LDSG-Net: an efficient lightweight convolutional neural network for acute hypotensive episode prediction during ICU hospitalization.

Objective. Acute hypotension episode (AHE) is one of the most critical complications in intensive care unit (ICU). A timely and precise AHE prediction system can provide clinicians with sufficient time to respond with proper therapeutic measures, playing a crucial role in saving patients' lives. Recent studies have focused on utilizing more complex models to improve predictive performance. However, these models are not suitable for clinical application due to limited computing resources for bedside monitors.Approach. To address this challenge, we propose an efficient lightweight dilated shuffle group network. It effectively incorporates shuffling operations into grouped convolutions on the channel and dilated convolutions on the temporal dimension, enhancing global and local feature extraction while reducing computational load.Main results. Our benchmarking experiments on the MIMIC-III and VitalDB datasets, comprising 6036 samples from 1304 patients and 2958 samples from 1047 patients, respectively, demonstrate that our model outperforms other state-of-the-art lightweight CNNs in terms of balancing parameters and computational complexity. Additionally, we discovered that the utilization of multiple physiological signals significantly improves the performance of AHE prediction. External validation on the MIMIC-IV dataset confirmed our findings, with prediction accuracy for AHE 5 min prior reaching 93.04% and 92.04% on the MIMIC-III and VitalDB datasets, respectively, and 89.47% in external verification.Significance. Our study demonstrates the potential of lightweight CNN architectures in clinical applications, providing a promising solution for real-time AHE prediction under resource constraints in ICU settings, thereby marking a significant step forward in improving patient care.

[Development of Vital Signal Monitoring System Based on Accelerometer].

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.

A streamlined platform for analyzing tera-scale DDA and DIA mass spectrometry data enables highly sensitive immunopeptidomics.

Integrating data-dependent acquisition (DDA) and data-independent acquisition (DIA) approaches can enable highly sensitive mass spectrometry, especially for imunnopeptidomics applications. Here we report a streamlined platform for both DDA and DIA data analysis. The platform integrates deep learning-based solutions of spectral library search, database search, and de novo sequencing under a unified framework, which not only boosts the sensitivity but also accurately controls the specificity of peptide identification. Our platform identifies 5-30% more peptide precursors than other state-of-the-art systems on multiple benchmark datasets. When evaluated on immunopeptidomics datasets, we identify 1.7-4.1 and 1.4-2.2 times more peptides from DDA and DIA data, respectively, than previously reported results. We also discover six T-cell epitopes from SARS-CoV-2 immunopeptidome that might represent potential targets for COVID-19 vaccine development. The platform supports data formats from all major instruments and is implemented with the distributed high-performance computing technology, allowing analysis of tera-scale datasets of thousands of samples for clinical applications.

[Research Progress of Physiologic Parameters Monitoring Technology for Critical Neonates].

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.

[Clinical Significance of Application of Comprehensive Management of Atrial Fibrillation].

OBJECTIVE: To improve the accuracy of detection of arrhythmia in patients with atrial fibrillation (AF) and to enable the scientific management and assessment of AF, a comprehensive management tool for AF is proposed, which is helpful for medical staff to systematically evaluate and manage patients with AF. METHODS: A professional view of atrial fibrillation (AF View) was designed to unify the statistical information of AF event, and display the statistical distribution data of AF events and trend data of other physiological parameters or characteristics such as heart rate, blood pressure and ST value during the patient monitoring period in a centralized manner. A multi-dimensional summary information was obtained from AF View. In addition, the monitoring period and monitoring parameters or characteristics in the AF View can be adjusted so as to obtain the summary information under different periods and parameters or characteristics, and get the condition of AF of the patient. RESULTS: Accurate detection and comprehensive management of AF were achieved. CONCLUSIONS: The application of AF comprehensive management proposed in this study is helpful for medical staff to know the condition of AF patients in real time and adjust the treatment plan in time.

[Review of Physiological Parameters Monitoring Technology in the ICU].

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.

[Research on Patient Monitoring Alarms in ICU and NICU].

OBJECTIVE: The patient monitors were used to explore the alarm actuality in a ICU and NICU to investigate the awareness and reaction of medical staff to alarms. METHODS: A series of surveys and interviews were taken to acquire clinicians' feelings and attitudes to monitoring alarms. The researchers were scheduled to track the alarms with annotations, and collect the alarm data of patient monitors using central monitoring system. RESULTS: A total of 235 387 and 67 783 alarms occurred in ICU and NICU respectively. The average alarm rate was about 142 alarms/patient-day in ICU and 96 alarms/patient-day in NICU. CONCLUSIONS: There remains alarm fatigue in ICU and NICU, the main reason is the large number of false alarms and clinically irrelevant alarms. In addition, patient monitor is still in the level of threshold alarms or combined alarms, the data integrity and intelligence level need to be improved in future.

[Research of Methods to Reduce Alarm Fatigue of Monitoring System].

OBJECTIVE: In order to solve alarm fatigue, the algorithm optimization strategies were researched to reduce false and worthless alarms. METHODS: A four-lead arrhythmia analysis algorithm, a multiparameter fusion analysis algorithm, an intelligent threshold reminder, a refractory period delay technique were proposed and tested with collected 28 679 alarms in multi-center study. RESULTS: The sampling survey indicate that the 80.8% of arrhythmia false alarms were reduced by the four-lead analysis, the 55.9% of arrhythmia and pulse false alarms were reduced by the multi-parameter fusion analysis, the 28.0% and 29.8% of clinical worthless alarms were reduced by the intelligent threshold and refractory period delay techniques respectively. Finally, the total quantity of alarms decreased to 12 724. CONCLUSIONS: To increase the dimensionality of parametric analysis and control the alarm limits and delay time are conducive to reduce alarm fatigue in intensive care units.