Our team proposed and constructed an Expert-knowledge and Data-driven Comprehensive Evaluation Model of Chinese Patent Medicine (EDCEM-CPM) using the machine learning algorithm. This model could improve the system of the comprehensive evaluation of the Chinese patent medicine in technology and provide measurement tools for Chinese patent medicine according to its characteristics. The model evaluates the multi-dimensional value of Chinese patent medicine by data pre-treatment, clustering algorithms, and data training steps, such as automatic learning weighting. This evaluation model is already in practice. In this paper, we introduced the establishment of the model with the calculation process for reference.
As an interdisciplinary subject of medicine and artificial intelligence, intelligent diagnosis and treatment has received extensive attention in both academia and industry. Traditional Chinese medicine (TCM) is characterized by individual syndrome differentiation as well as personalized treatment with personality analysis, which makes the common law mining technology of big data and artificial intelligence appear distortion in TCM diagnosis and treatment study. This article put forward an intelligent diagnosis model of TCM, as well as its construction method. It could not only obtain personal diagnosis varying individually through active learning, but also integrate multiple machine learning models for training, so as to form a more accurate model of learning TCM. Firstly, we used big data extraction technique from different case sources to form a structured TCM database under a unified view. Then, taken a pediatric common disease pneumonia with dyspnea and cough as an example, the experimental analysis on large-scale data verified that the TCM intelligent diagnosis model based on active learning is more accurate than the pre-existing machine learning methods, which may provide a new effective machine learning model for studying TCM diagnosis and treatment.
With the development of artificial intelligence, machine learning has been widely used in diagnosis of diseases. It is crucial to conduct diagnostic test accuracy studies and evaluate the performance of models reasonably to improve the accuracy of diagnosis. For machine learning-based diagnostic test accuracy studies, this paper introduces the principles of study design in the aspects of target conditions, selection of participants, diagnostic tests, reference standards and ethics.
Hypertension is the primary disease that endangers human health. A convenient and accurate blood pressure measurement method can help to prevent the hypertension. This paper proposed a continuous blood pressure measurement method based on facial video signal. Firstly, color distortion filtering and independent component analysis were used to extract the video pulse wave of the region of interest in the facial video signal, and the multi-dimensional feature extraction of the pulse wave was preformed based on the time-frequency domain and physiological principles; Secondly, an integrated feature selection method was designed to extract the universal optimal feature subset; After that, we compared the single person blood pressure measurement models established by Elman neural network based on particle swarm optimization, support vector machine (SVM) and deep belief network; Finally, we used SVM algorithm to build a general blood pressure prediction model, which was compared and evaluated with the real blood pressure value. The experimental results showed that the blood pressure measurement results based on facial video were in good agreement with the standard blood pressure values. Comparing the estimated blood pressure from the video with standard blood pressure value, the mean absolute error (MAE) of systolic blood pressure was 4.9 mm Hg with a standard deviation (STD) of 5.9 mm Hg, and the MAE of diastolic blood pressure was 4.6 mm Hg with a STD of 5.0 mm Hg, which met the AAMI standards. The non-contact blood pressure measurement method based on video stream proposed in this paper can be used for blood pressure measurement.
This paper expounds the classification and characteristics of healthcare-associated infections (HAI) surveillance systems from the perspective of the informatization needs of HAI monitoring, explains the determination requirements of numerator and denominator in the surveillance statistical data, and introduces the regular verification for auditing the quality of HAI surveillance. The basic knowledge of machine learning and its achievements are introduced in processing surveillance data as well. Machine learning may become the mainstream algorithm of HAI automatic monitoring system in the future. Infection control professionals should learn relevant knowledge, cooperate with computer engineers and data analysts to establish more effective, reasonable and accurate monitoring systems, and improve the outcomes of HAI prevention and control in medical institutions.
Tuberculosis is one of the major infectious diseases that seriously endanger human health. Since 2014, it has surpassed human immunodeficiency virus/acquired immunodeficiency syndrome as the first infectious disease in patients with single pathogens. China is the third-largest country in the world in terms of high burden of tuberculosis. In 2016, there were about 900 000 new cases of tuberculosis in China. China is facing a severe tuberculosis epidemic, especially for the early diagnosis of tuberculosis and misdiagnosis of tuberculosis, which leads to delay in treatment and the spread of tuberculosis. With the application of artificial intelligence in the medical field, machine learning and deep learning methods have shown important value in the diagnosis of tuberculosis. This article will explain the application status and future development of machine learning and deep learning in the diagnosis of tuberculosis.
Alzheimer’s disease (AD) is a common and serious form of elderly dementia, but early detection and treatment of mild cognitive impairment can help slow down the progression of dementia. Recent studies have shown that there is a relationship between overall cognitive function and motor function and gait abnormalities. We recruited 302 cases from the Rehabilitation Hospital Affiliated to National Rehabilitation Aids Research Center and included 193 of them according to the screening criteria, including 137 patients with MCI and 56 healthy controls (HC). The gait parameters of the participants were collected during performing single-task (free walking) and dual-task (counting backwards from 100) using a wearable device. By taking gait parameters such as gait cycle, kinematics parameters, time-space parameters as the focus of the study, using recursive feature elimination (RFE) to select important features, and taking the subject’s MoCA score as the response variable, a machine learning model based on quantitative evaluation of cognitive level of gait features was established. The results showed that temporal and spatial parameters of toe-off and heel strike had important clinical significance as markers to evaluate cognitive level, indicating important clinical application value in preventing or delaying the occurrence of AD in the future.
Sleep apnea causes cardiac arrest, sleep rhythm disorders, nocturnal hypoxia and abnormal blood pressure fluctuations in patients, which eventually lead to nocturnal target organ damage in hypertensive patients. The incidence of obstructive sleep apnea hypopnea syndrome (OSAHS) is extremely high, which seriously affects the physical and mental health of patients. This study attempts to extract features associated with OSAHS from 24-hour ambulatory blood pressure data and identify OSAHS by machine learning models for the differential diagnosis of this disease. The study data were obtained from ambulatory blood pressure examination data of 339 patients collected in outpatient clinics of the Chinese PLA General Hospital from December 2018 to December 2019, including 115 patients with OSAHS diagnosed by polysomnography (PSG) and 224 patients with non-OSAHS. Based on the characteristics of clinical changes of blood pressure in OSAHS patients, feature extraction rules were defined and algorithms were developed to extract features, while logistic regression and lightGBM models were then used to classify and predict the disease. The results showed that the identification accuracy of the lightGBM model trained in this study was 80.0%, precision was 82.9%, recall was 72.5%, and the area under the working characteristic curve (AUC) of the subjects was 0.906. The defined ambulatory blood pressure features could be effectively used for identifying OSAHS. This study provides a new idea and method for OSAHS screening.
With the development of artificial intelligence (AI) technology, great progress has been made in the application of AI in the medical field. While foreign journals have published a large number of papers on the application of AI in epilepsy, there is a dearth of studies within domestic journals. In order to understand the global research progress and development trend of AI applications in epilepsy, a total of 895 papers on AI applications in epilepsy included in the Web of Science Core Collection and published before December 31, 2022 were selected as the research objects. The annual number of papers and their cited times, the most published authors, institutions and countries, and their cooperative relationships were analyzed, and the research hotspots and future trends in this field were explored by using bibliometrics and other methods. The results showed that before 2016, the annual number of papers on the application of AI in epilepsy increased slowly, and after 2017, the number of publications increased rapidly. The United States had the largest number of papers (n=273), followed by China (n=195). The institution with the largest number of papers was the University of London (n=36), and Capital Medical University in China had 23 papers. The author with the most published papers was Gregory Worrell (n=14), and the scholar with the most published articles in China was Guo Jiayan from Xiamen University (n=7). The application of machine learning in the diagnosis and treatment of epilepsy is an early research focus in this field, while the seizure prediction model based on EEG feature extraction, deep learning especially convolutional neural network application in epilepsy diagnosis, and cloud computing application in epilepsy healthcare, are the current research priorities in this field. AI-based EEG feature extraction, the application of deep learning in the diagnosis and treatment of epilepsy, and the Internet of things to solve epilepsy health-related problems are the research aims of this field in the future.
ObjectiveTo explore the development and application of a novel ventilator alarm management model in critically ill patients receiving invasive mechanical ventilation (MV) in the intensive care unit (ICU) using machine learning (ML) and Internet of Medical Things (IoMT). The study aims to identify alarms’ intervention requirements. MethodsA retrospective cohort study and ML analysis were conducted, including adult patients receiving invasive MV in the ICU at West China Hospital from February 10, 2024, to July 22, 2024. A total of 76 ventilator alarm-related parameters were collected through the IoMT system. Feature selection was performed using a stratified approach, and six ML algorithms were applied: Gaussian Naive Bayes, K-Nearest Neighbors, Linear Discriminant Analysis, Support Vector Machine, Categorical Boosting (CatBoost), and Logistic Regression. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC). ResultsA total of 107 patients and their associated ventilator alarm records were included. Thirteen highly relevant features were selected from the 76 parameters for model training through stratified feature selection. The CatBoost model demonstrated the best predictive performance, with an AUC-ROC of 0.984 7 and an accuracy of 0.912 3 in the training set. External validation of the CatBoost model yielded an AUC-ROC of 0.805 4. ConclusionThe CatBoost-based ML model successfully constructed in this study has high accuracy and reliability in predicting the ventilator alarms in ICU patients, providing an effective tool for ventilator alarm management. The CatBoost-based ML method exhibited remarkable efficacy in predicting the necessity of ventilator intervention in critically ill ICU patients. Further large-scale multicenter studies are recommended to validate its clinical application value and promote model optimization and implementation.