Cardiotocography (CTG) is a non-invasive and important tool for diagnosing fetal distress during pregnancy. To meet the needs of intelligent fetal heart monitoring based on deep learning, this paper proposes a TWD-MOAL deep active learning algorithm based on the three-way decision (TWD) theory and multi-objective optimization Active Learning (MOAL). During the training process of a convolutional neural network (CNN) classification model, the algorithm incorporates the TWD theory to select high-confidence samples as pseudo-labeled samples in a fine-grained batch processing mode, meanwhile low-confidence samples annotated by obstetrics experts were also considered. The TWD-MOAL algorithm proposed in this paper was validated on a dataset of 16 355 prenatal CTG records collected by our group. Experimental results showed that the algorithm proposed in this paper achieved an accuracy of 80.63% using only 40% of the labeled samples, and in terms of various indicators, it performed better than the existing active learning algorithms under other frameworks. The study has shown that the intelligent fetal heart monitoring model based on TWD-MOAL proposed in this paper is reasonable and feasible. The algorithm significantly reduces the time and cost of labeling by obstetric experts and effectively solves the problem of data imbalance in CTG signal data in clinic, which is of great significance for assisting obstetrician in interpretations CTG signals and realizing intelligence fetal monitoring.
Humans ; Pregnancy ; Female ; Cardiotocography/methods* ; Deep Learning ; Neural Networks, Computer ; Algorithms ; Fetal Monitoring/methods* ; Heart Rate, Fetal ; Fetal Distress/diagnosis* ; Fetal Heart/physiology*

Heart failure (HF) is the end-stage of all cardiac diseases, characterized by high prevalence, high mortality, and heavy social and economic burden. Early warning of HF exacerbation is of great value for outpatient management and reducing readmission rates. Currently, remote dynamic monitoring technology, which captures changes in hemodynamic and physiological parameters of HF patients, has become the primary method for early warning and is a hot research topic in clinical studies. This paper systematically reviews the progress in this field, which was categorized into invasive monitoring based on implanted devices, non-invasive monitoring based on wearable devices, and other monitoring technologies based on audio and video. Invasive monitoring primarily involves direct hemodynamic parameters such as left atrial pressure and pulmonary artery pressure, while non-invasive monitoring covers parameters such as thoracic impedance, electrocardiogram, respiration, and activity levels. These parameters exhibit characteristic changes in the early stages of HF exacerbation. Given the clinical heterogeneity of HF patients, multi-source information fusion analysis can significantly improve the prediction accuracy of early warning models. The results of this study suggest that, compared with invasive monitoring, non-invasive monitoring technology, with its advantages of good patient compliance, ease of operation, and cost-effectiveness, combined with AI-driven multimodal data analysis methods, shows significant clinical application potential in establishing an outpatient management system for HF.
Humans ; Heart Failure/physiopathology* ; Monitoring, Physiologic/methods* ; Wearable Electronic Devices ; Remote Sensing Technology ; Early Diagnosis ; Electrocardiography ; Hemodynamics

General anesthesia, pivotal for surgical procedures, requires precise depth monitoring to mitigate risks ranging from intraoperative awareness to postoperative cognitive impairments. Traditional assessment methods, relying on physiological indicators or behavioral responses, fall short of accurately capturing the nuanced states of unconsciousness. This study introduces a machine learning-based approach to decode anesthesia depth, leveraging EEG data across different anesthesia states induced by propofol and esketamine in rats. Our findings demonstrate the model's robust predictive accuracy, underscored by a novel intra-subject dataset partitioning and a 5-fold cross-validation method. The research diverges from conventional monitoring by utilizing anesthetic infusion rates as objective indicators of anesthesia states, highlighting distinct EEG patterns and enhancing prediction accuracy. Moreover, the model's ability to generalize across individuals suggests its potential for broad clinical application, distinguishing between anesthetic agents and their depths. Despite relying on rat EEG data, which poses questions about real-world applicability, our approach marks a significant advance in anesthesia monitoring.
Animals ; Machine Learning ; Electroencephalography/methods* ; Ketamine/administration & dosage* ; Rats ; Male ; Propofol/administration & dosage* ; Rats, Sprague-Dawley ; Anesthesia, General/methods* ; Brain/physiology* ; Intraoperative Neurophysiological Monitoring/methods*

To explore the feasibility of using UAV-LiDAR for measuring the leaf area index (LAI) of crop canopies, we employed UAV-LiDAR to scan sugarcane canopies during the tillering and elongation stages, acquiring canopy point cloud data. Subsequently, features such as average row height, projected row area, point cloud density at different canopy layers, and the ratios between these parameters were extracted. Three feature selection methods-partial least squares regression (PLSR), XGBoost feature importance (XGBoost-FI), and random forest-recursive feature elimination (RF-RFE)-were adopted to evaluate and identify the optimal input variables for modeling. With these selected variables, LAI inversion models were developed based on random forest (RF) and adaptive boosting (AdaBoost) algorithms, and their performance was assessed. Among the extracted features, the projected row area S_p and the total row point count C_total exhibited strong correlations with LAI, with correlation coefficients of 0.73 and 0.72, respectively. The AdaBoost-based LAI inversion model, using the projected row area S_p, average height H_avg, mid-layer point cloud density C_m, and total row point count C_total as input variables, achieved the best performance, with a coefficient of determination (R_v²) of 0.713 and a root mean square error (RMSE_v) of 0.25 on the validation set. This study provides an effective method for high-throughput acquisition of LAI in field crops, offering valuable scientific support for sugarcane field management and breeding efforts.
Plant Leaves/growth & development* ; Saccharum/growth & development* ; Algorithms ; Unmanned Aerial Devices ; Remote Sensing Technology/methods* ; Crops, Agricultural/growth & development*

Objective To assess the blood pressure control and its influencing factors among hypertensive patients in communities in different time periods by 24 h ambulatory blood pressure monitoring(24 h ABPM)and provide reference for optimizing the health management services for hypertension in communities. Methods A total of 765 hypertensive patients registered in the hypertension management project of national essential public health services in Sanxiang Town,Zhongshan City from October 2022 to September 2023 were identified as target subjects.The 24 h ABPM devices were distributed for blood pressure monitoring and a questionnaire survey was conducted to analyze the influencing factors of blood pressure control. Results Of all the participants,16.5% did not monitor blood pressure regularly,and 59.2% monitored blood pressure 1-2 times per week.The patients who were not on night shifts/staying up late had higher mean rates of achieving the target blood pressure and the circadian rhythm of blood pressure during 24 h,nighttime,and early morning than those who were on night shifts/staying up late(all P<0.05).The patients who never drank alcohol had higher rate of achieving the target blood pressure in early morning than those who drank alcohol(P=0.012).The average blood pressure during daytime,nighttime,and 24 h were different by sex(all P<0.05).The average blood pressure during nighttime was different by age and job types(all P<0.05).The average blood pressure during daytime,nighttime,and 24 h were different in patients with different body weight types(all P<0.05).The results of the multivariate logistic regression analysis showed that uncontrolled blood pressure during daytime was more likely to occur in male patients(OR=1.394,95%CI=1.045-1.858,P=0.024),and that during nighttime was more likely to be associated with male patients(OR=1.573,95%CI=1.088-2.275,P=0.016)and night shifts(OR=2.467,95%CI=1.198-5.077,P=0.014).It was difficult to achieve blood pressure control in early morning for the patients who drank alcohol for more than three times per week(OR=4.567,95%CI=1.629-12.807,P=0.004),woke up at night(OR=1.800,95%CI=1.125-2.878,P=0.014),and had night shifts(OR=1.579,95%CI=1.102-2.465,P=0.044).The patients on night shifts were more likely to have abnormal circadian rhythm of blood pressure(OR=1.753,95%CI:1.018-3.018,P=0.043). Conclusions The personal characteristics and lifestyle of hypertensive patients significantly affect the blood pressure control in different time periods(daytime,nighttime,and early morning)and the circadian rhythm of blood pressure.The family doctor team of community healthcare institutions can implement targeted and precise intervention measures for hypertensive patients according to the influencing factors of blood pressure control in different time periods,so as to achieve better management effects.
Humans ; Blood Pressure Monitoring, Ambulatory ; Hypertension/physiopathology* ; Male ; Female ; Middle Aged ; Circadian Rhythm ; Blood Pressure ; Surveys and Questionnaires ; Adult ; Aged ; Time Factors

Objective To investigate the correlations of circulating miRNA-205 expression with systemic immune-inflammation index(SII)and systemic inflammation response index(SIRI)in patients with severe obstructive sleep apnea(OSA). Methods The patients who attended the Hypertension Center of the People's Hospital of Xinjiang Uygur Autonomous Region from January to June 2023 and underwent complete overnight polysomnography were consecutively included in this study.Among them,30 patients had severe OSA,and 32 patients did not have OSA.Blood routine tests(white blood cells,neutrophils,monocytes,platelets,etc.)were performed and the expression of miRNA-205 was determined by quantitative reverse transcription PCR.Simple regression was adopted to analyze the correlations among miRNA-205,SII,SIRI,and OSA parameters.The potential regulatory effects of miRNA-205 on OSA and inflammation indices were further evaluated. Results The patients with severe OSA showed lower expression of circulating miRNA-205[1.910(1.240,2.403)vs.3.650(2.148,5.109),z=-3.874,P<0.001]and higher SIRI[1.090(0.775,1.573)vs.0.870(0.650,1.240),z=-2.031,P=0.041]and SII[555.200(451.780,936.350)vs.448.685(380.823,646.073),z=-2.029,P=0.042]than non-OSA patients.In the whole population,apnea-hypopnea index(AHI)showed a negative correlation with circulating miRNA-205(r=-0.391,P=0.002).Among severe OSA patients,each 1-unit increase in AHI was associated with a reduction of 0.030 in miRNA-205 and increases of 10.046 and 0.037 in SII and SIRI,respectively(SII:P=0.003;SIRI:P=0.037).Conversely,each 1-unit rise in miRNA-205 predicted a decrease of 121.093 in SII(β=-0.40,P=0.046).The low expression of miRNA-205 might have a negative moderating effect on elevated SII(β=-0.40,P=0.004). Conclusions Compared with the patients without OSA,those with severe OSA showed elevated SII and SIRI and down-regulated expression of miRNA-205.The low expression of miRNA-205 might have a negative moderating effect on the systemic inflammatory state associated with severe OSA.
Humans ; Sleep Apnea, Obstructive/blood* ; MicroRNAs/blood* ; Inflammation/blood* ; Male ; Polysomnography ; Middle Aged ; Female ; Adult

This article reports the complete screening-diagnosis-rehabilitation process for an Air Force non-commissioned officer diagnosed with narcolepsy（NP） comorbid with obstructive sleep apnea （OSA） and REM sleep behavior disorder（RBD）.The patient attended the hospital due to uncontrollable daytime sleep for 3 years and one episode of cataplexy，and a confirmed diagnosis was made based on polysomnography， multiple sleep latency test （MSLT）， and imaging examination， with the exclusion of organic lesions. As for treatment， since the patient showed no response to venlafaxine alone， the treatment regimen was switched to a comprehensive regimen of behavioral interventions， traditional Chinese medicine syndrome differentiation， and pitolisant. Based on this case report and the literature review， it is proposed that the armed forces should introduce a modern diagnostic and therapeutic mode integrating routine screening （Epworth Sleepiness Scale and MSLT）， multidisciplinary dynamic assessment， and individualized comprehensive care， in order to provide evidence-based guidance for the early identification， diagnosis， and treatment of sleep disorders in military personnel.
Narcolepsy ; Polysomnography

BACKGROUND: In the real world, the plasma drug concentration range of Icotinib treated with epidermal growth factor receptor (EGFR) gene mutant non-small cell lung cancer (NSCLC) is not yet clear, and there may be a correlation between drug concentration and its efficacy, as well as adverse reactions. This study conducted therapeutic drug monitoring (TDM) of Icotinib. The aim of this study was to analyze the drug exposure of Icotinib in targeted therapy for NSCLC, and to investigate the relationship between Icotinib drug concentration and its efficacy and safety. METHODS: Prospective blood samples were collected from NSCLC patients with EGFR-sensitive mutations who received treatment with Icotinib in Peking University Cancer Hospital from April 2022 to July 2024. The drug trough concentration of Icotinib in plasma was detected, and the correlation between drug concentration and efficacy, as well as the toxic side effects, were further analyzed based on the patient's clinical medical records. RESULTS: 22 patients who were treated with Icotinib underwent TDM, but one of them did not acquire the data due to prolonged discontinuation. The remaining 21 patients, each with 1-7 blood draws, obtained a total of 32 plasma drug concentration data. The drug concentration of icotinib is a range of 126.9-2317.1 ng/mL. Among the 21 patients, 18 cases were female (85.7%), and 3 cases were male (14.3%), with an age range of 44-85 years old. The pathological types are all lung adenocarcinoma. Except for 5 patients receiving postoperative adjuvant therapy, 16 patients had assessable tumors. The objective response rate was 43.8% (7/16), and the disease control rate reached 100.0% (16/16). The median value of drug concentration is 805.5 ng/mL among those 21 patients. Compared with the patients who achieved stable disease, the median value of drug concentrations of Icotinib in patients who achieved partial response were 497.2 and 1195.5 ng/mL, respectively (P=0.017). The median value of drug concentrations for patients who did not experience adverse reactions during treatment and those who experienced adverse reactions were 997.0 and 828.6 ng/mL, respectively (P=0.538). CONCLUSIONS Icotinib demonstrates good therapeutic effect and tolerable toxicity on the EGFR gene mutant NSCLC. There is a certain negative correlation between the plasma drug concentration of Icotinib and its efficacy, while there seems no significant correlation with safety.
Humans ; Carcinoma, Non-Small-Cell Lung/genetics* ; ErbB Receptors/metabolism* ; Lung Neoplasms/genetics* ; Male ; Female ; Crown Ethers/blood* ; Middle Aged ; Drug Monitoring ; Aged ; Quinazolines/blood* ; Mutation ; Adult ; Aged, 80 and over ; Antineoplastic Agents/blood* ; Prospective Studies

The application of small molecule targeted drugs for lung cancer has significantly improved the survival of lung cancer patients. However, these drugs have a wide variety of types, fast development and market launch of new drugs, complex adverse reactions, and are mostly used at home, which increases the risk of irrational drug use. At the same time, insufficient monitoring of efficacy and safety is also prone to occur, ultimately affecting treatment outcomes. This consensus focuses on 43 small molecule targeted drugs or combinations for lung cancer, providing standardized recommendations for rational drug use and monitoring of efficacy/adverse reactions in clinical practice. The recommendations are regarding drug selection, dosage adjustment, efficacy monitoring, adverse reaction monitoring, and improvement of patient compliance. This consensus aims to improve the rational use and efficacy/safety monitoring quality of small molecule targeted drugs for lung cancer, ensure the effectiveness and safety of drug treatment, prolong the survival of lung cancer patients and improve their quality of life.
.
Humans ; Lung Neoplasms/drug therapy* ; Antineoplastic Agents/adverse effects* ; Consensus ; Molecular Targeted Therapy ; Drug Monitoring ; Small Molecule Libraries/therapeutic use*

Mycophenolic acid (MPA), the active moiety of both mycophenolate mofetil (MMF) and enteric-coated mycophenolate sodium (EC-MPS), serves as a primary immunosuppressant for maintaining solid organ transplants. Therapeutic drug monitoring (TDM) enhances treatment outcomes through tailored approaches. This study aimed to develop an evidence-based guideline for MPA TDM, facilitating its rational application in clinical settings. The guideline plan was drawn from the Institute of Medicine and World Health Organization (WHO) guidelines. Using the Delphi method, clinical questions and outcome indicators were generated. Systematic reviews, Grading of Recommendations Assessment, Development, and Evaluation (GRADE) evidence quality evaluations, expert opinions, and patient values guided evidence-based suggestions for the guideline. External reviews further refined the recommendations. The guideline for the TDM of MPA (IPGRP-2020CN099) consists of four sections and 16 recommendations encompassing target populations, monitoring strategies, dosage regimens, and influencing factors. High-risk populations, timing of TDM, area under the curve (AUC) versus trough concentration (C₀), target concentration ranges, monitoring frequency, and analytical methods are addressed. Formulation-specific recommendations, initial dosage regimens, populations with unique considerations, pharmacokinetic-informed dosing, body weight factors, pharmacogenetics, and drug‍-‍drug interactions are covered. The evidence-based guideline offers a comprehensive recommendation for solid organ transplant recipients undergoing MPA therapy, promoting standardization of MPA TDM, and enhancing treatment efficacy and safety.
Mycophenolic Acid/administration & dosage* ; Drug Monitoring/methods* ; Humans ; Organ Transplantation ; Immunosuppressive Agents/administration & dosage* ; Delphi Technique