XGBoost-based machine learning test improves the accuracy of hemorrhage prediction among geriatric patients with long-term administration of rivaroxaban.

BACKGROUND: Hemorrhage is a potential and serious adverse drug reaction, especially for geriatric patients with long-term administration of rivaroxaban. It is essential to establish an effective model for predicting bleeding events, which could improve the safety of rivaroxaban use in clinical practice. METHODS: The hemorrhage information of 798 geriatric patients (over the age of 70 years) who needed long-term administration of rivaroxaban for anticoagulation therapy was constantly tracked and recorded through a well-established clinical follow-up system. Relying on the 27 collected clinical indicators of these patients, conventional logistic regression analysis, random forest and XGBoost-based machine learning approaches were applied to analyze the hemorrhagic risk factors and establish the corresponding prediction models. Furthermore, the performance of the models was tested and compared by the area under curve (AUC) of the receiver operating characteristic (ROC) curve. RESULTS: A total of 112 patients (14.0%) had bleeding adverse events after treatment with rivaroxaban for more than 3 months. Among them, 96 patients had gastrointestinal and intracranial hemorrhage during treatment, which accounted for 83.18% of the total hemorrhagic events. The logistic regression, random forest and XGBoost models were established with AUCs of 0.679, 0.672 and 0.776, respectively. The XGBoost model showed the best predictive performance in terms of discrimination, accuracy and calibration among all the models. CONCLUSION: An XGBoost-based model with good discrimination and accuracy was built to predict the hemorrhage risk of rivaroxaban, which will facilitate individualized treatment for geriatric patients.

Varying association of laboratory values with reference ranges and outcomes in critically ill patients: an analysis of data from five databases in four countries across Asia, Europe and North America.

BACKGROUND: Despite wide usage across all areas of medicine, it is uncertain how useful standard reference ranges of laboratory values are for critically ill patients. OBJECTIVES: The aim of this study is to assess the distributions of standard laboratory measurements in more than 330 selected intensive care units (ICUs) across the USA, Amsterdam, Beijing and Tarragona; compare differences and similarities across different geographical locations and evaluate how they may be associated with differences in length of stay (LOS) and mortality in the ICU. METHODS: A multi-centre, retrospective, cross-sectional study of data from five databases for adult patients first admitted to an ICU between 2001 and 2019 was conducted. The included databases contained patient-level data regarding demographics, interventions, clinical outcomes and laboratory results. Kernel density estimation functions were applied to the distributions of laboratory tests, and the overlapping coefficient and Cohen standardised mean difference were used to quantify differences in these distributions. RESULTS: The 259 382 patients studied across five databases in four countries showed a high degree of heterogeneity with regard to demographics, case mix, interventions and outcomes. A high level of divergence in the studied laboratory results (creatinine, haemoglobin, lactate, sodium) from the locally used reference ranges was observed, even when stratified by outcome. CONCLUSION: Standardised reference ranges have limited relevance to ICU patients across a range of geographies. The development of context-specific reference ranges, especially as it relates to clinical outcomes like LOS and mortality, may be more useful to clinicians.

TOP-Net Prediction Model Using Bidirectional Long Short-term Memory and Medical-Grade Wearable Multisensor System for Tachycardia Onset: Algorithm Development Study.

BACKGROUND: Without timely diagnosis and treatment, tachycardia, also called tachyarrhythmia, can cause serious complications such as heart failure, cardiac arrest, and even death. The predictive performance of conventional clinical diagnostic procedures needs improvement in order to assist physicians in detecting risk early on. OBJECTIVE: We aimed to develop a deep tachycardia onset prediction (TOP-Net) model based on deep learning (ie, bidirectional long short-term memory) for early tachycardia diagnosis with easily accessible data. METHODS: TOP-Net leverages 2 easily accessible data sources: vital signs, including heart rate, respiratory rate, and blood oxygen saturation (SpO2) acquired continuously by wearable embedded systems, and electronic health records, containing age, gender, admission type, first care unit, and cardiovascular disease history. The model was trained with a large data set from an intensive care unit and then transferred to a real-world scenario in the general ward. In this study, 3 experiments incorporated merging patients' personal information, temporal memory, and different feature combinations. Six metrics (area under the receiver operating characteristic curve [AUROC], sensitivity, specificity, accuracy, F1 score, and precision) were used to evaluate predictive performance. RESULTS: TOP-Net outperformed the baseline models on the large critical care data set (AUROC 0.796, 95% CI 0.768-0.824; sensitivity 0.753, 95% CI 0.663-0.793; specificity 0.720, 95% CI 0.645-0.758; accuracy 0.721; F1 score 0.718; precision 0.686) when predicting tachycardia onset 6 hours in advance. When predicting tachycardia onset 2 hours in advance with data acquired from our hospital using the transferred TOP-Net, the 6 metrics were 0.965, 0.955, 0.881, 0.937, 0.793, and 0.680, respectively. The best performance was achieved using comprehensive vital signs (heart rate, respiratory rate, and SpO2) statistical information. CONCLUSIONS: TOP-Net is an early tachycardia prediction model that uses 8 types of data from wearable sensors and electronic health records. When validated in clinical scenarios, the model achieved a prediction performance that outperformed baseline models 0 to 6 hours before tachycardia onset in the intensive care unit and 2 hours before tachycardia onset in the general ward. Because of the model's implementation and use of easily accessible data from wearable sensors, the model can assist physicians with early discovery of patients at risk in general wards and houses.

Geraniin inhibits proliferation and induces apoptosis through inhibition of phosphatidylinositol 3-kinase/Akt pathway in human colorectal cancer in vitro and in vivo.

Geraniin, a polyphenolic component isolated from Phyllanthus amarus, has been reported to possess diverse biological activities, including antitumor, antiinflammatory, antihyperglycemic, antihypertensive, and antioxidant. However, the role and underlying mechanisms of geraniin in colorectal cancer still remain unclear. In the present study, we found that geraniin notably inhibited cell proliferation and clonogenic formation of colorectal cancer cell SW480 and HT-29 in a dose-dependent manner by Cell Counting Kit 8, EdU, and colony formation assays, respectively. Additionally, geraniin remarkably induced apoptosis of SW480 and HT-29 cells in a dose-dependent way by Hoechst 33342 staining, flow cytometric analysis, and TdT-mediated dUTP nick-end labeling assays and increased the expressions of Bax, caspase-3, and caspase-9, while decreased the level of Bcl-2. Besides, wound healing, transwell migration, and invasion assays demonstrated that geraniin obviously inhibited the migration and invasion of SW480 and HT-29 cells. Moreover, it also inhibited the levels of phospho (p)-phosphatidylinositol 3-kinase and p-Akt. Furthermore, in-vivo animal study revealed that geraniin had the significant inhibitory effects on tumor growth and promoted cancer cell apoptosis remarkably, which further confirmed the antitumor effect of geraniin. Taken together, the present study exhibited the positive role of geraniin in inhibiting proliferation and inducing apoptosis through suppression of phosphatidylinositol 3-kinase/Akt pathway in colorectal cancer cells in vitro and in vivo, which might provide new insights in searching for new drug candidates of anticolorectal cancer.

Association between dietary sodium intake and blood pressure variability in Chinese patients with hypertension.

BACKGROUND: The association between dietary sodium intake and blood pressure variability (BPV) in hypertensive patients remains unclear. The objective of this study was to demonstrate whether dietary sodium intake is a predictor of elevated BPV in Chinese patients with hypertension. METHODS: A total of 235 patients with essential hypertension were enrolled in the Department of Cardiology, Chinese People's Liberation Army (PLA) General Hospital in 2018 to 2019, all of whom underwent 24-h ambulatory blood pressure monitoring. BPV was calculated as the standard deviation (SD), coefficient of variation (CV), variation independent of mean (VIM) of blood pressure measurements, respectively, and divided into diurnal systolic BPV (SBPV), diurnal diastolic BPV (DBPV), nocturnal SBPV, and nocturnal DBPV. 24-h urine samples were collected to measure 24-h urine sodium excretion, which represents dietary sodium intake. The relationship between dietary sodium intake and BPV was analyzed by using Spearman correlations and multiple linear regression analysis. RESULTS: Nocturnal SBPV-SD, CV, VIM, and nocturnal DBPV-SD in the high urine sodium excretion group were significantly higher than those in the medium and low urine sodium excretion groups, whereas diurnal SBPV-SD, CV, VIM, diurnal DBPV-SD, CV, VIM, and nocturnal DBPV-CV, VIM were not. Using the Spearman correlation analysis, we found a linear correlation between 24-h urine sodium excretion and nocturnal SBPV-SD, CV, VIM (SD, r = 0.22, P = 0.001; CV, r = 0.17, P = 0.009; VIM, r = 0.16, P = 0.020), nocturnal DBPV-SD (r = 0.21, P = 0.001), respectively. After further adjusting for confounding factors by multiple linear regression, the positive correlations remained between 24-h urine sodium excretion and nocturnal SBPV-SD, CV, VIM (SD, ß = 0.224, P < 0.001; CV, ß = 0.211, P = 0.001; VIM, ß = 0.213, P = 0.001), nocturnal DBPV (SD, ß = 0.215, P = 0.001), respectively. CONCLUSIONS: Dietary sodium intake is associated with nocturnal SBPV in Chinese patients with hypertension.

[Construction of multi-parameter emergency database and preliminary application research].

The analysis of big data in medical field cannot be isolated from the high quality clinical database, and the construction of first aid database in our country is still in the early stage of exploration. This paper introduces the idea and key technology of the construction of multi-parameter first aid database. By combining emergency business flow with information flow, an emergency data integration model was designed with reference to the architecture of the Medical Information Mart for Intensive Care III (MIMIC-III), created by Computational Physiology Laboratory of Massachusetts Institute of Technology (MIT), and a high-quality first-aid database was built. The database currently covers 22 941 medical records for 19 814 different patients from May 2015 to October 2017, including relatively complete information on physiology, biochemistry, treatment, examination, nursing, etc. And based on the database, the first First-Aid Big Data Datathon event, which 13 teams from all over the country participated in, was launched. The First-Aid database provides a reference for the construction and application of clinical database in China. And it could provide powerful data support for scientific research, clinical decision making and the improvement of medical quality, which will further promote secondary analysis of clinical data in our country.

[Diagnostic Values of Procalcitonin, C-reactive Protein and Interleukin-6 in Hematological Diseases with Bacterial Infection].

OBJECTIVE: To evaluate the diagnostic values of procalcitonin(PCT), C-reactive protein(CRP) and interleukin-6 (IL-6) in patients suffered from hematological diseases with bacterial infection, and to provide further evidence for clinical application. METHODS: A total of 3631 blood cultures, serum levels of PCT and CRP and IL-6 (n=1587) from the inpatients from 2014-01-02 to 2018-01-27 were retrospectively analyzed. The patients were divided into positive (n=208) and negative blood culture (n=3423) groups. Positive blood culture group were redivided into gram-positive (n=34) and gram-negative (n=174) subgroups. The values CRP, PCT and IL-6 were compared respectively in these groups. The data were analyzed by using R 3.4.4 language. RESULTS: The medians of PCT values in positive and negative blood culture groups were 0.41(0.04-103.34) µg/L and 0.20(0.02-200) µg/L(P<0.001) respectively. The medians of CRP values in positive and negative blood culture groups were 9.49(0.1-370) mg/dl and 5.42(0-370) mg/dl (P<0.001) respectively. The medians of IL-6 values in positive and negative blood culture groups were 186.1(2.0-5000, n=91) pg/ml and 52.65(1.5-5000, n=1496) pg/ml (P<0.001). The medians of PCT values in gram-positive and gram-negative groups were 0.20(0.05-93.83) µg/L and 0.58(0.04-103.34) µg/L (P=0.006) respectively. The medians of CRP value in gram-positive and gram-negative groups were 9.19(0.1-35.3)mg/dL and 9.49(0.1-370) mg/dl (P=0.300) respectively. The medians of IL-6 values in gram-positive and gram-negative groups were 83.01(5.61-1500, n=12) pg/ml and 208(2.0-5000, n=79) pg/ml (P=0.357). CONCLUSION: The PCT, CRP and IL-6 levels were significantly higher in the positive blood culture group than those in the negative blood culture group, so provide the effective early diagnostic markers for blood culture. PCT levels in gram-positive group were significantly higher than that in gram-negative groups, contributing to distinguish between the 2 groups.

[A cross-disciplinary collaborative "Datathon" model to promote the application of medical big data].

OBJECTIVE: Medical practice generates and stores immense amounts of clinical process data, while integrating and utilization of these data requires interdisciplinary cooperation together with novel models and methods to further promote applications of medical big data and research of artificial intelligence. A "Datathon" model is a novel event of data analysis and is typically organized as intense, short-duration, competitions in which participants with various knowledge and skills cooperate to address clinical questions based on "real world" data. This article introduces the origin of Datathon, organization of the events and relevant practice. The Datathon approach provides innovative solutions to promote cross-disciplinary collaboration and new methods for conducting research of big data in healthcare. It also offers insight into teaming up multi-expertise experts to investigate relevant clinical questions and further accelerate the application of medical big data.

[Pilot research: construction of emergency rescue database].

OBJECTIVE: To construct a database containing multiple kinds of diseases that can provide "real world" data for first-aid clinical research. METHODS: Structured or non-structured information from hospital information system, laboratory information system, emergency medical system, emergency nursing system and bedside monitoring instruments of patients who visited department of emergency in PLA General Hospital from January 2014 to January 2018 were extracted. Database was created by forms, code writing, and data process. RESULTS: Emergency Rescue Database is a single center database established by PLA General Hospital. The information was collected from the patients who had visited the emergency department in PLA General Hospital since January 2014 to January 2018. The database included 530 585 patients' information of triage and 22 941 patients' information of treatment in critical rescue room, including information related to human demography, triage, medical records, vital signs, lab tests, image and biological examinations and so on. There were 12 tables (PATIENTS, TRIAGE_PATIENTS, EMG_PATIENTS_VISIT, VITAL_SIGNS, CHARTEVENTS, MEDICAL_ORDER, MEDICAL_RECORD, NURSING_RECORD, LAB_TEST_MASTER, LAB_RESULT, MEDICAL_EXAMINATION, EMG_INOUT_RECORD) that containing different kinds of patients' information. CONCLUSIONS: The setup of high quality emergency databases lay solid ground for scientific researches based on data. The model of constructing Emergency Rescue Database could be the reference for other medical institutions to build multiple-diseases databases.