1.Comparison of the predictive performance of SARIMA, Prophet, and BSTS models in forecasting the incidence of hand, foot, and mouth disease
LU Wenhai ; KONG Xiaojie ; SONG Lixia ; LU Chunru ; YU Bikun ; XIE Yan
Journal of Preventive Medicine 2026;38(1):79-84
Objective:
To compare the predictive performance of the seasonal autoregressive integrated moving average (SARIMA) model, the Prophet model, and the Bayesian structural time series (BSTS) model in forecasting the incidence of hand, foot, and mouth disease (HFMD) , so as to provide a basis for optimizing the early warning system of this disease.
Methods:
Weekly incidence data of HFMD in Longgang District, Shenzhen City from 2014 to 2024 were collected. The HFMD incidence data from 2014-2019 and 2023 were used as the training set to construct SARIMA, Prophet, and BSTS models, while the data from 2024 were used as the test set to compare and evaluate the predictive performance of the three models. The technique for order preference by similarity to ideal solution (TOPSIS) method was employed to calculate the C-value. This approach integrates multiple evaluation metrics, such as the mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and symmetric mean absolute percentage error (SMAPE), to comprehensively assess model performance.
Results:
A total of 150 111 cases of HFMD were reported in Longgang District from 2014 to 2024, with an average annual incidence of 400.72/105. The weekly incidence fluctuated between 0 and 63.78/105, exhibiting a bimodal seasonal pattern characterized by a primary peak from May to July and a secondary peak from September to October. In the training set, all three models demonstrated a good fit to the bimodal epidemic trend of HFMD, with the BSTS model achieving the best fit. The BSTS model yielded performance metrics as follows: MAE=0.124, MSE=0.050, RMSE=0.223, SMAPE=0.021, and a C-value of 1.000. In the test set, all three models, including SARIMA, Prophet, and BSTS, performed well for short-term predictions (≤16 weeks), with the Prophet model showing relatively superior predictive performance. However, the prediction accuracy of all models declined as the forecast horizon extended. During the primary peak period (May-July), the Prophet model exhibited better predictive performance, whereas the BSTS model performed relatively better during the secondary peak period (September-October).
Conclusions
For the short-term forecasting of weekly HFMD incidence, the Prophet model outperformed both the SARIMA and BSTS models. During the primary peak period, the Prophet model demonstrated superior predictive performance, whereas the BSTS model exhibited better accuracy in forecasting the secondary peak period.
2.Explainable Machine Learning Model for Predicting Prognosis in Patients with Malignant Tumors Complicated by Acute Respiratory Failure: Based on the eICU Collaborative Research Database in the United States
Zihan NAN ; Linan HAN ; Suwei LI ; Ziyi ZHU ; Qinqin ZHU ; Yan DUAN ; Xiaoting WANG ; Lixia LIU
Medical Journal of Peking Union Medical College Hospital 2026;17(1):98-108
To develop and validate a model for predicting intensive care unit (ICU) mortality risk in patients with malignant tumors complicated by acute respiratory failure (ARF) based on an explainable machine learning framework. Clinical data of patients with malignant tumors and ARF were extracted from the eICU Collaborative Research Database in the United States, including demographic characteristics, comorbidities, vital signs, laboratory test indicators, and major interventions within the first 24 hours after ICU admission.The study outcome was ICU death.Enrolled patients were randomly divided into a training set and a validation set at a ratio of 7:3.Predictor variables were selected using least absolute shrinkage and selection operator (LASSO) regression.Five machine learning algorithms-extreme gradient boosting (XGBoost), support vector machine (SVM), Logistic regression, multilayer perceptron (MLP), and C5.0 Decision Tree-were employed to construct predictive models.Model performance was evaluated based on the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and other metrics.The optimal model was further interpreted using the Shapley additive explanations (SHAP) algorithm. A total of 3196 patients with malignant tumors complicated by ARF were included.The training set comprised 2, 261 patients and the validation set 935 patients; 683 patients died during ICU stay, while 2513 survived.LASSO regression ultimately selected 12 variables closely associated with patient ICU outcomes, including sepsis comorbidity, use of vasoactive drugs, and within the first 24 hours after ICU admission: minimum mean arterial pressure, maximum heart rate, maximum respiratory rate, minimum oxygen saturation, minimum serum bicarbonate, minimum blood urea nitrogen, maximum white blood cell count, maximum mean corpuscular volume, maximum serum potassium, and maximum blood glucose.After model evaluation, the XGBoost model demonstrated the best performance.The AUCs for predicting ICU mortality risk in the training and validation sets were 0.940 and 0.763, respectively; accuracy was 88.3% and 81.2%;sensitivity was 98.5% and 95.9%.Its predictive performance also remained optimal in sensitivity analyses.SHAP analysis indicated that the top five variables contributing to the model's predictions were minimum oxygen saturation, minimum serum bicarbonate, minimum mean arterial pressure, use of vasoactive drugs, and maximum white blood cell count. This study successfully developed a mortality risk prediction model for ICU patients with malignant tumors complicated by ARF based on a large-scale dataset and performed explainability analysis.The model aids clinicians in early identification of high-risk patients and implementing individualized interventions.
3.Development and application of intensive care unit digital intelligence multimodal shift handover system.
Xue BAI ; Lixia CHANG ; Wei FANG ; Zhengang WEI ; Yan CHEN ; Zhenfeng ZHOU ; Min DING ; Hongli LIU ; Jicheng ZHANG
Chinese Critical Care Medicine 2025;37(10):950-955
OBJECTIVE:
To develop a digital intelligent multimodal shift handover system for the intensive care unit (ICU) and evaluate its application effect in ICU shift handovers.
METHODS:
A research and development team was established, consisting of 1 department director, 1 head nurse, 3 information technology engineers, 3 nurses, and 2 doctors. Team members were assigned responsibilities including overall coordination and planning, platform design and maintenance, pre-application training, collection and organization of clinical feedback, and research investigation respectively. A digital intelligent multimodal shift handover system was developed for ICU based on the Shannon-Weaver linear transmission model. This innovative system integrated automated data collection, intelligent dynamic monitoring, multidimensional condition analysis and visual reporting functions. A cloud platform was used to gather data from multi-parameter vital signs monitors, infusion pumps, ventilators and other devices. Artificial intelligence algorithms were employed to standardize and analyze the data, providing personalized recommendations for healthcare professionals. A self-controlled before-after method was adopted. Before the application of the ICU digital intelligent multimodal shift handover system (from December 2023 to March 2024), the traditional verbal bedside handover was used; from June 2024 to March 2025, the ICU digital intelligent multimodal shift handover system was applied for shift handovers. Questionnaires before the application of the shift handover system were collected in April 2024, and those after the application were collected in April 2025. The shift handover time, handover quality (scored by the nursing handover evaluation scale), satisfaction with doctor-nurse communication (scored by the ICU doctor-nurse scale) before and after the application of the handover system were compared, and nurses' satisfaction with the shift handover system (scored by the clinical nursing information system effectiveness evaluation scale) was investigated.
RESULTS:
After the application of the ICU digital intelligent multimodal shift handover system, the shift handover time was significantly shorter than that before the application [minutes: 20 (15, 25) vs. 30 (22, 40)], the handover quality was significantly higher than that before the application [score: 84.0 (78.0, 88.5) vs. 71.0 (55.0, 79.0)], and the satisfaction with doctor-nurse communication was also significantly higher than that before the application (score: 84.58±6.79 vs. 74.50±11.30). All differences were statistically significant (all P < 0.05). In addition, the nurses' system effectiveness evaluation scale score was 102.30±10.56, which indicated that nurses had a very high level of satisfaction with the ICU digital intelligent multimodal shift handover system.
CONCLUSIONS
The application of the ICU digital intelligent multimodal shift handover system can shorten the shift handover time, improve the handover quality, and enhance the satisfaction with doctor-nurse communication. Nurses have a high level of satisfaction with this system.
Intensive Care Units
;
Humans
;
Patient Handoff
;
Artificial Intelligence
;
Algorithms
4.Effect of flexible endoscopic evaluation of swallowing on clinical functional outcomes in patients with intensive care unit-acquired swallowing disorders
Yandong SUN ; Lixia HAO ; Yan ZHANG ; Naqi ZHOU ; Zhiyu JIAO ; Ying JIAO ; Yihuan DONG ; Ling XU ; Huri LETEMUER
Chinese Journal of Otorhinolaryngology Head and Neck Surgery 2025;60(11):1383-1388
Objective:To evaluate the effect of fiberoptic endoscopic evaluation of swallowing (FEES) on clinical functional outcomes of patients with intensive care unit-acquired swallowing disorders (ICU-ASD).Methods:This retrospective cohort study analyzed clinical data of patients diagnosed with post-extubation dysphagia (PED) in the intensive care unit (ICU) and respiratory intensive care unit (RICU) of the Affiliated Hospital of Inner Mongolia Medical University from February 2020 to February 2025. Patients were categorized into a FEES group of 60 cases [34 males, 26 females, aged 37-80 years (median age 62 years)] and a control group without FEES of 58 cases [32 males, 26 females, aged 39-77 years (median age 61 years)].The patients in two groups received swallowing function and feeding training based on the results of the FEES assessment and the Volume-Viscosity Swallow Test-Clinical Version (VVST-CV), respectively. Clinical functional outcome measures included pneumonia incidence, clinical pulmonary infection score (CPIS), pneumonia severity index (PSI), Functional Oral Intake Scale (FOIS), and dietary method at discharge. χ2 test, Mann-Whitney U test, and Wilcoxon signed-rank test, were employed for statistical analysis of the outcome measures. Results:Compared with the control group, the FEES group had significantly lower aspiration pneumonia incidence at discharge [3.3% (2/60) vs 15.5% (9/58), χ2=5.179, P=0.023]. Regarding dietary methods,a significantly higher proportion of patients in the FEES group achieved complete oral feeding compared with the control group [75.0% (45/60) vs 67.3% (39/58), χ2=8.065, P<0.05]. After training, the FEES group had higher median FOIS scores than the control group (7.00 vs 6.00, Z=-2.370, P=0.018), and lower CPIS scores (2.50 vs 5.00, Z=-2.216, P=0.027) and PSI scores (59.00 vs 73.00, Z=-2.251, P=0.024). Within-group comparisons revealed that FOIS scores significantly improved post-training in both groups (both P<0.001). Conclusion:Early FEES examination for ICU patients with acquired swallowing disorders is associated with a lower incidence of pneumonia, improved swallowing function, and superior clinical functional outcomes.
5.Pain, agitation, and delirium practices in Chinese intensive care units: A national multicenter survey study.
Xiaofeng OU ; Lijie WANG ; Jie YANG ; Pan TAO ; Cunzhen WANG ; Minying CHEN ; Xuan SONG ; Zhiyong LIU ; Zhenguo ZENG ; Man HUANG ; Xiaogan JIANG ; Shusheng LI ; Erzhen CHEN ; Lixia LIU ; Xuelian LIAO ; Yan KANG
Chinese Medical Journal 2025;138(22):3031-3033
6.Expert consensus on visualized tele-round and quality control management based on the improvement of clinical practice ability
Wanhong YIN ; Xiaoting WANG ; Ran ZHOU ; Dawei LIU ; Yan KANG ; Yaoqing TANG ; Xiaochun MA ; Jianguo LI ; Zhenjie HU ; Haitao ZHANG ; Wei HE ; Lixia LIU ; Wenjin CHEN ; Ran ZHU ; Jun WU ; Hongmin ZHANG ; Lina ZHANG ; Wenzhao CHAI ; Shihong ZHU ; Wangbin XU ; Rongqing SUN ; Xiangyou YU ; Tianjiao SONG ; Ying ZHU ; Hong REN ; Ai SHANMU ; Qing ZHANG ; Wei FANG ; Xiuling SHANG ; Liwen LYU ; Shuhan CAI ; Xin DING ; Heng ZHANG ; Guang FENG ; Lipeng ZHANG ; Bo HU ; Dong ZHANG ; Weidong WU ; Feng SHEN ; Xiaojun YANG ; Zhenguo ZENG ; Qibing HUANG ; Xueying ZENG ; Tongjuan ZOU ; Milin PENG ; Yulong YAO ; Mingming CHEN ; Hui LIAN ; Jingmei WANG ; Yong LI ; Feng QU ; Gang YE ; Rongli YANG ; Xiukai CHEN ; Suwei LI ; Juxiang WANG ; Yangong CHAO
Chinese Journal of Internal Medicine 2025;64(2):101-109
Turning to critical illness is a common stage of various diseases and injuries before death. Patients usually have complex health conditions, while the treatment process involves a wide range of content, along with high requirements for doctor′s professionalism and multi-specialty teamwork, as well as a great demand for time-sensitive treatments. However, this is not matched with critical care professionals and the current state of medical care in China. Telemedicine, which shortens the distance of medical professionals and the gap of disease diagnosis and treatments in various regions through electronic information, can effectively solve the current problem. Therefore, there is an urgent need to develop a standardized, high-quality visualization telemedicine round system .Therefore, experts have been organized to search domestic and foreign literature on telemedicine round for critically ill patients and to form this consensus based on clinical experiences so as to further improve the level of critical care treatments in regions.
7.Clinical value analysis of different MRI measurement methods in evaluating the efficacy of neoadjuvant therapy for breast cancer
Yuling DUAN ; Xuezhi ZHOU ; Yongyi LI ; Lixia MA ; Desheng YANG ; Jiao CHENG ; Yan WU ; Tao LIU ; Guoyuan JIANG ; Mei WANG
The Journal of Practical Medicine 2025;41(14):2152-2159
Objective To compare the diagnostic performance of three breast MRI measurement methods—RECIST 1.1,the optimal method,and three-dimensional(3D)volumetric assessment—in assessing the efficacy of neoadjuvant chemotherapy(NAC)in breast cancer patients,with the objective of identifying the most clinically practical approach.Methods A total of 110 breast cancer patients who underwent NAC followed by surgical treatment between 2019 and 2023 were included in the study.Breast magnetic resonance imaging(MRI)was conducted within one week before and after the completion of NAC.Tumor response was evaluated using RECIST 1.1 criteria,widely recognized as the optimal method,as well as 3D volume measurement.Pathological response was determined according to the Miller-Payne grading system.Sensitivity,specificity,accuracy,and the area under the receiver operating characteristic curve(AUC)were computed and compared using the DeLong test.Results The AUC values for RECIST 1.1,the optimal method,and 3D volumetric assessment were 0.768,0.795,and 0.883,respectively.The 3D volumetric assessment exhibited significantly better discriminative performance(P<0.05),with the highest sensitivity(98.9%),specificity(77.8%),and accuracy(95.5%).Additionally,the optimal method demonstrated superior performance over RECIST 1.1 across multiple parameters.Conclusions 3D volumetric mea-surement demonstrates superior performance compared to RECIST 1.1 and the optimal method in evaluating the response to NAC,offering a more accurate and comprehensive assessment tool.Additionally,the optimal method shows advantages over RECIST 1.1 and may serve as a practical alternative in settings where 3D software is not available.
8.Effect of flexible endoscopic evaluation of swallowing on clinical functional outcomes in patients with intensive care unit-acquired swallowing disorders
Yandong SUN ; Lixia HAO ; Yan ZHANG ; Naqi ZHOU ; Zhiyu JIAO ; Ying JIAO ; Yihuan DONG ; Ling XU ; Huri LETEMUER
Chinese Journal of Otorhinolaryngology Head and Neck Surgery 2025;60(11):1383-1388
Objective:To evaluate the effect of fiberoptic endoscopic evaluation of swallowing (FEES) on clinical functional outcomes of patients with intensive care unit-acquired swallowing disorders (ICU-ASD).Methods:This retrospective cohort study analyzed clinical data of patients diagnosed with post-extubation dysphagia (PED) in the intensive care unit (ICU) and respiratory intensive care unit (RICU) of the Affiliated Hospital of Inner Mongolia Medical University from February 2020 to February 2025. Patients were categorized into a FEES group of 60 cases [34 males, 26 females, aged 37-80 years (median age 62 years)] and a control group without FEES of 58 cases [32 males, 26 females, aged 39-77 years (median age 61 years)].The patients in two groups received swallowing function and feeding training based on the results of the FEES assessment and the Volume-Viscosity Swallow Test-Clinical Version (VVST-CV), respectively. Clinical functional outcome measures included pneumonia incidence, clinical pulmonary infection score (CPIS), pneumonia severity index (PSI), Functional Oral Intake Scale (FOIS), and dietary method at discharge. χ2 test, Mann-Whitney U test, and Wilcoxon signed-rank test, were employed for statistical analysis of the outcome measures. Results:Compared with the control group, the FEES group had significantly lower aspiration pneumonia incidence at discharge [3.3% (2/60) vs 15.5% (9/58), χ2=5.179, P=0.023]. Regarding dietary methods,a significantly higher proportion of patients in the FEES group achieved complete oral feeding compared with the control group [75.0% (45/60) vs 67.3% (39/58), χ2=8.065, P<0.05]. After training, the FEES group had higher median FOIS scores than the control group (7.00 vs 6.00, Z=-2.370, P=0.018), and lower CPIS scores (2.50 vs 5.00, Z=-2.216, P=0.027) and PSI scores (59.00 vs 73.00, Z=-2.251, P=0.024). Within-group comparisons revealed that FOIS scores significantly improved post-training in both groups (both P<0.001). Conclusion:Early FEES examination for ICU patients with acquired swallowing disorders is associated with a lower incidence of pneumonia, improved swallowing function, and superior clinical functional outcomes.
9.Investigation on the current nursing practice status of prone position ventilation in patients with moderate to severe acute respiratory distress syndrome among intensive care unit nurses in Shandong province
Lixia CHANG ; Jicheng ZHANG ; Min DING ; Fengzhi CHEN ; Yan CHEN ; Beibei LIU ; Li CHEN ; Xue BAI
Chinese Journal of Integrated Traditional and Western Medicine in Intensive and Critical Care 2025;32(1):67-72
Objective To understand the nursing practice of prone position ventilation for patients with moderate to severe acute respiratory distress syndrome(ARDS)in intensive care unit(ICU)in Shandong province,so as to provide basis for standardizing the nursing practice process of prone position ventilation and carrying out training for hospitals.Methods A self-made questionnaire was used,and convenience sampling was adopted.From September 15th to November 5th,2023,ICU nurses were selected from various hospital levels in Shandong province to investigate the obstructive factors of prone ventilation implementation,the weak links in nursing practice and status,and the occurrence of complications.Results A total of 1 188 questionnaires were collected,of which 991 were valid.92.8%(920/991)of nurses had performed prone position ventilation.The biggest obstacle to the implementation of prone position ventilation was the complexity of patient treatments and multiple devices involved[74.6%(686/920)].Regarding the status of training,90.5%(897/991)of nurses had received training on prone position ventilation and 77.0%(763/991)of nurses felt that training was needed.As for pre-operation assessment,more than 80.0%of nurses evaluated patients'vital signs,airway and secretions and so on,among which the evaluation awareness of analgesia was the worst[81.6%(751/920)].As for the main points of implementation,only 14.0%(129/920)of nurses chose the opposite side of the most important pipeline as the turning direction;48.6%(447/920)of nurses chose the anti-Trendelenburg position;36.3%(334/920)of nurses chose to ventilate≥12 hours.Facial edema[81.7%(752/920)],skin pressure injury[78.9%(726/920)]and eye complication[75.8%(697/920)]were the top 3 most frequent complications.Conclusions ICU nurses'prone position ventilation practices were generally line with the nursing team standard for prone position of adult mechanically ventilated patients and the best evidence recommendation,and needs to be further standardized in aspects of turning direction,position management,ventilation duration,and enteral nutrition management.It is recommended that nursing managers at all levels of hospitals further improve the quality of nursing practice of prone position ventilation according to relevant evidence-based evidence and the actual situation of hospitals.
10.A cross-sectional study of anxiety disorders in adults in Inner Mongolia Autonomous Region
Xin WANG ; Lixia CHEN ; Tingting ZHANG ; Ping LYU ; Dongsheng LYU ; Zhaorui LIU ; Jie YAN ; Ruiqi WANG ; Hua DING ; Yinxia BAI ; Yueqin HUANG ; Xiaojie SUI
Chinese Mental Health Journal 2025;39(5):385-391
Objective:To describe the prevalence of anxiety disorders and its distribution in Inner Mongolia Autonomous Region,and to explore the relevant factors of anxiety disorders.Methods:From June 2019 to Decem-ber 2019,representative multi-stage disproportionate stratified sampling procedure was used to sample in residents aged 18 and over in the Inner Mongolia Autonomous Region.All respondents were face-to-face interviewed by trained interviewers.Composite International Diagnostic Interview-3.0(CIDI-3.0)was used to diagnose anxiety disorders according to the criteria and definition of the Diagnostic and Statistical Manual of Mental Disorders,Fourth Edition(DSM-Ⅳ).Chi-square test and multivariate logistic regression analysis were used for statistical anal-ysis.Results:Totally 12 315 people were interviewed in the survey.The weighted 12-mouth prevalence rate of any anxiety disorder was 4.64%,and the lifetime prevalence rate was 6.25%.The weighted 12-month prevalence rate of anxiety disorders was higher in female than that in male(5.38%vs.3.92%).The rate was higher in rural resi-dents than that in urban residents(5.67%vs.3.95%).The rate was higher in people with chronic diseases than that in people without chronic diseases(6.81%vs.2.29%).Logistic regression analysis showed that unmarried(OR=2.32,95%CI:1.31-4.10),separated/divorced(OR=2.49,95%CI:1.33-4.67),in debt(OR=1.55,95%CI:1.04-2.32),chronic disease(OR=2.22,95%CI:1.39-3.53),family history of anxiety disorders(OR=12.05,95%CI:8.78-16.53),poor sleep(OR=2.64,95%CI:1.97-3.54)were risk factors of occurrence of anxiety disorders,while junior high school(OR=0.65,95%CI:0.44-0.96)was protective factor of anxiety disor-ders.Conclusion:Adults with chronic diseases,poor sleep,unmarried or separated/divorced,family history of anxi-ety disorders,and financial debt are at higher risk groups of anxiety disorder in Inner Mongolia Autonomous Re-gion.


Result Analysis
Print
Save
E-mail