1.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.
2.Serological and molecular biological analysis of a rare Dc- variant individual
Xue TIAN ; Hua XU ; Sha YANG ; Suili LUO ; Qinqin ZUO ; Liangzi ZHANG ; Xiaoyue CHU ; Jin WANG ; Dazhou WU ; Na FENG
Chinese Journal of Blood Transfusion 2025;38(8):1101-1106
Objective: To reveal the molecular biological mechanism of a rare Dc-variant individual using PacBio third-generation sequencing technology. Methods: ABO and Rh blood type identification, DAT, unexpected antibody screening and D antigen enhancement test were conducted by serological testing. The absorption-elution test was used to detect the e antigen. RHCE gene typing was performed by PCR-SSP, and the 1-10 exons of RHCE were sequenced by Sanger sequencing. The full-length sequences of RHCE, RHD and RHAG were detected by PacBio third-generation sequencing technology. Results: Serological findings: Blood type O, Dc-phenotype, DAT negative, unexpected antibody screening negative; enhanced D antigen expression; no detection of e antigen in the absorption-elution test. PCR-SSP genotyping indicated the presence of only the RHCE
c allele. Sanger sequencing results: Exons 5-9 of RHCE were deleted, exon 1 had a heterozygous mutation at c. 48G/C, and exon 2 had five heterozygous mutations at c. 150C/T, c. 178C/A, c. 201A/G, c. 203A/G and c. 307C/T. Third-generation sequencing results: RHCE genotype was RHCE
02N. 08/RHCE-D(5-9)-CE; RHD genotype was RHD
01/RHD
01; RHAG genotype was RHAG
01/RHAG
01 (c. 808G>A and c. 861G>A). Conclusion: This Dc-individual carries the allele RHCE
02N. 08 and the novel allele RHCE-D(5-9)-CE. The findings of this study provide data support and a theoretical basis for elucidating the molecular mechanisms underlying RhCE deficiency phenotypes.
3.Differences in cytokines expression between mild and severe infant cases infected with respiratory syncytial virus
Guangyu XUE ; Yuting HU ; Kexin ZONG ; Qin LUO ; Shengnan YANG ; Miao FENG ; Xiaoyu YI ; Zhiqiang XIA ; Chen GAO ; Haijun DU ; Ying LI ; Ying CHEN ; Feng HE ; Yajuan WANG ; Yingli QU ; Jin CAO ; Wenyan TIAN ; Qinqin SONG ; Hailan YAO ; Jun HAN
Chinese Journal of Experimental and Clinical Virology 2025;39(3):370-377
Objective:To analyze the clinical characteristics and cytokines expression characteristics in infants with mild and severe respiratory syncytial virus (RSV) infection.Methods:From May 2023 to December 2023, plasma samples and clinical information were collected from 16 infants with RSV infection and 14 control infants. Cytek Aurora flow cytometry (Cytek, America) and Enzyme linked immunosorbent assay (ELISA) were used to detect the expression levels of 25 cytokines after mild and severe RSV infection.Results:Cough and nasal obstruction were the main clinical manifestations in infants with mild RSV infection, accompanied by polypnea, wheezing and other symptoms. The main symptoms of severe RSV infection were cough and rales, accompanied by fever and polypnea. In comparison with the control group, the expression levels of IL-2, IL-4, IL-5, IL-6, IL-9, IL-13, IL-22, TNF-α, IFN-α, IFN-β, MIP-1β, I-TAC, ENA-78, GROα, Eotaxin, and MCP-1 in the RSV infection group all exhibited an upregulation trend. Both IP-10 and MIP-3α demonstrated a downward trend in the RSV infection group; however, there was no statistically significant difference ( P>0.05). The levels of IL-10, IFN-γ, MIP-1α, and IL-8 in the RSV infection group were significantly higher than those in the control group, whereas the levels of MIG, TARC, and RANTES in the RSV infection group were significantly lower than those in the control group ( P<0.05). The levels of IL-2, IL-4, IL-5, IL-6, IL-9, IL-10, IL-13, IL-22, IFN-β, IFN-γ, TNF-α, IL-8, I-TAC, MIP-1β, Eotaxin, and MCP-1 in the mild RSV infection group were significantly higher than those in the severe RSV infection group ( P>0.05). Among these, the levels of MIG, RANTES, TARC, MIP-3α, and ENA-78 in the mild infection group were all lower than those in the severe infection group. The expressions of ENA-78 and MIP-1α in the severe infection group were significantly higher than those in the mild infection group and also higher than those in the control group. There was no significant difference in IP-10 and GROα between the mild and severe RSV infection groups ( P>0.05). Conclusions:The differences in clinical features and cytokines between infants with mild and severe RSV infection provide important data support for the prevention and treatment of RSV infection in infants.
4.Construction of a new predictive score for severe fever with thrombocytopenia syndrome combined with bacterial/fungal infections based on clinical data
Ran WANG ; Yan DAI ; Qinqin PU ; Nannan HU ; Ke JIN ; Jun LI
Chinese Journal of Infectious Diseases 2025;43(4):202-209
Objective:To study the risk factors for combined bacterial/fungal infections in patients with severe fever with thrombocytopenia syndrome (SFTS) and to develop a novel and validated prediction model.Methods:The basic data and the results of the first laboratory examination after admission were retrospectively collected from patients diagnosed with SFTS who were hospitalized in the First Affiliated Hospital, Nanjing Medical University from January 2018 to December 2022. The patients were categorized into co-infected and non-co-infected groups according to whether they had co-infections with bacterial/fungal infections or not.Independent risk factors were screened by multivariate logistic regression analyses. A novel prediction model was constructed, and the predictive value of the model was assessed using receiver operating characteristic curve. Non-parametric tests and chi-square test were used for statistical analysis.Results:A total of 294 patients were included, and 62 cases were in the combined infection group including 39 cases of simple respiratory tract infections, 11 cases of simple bloodstream infections, four cases of simple urinary tract infections, four cases of respiratory tract combined with bloodstream infection, and four cases of respiratory tract combined with urinary tract infection. Acinetobacter baumannii was mostly found in bacterial infections, with a total of 19 strains, followed by Escherichia coli and Pseudomonas aeruginosa, both with seven strains. Aspergillus were mostly common in fungi, with a total of 16 strains which were all collected from patients with pulmonary infections. Compared with the non-co-infected group, patients in the co-infected group had longer hospital stays, with statistically significant differences ( Z=-6.18, P<0.001). The patients also had higher frequencies of bleeding symptoms, neurological symptoms, severe illness, and death, with statistically significant differences ( χ2=23.91, 16.37, 15.51 and 15.58, respectively, all P<0.001). The aspartate transaminase-to-platelet ratio index (APRI) was also higher in patients with coinfection, with a statistically significant difference ( Z=-4.64, P<0.001). Multivariate binary logistic regression showed that severe illness (odds ratio ( OR)=2.567, 95% confidence interval ( CI) 1.344 to 4.904, P=0.004), blood glucose level higher than 7.782 mmol/L ( OR=4.766, 95% CI 2.493 to 9.109, P<0.001), procalcitonin level higher than 0.228 μg/L ( OR=2.487, 95% CI 1.289 to 4.799, P=0.007), and APRI value higher than 6.268 ( OR=3.032, 95% CI 1.404 to 6.548, P=0.005) were the independent risk factors for co-infections in SFTS patients. Disease severity, blood glucose, procalcitonin, and APRI were combined to construct a novel predictive model: Infect-risk score=-3.331+ 0.654×severity (severe=1, non-severe=0)+ 0.160×blood glucose+ 0.066×procalcitonin+ 0.013×APRI. The AUC for this score was 0.764 (95% CI 0.698 to 0.830, P<0.001), with Youden index of 0.416, sensitivity of 0.839, and specificity of 0.578. Conclusions:Severe illness, blood glucose levels higher than 7.782 mmol/L, procalcitonin levels above 0.228 μg/L, and APRI values above 6.268 are independent risk factors for bacterial/fungal coinfection in SFTS patients. The constructed Infect-risk score model has good predictive value for bacterial/fungal coinfection in SFTS patients.
5.Research on the current status and influencing factors of post ICU syndrome in severe patients
Tingshu WANG ; Li YAO ; Yan LIU ; Bei JING ; Qinqin LI ; Tingrui WANG
Chinese Journal of Nursing 2025;60(19):2356-2363
Objective To explore the current situation and influencing factors of post-intensive care syndrome(PICS)in critically ill patients a month after their transfer out,and to provide a basis for formulating individualized intervention measures.Methods By the convenience sampling method,550 patients who were transferred out of the ICU of a tertiary A hospital in Guizhou Province for a month from April to November 2024 were selected as the survey subjects.The general information of the patients was collected and sorted out.During their stay in the ICU,the Barthel Index,the Richards Campbell Sleep Scale,and the Perceived Social Support Scale were employed for evaluation.A month after the patients were transferred out of the ICU,the assessment was completed through telephone follow-up using the Chinese version of the Brain Care Monitoring Questionnaire for Healthy Aging.According to the assessment a month after the patients were transferred out,they were divided into a PICS group and a non-PICS group.Univariate analysis and binary Logistic regression analysis were completed based on the data of the 2 groups.Results A total of 550 questionnaires were distributed,and 442 valid questionnaires were ultimately collected,with a valid questionnaire collection rate of 80.3%.Among them,194 cases(43.9%)were high-risk patients with PICS.Binary logistic regression analysis showed that advanced age,pulmonary infection,total hospitalization time>15 days,and internal environment disorder were the risk factors for PICS in ICU patients(P<0.05).Conclusion The risk of PICS is relatively high in critically ill patients a month after the transfer.Medical staff need to pay attention to patients who are older,have pulmonary infections and internal environment disorders,and formulate personalized intervention measures for different disease types to improve the long-term health prognosis of patients.
6.Effect of HEDIS-based phased health education on clinical nursing in infertile patients treated with assisted reproductive technology
Xiangling HAN ; Yang WANG ; Qing ZHANG ; Yanju QIN ; Yanmin LUAN ; Qinqin ZHANG
Journal of Navy Medicine 2025;46(6):614-619
Objective To investigate the application of the Health Effective Data and Information System(HEDIS)-based phased health education in infertile patients treated with assisted reproductive technology(ART).Methods A total of 120 infertile patients who were admitted to The First Affiliated Hospital of Naval Medical University from March 2023 to September 2023 were consecutively selected and randomly assigned to observation group or control group at a ratio of 1:1 using a random number table.During the ART treatment period,the control group was given conventional nursing care,while the observation group was given HEDIS based phased health education for nursing intervention.The negative emotion score,shame score,self-management ability score,and nursing satisfaction were compared between the two groups.Results After intervention,the Hamilton Anxiety Scale(HAMA)score and Hamilton Depression Scale(HAMD)score,and self-rating scale(ISS)scores of the observation group were lower than those of the control group(P<0.05).The degree of nursing satisfaction of the observation group was higher than that of the control group(P<0.05).Conclusion The HEDIS-based phased health education can alleviate the negative emotions of anxiety and depression,reduce the sense of shame,and enhance nursing satisfaction in infertile patients during ART treatment.
7.Effect of walking-cognition dual-task training combined with active self-disclosure on elderly patients with acute ischemic stroke
Qinqin HU ; Xueying SHI ; Anna WANG ; Pengchao WU ; Qin ZHOU ; Jiaojiao LI ; Xing YUAN ; Jian LI
Chinese Journal of Geriatric Heart Brain and Vessel Diseases 2025;27(2):197-201
Objective To observe the effect of specialist team-led walking-cognition dual-task train-ing combined with active self-disclosure on control and balance abilities in elderly patients with acute ischemic stroke(AIS).Methods A total of 90 elderly AIS patients treated in our hospital from January 2022 to January 2024 were enrolled and randomly assigned into the control group and the observation group,with 45 cases in each group.The control group received routine walk-ing training,while the observation group received specialist team-led walking-cognition dual-task training combined with active self-disclosure intervention.Control ability,balance ability,walking ability,cognitive function and psychological status were compared between the two groups.Results After intervention,the scores of Sheikh Trunk Control Scale and Fugl-Meyer Assessment(FMA),and the static balance score,dynamic balance score and total score of Berg Balance Scale(BBS)were significantly increased in both the observation and the control groups(P<0.05),and all above scores were obviously higher in the former group than the latter one(P<0.01).The two groups also obtained notably shorter single-and dual-task walking time after intervention,but there were no statistical difference in the single-task walking time in both groups before and after intervention(P>0.05).After intervention,the observation group had significantly shorter dual-task walking time(22.87±7.36 s vs 27.52±8.71 s,P=0.008)and lower walking time cost of dual task[(11.16±4.07)%vs(25.61±7.82)%,P=0.000]when compared with the control group.After intervention,the scores of Mini-Mental Status Examination were increased,and the scores of Hamilton Depression Rating Scale and Hamilton Anxiety Rating Scale were decreased in the two groups(P<0.05).Conclusion Specialist team-led walking-cognition dual-task training com-bined with active self-disclosure intervention can effectively improve trunk control ability,balance ability,walking ability,cognitive function and psychological state in elderly AIS patients,has cer-tian clinical application value.
8.Therapeutic effects of piperacillin/tazobactam combined with acetylcysteine solution on severe pneumonia after cerebral infarction
Yongfei ZHU ; Qinqin WANG ; Wenzheng XU ; Haichang LI
Chinese Journal of Nosocomiology 2025;35(15):2258-2262
OBJECTIVE To explore the effects of piperacillin/tazobactam combined with acetylcysteine solution on severe pneumonia after cerebral infarction,and to analyze its impact on cardiopulmonary and neurological function.METHODS A total of 86 patients with severe pneumonia after cerebral infarction admitted to Yulin Xingyuan Hos-pital from Jan.2022 to Jun.2024 were selected and divided into a control group and a study group using the ran-dom number table method(single blind),with 43 cases in each group.The control group was treated with intrave-nous drip of piperacillin/tazobactam,while the study group received additional inhalation of acetylcysteine solution based on the control group's treatment.The levels of inflammatory factors[C-reactive protein(CRP),interleukin-6(IL-6)and procalcitonin(PCT)],lung function indicators[forced vital capacity(FVC),peak expiratory flow rate(PEF),forced expiratory volume in one second(FEV1)and mean maximal expiratory flow rate(MMEF)],cardiac function indicators[left ventricular ejection fraction(LVEF),cardiac output(CO),cardiac index(CI)and stroke volume(SV)],NIH Stroke Scale(NIHSS)score,clinical efficacy,and the occurrence of adverse reactions were compared before and after treatment.RESULTS Compared with the control group,the study group had low levels of CRP,IL-6,PCT and NIHSS scores after treatment(P<0.05),and high levels of FVC,PEF,FEV1,MMEF,LVEF,CO,CI,and SV after treatment(P<0.05).The overall response rate in the study group was 95.35%,higher than 81.40%in the control group(χ2=4.074,P=0.044).There was no statistically significant difference in the incidence of adverse reactions between the control group and the study group during treatments(χ2=0.179,P=0.672).CONCLUSION Piperacillin/tazobactam combined with inhaled acetylcysteine solution for the treatment of severe pneumonia after cerebral infarction can improve clinical efficacy,reduce levels of inflamma-tory factors,and enhance cardiopulmonary and neurological functions in patients,which has a high safety profile.
9.Application of 18F-FDG PET/MR and its derived parameters in the diagnosis and staging of bladder cancer
Qinqin YOU ; Fei YU ; Rushuai LI ; Fengjiao YANG ; Shuyue AI ; Jun TANG ; Feng WANG
Chinese Journal of Nuclear Medicine and Molecular Imaging 2025;45(7):405-410
Objective:To investigate the application of 18F-FDG PET/MR and its derived parameters in the diagnosis and staging of bladder cancer. Methods:Forty patients (32 males, 8 females; age (66.8±11.2) years) with suspected bladder cancer between December 2019 and March 2022 were retrospectively included and underwent 18F-FDG PET/MR in Nanjing First Hospital. Parameters including SUV max, SUV mean, maximum tumor diameter and mean of apparent diffusion coefficient (ADC mean) were obtained, and bladder cancer muscle invasiveness and lymph node involvement were determined. The efficacy of 18F-FDG PET/MR and its derived parameters for tumor diagnosis and staging was analyzed using transurethral resection of bladder tumor (TUR-BT) or radical cystectomy (RC) and extended pelvic lymph node dissection (ePLND) histopathology as the " gold standard". Independent-sample t test, Mann-Whitney U test or χ2 test was used to analyze the data, and Delong test was used to compare different AUCs. Results:Of 40 patients, 8 were non-muscle invasive bladder cancer (NMIBC), 32 were muscle invasive bladder cancer (MIBC), and 5 were pathologically confirmed to have lymph node metastasis. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of 18F-FDG PET/MR for identifying MIBC were 96.9%(31/32), 7/8, 96.9%(31/32), 7/8, 95.0%(38/40), respectively, and those for lymph node metastasis were 4/5, 90.0%(18/20), 4/6, 18/19, 88.0%(22/25), respectively. For pathological tumor (pT) staging, significant differences were observed between pT2-3 and pT1 groups in maximum tumor diameter ( t=-2.37, P=0.024), SUV mean( Z=-2.11, P=0.035), and ADC mean( t=2.91, P=0.006). The AUCs of maximum tumor diameter, SUV mean and ADC mean in distinguishing MIBC were 0.781, 0.746, and 0.825, respectively. The sensitivity, specificity, PPV, NPV, and accuracy of MRI alone in identifying MIBC were 87.5%(28/32), 1/8, 80.0%(28/35), 1/5 and 72.5%(29/40), respectively, with the AUC of 0.500. The AUC of 18F-FDG PET/MR in identifying MIBC was 0.796, which was better than MRI alone ( Z=5.54, P<0.001), and the accuracy of PET/MR was also higher than MRI alone ( χ2=7.44, P=0.006). Conclusion:Compared with MRI alone, 18F-FDG PET/MR significantly improves the diagnostic efficacy of bladder cancer and the accuracy of pT staging.
10.Bilateral transcranial direct current stimulation can relieve dysphagia among hemispheric stroke patients
Guoping DUAN ; Qiuyue WANG ; Yingxia JI ; Li ZHANG ; Jie ZHANG ; Yuanyuan LI ; Qinqin HAN ; Heliu HUA ; Dongyu WU
Chinese Journal of Physical Medicine and Rehabilitation 2025;47(11):967-972
Objective:To explore the effect of transcranial direct current stimulation (tDCS) on dysphagia in hemispheric stroke patients.Methods:Sixty-two hemispheric stroke patients with dysphagia were randomized into an ipsilateral group, a contralateral group and a bilateral group with 20 in each group. The ipsilateral and contralateral groups received tDCS over their ipsilesional and contralesional hemispheres, respectively, while in the bilateral group it was over both hemispheres. That was followed by conventional swallowing therapy. Before and after 2 weeks of the treatment, swallowing function was assessed using the modified Mann Assessment of Swallowing Ability (MMASA) and a Swallow Severity scale (SSS). Linear regressions were evaluated to highlight the factors most influencing recovery from post-stroke hemispheric dysphagia.Results:After the treatments, the average MMASA and SSS scores had increased significantly in all three groups. There was no significant difference in the average post-treatment MMASA and SSS scores between the ipsilateral and contralateral groups, but the bilateral group showed significantly better average post-treatment MMASA and SSS scores compared to the other two groups. Linear regression analysis confirmed that the tDCS protocol (group allocation) was a significant predictor of recovery.Conclusion:Bilateral tDCS can effectively promote the recovery of swallowing function after a hemispheric stroke. It demonstrates greater therapeutic benefits than unilateral tDCS.

Result Analysis
Print
Save
E-mail