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.On the Internal Logic of "Syndrome-Treatment-Effect" in Traditional Chinese Medicine Syndrome Differentiation and Treatment from the Perspective of Hermeneutics
Journal of Traditional Chinese Medicine 2026;67(10):1033-1037
The concept of syndrome differentiation and treatment is often misunderstood as "arbitrary empiricism" or dismissed as unjustifiable when judged by a single external indicator. To address it, this paper draws on hermeneutics, especially the idea that "tradition, understanding, and practice" are mutually generative, to elucidate the object levels, inferential pathways, and efficacy-based validation and correction mechanisms underlying this approach in the clinical process. It is argued that "syndrome" is not a substitute for a disease label or an isolated indicator, but rather a structured configuration of manifestations and an evolving trajectory of illness situated in a specific clinical context. The correlation of all four examinations and physician-patient dialogue form a reasoned chain for the selection of diagnoses, through which discrete signs and symptoms are organized into a syndrome judgment that can be articulated and debated. Therapeutic principles and prescriptions externalize clinical understanding and, through feedback from therapeutic effects, reflexively prompt re-differentiation, thereby forming a cyclical, self-corrective dynamic loop of "syndrome, treatment and effect". Accordingly, syndrome differentiation and treatment should not be regarded as a contingent accumulation of experience, but as a form of clinical rationality under multiple constraints, including classical methods, communal training, and clinical verification.
3.Construction of novel transmembrane fusion antioxidant enzymes and their protective effect against hydrogen peroxide-mediated cellular oxidative damage.
Jianru PAN ; Ziyi ZHANG ; Jinnan CHU ; Yanan HAN ; Xueying ZHENG ; Shirong CAI ; Huocong HE
Chinese Journal of Biotechnology 2025;41(4):1547-1558
Reactive oxygen species (ROS) are major contributors to radiation therapy-induced side effects in cancer patients. A fusion antioxidant enzyme comprising glutathione S-transferase (GST), superoxide dismutase 1 (SOD1), and a transmembrane peptide has been shown to effectively mitigate ROS-induced damage. To enhance its targeting capability, the fusion protein was further modified by incorporating a matrix metalloproteinase-2/9 substrate peptide (X) and the transmembrane peptide R9, yielding the antioxidant enzyme GST-SOD1-X-R9 (GS1XR). This modification reduced its transmembrane ability in tumor cells, thereby selectively protecting normal cells from oxidative stress. However, the use of non-human GST poses potential immunogenicity risks. In this study, we employed seamless cloning technology to construct an expression vector containing the human GST gene to replace the non-human GST gene, and then expressed and purified novel fusion antioxidant enzymes GS1R and GS1XR. The protective effects of newly constructed GS1R and GS1XR against hydrogen peroxide (H2O2)-induced oxidative damage in L-02 cells were then evaluated using GS1 as a control. Enzymatic activity assays revealed that the specific activity of GST in GS1XR remained unchanged compared to the unmodified protein, while SOD activity was enhanced. Exposure to 200 μmol/L H₂O₂ transiently activated the nuclear factor-erythroid 2-related factor 2 (Nrf2) pathway; however, this activation diminished after 24 h, reducing cell viability to 48.4%. Both GS1R and GS1XR effectively scavenged intracellular ROS, directly counteracting oxidative stress and promoting Nrf2 nuclear translocation, thereby activating antioxidant pathways and restoring cell viability to normal levels. The two enzymes showed comparable efficacy. In contrast, GS1, lacking transmembrane capability, was restricted to scavenging extracellular ROS and provided only limited protection. In conclusion, both novel fusion antioxidant enzymes demonstrated significant potential in safeguarding normal cells from ROS-mediated oxidative damage. The findings provide a foundation for further investigation in related field.
Humans
;
Oxidative Stress/drug effects*
;
Hydrogen Peroxide
;
Antioxidants/metabolism*
;
Glutathione Transferase/metabolism*
;
Recombinant Fusion Proteins/pharmacology*
;
Superoxide Dismutase-1
;
Reactive Oxygen Species/metabolism*
;
Superoxide Dismutase/biosynthesis*
4.Chemotherapy-free induction therapy for a critically ill pregnant woman with Philadelphia chromosome-positive acute lymphoblastic leukemia: a case report and literature review
Meng GAO ; Yan XIE ; Ziyi LIU ; Peiqi LIANG ; Limin LIU ; Jie YIN ; Dong WANG ; Bing HAN ; Huiying QIU ; Jianhong FU ; Depei WU
Chinese Journal of Hematology 2025;46(10):967-971
This report presents the management of a critically ill 36-year-old woman diagnosed with Philadelphia chromosome-positive acute lymphoblastic leukemia (Ph +ALL) at 28 weeks of gestation. The patient rapidly deteriorated, developing disseminated intravascular coagulation (DIC) , diffuse alveolar hemorrhage (DAH) , septic shock, and multi-organ dysfunction, necessitating admission to the hematological intensive care unit. Given her critical condition and advanced pregnancy, a chemotherapy-free induction regimen comprising imatinib and dexamethasone was initiated, alongside comprehensive supportive measures, including mechanical ventilation, continuous renal replacement therapy (CRRT) , broad-spectrum antibiotics, and high-dose corticosteroids. During treatment, intrauterine fetal demise occurred, and a stillborn was delivered following obstetric intervention. With aggressive treatment, the patient's respiratory failure, DIC, and DAH gradually resolved, and she achieved complete remission. She subsequently received consolidation chemotherapy, CAR-T cell therapy, and allogeneic hematopoietic stem cell transplantation, achieving sustained complete molecular remission on long-term follow-up. This case demonstrates that for critically ill pregnant patients with Ph + ALL, a chemotherapy-free regimen of targeted therapy and corticosteroids, when combined with intensive supportive care, is a safe and effective approach that may offer a therapeutic option for similar cases.
5.Regional distribution of depressive symptoms in middle-aged and portioulate matter elderly Chinese population and its ecological association with particulate matter 25
Ziyi LUO ; Shijia YUAN ; Ronghang LIU ; Wenhui GAO ; Chunlei HAN
Chinese Mental Health Journal 2025;39(7):597-603
Objective:Against the backdrop of population aging and air pollution,this study examined the re-gional distribution of depressive symptoms among middle-aged and elderly people in China and explores the influ-ence of patrticulate matter 2.5(PM2.5)concentration on these symptoms.This study examined the regional distri-bution of depressive symptoms in middle-aged and elderly people in China and explores the influence of PM2.5 concentration and related factors on these symptoms.Methods:Middle-aged and elderly people aged 45 years and above in CHARLS database in 2013,2015 and 2018 were selected as research objects,and the Center for Epidemio-logic Studies Depression Scale(CESD-10)to obtain the detection rate of depressive symptoms.The PM2.5 concen-tration data were derived from the annual data of the China Environmental Monitoring Station.t-test,x2 test and DID model were used to analyze the related factors of depressive symptoms.Stata17.0 and Arc GIS10.8 were used for spatial autocorrelation analysis to explore the regional distribution and relationship of depressive symptoms in mid-dle-aged and elderly people in China.Results:From east to west,the detection rate of depressive symptoms in mid-dle-aged and elderly people in China showed an increasing trend.The regional distribution of PM2.5 mainly showed that the central region was higher than the northern and southern regions and the western region(except Xinjiang)was higher than the eastern region.Conclusion:Both the PM2.5 concentration and depression symptoms exhibit spatial clustering across China.PM2.5 has a negative impact on depression symptoms in middle-aged and elderly people,with other related factors including gender,age,education level,marital status,living area,smoking status.
6.Analysis of factors affecting fibrosis reversal in patients with metabolic associated steatohepatitis based on magnetic resonance elastography
Ziyi ZHANG ; Chenglin SUN ; Hao REN ; Dawei YANG ; Xinyu ZHAO ; Mengyang ZHANG ; Xiao HAN ; Jingjie ZHAO ; Qianyi WANG ; Yameng SUN ; Xinyan ZHAO ; Jidong JIA ; Zhenghan YANG ; Xiaofei TONG ; Hong YOU
Chinese Journal of Hepatology 2025;33(10):1001-1008
Objective:To dynamically assess liver fibrosis using magnetic resonance elastography (MRE) and explore factors associated with fibrosis reversal in patients with metabolic dysfunction-associated steatohepatitis (MASH).Methods:This study included data from patients diagnosed with MASH by liver biopsy who underwent at least two MRE examinations. Patients were divided into a fibrosis reversal group and a non-reversal group according to whether MRE values decreased by 20% during follow-up. Differences in clinical data between the groups were compared using analysis of variance, the Kruskal-Wallis test, and the chi-square test. Univariate and multivariate logistic regression analyses were used to explore independent risk factors for fibrosis reversal in MASH.Results:A total of 46 cases were included in this study (mean age 50.1±12.3 years, BMI 26.1±3.1 kg/m2). Among them, the reversal group accounted for 26.1%. The rate of decrease in MRI proton density fat fraction (PDFF) was significantly higher in the reversal group (-50.0% vs. -8.1%, P=0.001) than in the non-reversal group between the two MRE examinations. The reversal group showed a more significant change rate of decreases in fasting insulin (-37.3% vs. -3.6%, P=0.011), insulin resistance index (-38.6% vs. -6.5%, P=0.044), and ALP (-24.9% vs. 0, P=0.004). Multivariate logistic regression analysis indicated that the rate of change in MRI PDFF was an independent predictor of fibrosis reversal ( OR=0.96, 95% CI: 0.92-1.00, P=0.046). Conclusion:A decrease in MRI proton density fat fraction levels is independently associated with liver fibrosis reversal in MASH, suggesting that intervention targeting liver fat content may be an effective treatment strategy.
7.Association between skeletal muscle function, insulin resistance and type 2 diabetes mellitus
Hongxia LIU ; Mingyu ZHU ; Tingting HAN ; Ning CHEN ; Yue LIU ; Ziyi WEI ; Yurong WENG ; Yaomin HU
Chinese Journal of Endocrinology and Metabolism 2025;41(5):365-371
Objective:To investigate the association of skeletal muscle function(including muscle strength and physical performance) and insulin resistance as well as type 2 diabetes mellitus(T2DM).Methods:The retrospective study included 942 patients who visited the Department of Geriatrics at Renji Hospital, Shanghai Jiao Tong University School of Medicine, between October 2020 and July 2024. Low skeletal muscle function was defined as either reduced muscle strength or impaired physical performance. Muscle strength was assessed by grip strength, while physical performance was evaluated using the 5-time chair stand test. The associations between muscle function, insulin resistance, and T2DM were analyzed.Results:A significant association was observed between decreased skeletal muscle function and a higher prevalence of T2DM( P=0.001). Further analysis revealed that decreased physical performance was significantly associated with increased T2DM prevalence( P<0.001), whereas reduced muscle strength showed no significant association with T2DM prevalence( P=0.331). Linear regression analysis indicated that both the homeostasis model assessment of insulin resistance(HOMA2-IR) and fasting blood glucose levels increased significantly with longer chair stand times( P<0.05). Restrictive cubic spline(RCS) analysis demonstrated a nonlinear relationship between chair-rising time and HOMA2-IR. Notably, when the cumulative chair-rising time exceed 8.1 s, HOMA2-IR increased significantly with prolonged chair stand time. Logistic regression analysis showed that compared with patients with normal physical performance, those with decreased physical performance had significantly higher odds of T2DM( OR=2.64, P<0.001) and insulin resistance( OR=2.34, P=0.002). Conclusion:Decline in physical performance is significantly positively associated with insulin resistance and the risk of T2DM. Morever, when the cumulative chair stand time exceed 8.1 s, HOMA2-IR increases progressively with further prolongation of chair stand time.
8.Regional distribution of depressive symptoms in middle-aged and portioulate matter elderly Chinese population and its ecological association with particulate matter 25
Ziyi LUO ; Shijia YUAN ; Ronghang LIU ; Wenhui GAO ; Chunlei HAN
Chinese Mental Health Journal 2025;39(7):597-603
Objective:Against the backdrop of population aging and air pollution,this study examined the re-gional distribution of depressive symptoms among middle-aged and elderly people in China and explores the influ-ence of patrticulate matter 2.5(PM2.5)concentration on these symptoms.This study examined the regional distri-bution of depressive symptoms in middle-aged and elderly people in China and explores the influence of PM2.5 concentration and related factors on these symptoms.Methods:Middle-aged and elderly people aged 45 years and above in CHARLS database in 2013,2015 and 2018 were selected as research objects,and the Center for Epidemio-logic Studies Depression Scale(CESD-10)to obtain the detection rate of depressive symptoms.The PM2.5 concen-tration data were derived from the annual data of the China Environmental Monitoring Station.t-test,x2 test and DID model were used to analyze the related factors of depressive symptoms.Stata17.0 and Arc GIS10.8 were used for spatial autocorrelation analysis to explore the regional distribution and relationship of depressive symptoms in mid-dle-aged and elderly people in China.Results:From east to west,the detection rate of depressive symptoms in mid-dle-aged and elderly people in China showed an increasing trend.The regional distribution of PM2.5 mainly showed that the central region was higher than the northern and southern regions and the western region(except Xinjiang)was higher than the eastern region.Conclusion:Both the PM2.5 concentration and depression symptoms exhibit spatial clustering across China.PM2.5 has a negative impact on depression symptoms in middle-aged and elderly people,with other related factors including gender,age,education level,marital status,living area,smoking status.
9.Association between skeletal muscle function, insulin resistance and type 2 diabetes mellitus
Hongxia LIU ; Mingyu ZHU ; Tingting HAN ; Ning CHEN ; Yue LIU ; Ziyi WEI ; Yurong WENG ; Yaomin HU
Chinese Journal of Endocrinology and Metabolism 2025;41(5):365-371
Objective:To investigate the association of skeletal muscle function(including muscle strength and physical performance) and insulin resistance as well as type 2 diabetes mellitus(T2DM).Methods:The retrospective study included 942 patients who visited the Department of Geriatrics at Renji Hospital, Shanghai Jiao Tong University School of Medicine, between October 2020 and July 2024. Low skeletal muscle function was defined as either reduced muscle strength or impaired physical performance. Muscle strength was assessed by grip strength, while physical performance was evaluated using the 5-time chair stand test. The associations between muscle function, insulin resistance, and T2DM were analyzed.Results:A significant association was observed between decreased skeletal muscle function and a higher prevalence of T2DM( P=0.001). Further analysis revealed that decreased physical performance was significantly associated with increased T2DM prevalence( P<0.001), whereas reduced muscle strength showed no significant association with T2DM prevalence( P=0.331). Linear regression analysis indicated that both the homeostasis model assessment of insulin resistance(HOMA2-IR) and fasting blood glucose levels increased significantly with longer chair stand times( P<0.05). Restrictive cubic spline(RCS) analysis demonstrated a nonlinear relationship between chair-rising time and HOMA2-IR. Notably, when the cumulative chair-rising time exceed 8.1 s, HOMA2-IR increased significantly with prolonged chair stand time. Logistic regression analysis showed that compared with patients with normal physical performance, those with decreased physical performance had significantly higher odds of T2DM( OR=2.64, P<0.001) and insulin resistance( OR=2.34, P=0.002). Conclusion:Decline in physical performance is significantly positively associated with insulin resistance and the risk of T2DM. Morever, when the cumulative chair stand time exceed 8.1 s, HOMA2-IR increases progressively with further prolongation of chair stand time.
10.Chemotherapy-free induction therapy for a critically ill pregnant woman with Philadelphia chromosome-positive acute lymphoblastic leukemia: a case report and literature review
Meng GAO ; Yan XIE ; Ziyi LIU ; Peiqi LIANG ; Limin LIU ; Jie YIN ; Dong WANG ; Bing HAN ; Huiying QIU ; Jianhong FU ; Depei WU
Chinese Journal of Hematology 2025;46(10):967-971
This report presents the management of a critically ill 36-year-old woman diagnosed with Philadelphia chromosome-positive acute lymphoblastic leukemia (Ph +ALL) at 28 weeks of gestation. The patient rapidly deteriorated, developing disseminated intravascular coagulation (DIC) , diffuse alveolar hemorrhage (DAH) , septic shock, and multi-organ dysfunction, necessitating admission to the hematological intensive care unit. Given her critical condition and advanced pregnancy, a chemotherapy-free induction regimen comprising imatinib and dexamethasone was initiated, alongside comprehensive supportive measures, including mechanical ventilation, continuous renal replacement therapy (CRRT) , broad-spectrum antibiotics, and high-dose corticosteroids. During treatment, intrauterine fetal demise occurred, and a stillborn was delivered following obstetric intervention. With aggressive treatment, the patient's respiratory failure, DIC, and DAH gradually resolved, and she achieved complete remission. She subsequently received consolidation chemotherapy, CAR-T cell therapy, and allogeneic hematopoietic stem cell transplantation, achieving sustained complete molecular remission on long-term follow-up. This case demonstrates that for critically ill pregnant patients with Ph + ALL, a chemotherapy-free regimen of targeted therapy and corticosteroids, when combined with intensive supportive care, is a safe and effective approach that may offer a therapeutic option for similar cases.

Result Analysis
Print
Save
E-mail