be directly called through the RESTful application programming interface when it is integrated with an EHR system. Eight algorithms were developed and deployed in the CANE system. Using a knowledge-based algorithm, physicians can screen patients who are prone to sepsis and obtain treatment guides for patients with sepsis with the CANE system. Further, using a nonknowledge-based algorithm, the CANE system supports emergency physicians' clinical decisions about optimum resource allocation by predicting a patient's acuity and prognosis during triage. CONCLUSIONS: We successfully developed a common data model-based platform that adheres to medical informatics standards and could aid artificial intelligence model deployment using R or Python.

Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Retrospective, Comparative, Machine Learning Study.

BACKGROUND: Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care. OBJECTIVE: This study aimed to develop and validate prediction models for UE in ICU patients using machine learning. METHODS: This study was conducted in an academic tertiary hospital in Seoul, Republic of Korea. The hospital had approximately 2000 inpatient beds and 120 ICU beds. As of January 2019, the hospital had approximately 9000 outpatients on a daily basis. The number of annual ICU admissions was approximately 10,000. We conducted a retrospective study between January 1, 2010, and December 31, 2018. A total of 6914 extubation cases were included. We developed a UE prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model's performance, we used the area under the receiver operating characteristic curve (AUROC). The sensitivity, specificity, positive predictive value, negative predictive value, and F1 score were also determined for each model. For performance evaluation, we also used a calibration curve, the Brier score, and the integrated calibration index (ICI) to compare different models. The potential clinical usefulness of the best model at the best threshold was assessed through a net benefit approach using a decision curve. RESULTS: Among the 6914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was higher during the night shift as compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality were higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.763, and for SVM was 0.740. CONCLUSIONS: We successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787 and the sensitivity was 0.949, which was obtained using the RF algorithm. The RF model was well-calibrated, and the Brier score and ICI were 0.129 and 0.048, respectively. The proposed prediction model uses widely available variables to limit the additional workload on the clinician. Further, this evaluation suggests that the model holds potential for clinical usefulness.

Temporal Change in Alert Override Rate with a Minimally Interruptive Clinical Decision Support on a Next-Generation Electronic Medical Record.

Background and objectives: The aim of this study is to describe the temporal change in alert override with a minimally interruptive clinical decision support (CDS) on a Next-Generation electronic medical record (EMR) and analyze factors associated with the change. Materials and Methods: The minimally interruptive CDS used in this study was implemented in the hospital in 2016, which was a part of the new next-generation EMR, Data Analytics and Research Window for Integrated kNowledge (DARWIN), which does not generate modals, 'pop-ups' but show messages as in-line information. The prescription (medication order) and alerts data from July 2016 to December 2017 were extracted. Piece-wise regression analysis and linear regression analysis was performed to determine the temporal change and factors associated with it. Results: Overall, 2,706,395 alerts and 993 doctors were included in the study. Among doctors, 37.2% were faculty (professors), 17.2% were fellows, and 45.6% trainees (interns and residents). The overall override rate was 61.9%. There was a significant change in an increasing trend at month 12 (p < 0.001). We found doctors' positions and specialties, along with the number of alerts and medication variability, were significantly associated with the change. Conclusions: In this study, we found a significant temporal change of alert override. We also found factors associated with the change, which had statistical significance.

Salusin-ß mediate neuroprotective effects for Parkinson's disease.

Neuropeptides, small peptides found in many mammalian brain, play key roles in communicating with each other to modulate neuronal activity. Here, we reported that endogenous neuropeptide salusin-ß has neuroprotective effects on the midbrain dopamine neurons and can be used as an effective therapeutic treatment for Parkinson's disease (PD). We found that the MrgprA1 receptor mediates the neuroprotective effects of salusin-ß on the midbrain dopamine neurons. Importantly, intranasal administration of salusin-ß in a PD mouse model show the neuroprotection of dopaminergic neurons and increased the survival of midbrain dopamine neurons. Furthermore, inhibition of the salusin-ß receptor, MrgprA1, abolished the neuroprotective effects induced by salusin-ß. Taken together, these results demonstrate the novel role of salusin-ß in the central nervous system and salusin-ß can be used as a novel therapeutic to effectively treat PD.

Modelling APOE ɛ3/4 allele-associated sporadic Alzheimer's disease in an induced neuron.

The recent generation of induced neurons by direct lineage conversion holds promise for in vitro modelling of sporadic Alzheimer's disease. Here, we report the generation of induced neuron-based model of sporadic Alzheimer's disease in mice and humans, and used this system to explore the pathogenic mechanisms resulting from the sporadic Alzheimer's disease risk factor apolipoprotein E (APOE) ɛ3/4 allele. We show that mouse and human induced neurons overexpressing mutant amyloid precursor protein in the background of APOE ɛ3/4 allele exhibit altered amyloid precursor protein (APP) processing, abnormally increased production of amyloid-ß42 and hyperphosphorylation of tau. Importantly, we demonstrate that APOE ɛ3/4 patient induced neuron culture models can faithfully recapitulate molecular signatures seen in APOE ɛ3/4-associated sporadic Alzheimer's disease patients. Moreover, analysis of the gene network derived from APOE ɛ3/4 patient induced neurons reveals a strong interaction between APOE ɛ3/4 and another Alzheimer's disease risk factor, desmoglein 2 (DSG2). Knockdown of DSG2 in APOE ɛ3/4 induced neurons effectively rescued defective APP processing, demonstrating the functional importance of this interaction. These data provide a direct connection between APOE ɛ3/4 and another Alzheimer's disease susceptibility gene and demonstrate in proof of principle the utility of induced neuron-based modelling of Alzheimer's disease for therapeutic discovery.

Generation of Integration-Free Induced Neurons Using Graphene Oxide-Polyethylenimine.

Direct conversion of somatic cells into induced neurons (iNs) without inducing pluripotency has great therapeutic potential for treating central nervous system diseases. Reprogramming of somatic cells to iNs requires the introduction of several factors that drive cell-fate conversion, and viruses are commonly used to deliver these factors into somatic cells. However, novel gene-delivery systems that do not integrate transgenes into the genome are required to generate iNs for safe human clinical applications. In this study, it is investigated whether graphene oxide-polyethylenimine (GO-PEI) complexes are an efficient and safe system for messenger RNA delivery for direct reprogramming of iNs. The GO-PEI complexes show low cytotoxicity, high delivery efficiency, and directly converted fibroblasts into iNs without integrating factors into the genome. Moreover, in vivo transduction of reprogramming factors into the brain with GO-PEI complexes facilitates the production of iNs that alleviated Parkinson's disease symptoms in a mouse model. Thus, the GO-PEI delivery system may be used to safely obtain iNs and could be used to develop direct cell reprogramming-based therapies for neurodegenerative diseases.

The effects of stepper exercise with visual feedback on strength, walking, and stair climbing in individuals following stroke.

[Purpose] This study investigated the effect of stepper exercise with visual feedback on strength, walking, and stair climbing in stroke patients. [Subjects] Twenty-six stroke patients were divided randomly into the stepper exercise with visual feedback group (n = 13) or the stepper exercise group (n = 13). [Methods] Subjects in the experimental group received feedback through the mirror during exercise, while those in the control group performed the exercise without visual feedback; both groups exercised for the 30 min thrice per week for 6 weeks. The hip extensor and knee extensor strength, 10-m walking test results, and 11-step stair climbing test results were evaluated before and after the intervention. [Results] The stepper exercise with visual feedback group showed significantly greater improvement for hip extensor strength and the 10-m walking test. The knee extensor strength and 11-step stair climbing in both groups showed significantly greater improvement after the intervention, but without any significant difference between groups. [Conclusion] The findings of this study indicate that the stepper exercise with visual feedback can help improve the strength of the hip extensor and the 10-m walking test; the stepper exercise alone may also improve the knee extensor strength and stair climbing ability.

The effect of trunk stabilization exercise using an unstable surface on the abdominal muscle structure and balance of stroke patients.

[Purpose] This study investigated the effect of unstable surface trunk stabilization exercise on the abdominal muscle structure and balance of stroke patients. [Subjects] The subjects were divided into two groups: an unstable surface trunk stabilization exercise group (n=13), and a stable surface trunk stabilization exercise group (n=11). [Methods] Both groups performed trunk stabilization exercise for 30 minutes, 3 days per week for 6 weeks. Abdominal muscle thickness and the Berg Balance Scale (BBS) were measured at the baseline and after 6 weeks. [Results] There was a significant improvement in the internal oblique muscle thickness, transversus abdominis thickness and balance ability of the unstable surface trunk stabilization exercise group. [Conclusion] The unstable surface trunk stabilization exercise improved the internal oblique and transversus abdominis muscles and balance ability. These results suggest that unstable surface trunk exercise is useful in the rehabilitation stroke patients.

RefQSR: Reference-Based Quantization for Image Super-Resolution Networks.

Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the expense of increased computational costs, limiting their use in resource-constrained environments. As a promising solution for computationally efficient network design, network quantization has been extensively studied. However, existing quantization methods developed for SISR have yet to effectively exploit image self-similarity, which is a new direction for exploration in this study. We introduce a novel method called reference-based quantization for image super-resolution (RefQSR) that applies high-bit quantization to several representative patches and uses them as references for low-bit quantization of the rest of the patches in an image. To this end, we design dedicated patch clustering and reference-based quantization modules and integrate them into existing SISR network quantization methods. The experimental results demonstrate the effectiveness of RefQSR on various SISR networks and quantization methods.

The potential for drug incompatibility and its drivers - A hospital wide retrospective descriptive study.

OBJECTIVE: Drug incompatibility, a significant subset of medication errors, threaten patient safety during the medication administration phase. Despite the undeniably high prevalence of drug incompatibility, it is currently poorly understood because previous studies are focused predominantly on intensive care unit (ICU) settings. To enhance patient safety, it is crucial to expand our understanding of this issue from a comprehensive viewpoint. This study aims to investigate the prevalence and mechanism of drug incompatibility by analysing hospital-wide prescription and administration data. METHODS: This retrospective cross-sectional study, conducted at a tertiary academic hospital, included data extracted from the clinical data warehouse of the study institution on patients admitted between January 1, 2021, and May 31, 2021. Potential contacts in drug pairs (PCs) were identified using the study site clinical workflow. Drug incompatibility for each PC was determined by using a commercial drug incompatibility database, the Trissel's™ 2 Clinical Pharmaceutics Database (Trissel's 2 database). Drivers of drug incompatibility were identified, based on a descriptive analysis, after which, multivariate logistic regression was conducted to assess the risk factors for experiencing one or more drug incompatibilities during admission. RESULTS: Among 30,359 patients (representing 40,061 hospitalisations), 24,270 patients (32,912 hospitalisations) with 764,501 drug prescriptions (1,001,685 IV administrations) were analysed, after checking for eligibility. Based on the rule for determining PCs, 5,813,794 cases of PCs were identified. Among these, 25,108 (0.4 %) cases were incompatible PCs: 391 (1.6 %) PCs occurred during the prescription process and 24,717 (98.4 %) PCs during the administration process. By classifying these results, we identified the following drivers contributing to drug incompatibility: incorrect order factor; incorrect administration factor; and lack of related research. In multivariate analysis, the risk of encountering incompatible PCs was higher for patients who were male, older, with longer lengths of stay, with higher comorbidity, and admitted to medical ICUs. CONCLUSIONS: We comprehensively described the current state of drug incompatibility by analysing hospital-wide drug prescription and administration data. The results showed that drug incompatibility frequently occurs in clinical settings.

Development, validation, and usability evaluation of machine learning algorithms for predicting personalized red blood cell demand among thoracic surgery patients.

INTRODUCTION: Preparing appropriate red blood cells (RBCs) before surgery is crucial for improving both the efficacy of perioperative workflow and patient safety. In particular, thoracic surgery (TS) is a procedure that requires massive transfusion with high variability for each patient. Hence, the precise prediction of RBC requirements for individual patients is becoming increasingly important. This study aimed to 1) develop and validate a machine learning algorithm for personalized RBC predictions for TS patients and 2) assess the usability of a clinical decision support system (CDSS) integrating this artificial intelligence model. METHODS: Adult patients who underwent TS between January 2016 and October 2021 were included in this study. Multiple models were developed by employing both traditional statistical- and machine-learning approaches. The primary outcome evaluated the model's performance in predicting RBC requirements through root mean square error and adjusted R2. Surgeons and informaticians determined the precision MSBOS-Thoracic Surgery (pMSBOS-TS) algorithm through a consensus process. The usability of the pMSBOS-TS was assessed using the System Usability Scale (SUS) survey with 60 clinicians. RESULTS: We identified 7,843 cases (6,200 for training and 1,643 for test sets) of TSs. Among the models with variable performance indices, the extreme gradient boosting model was selected as the pMSBOS-TS algorithm. The pMSBOS-TS model showed statistically significant lower root mean square error (mean: 3.203 and 95% confidence interval [CI]: 3.186-3.220) compared to the calculated Maximum Surgical Blood Ordering Schedule (MSBOS) and a higher adjusted R2 (mean: 0.399 and 95% CI: 0.395-0.403) compared to the calculated MSBOS, while requiring approximately 200 fewer packs for RBC preparation compared to the calculated MSBOS. The SUS score of the pMSBOS-TS CDSS was 72.5 points, indicating good acceptability. CONCLUSIONS: We successfully developed the pMSBOS-TS capable of predicting personalized RBC transfusion requirements for perioperative patients undergoing TS.

Quantifying emergency department nursing workload at the task level using NASA-TLX: An exploratory descriptive study.

BACKGROUND: Emergency departments (ED) nurses experience high mental workloads because of unpredictable work environments; however, research evaluating ED nursing workload using a tool incorporating nurses' perception is lacking. Quantify ED nursing subjective workload and explore the impact of work experience on perceived workload. METHODS: Thirty-two ED nurses at a tertiary academic hospital in the Republic of Korea were surveyed to assess their subjective workload for ED procedures using the National Aeronautics and Space Administration Task Load Index (NASA-TLX). Nonparametric statistical analysis was performed to describe the data, and linear regression analysis was conducted to estimate the impact of work experience on perceived workload. RESULTS: Cardiopulmonary resuscitation (CPR) had the highest median workload, followed by interruption from a patient and their family members. Although inexperienced nurses perceived the 'special care' procedures (CPR and defibrillation) as more challenging compared with other categories, analysis revealed that nurses with more than 107 months of experience reported a significantly higher workload than those with less than 36 months of experience. CONCLUSION: Addressing interruptions and customizing training can alleviate ED nursing workload. Quantified perceived workload is useful for identifying acceptable thresholds to maintain optimal workload, which ultimately contributes to predicting nursing staffing needs and ED crowding.

In vitro broad-spectrum antiviral activity of MIT-001, a mitochondria-targeted reactive oxygen species scavenger, against severe acute respiratory syndrome coronavirus 2 and multiple zoonotic viruses.

The COVID-19 pandemic caused by SARS-CoV-2 becomes a serious threat to global health and requires the development of effective antiviral therapies. Current therapies that target viral proteins have limited efficacy with side effects. In this study, we investigated the antiviral activity of MIT-001, a small molecule reactive oxygen species (ROS) scavenger targeting mitochondria, against SARS-CoV-2 and other zoonotic viruses in vitro. The antiviral activity of MIT-001 was quantified by RT-qPCR and plaque assay. We also evaluated the functional analysis of MIT-001 by JC-1 staining to measure mitochondrial depolarization, total RNA sequencing to investigate gene expression changes, and immunoblot to quantify protein expression levels. The results showed that MIT-001 effectively inhibited the replication of B.1.617.2 and BA.1 strains, Zika virus, Seoul virus, and Vaccinia virus. Treatment with MIT-001 restored the expression of heme oxygenase-1 (HMOX1) and NAD(P)H: quinone oxidoreductase 1 (NqO1) genes, anti-oxidant enzymes reduced by SARS-CoV-2, to normal levels. The presence of MIT-001 also alleviated mitochondrial depolarization caused by SARS-CoV-2 infection. These findings highlight the potential of MIT-001 as a broad-spectrum antiviral compound that targets for zoonotic RNA and DNA viruses, providing a promising therapeutic approach to combat viral infection.

Healthcare Professionals' Expectations of Medical Artificial Intelligence and Strategies for its Clinical Implementation: A Qualitative Study.

OBJECTIVES: Although medical artificial intelligence (AI) systems that assist healthcare professionals in critical care settings are expected to improve healthcare, skepticism exists regarding whether their potential has been fully actualized. Therefore, we aimed to conduct a qualitative study with physicians and nurses to understand their needs, expectations, and concerns regarding medical AI; explore their expected responses to recommendations by medical AI that contradicted their judgments; and derive strategies to implement medical AI in practice successfully. METHODS: Semi-structured interviews were conducted with 15 healthcare professionals working in the emergency room and intensive care unit in a tertiary teaching hospital in Seoul. The data were interpreted using summative content analysis. In total, 26 medical AI topics were extracted from the interviews. Eight were related to treatment recommendation, seven were related to diagnosis prediction, and seven were related to process improvement. RESULTS: While the participants expressed expectations that medical AI could enhance their patients' outcomes, increase work efficiency, and reduce hospital operating costs, they also mentioned concerns regarding distortions in the workflow, deskilling, alert fatigue, and unsophisticated algorithms. If medical AI decisions contradicted their judgment, most participants would consult other medical staff and thereafter reconsider their initial judgment. CONCLUSIONS: Healthcare professionals wanted to use medical AI in practice and emphasized that artificial intelligence systems should be trustworthy from the standpoint of healthcare professionals. They also highlighted the importance of alert fatigue management and the integration of AI systems into the workflow.

Theoretical and experimental study of waste-heat-recovery boiler with water injection.

The waste-heat-recovery boiler with water injection (HR-B/W) applies the heat exchange between the intake air and exhaust gas with the water injection into the intake air. Previous theoretical studies have discussed that the HR-B/W would increase the thermal efficiency of the boiler by the active heat exchange between the intake air and exhaust gas. It has also been discussed that the increased fraction of water vapor in the air would reduce the flame temperature which in turn decreases the NOx emission. However, the potential performance of the HR-B/W has not been validated through practical boiler tests by considering the evaporation characteristics of the injected water, which plays a critical role in the performance of the HR-B/W. In this study the effects of water injection into the intake air on the thermal efficiency and pollutant emissions of the waste-heat-recovery boiler are investigated using a commercial 24 kW condensing boiler in full load condition. Thermodynamic analysis is performed to evaluate the adequate amount of water injection and trace the physical properties in the boiler upon the water injection amount and evaporation characteristics. The boiler test results showed water injection can increase thermal efficiency to 4.4% point and reduce NOx and CO emissions by 69% and 33% respectively compared to those without water injection. These advantages can be further enhanced if the atomization and evaporation performance of injected water is improved.

Prognostic Performance of Sequential Organ Failure Assessment, Acute Physiology and Chronic Health Evaluation III, and Simplified Acute Physiology Score II Scores in Patients with Suspected Infection According to Intensive Care Unit Type.

We investigated the prognostic performance of scoring systems by the intensive care unit (ICU) type. This was a retrospective observational study using data from the Marketplace for Medical Information in the Intensive Care IV database. The primary outcome was in-hospital mortality. We obtained Sequential Organ Failure Assessment (SOFA), Acute Physiology and Chronic Health Evaluation (APACHE) III, and Simplified Acute Physiology Score (SAPS) II scores in each ICU type. Prognostic performance was evaluated with the area under the receiver operating characteristic curve (AUROC) and was compared among ICU types. A total of 29,618 patients were analyzed, and the in-hospital mortality was 12.4%. The overall prognostic performance of APACHE III was significantly higher than those of SOFA and SAPS II (0.807, [95% confidence interval, 0.799-0.814], 0.785 [0.773-0.797], and 0.795 [0.787-0.811], respectively). The prognostic performance of SOFA, APACHE III, and SAPS II scores was significantly different between ICU types. The AUROC ranges of SOFA, APACHE III, and SAPS II were 0.723-0.826, 0.728-0.860, and 0.759-0.819, respectively. The neurosurgical and surgical ICUs had lower prognostic performance than other ICU types. The prognostic performance of scoring systems in patients with suspected infection is significantly different according to ICU type. APACHE III systems have the highest prediction performance. ICU type may be a significant factor in the prognostication.

Gene Therapy Using Efficient Direct Lineage Reprogramming Technology for Neurological Diseases.

Gene therapy is an innovative approach in the field of regenerative medicine. This therapy entails the transfer of genetic material into a patient's cells to treat diseases. In particular, gene therapy for neurological diseases has recently achieved significant progress, with numerous studies investigating the use of adeno-associated viruses for the targeted delivery of therapeutic genetic fragments. This approach has potential applications for treating incurable diseases, including paralysis and motor impairment caused by spinal cord injury and Parkinson's disease, and it is characterized by dopaminergic neuron degeneration. Recently, several studies have explored the potential of direct lineage reprogramming (DLR) for treating incurable diseases, and highlighted the advantages of DLR over conventional stem cell therapy. However, application of DLR technology in clinical practice is hindered by its low efficiency compared with cell therapy using stem cell differentiation. To overcome this limitation, researchers have explored various strategies such as the efficiency of DLR. In this study, we focused on innovative strategies, including the use of a nanoporous particle-based gene delivery system to improve the reprogramming efficiency of DLR-induced neurons. We believe that discussing these approaches can facilitate the development of more effective gene therapies for neurological disorders.

Identifying the Risk of Sepsis in Patients With Cancer Using Digital Health Care Records: Machine Learning-Based Approach.

BACKGROUND: Sepsis is diagnosed in millions of people every year, resulting in a high mortality rate. Although patients with sepsis present multimorbid conditions, including cancer, sepsis predictions have mainly focused on patients with severe injuries. OBJECTIVE: In this paper, we present a machine learning-based approach to identify the risk of sepsis in patients with cancer using electronic health records (EHRs). METHODS: We utilized deidentified anonymized EHRs of 8580 patients with cancer from the Samsung Medical Center in Korea in a longitudinal manner between 2014 and 2019. To build a prediction model based on physical status that would differ between sepsis and nonsepsis patients, we analyzed 2462 laboratory test results and 2266 medication prescriptions using graph network and statistical analyses. The medication relationships and lab test results from each analysis were used as additional learning features to train our predictive model. RESULTS: Patients with sepsis showed differential medication trajectories and physical status. For example, in the network-based analysis, narcotic analgesics were prescribed more often in the sepsis group, along with other drugs. Likewise, 35 types of lab tests, including albumin, globulin, and prothrombin time, showed significantly different distributions between sepsis and nonsepsis patients (P<.001). Our model outperformed the model trained using only common EHRs, showing an improved accuracy, area under the receiver operating characteristic (AUROC), and F1 score by 11.9%, 11.3%, and 13.6%, respectively. For the random forest-based model, the accuracy, AUROC, and F1 score were 0.692, 0.753, and 0.602, respectively. CONCLUSIONS: We showed that lab tests and medication relationships can be used as efficient features for predicting sepsis in patients with cancer. Consequently, identifying the risk of sepsis in patients with cancer using EHRs and machine learning is feasible.

Clinical Trends in Management of Locally Advanced ESCC: Real-World Evidence from a Large Single-Center Cohort Study.

Neoadjuvant chemoradiation followed by surgery (NCRT+S) has been widely applied to patients with locally advanced esophageal squamous cell carcinoma (ESCC); however, treatment trends and their survival outcomes in a real-world clinical setting are poorly understood. This study aimed to analyze real-world evidence to understand treatment patterns and outcomes for patients with ESCC. We analyzed the treatment pattern and 5-year overall survival (5yOS) by synthesizing the individuals' general characteristics, cancer information, and treatment records extracted from the Clinical Data Warehouse from 1994 to 2018. Of a total of 2151 patients, most patients received upfront surgery and 5yOS was 36.8% (31.4−43.1%). From 2003 to 2012, the use of NCRT increased, and 5yOS was improved to 42.2% (38.8−45.7%). Notably, after 2013, the proportion of NCRT+S markedly increased up to >50% of patients: 5yOS was much improved to 56.3% (53.2−59.6%). With regard to treatment, patients with NCRT+S had the most favorable 5yOS of 58.1% (53−63.7%), although that for patients with upfront surgery was 48.6% (45.9−51.5%, p < 0.001). Moreover, patients who received adjuvant therapy after surgery had better OS than those with surgery alone (58.4% (52.7−64.7%) vs. 47.3% (44.1−50.7%), p < 0.001). This analysis of real-world data demonstrated a significantly improved survival outcome for locally advanced ESCC over time since NCRT prior to surgery had been routinely applied. We revealed that NCRT+S was the most effective treatment for locally advanced ESCC and that adjuvant chemotherapy may be an encouraging therapeutic option for patients with positive nodes after upfront surgery.