ABSTRACT
OBJECTIVE@#Reduce the number of false alarms and measurement time caused by movement interference by the sync waveform of the movement.@*METHODS@#Vital signal monitoring system based on motion sensor was developed, which collected and processed the vital signals continuously, optimized the features and results of vital signals and transmitted the vital signal results and alarms to the interface.@*RESULTS@#The system was tested in many departments, such as digestive department, cardiology department, internal medicine department, hepatobiliary surgery department and emergency department, and the total collection time was 1 940 h. The number of false electrocardiograph (ECG) alarms decreased by 82.8%, and the proportion of correct alarms increased by 28%. The average measurement time of non-invasive blood pressure (NIBP) decreased by 16.1 s. The total number of false respiratory rate measurement decreased by 71.9%.@*CONCLUSIONS@#False alarms and measurement failures can be avoided by the vital signal monitoring system based on accelerometer to reduce the alarm fatigue in clinic.
Subject(s)
Humans , Monitoring, Physiologic , Electrocardiography , Arrhythmias, Cardiac , Blood Pressure , Accelerometry , Clinical AlarmsABSTRACT
PURPOSE: Cardiac arrest (CA) is the most serious death-related event in critically ill patients and the early detection of CA is beneficial to reduce mortality according to clinical research. This study aims to develop and verify a real-time, interpretable machine learning model, namely cardiac arrest prediction index (CAPI), to predict CA of critically ill patients based on bedside vital signs monitoring. METHODS: A total of 1,860 patients were analyzed retrospectively from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Based on vital signs, we extracted a total of 43 features for building machine learning model. Extreme Gradient Boosting (XGBoost) was used to develop a real-time prediction model. Three-fold cross validation determined the consistency of model accuracy. SHAP value was used to capture the overall and real-time interpretability of the model. RESULTS: On the test set, CAPI predicted 95% of CA events, 80% of which were identified more than 25 min in advance, resulting in an area under the receiver operating characteristic curve (AUROC) of 0.94. The sensitivity, specificity, area under the precision-recall curve (AUPRC) and F1-score were 0.86, 0.85, 0.12 and 0.05, respectively. CONCLUSION: CAPI can help predict patients with CA in the vital signs monitoring at bedside. Compared with previous studies, CAPI can give more timely notifications to doctors for CA events. However, current performance was at the cost of alarm fatigue. Future research is still needed to achieve better clinical application.
Subject(s)
Critical Illness , Heart Arrest , Heart Arrest/diagnosis , Humans , Machine Learning , Retrospective Studies , Vital SignsABSTRACT
Physiological parameter monitoring is essential to medical staff to evaluate, diagnose and treat patients in neonatal intensive care unit (NICU). Monitoring in NICU includes basic vital signal monitoring and functional monitoring. Basic vital signal monitoring (including ECG, respiration, SpO2, blood pressure, temperature) is advanced and focus on study of usability, continuity and anti-interference. Functional monitoring (including respiratory function, circulatory function, cerebral function) still focus on study of monitoring precision and reliability. Meanwhile, video monitoring and artifact intelligence have presented well performance on improving monitoring precision and anti-interference. In this article, the main parameters and relevant measurement technology for monitoring critical neonates were described.
Subject(s)
Humans , Infant, Newborn , Intensive Care Units, Neonatal , Monitoring, Physiologic , Reproducibility of Results , Respiration , Technology , Vital SignsABSTRACT
Objective:Pulse oximetry plethysmographic (POP) waveform to indicate the patient's perfusion status and the quality of resuscitation has been affirmed. The POP waveform is obtained by a non-invasive monitoring method, and its clinical feasibility during CPR is better than that of invasive monitoring technologies. This study aimed to analyze the three parameters derived from POP waveform: CPR quality index (CQI), perfusion index (PI), and chest compression fraction (CCF) in evaluating the CPR quality and ROSC possibility.Methods:A prospective descriptive study was conducted on 74 CPR patients who were divided into the ROSC group and non-ROSC group according to their resuscitation results. The clinical data were extracted from patient monitor, the distribution and changes of the three parameters during CPR were collected, and their value of evaluating resuscitation outcome were analyzed.Results:At the end stage of resuscitation, there were statistically significant differences in the three parameters between the two groups ( P<0.05). In addition, CQI was significantly more capable in evaluating the possibility of ROSC than PI and CCF ( P<0.05). Conclusions:CQI, PI and CCF derived from POP waveform can all be applied to evaluate CPR quality and ROSC possibility. CQI has higher prognosis value than PI and CCF.
ABSTRACT
Physiological parameters monitoring is essential to direct medical staff to evaluate, diagnose and treat critical patients quantitatively. ECG, blood pressure, SpO2, respiratory rate and body temperature are the basic vital signs of patients in the ICU. The measuring methods are relatively mature at present, and the trend is to be wireless and more accurate and comfortable. Hemodynamics, oxygen metabolism and microcirculation should be taken seriously during the treatment of acute critical patients. The related monitoring technology has made significant progress in recent years, the trend is to reduce the trauma and improve the accuracy and usability. With the development of machine vision and data fusion technology, the identification of patient behavior and deterioration has become hot topics. This review is focused on current parameters monitoring technologies, aims to provide reference for future related research.
Subject(s)
Humans , Intensive Care Units , Monitoring, Physiologic , Oxygen Saturation , Technology , Vital SignsABSTRACT
Water is an important component in liquid medical device products for human assisted reproductive technology. Water traits, conductivity, microbial limits, total organic carbon, easy oxides, heavy metal content, bacterial endotoxin and other indicators have an important impact on sperm, egg and embryo development in vitro, so for such products, the quality of water control is extremely important. The production water for producing such products is generally prepared by MilliQ purification system. In this research, we used four different types of water to fabricate the IVF liquids. It included deionized reverse osmosis water, ultra purified water and ultra purified water without endotoxin or nucleic acid, and compared with tap water. The in vitro rat embryo test system was used to study the embryotoxicity of this four different culture liquid production waters. From the result, the group of the super purified water without endotoxin and nucleic acid has the best result of the embryo formation rate, the number of total cell number and the inner cell number. This study proved the importance of removing endotoxin and nucleic acid from the water used for the preparation of the liquid products for assisted reproduction, and provided the basis for the selection of water quality for the liquid products for assisted reproduction.
Subject(s)
Animals , Humans , Rats , Embryonic Development , Equipment Contamination , Fertilization in Vitro/instrumentation , Reproductive Techniques, Assisted , Research , Technology , WaterABSTRACT
Various types of medical devices used in assisted reproductive technologies (ART) should be detected for their safety by strict biological assays. Mouse embryo assay(MEA)has been recognized as one of the most important and standardized methods with the threshold more than 80% of blastocyst formation rate (BR) after 96 h culture of fertilized eggs. The disadvantage using BR for embryonic quality control has been concerned as it is ubiquitously dependent of embryonic morphology and the detailed data including molecular and genetic information is obviously missing and incomplete. This leads to the urgent requirement for more sensitive and efficient assessments for the quality control of ART. This study evaluated the reliability of an immunofluorescent MEA by counting total cell and differential number of the cells in the inner cell mass (ICM) and trophectoderm (TE) in the blastocyst. This method improved the traditional MEA, provided a sensitive and powerful platform to assess embryonic developmental viability and should be suggested as a standard assay to be globally used for the quality control of medical devices and pre-clinical procedures in ART.